FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003
COMPLETE SPECIFICATION
(See Section 10 and Rule 13)
Title of invention:
METHODS AND SYSTEMS FOR GROUND WATER PREDICTION USING INTEGRATION OF SATELLITE AND AUXILIARY OBSERVATIONS
Applicant
Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th floor,
Nariman point, Mumbai 400021,
Maharashtra, India
Preamble to the description:
The following specification particularly describes the invention and the manner in which it is to be performed
2
TECHNICAL FIELD
[001]
The disclosure herein generally relates to the field of ground water prediction, and more specifically to methods and systems for ground water prediction using integration of satellite and auxiliary observations.
5
BACKGROUND
[002]
Ground water depletion is the new challenge as it impacts the environment, causes land subsidence, and increases the risk of flooding in coastal areas. The reasons for ground water depletion are over-exploitation of ground water from agriculture, population growth, urbanization, and climate change, which affect 10 precipitation patterns and ground water recharge. Forecasting of future ground water levels helps in effective decision-making, promotes responsible water management practices, and helps ensure the long-term availability of this vital resource for future generations. Conventional techniques in the art for ground water level prediction employ various types of models, including hydrogeological, 15 statistical, and ground water flow-based models. These models mostly utilized remote sensing data to extract specific parameters individually or in combination for the modelling.
[003]
However, there are several other parameters such as population, industrial usage, environmental parameters and so on which are contributing to the 20 depletion of ground water, and without considering those parameters it may lead to imbalance in the forecasting the ground water level. Hence the conventional techniques in the art for the ground water level prediction are not accurate and efficient for predicting the ground water level.
25
SUMMARY
[004]
Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems.
[005]
In an aspect, a processor-implemented method for ground water 30 prediction using integration of satellite and auxiliary observations is provided. The
3
method including the steps
of: receiving an input data associated to a predefined geographical region for which a ground water level is to be predicted, from a remote sensing satellite data and one or more input information sources; determining an input parameter data associated to the predefined geographical region for which the ground water level is to be predicted, from the input data, wherein the input 5 parameter data is of a predefined time period and comprises one or more of (i) one or more weather related parameters, (ii) one or more soil related parameters, (iii) one or more agriculture related parameters, (iv) one or more population related parameters, (v) one or more surface water related parameters, (vi) one or more industry related parameters, (vii) one or more drought related parameters, (viii) one 10 or more seismic related parameters, and (ix) one or more surface deformation related parameters; passing the input parameter data of the one or more weather related parameters and the one or more soil related parameters, to a weather and soil process-based model, to obtain an amount of total surface water from rainfall infiltrated to aquifer during the predefined time period; passing the input parameter 15 data of the one or more agriculture related parameters, to an agriculture process-based model, to obtain an amount of ground water extracted from aquifer for agriculture during the predefined time period; passing the input parameter data of the one or more population related parameters, to a population process-based model, to obtain a net amount of ground water extracted from aquifer by population 20 during the predefined time period; passing the input parameter data of the one or more soil related parameters and the one or more surface water related parameters, to a soil and surface process-based model, to obtain a net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period; passing the input parameter data of the one or more industry related 25 parameters, to an industry process-based model, to obtain a net amount of ground water extracted from aquifer for industrial use during the predefined time period; passing the input parameter data of the one or more drought related parameters, to a pretrained machine learning model for drought, to obtain a drought index for the predefined time period; passing the input parameter data of the one or more seismic 30 related parameters, to a seismic process-based model, to obtain a seismic index for
4
the predefined time period; passing the input parameter data of the one or more
surface deformation related parameters, to a surface deformation process-based model, to obtain an amount of total surface deformation during the predefined time period; passing (i) the amount of total surface water from rainfall infiltrated to aquifer during the predefined time period, (ii) the amount of ground water extracted 5 from aquifer for agriculture during the predefined time period, (iii) the net amount of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period, (v) the net amount of ground water extracted from aquifer for industrial use during the predefined time period, 10 (vi) the drought index for the predefined time period, (vii) the seismic index for the predefined time period, (viii) the amount of total surface deformation during the predefined time period, to a process-based weighted integrated forecasting model, to predict the ground water level of the predefined geographical region; receiving a forecasted input data associated to the predefined geographical region for which a 15 ground water level is to be predicted, from the remote sensing satellite data and one or more input information sources; determining a forecasted input parameter data is of the predefined time period and comprises of (i) the one or more weather related parameters, (ii) the one or more soil related parameters, (iii) the one or more agriculture related parameters, (iv) the one or more population related parameters, 20 (v) the one or more surface water related parameters, (vi) the one or more industry related parameters, (vii) the one or more drought related parameters, (viii) the one or more seismic related parameters, and (ix) the one or more surface deformation related parameters; determining (i) the amount of total surface water from rainfall infiltrated to aquifer during the predefined time period, (ii) the amount of ground 25 water extracted from aquifer for agriculture during the predefined time period, (iii) the net amount of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period, (v) the net amount of ground water extracted from aquifer for industrial use during the 30 predefined time period, (vi) the drought index for the predefined time period, (vii)
5
the seismic index for the predefined time period, (viii) the amount of total surface
deformation during the predefined time period, from the forecasted input parameter data; and passing (i) the amount of total surface water from rainfall infiltrated to aquifer during the predefined time period, (ii) the amount of ground water extracted from aquifer for agriculture during the predefined time period, (iii) the net amount 5 of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period, (v) the net amount of ground water extracted from aquifer for industrial use during the predefined time period, (vi) the drought index for the predefined time period, (vii) the seismic index for the 10 predefined time period, (viii) the amount of total surface deformation during the predefined time period, to the process-based weighted integrated forecasting model, to predict a forecasted ground water level of the predefined geographical region.
[006]
In another aspect, a system for ground water prediction using integration of satellite and auxiliary observations is provided. The system includes: 15 a memory storing instructions; one or more Input/Output (I/O) interfaces; and one or more hardware processors coupled to the memory via the one or more I/O interfaces, wherein the one or more hardware processors are configured by the instructions to:
[007]
In yet another aspect, there is provided a computer program product 20 comprising a non-transitory computer readable medium having a computer readable program embodied therein, wherein the computer readable program, when executed on a computing device, causes the computing device to: receive an input data associated to a predefined geographical region for which a ground water level is to be predicted, from a remote sensing satellite data and one or more input information 25 sources; determine an input parameter data associated to the predefined geographical region for which the ground water level is to be predicted, from the input data, wherein the input parameter data is of a predefined time period and comprises one or more of (i) one or more weather related parameters, (ii) one or more soil related parameters, (iii) one or more agriculture related parameters, (iv) 30 one or more population related parameters, (v) one or more surface water related
6
parameters, (vi) one or more industry related parameters, (vii) one or more drought
related parameters, (viii) one or more seismic related parameters, and (ix) one or more surface deformation related parameters; pass the input parameter data of the one or more weather related parameters and the one or more soil related parameters, to a weather and soil process-based model, to obtain an amount of total surface 5 water from rainfall infiltrated to aquifer during the predefined time period; pass the input parameter data of the one or more agriculture related parameters, to an agriculture process-based model, to obtain an amount of ground water extracted from aquifer for agriculture during the predefined time period; pass the input parameter data of the one or more population related parameters, to a population 10 process-based model, to obtain a net amount of ground water extracted from aquifer by population during the predefined time period; pass the input parameter data of the one or more soil related parameters and the one or more surface water related parameters, to a soil and surface process-based model, to obtain a net amount of ground water infiltrated to aquifer through one or more water sources during the 15 predefined time period; pass the input parameter data of the one or more industry related parameters, to an industry process-based model, to obtain a net amount of ground water extracted from aquifer for industrial use during the predefined time period; pass the input parameter data of the one or more drought related parameters, to a pretrained machine learning model for drought, to obtain a drought index for 20 the predefined time period; pass the input parameter data of the one or more seismic related parameters, to a seismic process-based model, to obtain a seismic index for the predefined time period; pass the input parameter data of the one or more surface deformation related parameters, to a surface deformation process-based model, to obtain an amount of total surface deformation during the predefined time period; 25 pass (i) the amount of total surface water from rainfall infiltrated to aquifer during the predefined time period, (ii) the amount of ground water extracted from aquifer for agriculture during the predefined time period, (iii) the net amount of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated to aquifer through one or more water 30 sources during the predefined time period, (v) the net amount of ground water
7
extracted from aquifer for industrial use during the predefined time period, (vi) the
drought index for the predefined time period, (vii) the seismic index for the predefined time period, (viii) the amount of total surface deformation during the predefined time period, to a process-based weighted integrated forecasting model, to predict the ground water level of the predefined geographical region; receive a 5 forecasted input data associated to the predefined geographical region for which a ground water level is to be predicted, from the remote sensing satellite data and one or more input information sources; determine a forecasted input parameter data is of the predefined time period and comprises of (i) the one or more weather related parameters, (ii) the one or more soil related parameters, (iii) the one or more 10 agriculture related parameters, (iv) the one or more population related parameters, (v) the one or more surface water related parameters, (vi) the one or more industry related parameters, (vii) the one or more drought related parameters, (viii) the one or more seismic related parameters, and (ix) the one or more surface deformation related parameters; determine (i) the amount of total surface water from rainfall 15 infiltrated to aquifer during the predefined time period, (ii) the amount of ground water extracted from aquifer for agriculture during the predefined time period, (iii) the net amount of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period, (v) the net 20 amount of ground water extracted from aquifer for industrial use during the predefined time period, (vi) the drought index for the predefined time period, (vii) the seismic index for the predefined time period, (viii) the amount of total surface deformation during the predefined time period, from the forecasted input parameter data; and pass (i) the amount of total surface water from rainfall infiltrated to aquifer 25 during the predefined time period, (ii) the amount of ground water extracted from aquifer for agriculture during the predefined time period, (iii) the net amount of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period, (v) the net amount of ground 30 water extracted from aquifer for industrial use during the predefined time period,
8
(vi) the drought index for the predefined time period, (vii) the seismic index for the
predefined time period, (viii) the amount of total surface deformation during the predefined time period, to the process-based weighted integrated forecasting model, to predict a forecasted ground water level of the predefined geographical region.
[008]
In an embodiment, the one or more weather related parameters 5 comprises (i) a daily rainfall, (ii) a daily land surface temperature, and (iii) a daily evapotranspiration rate. The one or more soil related parameters comprises (i) a soil type, (ii) a soil compaction index (SCI), (iii) a soil saturation level (SSL), and (iv) a soil infiltration capacity. The one or more agriculture related parameters comprises (i) a total agriculture area, (ii) of crop grown in each season, and (iii) a 10 crop grown area in each season. The one or more population related parameters comprises (i) a year-wise population amount, (ii) a population growth rate, (iii) a year-wise number of residential establishments, (iv) a year-wise number of residential establishments with ground water recharge facilities, and (v) a year-wise area of residential establishments with ground water recharge facilities. The one or 15 more surface water related parameters comprises (i) a total area of one or more water reserve sources, and (ii) a total water holding capacity of the one or more water reserve sources. The one or more industry related parameters comprises (i) a year-wise number of industry establishments, (ii) year-wise type of industry establishments, (iii) a year-wise total amount of ground water utilized by industry 20 establishments, (iv) a year-wise number of industry establishments with ground water recharge facilities, (v) a year-wise area of permanent industry establishments with ground water recharge facilities, and (vi) a year-wise total amount of rain water given to aquifer by industry establishments. The one or more drought related parameters comprises (i) a season-wise spatially distributed drought affected area, 25 and (ii) a season-wise spatially distributed drought intensity. The one or more seismic related parameters comprises (i) a region of interest (RoI) seismic zone type, and (ii) a year-wise seismic magnitude. The one or more surface deformation related parameters comprises a year-wise amount of land surface deformation.
9
[009]
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
BRIEF DESCRIPTION OF THE DRAWINGS 5
[010]
The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles:
[011]
FIG. 1 is an exemplary block diagram of a system for ground water prediction using integration of satellite and auxiliary observations, in accordance 10 with some embodiments of the present disclosure.
[012]
FIG. 2 is an exemplary block diagram illustrating a plurality of modules of the system of FIG. 1, for ground water prediction using integration of satellite and auxiliary observations, in accordance with some embodiments of the present disclosure. 15
[013]
FIGS. 3A through 3C illustrate exemplary flow diagrams of a processor-implemented method for ground water prediction using integration of satellite and auxiliary observations, using the system of FIG. 1, in accordance with some embodiments of the present disclosure.
20
DETAILED DESCRIPTION OF EMBODIMENTS
[014]
Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer 25 to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed embodiments.
[015]
Ground water depletion refers to the long-term decline in the water levels of underground aquifers. The primary cause of ground water over-30 exploitation has been the rising demand for ground water from agriculture. A shift
10
toward water
-intensive or cash crops for financial gain has become a reason for the depletion of ground water. In India, state governments offered subsidized/free electricity to smallholder farmers for pumping ground water for irrigation which consequently led to widespread ground water depletion. Apart from agriculture, the other factors contributing to depletion includes population growth, urbanization, 5 and climate change, which affect precipitation patterns and ground water recharge. Ground water depletion impacts the environment, and causes land subsidence which can damage infrastructure, such as buildings, roads, and pipelines, and increase the risk of flooding in coastal areas. The water level data collected by Central Ground Water Board (CGWB) during the year 2021, when compared with 10 the decadal mean of November 2011 to November 2020, indicates that about 30% of the wells monitored have registered decline in ground water level.
[016]
knowledge about future ground water depletion is crucial for proactive water resource planning, sustainable agriculture, environmental conservation, infrastructure development, policy formulation, and stakeholder 15 engagement. It enables effective decision-making, promotes responsible water management practices, and helps ensure the long-term availability of this vital resource for future generations.
[017]
In the past, several studies have been conducted using various types of models, including hydrogeological, statistical, and ground water flow-based 20 models. These models utilized remote sensing data to extract specific parameters for modeling. Hydrogeological models aimed to represent the physical and hydrological characteristics of an aquifer system, incorporating data on ground water levels, recharge rates, and hydraulic properties of the subsurface. Statistical methods involved the analysis of historical ground water data to identify patterns, 25 trends, and correlations. Ground water flow models, on the other hand, simulated the movement of ground water through an aquifer by solving mathematical equations based on physical laws and boundary conditions. As most of these methods relied on subset of parameters or focused on considering individual datasets such as satellite, they are limited in terms of precision as the holistic 30 parameterization.
11
[018]
However, none of these models collectively considered comprehensive parameters such as weather conditions, soil properties, agriculture data, population data, water resources information, industry details, drought information, seismic data, and surface deformation trends over the years for the specific region under study. Importantly, there is impact of earthquake and land 5 subsidence on the ground water movement. The ground water of the region can be influenced by each of these parameters separately, and it is crucial to comprehend their collective impact on ground water depletion. Consideration of these parameters helps in precise prediction of ground water. Therefore, a model is required where comprehensive parameterization needs to be considered. 10
[019]
The present disclosure solves the technical problems in the art with the methods and systems for ground water prediction using integration of satellite and auxiliary observations. The present disclosure predicts the ground water situation i.e. rising or declining for a given region based on the archived remote sensing and comprehensive auxiliary datasets i.e. weather conditions, soil 15 properties, agriculture data, population data, water resources information, industry details, drought information, seismic data, and surface deformation trends. The present disclosure also considers different future scenarios such as cropping pattern, weather conditions, use of irrigation system etc. Accurate ground water prediction over the large duration based on our proposed approach can help farmers to plan 20 their irrigation practices effectively. Also, the present disclosure enables farmers to make informed decisions about the types of crops they should cultivate. Hence the present disclosure has the potential to scale up and implement in any part of the world.
[020]
When forecasting ground water levels, it is essential to consider 25 various components as they can significantly impact ground water dynamics and availability. Each component plays a specific role in influencing ground water levels, and incorporating these factors can lead to more accurate and comprehensive predictions. Here's a brief overview of the importance of each component:
[021]
1. Weather conditions: Weather, including precipitation and 30 evapotranspiration rates, directly affects ground water recharge and discharge
12
processes. Accurate weather data is crucial for estimating water inputs and outputs
in the ground water system.
[022]
2. Soil properties: Soil characteristics, such as permeability, porosity, and water-holding capacity, determine how water moves through the soil and eventually reaches the ground water table. Understanding soil properties helps 5 assess ground water recharge and flow rates.
[023]
3. Agricultural data: Agriculture is a significant consumer of ground water for irrigation purposes. Monitoring agricultural water use and crop water requirements is essential for understanding the demand-side influences on ground water levels. 10
[024]
4. Population statistics: Population growth affects the overall water demand, including both domestic and industrial uses. As the population increases, there may be higher water withdrawals from the ground water system, leading to potential depletion.
[025]
5. Water resources information: Information about surface water 15 bodies, reservoirs, and other water resources connected to the ground water system can influence ground water levels through interactions and exchanges.
[026]
6. Industrial details: Industrial activities can lead to ground water contamination or increased water demand. Understanding industrial water usage and potential sources of pollution is essential for assessing ground water 20 sustainability.
[027]
7. Drought records: Past drought events can provide valuable insights into ground water system resilience and vulnerability during periods of low precipitation and increased water stress.
[028]
8. Seismic data: Seismic activities can affect ground water flow by 25 altering subsurface fractures and permeability. Monitoring seismic data can help assess potential impacts on ground water levels.
[029]
9. Surface deformation patterns: Subsidence or uplift in the land surface can occur due to ground water extraction or recharge processes. Tracking surface deformation patterns can indicate changes in ground water levels. 30
13
[030]
10. Future cropping pattern: Changes in cropping patterns can affect water demand and irrigation practices, which, in turn, impact ground water usage and recharge.
[031]
11. Forecasted weather conditions: Future weather predictions help anticipate changes in precipitation patterns, temperature, and 5 evapotranspiration rates, enabling better assessment of ground water recharge and discharge rates.
[032]
12. Use of irrigation systems in the future: Future changes in irrigation practices, such as the adoption of more efficient irrigation systems, can affect ground water demand and availability. 10
[033]
13. Future population growth: Anticipated population growth have direct implications for water demand and ground water usage, affecting the overall water balance.
[034]
Considering all these components in ground water forecasting allows for a more comprehensive understanding of the system dynamics and helps 15 develop effective strategies for sustainable ground water management.
[035]
The systems and methods of the present disclosure first combines time-series archived remote sensing data with a wide array of past auxiliary datasets (which directly or indirectly influence ground water condition) specific to a given region for precise prediction of future ground water condition. These encompass 20 diverse information such as weather conditions, soil properties, agricultural data, population statistics, water resources information, industrial details, drought records, seismic data, and surface deformation patterns among others. Importantly, the movement of ground water due to earthquakes in the given region is considered. Also, the systems and methods of the present disclosure consider different future 25 scenarios which can be built on future cropping patterns, forecasted weather conditions, use of irrigation system in the future, and future population growth of the given region. This helps in providing specific recommendation of best practices based on scenarios-based analysis using the historical pattern and future predictions. For instance, in scenario 1, the prediction of future ground water levels 30 could rely on a situation where the future conditions of all components (such as
14
weather, soil, population, etc.) are assumed to be identical to those observed in the
past. In scenario 2, specific components such as weather and population are anticipated to undergo changes (positive or negative) compared to their previous states whereas other components have the same future trend as observed in past. Similarly, various other scenarios can be generated. 5
[036]
For each parameter extraction, the data used are (1) the freely available satellite data from optical satellites such as Sentinel-2, Landsat, and SAR satellites such as Sentinel-1 and the like, (2) government statistics or (3) any other sources available. For ground water prediction, a comprehensive process-based model is developed where each parameter derived from the particular components 10 (i.e. weather conditions, soil properties, agricultural data, population statistics, water resources information, industrial details, drought records, seismic data, and surface deformation patterns) is collectively used along with the future scenario information (future cropping pattern, forecasted weather conditions, use of irrigation system in future, and future population growth). 15
[037]
Hence in predicting the future ground water level, the present disclosure considers parameters such as weather conditions, soil properties, agriculture data, population data, water resources information, industry details, drought information, seismic data, and surface deformation trends over the years for the specific region. 20
[038]
Referring now to the drawings, and more particularly to FIG. 1 through FIG. 3C, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments, and these embodiments are described in the context of the following exemplary systems and/or methods. 25
[039]
FIG. 1 is an exemplary block diagram of a system 100 for ground water prediction using integration of satellite and auxiliary observations, in accordance with some embodiments of the present disclosure. In an embodiment, the system 100 includes or is otherwise in communication with one or more hardware processors 104, communication interface device(s) or input/output (I/O) 30 interface(s) 106, and one or more data storage devices or memory 102 operatively
15
coupled to the one or more hardware processors 104
. The one or more hardware processors 104, the memory 102, and the I/O interface(s) 106 may be coupled to a system bus 108 or a similar mechanism.
[040]
The I/O interface(s) 106 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface (GUI), 5 and the like. The I/O interface(s) 106 may include a variety of software and hardware interfaces, for example, interfaces for peripheral device(s), such as a keyboard, a mouse, an external memory, a plurality of sensor devices, a printer and the like. Further, the I/O interface(s) 106 may enable the system 100 to communicate with other devices, such as web servers and external databases. 10
[041]
The I/O interface(s) 106 can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, local area network (LAN), cable, etc., and wireless networks, such as Wireless LAN (WLAN), cellular, or satellite. For the purpose, the I/O interface(s) 106 may include one or more ports for connecting a number of computing systems 15 with one another or to another server computer. Further, the I/O interface(s) 106 may include one or more ports for connecting a number of devices to one another or to another server.
[042]
The one or more hardware processors 104 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal 20 processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the one or more hardware processors 104 are configured to fetch and execute computer-readable instructions stored in the memory 102. In the context of the present disclosure, the expressions ‘processors’ and ‘hardware processors’ may 25 be used interchangeably. In an embodiment, the system 100 can be implemented in a variety of computing systems, such as laptop computers, portable computers, notebooks, hand-held devices, workstations, mainframe computers, servers, a network cloud and the like.
[043]
The memory 102 may include any computer-readable medium 30 known in the art including, for example, volatile memory, such as static random
16
access memory (SRAM) and dynamic random access memory (DRAM), and/or
non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. In an embodiment, the memory 102 includes a plurality of modules 102a and a repository 102b for storing data processed, received, and generated by one or more of the 5 plurality of modules 102a. The plurality of modules 102a may include routines, programs, objects, components, data structures, and so on, which perform particular tasks or implement particular abstract data types.
[044]
The plurality of modules 102a may include programs or computer-readable instructions or coded instructions that supplement applications or 10 functions performed by the system 100. The plurality of modules 102a may also be used as, signal processor(s), state machine(s), logic circuitries, and/or any other device or component that manipulates signals based on operational instructions. Further, the plurality of modules 102a can be used by hardware, by computer-readable instructions executed by the one or more hardware processors 104, or by 15 a combination thereof. In an embodiment, the plurality of modules 102a can include various sub-modules (not shown in FIG. 1). Further, the memory 102 may include information pertaining to input(s)/output(s) of each step performed by the processor(s) 104 of the system 100 and methods of the present disclosure.
[045]
The repository 102b may include a database or a data engine. 20 Further, the repository 102b amongst other things, may serve as a database or includes a plurality of databases for storing the data that is processed, received, or generated as a result of the execution of the plurality of modules 102a. Although the repository 102b is shown internal to the system 100, it is noted that, in alternate embodiments, the repository 102b can also be implemented external to the system 25 100, where the repository 102b may be stored within an external database (not shown in FIG. 1) communicatively coupled to the system 100. The data contained within such external database may be periodically updated. For example, data may be added into the external database and/or existing data may be modified and/or non-useful data may be deleted from the external database. In one example, the data 30 may be stored in an external system, such as a Lightweight Directory Access
17
Protocol (LDAP) directory and a Relational Database Management System
(RDBMS). In another embodiment, the data stored in the repository 102b may be distributed between the system 100 and the external database.
[046]
Referring collectively to FIG. 2 and FIGS. 3A through 3C, components and functionalities of the system 100 are described in accordance with 5 an example embodiment of the present disclosure. For example, FIG. 2 is an exemplary block diagram illustrating the plurality of modules 102a of the system 100 of FIG. 1, for ground water prediction using integration of satellite and auxiliary observations, in accordance with some embodiments of the present disclosure. In an embodiment, the plurality of modules 102a include a weather and 10 soil process-based model 202, an agriculture process-based model 204, a population process-based model 206, a soil and surface process-based model 208, an industry process-based model 210, a pretrained machine learning model for drought 212, a seismic process-based model 214, a surface deformation process-based model 216, and a process-based weighted integrated forecasting model 218. 15
[047]
For example, FIGS. 3A through 3C illustrate exemplary flow diagrams of a processor-implemented method 300 for ground water prediction using integration of satellite and auxiliary observations, using the system 100 of FIG. 1, in accordance with some embodiments of the present disclosure. Although steps of method 300 including process steps, method steps, techniques or the like 20 may be described in a sequential order, such processes, methods, and techniques may be configured to work in alternate orders. In other words, any sequence or order of steps that may be described does not necessarily indicate a requirement that the steps be performed in that order. The steps of processes described herein may be performed in any practical order. Further, some steps may be performed 25 simultaneously, or some steps may be performed alone or independently.
[048]
At step 302 of the method 300, the one or more hardware processors 104 of the system 100 are configured to receive an input data associated to a predefined geographical region for which a ground water level is to be predicted. In an embodiment, the input data associated to the predefined geographical region 30 is received from a remote sensing satellite data and one or more input information
18
sources.
In an embodiment, the remote sensing satellite data is obtained from satellite centers maintained by various public and private bodies or entities. In an embodiment, the one or more input information sources include but are not limited to databases of weather, soil, agriculture, population, surface water, industry and drought data maintained by various public and private bodies or entities. 5
[049]
At step 304 of the method 300, the one or more hardware processors 104 of the system 100 are configured to determine an input parameter data associated to the predefined geographical region for which the ground water level is to be predicted. The input data associated to predefined geographical region received at step 302 of the method 300 is utilized to determine the input parameter 10 data. In an embodiment, the input parameter data includes one or more of (i) one or more weather related parameters, (ii) one or more soil related parameters, (iii) one or more agriculture related parameters, (iv) one or more population related parameters, (v) one or more surface water related parameters, (vi) one or more industry related parameters, (vii) one or more drought related parameters, (viii) one 15 or more seismic related parameters, and (ix) one or more surface deformation related parameters.
[050]
In an embodiment, the input parameter data is of a predefined time period having a start date (𝑡1) and end date (𝑡2), and the data of each of the parameters is of a predefined frequency such as daily, weekly, monthly, and so on. 20
[051]
In an embodiment, the one or more weather related parameters includes (i) a daily rainfall, (ii) a daily land surface temperature, and (iii) a daily evapotranspiration rate. The daily rainfall is defined as an amount of precipitation, in the form of rain (water from clouds), that descends onto the surface of Earth each day. The daily land surface temperature is a measurement of how hot the land is 25 during the rainfall each day. The daily evapotranspiration rate is defined as a sum of all processes by which water moves from the land surface to the atmosphere via evaporation and transpiration.
[052]
In an embodiment, the daily rainfall data (𝑅𝑡1−𝑡2) is determined using a Precipitation Estimation from Remotely Sensed Information using Artificial 30 Neural Networks-Cloud Classification System (PERSIANN-CCS) tool from the
19
rain data. In an embodiment, the
daily land surface temperature data (𝐿𝑆𝑇𝑡1−𝑡2) is determined from a Moderate Resolution Imaging Spectroradiometer (MODIS), wherein the (𝐿𝑆𝑇𝑡1−𝑡2) is available with spatial resolution of 1 km provided by MODIS. In an embodiment, the daily evapotranspiration rate data (𝐸𝑡1−𝑡2) is determined using a United States Geological Survey (USGS) Famine Early 5 Warning Systems Network (FEWS NET) data portal.
[053]
In an embodiment, the one or more soil related parameters include (i) a soil type, (ii) soil compaction index (SCI), (iii) a soil saturation level (SSL), and (iv) a soil infiltration capacity. The soil type is defined as the type of soil present in the predefined geographical region. The soil can be classified into three primary 10 types based on its texture – sand, silt, and clay. However, the percentage of these can vary, resulting in more compound types of soil such as loamy sand, sandy clay, silty clay, and so on. The soil compaction index (SCI) is defined as a measure of compactness in soil in terms of a density and a pore space. The soil saturation level (SSL) is the threshold at which all the pores (empty spaces between the solid soil 15 particles) are filled with water. The soil infiltration capacity is the maximum rate at which the soil is capable of absorbing water in a given condition.
[054]
In an embodiment, the information on spatially distributed soil type (𝑆𝑇) is determined from a machine-learning or a deep-learning based image texture analysis model where the Sentinel-1 derived radar backscatter response in vertical-20 vertical (VV) and vertical-horizontal (VH) polarization along with the local incidence angle (LIA) is used. Radar backscatter response in VV and VH polarization is denoted as 𝜎𝑉𝑉0 and 𝜎𝑉𝐻0, respectively. For each 𝑆𝑇, radar backscatter response in the polarization is different. Model may take the following form to determine the spatially distributed soil type (𝑆𝑇): 25
𝑆𝑇=𝑓(𝜎𝑉𝑉0, 𝜎𝑉𝐻0,𝐿𝐼𝐴)
[055]
In an embodiment, the spatially distributed soil compaction index (𝑆𝐶𝐼) is determined from the machine-learning or deep-learning based approach. The 𝑆𝐶𝐼 is defines as a function of 𝑆𝑇, 𝑆𝑜𝑀𝑜𝑡1−𝑡2, 𝐿𝑆𝑇𝑡1−𝑡2. It is important to highlight that determining the 𝑆𝐶𝐼 using remote sensing involves identifying 30 indirect indicators or proxies that can provide information about the compactness
20
of the soil without directly measuring it.
The 𝑆𝐶𝐼 ranges from 0 to 1, where 0 represents low compaction whereas 1 represent very high compaction. Model may take the following form to determine the spatially distributed soil compaction index (𝑆𝐶𝐼):
𝑆𝐶𝐼=𝑓(𝑆𝑇, 𝑆𝑜𝑀𝑜𝑡1−𝑡2, 𝐿𝑆𝑇𝑡1−𝑡2) 5
wherein, 𝑆𝑜𝑀𝑜𝑡1−𝑡2 can be estimated using Dubois and Topp’s coupled model, where Sentinel-1 derived 𝜎𝑉𝑉0 is used as an input parameter.
[056]
In an embodiment, the spatially distributed soil saturation level (𝑆𝑆𝐿) is determined from the machine-learning or the deep-learning based approach. The 𝑆𝑆𝐿 can be defined as a function of 𝑆𝑇 and 𝑆𝐶𝐼. Model may take the 10 following form to determine the spatially distributed soil saturation level (𝑆𝑆𝐿):
𝑆𝑆𝐿=𝑓(𝑆𝑇, 𝑆𝐶𝐼)
[057]
In an embodiment, the spatially distributed soil infiltration capacity (𝑆𝐼𝐶) is determined from the machine-learning or deep-learning based approach. The soil infiltration capacity (𝑆𝐼𝐶) can be define as a function of 𝑆𝑇, 𝑆𝐶𝐼 and 𝑆𝑆𝐿 15 Model may take the following form:
𝑆𝐼𝐶=𝑓(𝑆𝑇, 𝑆𝐶𝐼, 𝑆𝑆𝐿)
[058]
In an embodiment, the one or more agriculture related parameters include (i) a total agriculture area, (ii) a type of crop grown in each season, and (iii) a crop grown area in each season. The total agriculture area is an area of agricultural 20 land that is typically devoted to agriculture in the predefined geographical region of interest. The type of crop grown in each season provides details about which crop grown in Kharif as well as Rabi season in the predefined geographical region of interest. The crop grown area in each season is the estimated season-wise and crop-wise cultivation area. 25
[059]
The agriculture sector is heavily dependent upon the ground water available in the region. Each crop needs a particular amount of water during the complete crop cycle. Since, this component only consider impact of agriculture, the total agriculture area (𝑇𝐴𝐴𝑡1−𝑡2) in the given region of interest needs to be determined. In an embodiment, the total agriculture area (𝑇𝐴𝐴𝑡1−𝑡2) is a function 30 of spatially distributed Normalized Difference Vegetation Index (𝑁𝐷𝑉𝐼) derived
21
from Sentinel
-2, and radar backscatter response (𝜎𝑉𝑉0 and 𝜎𝑉𝐻0) obtained from Sentinel-1. The 𝑁𝐷𝑉𝐼, 𝜎𝑉𝑉0 and 𝜎𝑉𝐻0 are obtained for two different dates- Date 1 and Date 2. Date 1 represents time when region is completely empty (bare soil) whereas Date 2 represents time of peak vegetation. The values of all the indices at the pixel level are altered due to the cultivation of crops on agricultural land. By comparing 5 the differences in pixel-level values, the total agriculture area (𝑇𝐴𝐴𝑡1−𝑡2) is determined using a following set of equations:
𝑁𝐷𝑉𝐼(𝑑𝑖𝑓𝑓)=𝑁𝐷𝑉𝐼(𝑑𝑎𝑡𝑒 1)−𝑁𝐷𝑉𝐼 (𝑑𝑎𝑡𝑒 2) 𝜎𝑉𝑉0(𝑑𝑖𝑓𝑓)=𝜎𝑉𝑉0(𝑑𝑎𝑡𝑒 1)−𝜎𝑉𝑉0(𝑑𝑎𝑡𝑒 2) 𝜎𝑉𝐻0(𝑑𝑖𝑓𝑓)=𝜎𝑉𝐻0(𝑑𝑎𝑡𝑒 1)−𝜎𝑉𝐻0(𝑑𝑎𝑡𝑒 2) 10 𝑇𝐴𝐴𝑡1−𝑡2=𝑓(𝑁𝐷𝑉𝐼(𝑑𝑖𝑓𝑓),𝜎𝑉𝑉0(𝑑𝑖𝑓𝑓),𝜎𝑉𝐻0(𝑑𝑖𝑓𝑓))
[060]
A machine-learning or deep learning crop classification model is developed based on 𝑁𝐷𝑉𝐼 and radar backscatter response (𝜎𝑉𝑉0 and 𝜎𝑉𝐻0) to determine the type of crop grown in each season (𝐶𝑇𝑦𝑝𝑒𝑡1−𝑡2). The basic idea is that each crop is giving different signature in 𝑁𝐷𝑉𝐼, 𝜎𝑉𝑉0 and 𝜎𝑉𝐻0). Therefore, 15 collective utilization of these indices helps to identify which crop (e.g. rice, wheat, corn etc.) is grown in the region of interest. The type of crop grown in each season (𝐶𝑇𝑦𝑝𝑒𝑡1−𝑡2) is defined as the function of 𝑁𝐷𝑉𝐼, 𝜎𝑉𝑉0 and 𝜎𝑉𝐻0), and is mathematically represented as a below equation:
𝐶𝑇𝑦𝑝𝑒𝑡1−𝑡2=𝑓(𝑁𝐷𝑉𝐼, 𝜎𝑉𝑉0 and 𝜎𝑉𝐻0) 20
[061]
Later, the crop grown area in each season (𝐶𝐺𝐴𝑡1−𝑡2) is determined for each crop type in the given season. The 𝐶𝐺𝐴𝑡1−𝑡2 is determined by using pixel-level 𝐶𝑇𝑦𝑝𝑒𝑡1−𝑡2 information and is defined as below equation:
𝐶𝐺𝐴𝑡1−𝑡2=𝑓(𝐶𝑇𝑦𝑝𝑒𝑡1−𝑡2 )
[062]
In an embodiment, the one or more population related parameters 25 include (i) a year-wise population amount, (ii) a population growth rate, (iii) a year-wise number of residential establishments, (iv) a year-wise number of residential establishments with ground water recharge facilities, and (v) a year-wise area of residential establishments with ground water recharge facilities.
22
[063]
It is well-known that huge amounts of water have been utilized by the population for domestic purposes. Therefore, to forecast ground water condition, it is important to know how much the year-wise population in the given region between time 𝑡1 and 𝑡2. Also, it is important to know how much amount of water is given back to the aquifer through rainwater harvesting facilities installed 5 on each house present in the region of interest.
[064]
In an embodiment, the year-wise population amount data (𝑃𝑡1−𝑡2) is determined using population data obtained from the government entity sources. As the population increases, so does the demand for water. More people mean more water is required for drinking, sanitation, agriculture, industry, and other activities. 10 This increased demand puts pressure on existing water sources and leads to water scarcity in some regions.
[065]
In an embodiment, the yearly population growth rate data (𝑃𝐺𝑅𝑡1−𝑡2) is determined from the year-wise population amount data (𝑃𝑡1−𝑡2) collected between 𝑡1 and 𝑡2. Because of the positive growth rate of population, 15 there is a greater likelihood of over-pumping and depleting ground water reserves faster than they can naturally recharge. This can lead to long-term water quality degradation and land subsidence.
𝑃𝐺𝑅𝑡1−𝑡2=𝑓(𝑃𝑡1−𝑡2)
[066]
In an embodiment, the Geo-tagged year-wise number of residential 20 establishments (𝑃𝐸𝑡1−𝑡2) is determined as a function of Normalized Difference Build-up Index (𝑁𝐷𝐵𝐼), 𝜎𝑉𝑉0 and 𝜎𝑉𝐻0). 𝑁𝐷𝐵𝐼 highlights urban areas and can be derived from Sentinel-2 data. Similarly, 𝜎𝑉𝑉0 and 𝜎𝑉𝐻0 estimated from Sentinel-1 give specific signatures for build-up area. This information helps to estimate the average water consumption by the individual house and building. 25
𝑃𝐸𝑡1−𝑡2=𝑓(𝑁𝐷𝐵𝐼, 𝜎𝑉𝑉0, 𝜎𝑉𝐻0)
[067]
In an embodiment, the Geo-tagged year-wise number of residential establishments with ground water recharge facilities data (𝑃𝐸𝑊𝑡1−𝑡2) is determined from the data sources collected by the government. This information helps to identify which house (geo-tagged location) in the region of interest is equipped with 30 artificial ground water recharge facility every year between time 𝑡1 and 𝑡2.
23
[068]
In an embodiment, the year-wise area of residential establishments with ground water recharge facilities (A𝑃𝐸𝑊𝑡1−𝑡2) is determined from the Geo-tagged year-wise number of residential establishments with ground water recharge facilities data (𝑃𝐸𝑊𝑡1−𝑡2) . Next, based on 𝑁𝐷𝐵𝐼, 𝜎𝑉𝑉0, 𝜎𝑉𝐻0 area of individual house and building equipped with ground water recharge facility is estimated. Individual 5 houses and building areas are also helpful in determining the amount of water going back to the aquifer from that particular house.
𝐴𝑃𝐸𝑊𝑡1−𝑡2=𝑓(𝑃𝐸𝑊𝑡1−𝑡2, 𝑁𝐷𝐵𝐼, 𝜎𝑉𝑉0, 𝜎𝑉𝐻0)
[069]
In an embodiment, the one or more surface water related parameters include (i) a total area of one or more water reserve sources, and (ii) a total water 10 holding capacity of the one or more water reserve sources. Water infiltration from lakes, ponds and rivers to aquifers refers to the process by which water from surface water bodies, such as lakes, ponds and rivers, seeps through the soil and permeable rock layers to recharge the aquifers. This natural process is a vital component of the water cycle and plays a significant role in maintaining ground water levels and 15 sustaining the overall water supply.
[070]
In an embodiment, the one or more water reserve sources includes but are not limited to lakes, ponds, dams, and rivers present in the predefined geographical region. Hence the total area of the one or more water reserve sources is defined as a combined area of the one or more water reserve sources present in 20 the predefined geographical region. Similarly, the total water holding capacity of the one or more water reserve sources is defined as a combined capacity of the one or more water reserve sources present in the predefined geographical region. In an embodiment, the total area of one or more water reserve sources (𝑇𝐴𝑊𝑡1−𝑡2), and the total water holding capacity of the one or more water reserve sources 25 (𝑇𝐴𝑊𝐻𝐶𝑡1−𝑡2), are determined from the Normalized Difference Water Index (𝑁𝐷𝑊𝐼), 𝜎𝑉𝑉0, 𝜎𝑉𝐻0, and local incidence angle (𝐿𝐼𝐴).
[071]
The 𝑁𝐷𝑊𝐼 highlights open water features in a satellite image, allowing a water body to stand out against the soil and vegetation. It can be obtained from the band combination of Sentinel-2 satellite data. The 𝜎𝑉𝑉0, 𝜎𝑉𝐻0 response of 30 the one or more water reserve sources is influenced by its surface conditions, such
24
as the presence of waves, ripples, or smoothness. Calm water surfaces tend to
produce lower backscatter values, while rougher surfaces with waves or other disturbances can lead to increased backscatter. The response also depends upon the radar frequency and local incidence angle (𝐿𝐼𝐴).
[072]
In an embodiment, the one or more industry related parameters 5 include (i) a year-wise number of industry establishments, (ii) year-wise type of industry establishments, (iii) a year-wise total amount of ground water utilized by industry establishments, (iv) a year-wise number of industry establishments with ground water recharge facilities, (v) a year-wise area of permanent industry establishments with ground water recharge facilities, and (vi) a year-wise total 10 amount of rain water given to aquifer by industry establishments.
[073]
Industries that heavily rely on water for activities such as manufacturing processes, cooling, cleaning, and other purposes can contribute significantly to ground water extraction in certain regions. It's important to note that the impact of industrial ground water extraction on local water resources can be 15 significant, especially in regions with water scarcity or over exploited aquifers. The year-wise number of industry establishments (𝑁𝐼𝑡1−𝑡2) with geo-tagged location, the year-wise type of industry establishments (𝑇𝐼𝑡1−𝑡2), the year-wise number of industry establishments with ground water recharge facilities (𝐼𝑊𝑅𝑡1−𝑡2), and the year-wise area of permanent industry establishments with ground water recharge 20 facilities (𝐼𝐴𝑊𝑅𝑡1−𝑡2), are utilized in order to determine the impact of industrial ground water extraction.
[074]
In an embodiment, 𝑁𝐼𝑡1−𝑡2, 𝑇𝐼𝑡1−𝑡2 , and 𝐼𝑊𝑅𝑡1−𝑡2 are obtained from government records. 𝐼𝐴𝑊𝑅𝑡1−𝑡2 is obtained from the geo-tagged 𝐼𝑊𝑅𝑡1−𝑡2. 𝑁𝐼𝑡1−𝑡2 and 𝑇𝐼𝑡1−𝑡2 is combinedly used to determine the year-wise total amount of 25 ground water utilized by industry establishments (𝑇𝐴𝐺𝑊𝑡1−𝑡2)
𝑇𝐴𝐺𝑊𝑡1−𝑡2=𝑓(𝑁𝐼𝑡1−𝑡2, 𝑇𝐼𝑡1−𝑡2)
[075]
In an embodiment, the year-wise total amount of rainwater given to aquifer by industry establishments (𝑇𝐴𝐺𝑊𝐴𝑡1−𝑡2) is computing using below relation: 30
25
𝑇𝐴𝐺𝑊𝐴𝑡1−𝑡2=𝑓(𝐼𝑊𝑅𝑡1−𝑡2,𝐼𝐴𝑊𝑅𝑡1−𝑡2,𝐷𝑅𝑡1−𝑡2,𝐷𝐸𝑡1−𝑡2,𝑆𝑇,𝑆𝐶𝐼,𝑆𝑆𝐿,𝑆𝐼𝐶)
[076]
In an embodiment, the one or more drought related parameters include (i) a season-wise spatially distributed drought affected area, and (ii) a season-wise spatially distributed drought intensity. The season-wise spatially 5 distributed drought affected area (𝐷𝐴𝐴𝑡1−𝑡2) refers to the predefined geographic region or location that is experiencing the adverse impacts of the drought conditions. The season-wise spatially distributed drought intensity (𝐷𝐼𝑛𝑡1−𝑡2) refers to the severity or degree of dryness and water scarcity experienced during a drought event. 10
[077]
In an embodiment, the season-wise spatially distributed drought affected area (𝐷𝐴𝐴𝑡1−𝑡2) is determined using the machine-learning or the deep learning based model where long-term spatially distributed soil moisture (𝑆𝑜𝑀𝑜𝑡1−𝑡2) information, NDVI time-series (𝑁𝐷𝑉𝐼𝑡1−𝑡2) and other input parameter i.e. daily land surface temperature (𝐷𝐿𝑆𝑇𝑡1−𝑡2) of weather component 15 are used as features.
𝐷𝐴𝐴𝑡1−𝑡2=𝑓(𝑆𝑜𝑀𝑜𝑡1−𝑡2,𝑁𝐷𝑉𝐼𝑡1−𝑡2,𝐷𝐿𝑆𝑇𝑡1−𝑡2)
Wherein 𝑆𝑜𝑀𝑜𝑡1−𝑡2 is estimated using Dubois and Topp’s coupled model, where Sentinel-1 derived 𝜎𝑉𝑉0 is used as an input parameter. 𝑁𝐷𝑉𝐼𝑡1−𝑡2 is derived from the Sentinel-2 satellite data. The daily land surface temperature 20 (𝐷𝐿𝑆𝑇𝑡1−𝑡2)belongs to the weather component and is obtained from remote sensing data.
[078]
In an embodiment, the season-wise spatially distributed drought intensity (𝐷𝐼𝑛𝑡1−𝑡2) is determined using the machine-learning or the deep learning based model where long-term spatially distributed soil moisture (𝑆𝑜𝑀𝑜𝑡1−𝑡2) 25 information, NDVI time-series (𝑁𝐷𝑉𝐼𝑡1−𝑡2) and other multiple input parameters i.e. the daily rainfall data (𝐷𝑅𝑡1−𝑡2), the daily land surface temperature (𝐷𝐿𝑆𝑇𝑡1−𝑡2) and daily evapotranspiration (𝐷𝐸𝑡1−𝑡2) of the weather are used as features.
𝐷𝐼𝑛𝑡1−𝑡2=𝑓(𝑆𝑜𝑀𝑜𝑡1−𝑡2,𝑁𝐷𝑉𝐼𝑡1−𝑡2,𝐷𝑅𝑡1−𝑡2,𝐷𝐿𝑆𝑇𝑡1−𝑡2,𝐷𝐸𝑡1−𝑡2) 30
26
[079]
In an embodiment, the one or more seismic related parameters include (i) a region of interest (RoI) seismic zone type, and (ii) a year-wise seismic magnitude. Seismic activities, such as earthquakes and ground vibrations, can potentially impact underground water resources in various ways. Some of the ways seismic activities can contribute to underground water depletion are: 5
•
Seismic activities can alter the storage capacity of aquifers and affect the recharge rates. The ground movements associated with earthquakes can compress or expand the subsurface rock formations, affecting the available pore space for storing water. This can lead to changes in the aquifer's ability to store and replenish ground water. 10
•
Seismic activities can cause the compaction of aquifer materials due to increased stress and shaking. This compaction can reduce the overall porosity of the aquifer, leading to a permanent loss of water storage capacity.
•
Seismic activities can cause faulting, which can offset aquifer layers and 15 change the ground water flow patterns.
[080]
The region of interest (RoI) seismic zone type (𝑆𝑍) refers to a geographic region that is susceptible to experiencing seismic activity, particularly earthquakes. The year-wise seismic magnitude (𝑆𝑀𝑡1−𝑡2) is a measure of the size or energy release of an earthquake. In an embodiment, the region of interest (RoI) 20 seismic zone type (𝑆𝑍) and the year-wise seismic magnitude (𝑆𝑀𝑡1−𝑡2) are determined from data obtained from government records or other input sources.
[081]
In an embodiment, the one or more surface deformation related parameters include a year-wise amount of land surface deformation. Land surface deformation is indeed served as a proxy or indicator of ground water depletion in 25 certain regions. This subsidence is a clear indication of ground water depletion, and it can be monitored and studied using different techniques, such as Interferometric Synthetic Aperture Radar (InSAR) and GPS measurements. In an embodiment, the year-wise amount of land surface deformation i.e. subsidence or uplifting (𝐿𝑆𝑡1−𝑡2) happened between time 𝑡1 and 𝑡2 over the given region is determined using the 30 small baseline subset (SBAS) InSAR technique.
27
[082]
The processing steps for determining the year-wise amount of land surface deformation (𝐿𝑆𝑡1−𝑡2) using the SBAS InSAR typically include:
•
Data Acquisition: Acquire a series of Sentinel-1 SAR images covering the area of interest. These images should be obtained with a short revisit time to capture the temporal changes in the land surface. 5
•
Pre-processing of SAR Data: Pre-process the SAR data to correct for artifacts and radiometric distortions. This step includes radiometric calibration, removal of thermal noise, speckle filtering, and geometric correction to ensure the data are in the appropriate format for InSAR processing. 10
•
Interferogram Generation: Perform interferometric processing to generate a series of interferograms. An interferogram is a combination of two SAR images taken at different times, and it represents the phase difference between the two acquisitions.
•
SBAS Processing: Implement the SBAS algorithm, which stands for Small 15 Baseline Subset. SBAS is a method that selects small baseline interferograms and groups them together to create a network of interferograms with minimal temporal and spatial decorrelation. This step is crucial for monitoring large areas with significant subsidence.
•
Phase Unwrapping: During interferometric processing, the phase values 20 obtained may be wrapped between -π and +π due to the inherent 2π ambiguity. Phase unwrapping is necessary to convert the wrapped phase into continuous values, allowing accurate measurements of the deformation.
•
Phase to Displacement Conversion: Convert the unwrapped phase values into displacement values in the line-of-sight direction (LOS). This step 25 involves using the radar wavelength and satellite geometry to convert the phase measurements into vertical deformation values (subsidence or uplift) in millimeters.
•
Temporal Coherence Thresholding: Apply a temporal coherence threshold to filter out areas with low coherence, which can occur due to vegetation, 30
28
decorrelation, or atmospheric effects. Low coherence areas may lead to
inaccurate deformation measurements.
•
Time-Series Analysis: Create a time-series of the estimated land subsidence by combining the deformation information (i.e. SDt1-t2) from multiple interferograms over time. This provides a comprehensive view of the land 5 surface behavior and allows for the identification of areas with continuous subsidence trends.
[083]
At step 306 of the method 300, the one or more hardware processors 104 of the system 100 are configured to pass the input parameter data of the one or more weather related parameters and the one or more soil related parameters 10 determine at step 304 of the method 300, to a weather and soil process-based model 202, to obtain an amount of total surface water from rainfall infiltrated to aquifer (𝑄𝑅𝑡1−𝑡2) during the predefined time period 𝑡1 and 𝑡2.
[084]
In an embodiment, the weather and soil process-based model 202 is one of a pretrained ML model or a process-based model that predicts the amount of 15 total surface water from rainfall infiltrated to aquifer (𝑄𝑅𝑡1−𝑡2) during the predefined time period 𝑡1 and 𝑡2. In an embodiment, the pretrained ML model is obtained by training a suitable ML model such as a classification model or a regression model with a suitable training data of the one or more weather related parameters and the one or more soil related parameters. In an embodiment, the 20 process-based model is obtained by using relationships that are described in terms of explicitly stated processes or mechanisms based on established scientific understanding.
[085]
A model equation of the weather and soil process-based model 202, to obtain the amount of total surface water from rainfall infiltrated to aquifer 25 (𝑄𝑅𝑡1−𝑡2) during the predefined time period 𝑡1 and 𝑡2, is mathematically represented as:
𝑄𝑅𝑡1−𝑡2=𝑓(𝑅𝑡1−𝑡2,𝐿𝑆𝑇𝑡1−𝑡2,𝐸𝑡1−𝑡2,𝑆𝑇,𝑆𝐶𝐼,𝑆𝑆𝐿,𝑆𝐼𝐶)
[086]
At step 308 of the method 300, the one or more hardware processors 104 of the system 100 are configured to pass the input parameter data of the one or 30 more agriculture related parameters, to an agriculture process-based model 204, to
29
obtain an amount of ground water extracted from aquifer for agriculture
(𝑄𝐸−𝐴𝑡1−𝑡2) during the predefined time period 𝑡1 and 𝑡2.
[087]
In an embodiment, the agriculture process-based model 204 is one of the pretrained ML model or the process-based model that is made to predict the amount of ground water extracted from aquifer for agriculture (𝑄𝐸−𝐴𝑡1−𝑡2) 5 during the predefined time period 𝑡1 and 𝑡2. In an embodiment, the pretrained ML model is obtained by training a suitable ML model such as a classification model or a regression model with a suitable training data of the one or more agriculture related parameters. In an embodiment, the process-based model is obtained by using relationships that are described in terms of explicitly stated processes or 10 mechanisms based on established scientific understanding.
[088]
The model equation of the agriculture process-based model 204, to obtain the amount of ground water extracted from aquifer for agriculture (𝑄𝐸−𝐴𝑡1−𝑡2) during the predefined time period 𝑡1 and 𝑡2, is mathematically represented as: 15
𝑄𝐸−𝐴𝑡1−𝑡2=𝑓(𝑇𝐴𝐴𝑡1−𝑡2, 𝐶𝑇𝑦𝑝𝑒𝑡1−𝑡2, 𝐶𝐺𝐴𝑡1−𝑡2)
[089]
At step 310 of the method 300, the one or more hardware processors 104 of the system 100 are configured to pass the input parameter data of the one or more population related parameters, to a population process-based model 206, to obtain a net amount of ground water extracted from aquifer by population 20 (𝑄𝐸−𝑃𝑡1−𝑡2) during the predefined time period 𝑡1 and 𝑡2.
[090]
In an embodiment, the population process-based model 206 is one of the pretrained ML model or the process-based model that is made to predict the net amount of ground water extracted from aquifer by population (𝑄𝐸−𝑃𝑡1−𝑡2) during the predefined time period 𝑡1 and 𝑡2. In an embodiment, the pretrained ML 25 model is obtained by training a suitable ML model such as a classification model or a regression model with a suitable training data of the one or more population related parameters. In an embodiment, the process-based model is obtained by using relationships that are described in terms of explicitly stated processes or mechanisms based on established scientific understanding. 30
30
[091]
The model equation of the population process-based model 206, to obtain the net amount of ground water extracted from aquifer by population (𝑄𝐸−𝑃𝑡1−𝑡2) during the predefined time period 𝑡1 and 𝑡2, is mathematically represented as:
𝑄𝐸−𝑃𝑡1−𝑡2=𝑓(𝑃𝑡1−𝑡2, 𝑃𝐺𝑅𝑡1−𝑡2, 𝑃𝐸𝑡1−𝑡2,𝑃𝐸𝑊𝑡1−𝑡2, 𝐴𝑃𝐸𝑊𝑡1−𝑡2) 5
[092]
At step 312 of the method 300, the one or more hardware processors 104 of the system 100 are configured to pass the input parameter data of the one or more soil related parameters and the one or more surface water related parameters, to a soil and surface process-based model 208, to obtain a net amount of ground water infiltrated to aquifer through one or more water sources (𝑄𝑅−𝑊𝑅𝑡1−𝑡2) 10 during the predefined time period 𝑡1 and 𝑡2.
[093]
In an embodiment, the soil and surface process-based model 208 is one of the pretrained ML model or the process-based model that is made to predict the net amount of ground water infiltrated to aquifer through one or more water sources (𝑄𝑅−𝑊𝑅𝑡1−𝑡2) during the predefined time period 𝑡1 and 𝑡2. In an 15 embodiment, the pretrained ML model is obtained by training a suitable ML model such as a classification model or a regression model with a suitable training data of the one or more soil related parameters and the one or more surface water related parameters. In an embodiment, the process-based model is obtained by using relationships that are described in terms of explicitly stated processes or 20 mechanisms based on established scientific understanding.
[094]
The model equation of the soil and surface process-based model 208 to predict the net amount of ground water infiltrated to aquifer through one or more water sources (𝑄𝑅−𝑊𝑅𝑡1−𝑡2) during the predefined time period 𝑡1 and 𝑡2, is mathematically represented as: 25
𝑄𝑅−𝑊𝑅𝑡1−𝑡2=𝑓(𝑇𝐴𝑊𝑡1−𝑡2,𝑇𝐴𝑊𝐻𝐶𝑡1−𝑡2,𝑆𝑇,𝑆𝐶𝐼,𝑆𝑆𝐿,𝑆𝐼𝐶)
[095]
At step 314 of the method 300, the one or more hardware processors 104 of the system 100 are configured to pass the input parameter data of the one or more industry related parameters, to an industry process-based model 210, to obtain a net amount of ground water extracted from aquifer for industrial use 30 (𝑄𝐸−𝐼𝑡1−𝑡2 ) during the predefined time period 𝑡1 and 𝑡2.
31
[096]
In an embodiment, the industry process-based model 210 is one of the pretrained ML model or the process-based model that is made to predict the net amount of ground water extracted from aquifer for industrial use (𝑄𝐸−𝐼𝑡1−𝑡2 ) during the predefined time period 𝑡1 and 𝑡2. In an embodiment, the pretrained ML model is obtained by training a suitable ML model such as a 5 classification model or a regression model with a suitable training data of the one or more industry related parameters. In an embodiment, the process-based model is obtained by using relationships that are described in terms of explicitly stated processes or mechanisms based on established scientific understanding.
[097]
The model equation of the industry process-based model 210 to 10 predict the net amount of ground water extracted from aquifer for industrial use (𝑄𝐸−𝐼𝑡1−𝑡2 ) during the predefined time period 𝑡1 and 𝑡2, is mathematically represented as:
𝑄𝐸−𝐼𝑡1−𝑡2 =𝑇𝐴𝐺𝑊𝑡1−𝑡2 −𝑇𝐴𝐺𝑊𝐴𝑡1−𝑡2
[098]
At step 316 of the method 300, the one or more hardware processors 15 104 of the system 100 are configured to pass the input parameter data of the one or more drought related parameters, to a pretrained machine learning model for drought 212, to obtain a drought index (𝐷𝐼𝑡1−𝑡2 ) for the time period 𝑡1 and 𝑡2. The drought index (𝐷𝐼𝑡1−𝑡2 ) value is typically a single number, which ranges 0 to 1, where o indicates low drought-prone area in the predefined geographical region and 20 1 indicates high drought-prone area in the predefined geographical region.
[099]
In an embodiment, the pretrained machine learning model for drought 212, is obtained by training a suitable ML model such as a classification model or a regression model with a suitable training data of the one or more drought related parameters. 25
[0100]
The model equation of the pretrained machine learning model for drought 212, to obtain a drought index (𝐷𝐼𝑡1−𝑡2 ) for the time period 𝑡1 and 𝑡2, is mathematically represented as:
𝐷𝐼𝑡1−𝑡2 =𝑓(𝐷𝐴𝐴𝑡1−𝑡2 ,𝐷𝐼𝑛𝑡1−𝑡2 )
[0101]
At step 318 of the method 300, the one or more hardware processors 30 104 of the system 100 are configured to pass the input parameter data of the one or
32
more seismic related parameters, to a seismic process
-based model 214, to obtain a seismic index (𝑆𝐼𝑡1−𝑡2 ) for the time period 𝑡1 and 𝑡2. The seismic index (𝑆𝐼𝑡1−𝑡2 ) value is typically a single number, which ranges 0 to 1, where o indicates low seismic -prone area in the predefined geographical region and 1 indicates high seismic -prone area in the predefined geographical region. 5
[0102]
In an embodiment, the seismic process-based model 214 is one of the pretrained ML model or the process-based model that is made to predict the seismic index (𝑆𝐼𝑡1−𝑡2 ) for the time period 𝑡1 and 𝑡2. In an embodiment, the pretrained ML model is obtained by training a suitable ML model such as a classification model or a regression model with a suitable training data of the one 10 or more seismic related parameters. In an embodiment, the process-based model is obtained by using relationships that are described in terms of explicitly stated processes or mechanisms based on established scientific understanding.
[0103]
The model equation of the seismic process-based model 214 to predict the seismic index (𝑆𝐼𝑡1−𝑡2 ) for the time period 𝑡1 and 𝑡2, is mathematically 15 represented as:
𝑆𝐼𝑡1−𝑡2 =𝑓(𝑆𝑍,𝑆𝑀𝑡1−𝑡2 )
[0104]
At step 320 of the method 300, the one or more hardware processors 104 of the system 100 are configured to pass the input parameter data of the one or more surface deformation related parameters, to a surface deformation process-20 based model 216, to obtain an amount of total surface deformation (𝑆𝐷𝑡1−𝑡2 ) for the time period 𝑡1 and 𝑡2.
[0105]
In an embodiment, the surface deformation process-based model 216 is one of the pretrained ML model or the process-based model that is made to predict the amount of total surface deformation (𝑆𝐷𝑡1−𝑡2 ). In an embodiment, the 25 pretrained ML model is obtained by training a suitable ML model such as a classification model or a regression model with a suitable training data of the one or more surface deformation related parameters. In an embodiment, the process-based model is obtained by using relationships that are described in terms of explicitly stated processes or mechanisms based on established scientific 30 understanding.
33
[0106]
The model equation of the surface deformation process-based model 216 to predict the amount of total surface deformation (𝑆𝐷𝑡1−𝑡2 ), is mathematically represented as:
𝑆𝐷𝑡1−𝑡2 =Σ𝐿𝑆𝑡1−𝑡2
[0107]
At step 322 of the method 300, the one or more hardware processors 5 104 of the system 100 are configured to pass the (i) the amount of total surface water from rainfall infiltrated to aquifer (𝑄𝑅𝑡1−𝑡2) during the predefined time period 𝑡1 and 𝑡2, (ii) the amount of ground water extracted from aquifer for agriculture (𝑄𝐸−𝐴𝑡1−𝑡2) during the predefined time period 𝑡1 and 𝑡2, (iii) the net amount of ground water extracted from aquifer by population (𝑄𝐸−𝑃𝑡1−𝑡2) during 10 the predefined time period 𝑡1 and 𝑡2, (iv) the net amount of ground water infiltrated to aquifer through one or more water sources (𝑄𝑅−𝑊𝑅𝑡1−𝑡2) during the predefined time period 𝑡1 and 𝑡2, (v) the net amount of ground water extracted from aquifer for industrial use (𝑄𝐸−𝐼𝑡1−𝑡2 ) during the predefined time period 𝑡1 and 𝑡2, (vi) the drought index (𝐷𝐼𝑡1−𝑡2 ) for the time period 𝑡1 and 𝑡2, (vii) the seismic 15 index (𝑆𝐼𝑡1−𝑡2 ) for the time period 𝑡1 and 𝑡2, (viii) the amount of total surface deformation (𝑆𝐷𝑡1−𝑡2 ) for the time period 𝑡1 and 𝑡2, to a process-based weighted integrated forecasting model 218, to predict the ground water level of the predefined geographical region.
[0108]
In an embodiment, the process-based weighted integrated 20 forecasting model 218 is one of the pretrained ML model or the process-based model that is made to predict the ground water level (𝐺𝑊𝐿𝑡1−𝑡2 ) of the predefined geographical region for the time period 𝑡1 and 𝑡2. In an embodiment, the pretrained ML model is obtained by training a suitable ML model such as a classification model or a regression model with a suitable training data of (i) the amount of total 25 surface water from rainfall infiltrated to aquifer (𝑄𝑅𝑡1−𝑡2), (ii) the amount of ground water extracted from aquifer for agriculture (𝑄𝐸−𝐴𝑡1−𝑡2), (iii) the net amount of ground water extracted from aquifer by population (𝑄𝐸−𝑃𝑡1−𝑡2), (iv) the net amount of ground water infiltrated to aquifer through one or more water sources (𝑄𝑅−𝑊𝑅𝑡1−𝑡2), (v) the net amount of ground water extracted from 30
34
aquifer for industrial use
(𝑄𝐸−𝐼𝑡1−𝑡2 ), (vi) the drought index (𝐷𝐼𝑡1−𝑡2 ), (vii) the seismic index (𝑆𝐼𝑡1−𝑡2 ), (viii) the amount of total surface deformation (𝑆𝐷𝑡1−𝑡2 ).
[0109]
In an embodiment, the process-based model is obtained by using relationships that are described in terms of explicitly stated processes or mechanisms based on established scientific understanding. 5
[0110]
The model equation of the process-based weighted integrated forecasting model 218 to predict the ground water level (𝐺𝑊𝐿𝑡1−𝑡2 ) of the predefined geographical region for the time period 𝑡1 and 𝑡2, is mathematically represented as:
𝐺𝑊𝐿𝑡1−𝑡2 =𝑓𝑤𝑒𝑖𝑔ℎ𝑡𝑒𝑑(𝑄𝑅𝑡1−𝑡2,𝑄𝐸−𝐴𝑡1−𝑡2,𝑄𝐸−𝑃𝑡1−𝑡2,𝑄𝑅10 −𝑊𝑅𝑡1−𝑡2,𝑄𝐸−𝐼𝑡1−𝑡2 ,𝐷𝐼𝑡1−𝑡2 ,𝑆𝐷𝑡1−𝑡2 )
[0111]
Further, the process-based weighted integrated forecasting model 218 employs weights for each of the (i) the amount of total surface water from rainfall infiltrated to aquifer (𝑄𝑅𝑡1−𝑡2), (ii) the amount of ground water extracted from aquifer for agriculture (𝑄𝐸−𝐴𝑡1−𝑡2), (iii) the net amount of ground water 15 extracted from aquifer by population (𝑄𝐸−𝑃𝑡1−𝑡2), (iv) the net amount of ground water infiltrated to aquifer through one or more water sources (𝑄𝑅−𝑊𝑅𝑡1−𝑡2), (v) the net amount of ground water extracted from aquifer for industrial use (𝑄𝐸−𝐼𝑡1−𝑡2 ), (vi) the drought index (𝐷𝐼𝑡1−𝑡2 ), (vii) the seismic index (𝑆𝐼𝑡1−𝑡2 ), (viii) the amount of total surface deformation (𝑆𝐷𝑡1−𝑡2 ), while predicting the 20 ground water level (𝐺𝑊𝐿𝑡1−𝑡2 ) of the predefined geographical region for the time period 𝑡1 and 𝑡2.
[0112]
In an embodiment, an Analytic Hierarchy Process (AHP) technique is used to assign weights to different criteria or parameters based on their relative importance. It involves pairwise comparisons to determine the significance of each 25 parameter in relation to the others. An example is provided below to assign weights while predicting the ground water level (𝐺𝑊𝐿𝑡1−𝑡2 ) of the predefined geographical region for the time period 𝑡1 and 𝑡2.
Step 1: Pairwise Comparisons: Each parameter is compared against every other parameter to derive their relative importance. 30
Let's assume a scale from 1 to 9:
35
1: Equal importance
3: Slightly more important
5: Clearly more important
7: Strongly more important
9: Extremely more important 5
Now, a hypothetical comparison matrix could look like this:
Parameters
Rainwater Infiltration
Agricultural Extraction
Population Extraction
Surface Water Infiltration
Industrial Extraction
Drought Index
Seismic Index
Surface Deformation
Rainwater Infiltration
1
3
5
3
3
7
5
5
Agricultural Extraction
1/3 (1/3)
1
3
3
3
5
3
3
Population Extraction
1/5 (1/5)
1/3 (1/3)
1
3
3
7
5
5
Surface Water Infiltration
1/3 (1/3)
1/3 (1/3)
1/3 (1/3)
1
3
5
3
3
Industrial Extraction
1/3 (1/3)
1/3 (1/3)
1/3 (1/3)
1/3 (1/3)
1
3
3
3
Drought Index
1/7 (1/7)
1/5 (1/5)
1/7 (1/7)
1/5 (1/5)
1/3 (1/3)
1
3
3
Seismic Index
1/5 (1/5)
1/3 (1/3)
1/5 (1/5)
1/3 (1/3)
1/3 (1/3)
1/3 (1/3)
1
3
36
Parameters
Rainwater Infiltration
Agricultural Extraction
Population Extraction
Surface Water Infiltration
Industrial Extraction
Drought Index
Seismic Index
Surface Deformation
Surface Deformation
1/5 (1/5)
1/3 (1/3)
1/5 (1/5)
1/3 (1/3)
1/3 (1/3)
1/3 (1/3)
1/3 (1/3)
Step 2: Calculate Relative Weights: The next step involves synthesizing these comparisons to obtain the relative weights of each parameter. This is done by calculating the eigenvector or averaging the values in each column. After performing these calculations, relative weights for each parameter are obtained. 5 Let's say after calculations, these weights are as follows:
Rainwater Infiltration: 0.25
Agricultural Extraction: 0.15
Population Extraction: 0.12
Surface Water Infiltration: 0.1 10
Industrial Extraction: 0.08
Drought Index: 0.18
Seismic Index: 0.06
Surface Deformation: 0.06
Step 3: Ground water level calculation: Now with the derived weights, the ground 15 water level (𝐺𝑊𝐿𝑡1−𝑡2 ) is determined using these parameters and weights as:
𝐺𝑊𝐿𝑡1−𝑡2 =𝐾× (𝑤𝑒𝑖𝑔ℎ𝑡 1×𝑝𝑎𝑟𝑎𝑚𝑒𝑡𝑒𝑟 1+𝑤𝑒𝑖𝑔ℎ𝑡 2×𝑝𝑎𝑟𝑎𝑚𝑒𝑡𝑒𝑟 2+⋯+𝑤𝑒𝑖𝑔ℎ𝑡 8×𝑝𝑎𝑟𝑎𝑚𝑒𝑡𝑒𝑟 8)
Where 𝐾 is a normalization factor ensuring the sum of weighted parameters equals 20 1.
[0113]
At step 324 of the method 300, the one or more hardware processors 104 of the system 100 are configured to receive a forecasted input data associated
37
to the predefined geographical region for which a ground water level
is to be predicted, from the remote sensing satellite data and one or more input information sources.
[0114]
At step 326 of the method 300, the one or more hardware processors 104 of the system 100 are configured determine a forecasted input parameter data 5 is of the predefined time period and comprises of (i) the one or more weather related parameters, (ii) the one or more soil related parameters, (iii) the one or more agriculture related parameters, (iv) the one or more population related parameters, (v) the one or more surface water related parameters, (vi) the one or more industry related parameters, (vii) the one or more drought related parameters, (viii) the one 10 or more seismic related parameters, and (ix) the one or more surface deformation related parameters.
[0115]
At step 328 of the method 300, the one or more hardware processors 104 of the system 100 are configured to determine (i) the amount of total surface water from rainfall infiltrated to aquifer during the predefined time period, (ii) the 15 amount of ground water extracted from aquifer for agriculture during the predefined time period, (iii) the net amount of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period, (v) the net amount of ground water extracted from aquifer for industrial use 20 during the predefined time period, (vi) the drought index for the predefined time period, (vii) the seismic index for the predefined time period, (viii) the amount of total surface deformation during the predefined time period, from the forecasted input parameter data.
[0116]
At step 330 of the method 300, the one or more hardware processors 25 104 of the system 100 are configured to pass (i) the amount of total surface water from rainfall infiltrated to aquifer during the predefined time period, (ii) the amount of ground water extracted from aquifer for agriculture during the predefined time period, (iii) the net amount of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated 30 to aquifer through one or more water sources during the predefined time period, (v)
38
the net amount of ground water extracted from aquifer for industrial use during the
predefined time period, (vi) the drought index for the predefined time period, (vii) the seismic index for the predefined time period, (viii) the amount of total surface deformation during the predefined time period, to the process-based weighted integrated forecasting model 218, to predict a forecasted ground water level of the 5 predefined geographical region.
[0117]
The methods and systems of the present disclosure considers parameters such as weather conditions, soil properties, agriculture data, population data, water resources information, industry details, drought information, seismic data, and surface deformation trends over the years for the specific region, to predict 10 the current and future ground water level based on the required time period.
[0118]
The present disclosure predicts ground water situation i.e. rising or declining for a given region based on the archived remote sensing and comprehensive auxiliary datasets i.e. weather conditions, soil properties, agriculture data, population data, water resources information, industry details, 15 drought information, seismic data, and surface deformation trends. The present disclosure also considers different future scenarios such as cropping pattern, weather conditions, use of irrigation system etc. Accurate ground water prediction over the large duration based on our proposed approach can help farmers to plan their irrigation practices effectively. Also, the present disclosure enables farmers to 20 make informed decisions about the types of crops they should cultivate. Hence the present disclosure has the potential to scale up and implement in any part of the world.
[0119]
The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the 25 subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims. 30
39
[0120]
The embodiments of the present disclosure herein address unresolved problem of ground water prediction using integration of satellite and auxiliary observations. The present disclosure considers various parameter data such as weather conditions, soil properties, agriculture data, population data, water resources information, industry details, drought information, seismic data, and 5 surface deformation trends over the years for the specific region, to predict the current and future ground water level based on the required time period. The ground water forecasting allows for a more comprehensive understanding of the system dynamics and helps develop effective strategies for sustainable ground water management. 10
[0121]
It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device 15 can be any kind of device which can be programmed including e.g., any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g., hardware means like e.g., an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g., an ASIC 20 and an FPGA, or at least one microprocessor and at least one memory with software processing components located therein. Thus, the means can include both hardware means, and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware 25 devices, e.g., using a plurality of CPUs.
[0122]
The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various components described herein may be implemented in other components or 30 combinations of other components. For the purposes of this description, a
40
computer
-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
[0123]
The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological 5 development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are 10 appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope of the disclosed embodiments. Also, the words “comprising,” “having,” “containing,” and “including,” and other similar forms are 15 intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise. 20
[0124]
Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more 25 processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, 30
41
nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any
other known physical storage media.
[0125]
It is intended that the disclosure and examples be considered as exemplary only, with a true scope of disclosed embodiments being indicated by the following claims.We Claim:
1. A processor-implemented method (300), comprising the steps of:
receiving, via one or more input/output (I/O) interfaces, an input data associated to a predefined geographical region for which ground water level is to be predicted, from a remote sensing satellite data and one or more input information sources (302);
determining, via one or more hardware processors, an input parameter data associated to the predefined geographical region for which the ground water level is to be predicted, from the input data, wherein the input parameter data is of a predefined time period and comprises one or more of (i) one or more weather related parameters, (ii) one or more soil related parameters, (iii) one or more agriculture related parameters, (iv) one or more population related parameters, (v) one or more surface water related parameters, (vi) one or more industry related parameters, (vii) one or more drought related parameters, (viii) one or more seismic related parameters, and (ix) one or more surface deformation related parameters (304);
passing, via the one or more hardware processors, the input parameter data of the one or more weather related parameters and the one or more soil related parameters, to a weather and soil process-based model, to obtain an amount of total surface water from rainfall infiltrated to aquifer during the predefined time period (306);
passing, via the one or more hardware processors, the input parameter data of the one or more agriculture related parameters, to an agriculture process-based model, to obtain an amount of ground water extracted from aquifer for agriculture during the predefined time period (308);
passing, via the one or more hardware processors, the input parameter data of the one or more population related parameters, to a population process-based model, to obtain a net amount of ground water extracted from aquifer by population during the predefined time period (310);

passing, via the one or more hardware processors, the input parameter data of the one or more soil related parameters and the one or more surface water related parameters, to a soil and surface process-based model, to obtain a net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period (312);
passing, via the one or more hardware processors, the input parameter data of the one or more industry related parameters, to an industry process-based model, to obtain a net amount of ground water extracted from aquifer for industrial use during the predefined time period (314);
passing, via the one or more hardware processors, the input parameter data of the one or more drought related parameters, to a pretrained machine learning model for drought, to obtain a drought index for the predefined time period (316);
passing, via the one or more hardware processors, the input parameter data of the one or more seismic related parameters, to a seismic process-based model, to obtain a seismic index for the predefined time period (318);
passing, via the one or more hardware processors, the input parameter data of the one or more surface deformation related parameters, to a surface deformation process-based model, to obtain an amount of total surface deformation during the predefined time period (320); and
passing, via the one or more hardware processors, (i) the amount of total surface water from rainfall infiltrated to aquifer during the predefined time period, (ii) the amount of ground water extracted from aquifer for agriculture during the predefined time period, (iii) the net amount of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period, (v) the net amount of ground water extracted from aquifer for industrial use during the predefined time period, (vi) the drought index for the predefined time period, (vii) the seismic index for the predefined time period, (viii) the

amount of total surface deformation during the predefined time period, to a process-based weighted integrated forecasting model, to predict the ground water level of the predefined geographical region (322).
2. The processor-implemented method as claimed in claim 1, comprising:
receiving, via the one or more hardware processors, a forecasted input data associated to the predefined geographical region for which a ground water level is to be predicted, from the remote sensing satellite data and one or more input information sources (324);
determining, the via one or more hardware processors, a forecasted input parameter data is of the predefined time period and comprises of (i) the one or more weather related parameters, (ii) the one or more soil related parameters, (iii) the one or more agriculture related parameters, (iv) the one or more population related parameters, (v) the one or more surface water related parameters, (vi) the one or more industry related parameters, (vii) the one or more drought related parameters, (viii) the one or more seismic related parameters, and (ix) the one or more surface deformation related parameters (326);
determining, via the one or more hardware processors, (i) the amount of total surface water from rainfall infiltrated to aquifer during the predefined time period, (ii) the amount of ground water extracted from aquifer for agriculture during the predefined time period, (iii) the net amount of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period, (v) the net amount of ground water extracted from aquifer for industrial use during the predefined time period, (vi) the drought index for the predefined time period, (vii) the seismic index for the predefined time period, (viii) the amount of total surface deformation during the predefined time period, from the forecasted input parameter data (328); and

passing, via the one or more hardware processors, (i) the amount of total surface water from rainfall infiltrated to aquifer during the predefined time period, (ii) the amount of ground water extracted from aquifer for agriculture during the predefined time period, (iii) the net amount of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period, (v) the net amount of ground water extracted from aquifer for industrial use during the predefined time period, (vi) the drought index for the predefined time period, (vii) the seismic index for the predefined time period, (viii) the amount of total surface deformation during the predefined time period, to the 45rocesss-based weighted integrated forecasting model, to predict a forecasted ground water level of the predefined geographical region (330).
3. The processor-implemented method as claimed in claim 1, wherein:
(a) the one or more weather related parameters comprises (i) a daily rainfall, (ii) a daily land surface temperature, and (iii) a daily evapotranspiration rate,
(b) the one or more soil related parameters comprises (i) a soil type, (ii) a soil compaction index (SCI), (iii) a soil saturation level (SSL), and (iv) a soil infiltration capacity,
(c) the one or more agriculture related parameters comprises (i) a total agriculture area, (ii) a type of crop grown in each season, and (iii) a crop grown area in each season,
(d) the one or more population related parameters comprises (i) a year-wise population amount, (ii) a population growth rate, (iii) a year-wise number of residential establishments, (iv) a year-wise number of residential establishments with ground water recharge facilities, and (v) a year-wise area of residential establishments with ground water recharge facilities,

(e) the one or more surface water related parameters comprises (i) a total area of one or more water reserve sources, and (ii) a total water holding capacity of the one or more water reserve sources,
(f) the one or more industry related parameters comprises (i) a year-wise number of industry establishments, (ii) year-wise type of industry establishments, (iii) a year-wise total amount of ground water utilized by industry establishments, (iv) a year-wise number of industry establishments with ground water recharge facilities, (v) a year-wise area of permanent industry establishments with ground water recharge facilities, and (vi) a year-wise total amount of rain water given to aquifer by industry establishments,
(g) the one or more drought related parameters comprises (i) a season-wise spatially distributed drought affected area, and (ii) a season-wise spatially distributed drought intensity,
(h) the one or more seismic related parameters comprises (i) a region of interest (RoI) seismic zone type, and (ii) a year-wise seismic magnitude, and
(i) the one or more surface deformation related parameters comprises a year-wise amount of land surface deformation.
4. A system (100) comprising:
a memory (102) storing instructions;
one or more input/output (I/O) interfaces (106); and
one or more hardware processors (104) coupled to the memory (102) via the one or more I/O interfaces (106), wherein the one or more hardware processors (104) are configured by the instructions to:
receive an input data associated to a predefined geographical region for which a ground water level is to be predicted, from a remote sensing satellite data and one or more input information sources;

determine an input parameter data associated to the predefined geographical region for which the ground water level is to be predicted, from the input data, wherein the input parameter data is of a predefined time period and comprises one or more of (i) one or more weather related parameters, (ii) one or more soil related parameters, (iii) one or more agriculture related parameters, (iv) one or more population related parameters, (v) one or more surface water related parameters, (vi) one or more industry related parameters, (vii) one or more drought related parameters, (viii) one or more seismic related parameters, and (ix) one or more surface deformation related parameters;
pass the input parameter data of the one or more weather related parameters and the one or more soil related parameters, to a weather and soil process-based model, to obtain an amount of total surface water from rainfall infiltrated to aquifer during the predefined time period;
pass the input parameter data of the one or more agriculture related parameters, to an agriculture process-based model, to obtain an amount of ground water extracted from aquifer for agriculture during the predefined time period;
pass the input parameter data of the one or more population related parameters, to a population process-based model, to obtain a net amount of ground water extracted from aquifer by population during the predefined time period;
pass the input parameter data of the one or more soil related parameters and the one or more surface water related parameters, to a soil and surface process-based model, to obtain a net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period;
pass the input parameter data of the one or more industry related parameters, to an industry process-based model, to obtain a net amount of ground water extracted from aquifer for industrial use during the predefined time period;

pass the input parameter data of the one or more drought related parameters, to a pretrained machine learning model for drought, to obtain a drought index for the predefined time period;
pass the input parameter data of the one or more seismic related parameters, to a seismic process-based model, to obtain a seismic index for the predefined time period;
pass the input parameter data of the one or more surface deformation related parameters, to a surface deformation process-based model, to obtain an amount of total surface deformation during the predefined time period; and
pass (i) the amount of total surface water from rainfall infiltrated to aquifer during the predefined time period, (ii) the amount of ground water extracted from aquifer for agriculture during the predefined time period, (iii) the net amount of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period, (v) the net amount of ground water extracted from aquifer for industrial use during the predefined time period, (vi) the drought index for the predefined time period, (vii) the seismic index for the predefined time period, (viii) the amount of total surface deformation during the predefined time period, to a process-based weighted integrated forecasting model, to predict the ground water level of the predefined geographical region
5. The system as claimed in claim 4, wherein the one or more hardware processors (104) are configured to:
receive a forecasted input data associated to the predefined geographical region for which a ground water level is to be predicted, from the remote sensing satellite data and one or more input information sources;
determine a forecasted input parameter data is of the predefined time period and comprises of (i) the one or more weather related parameters, (ii) the one or more soil related parameters, (iii) the one or more agriculture

related parameters, (iv) the one or more population related parameters, (v) the one or more surface water related parameters, (vi) the one or more industry related parameters, (vii) the one or more drought related parameters, (viii) the one or more seismic related parameters, and (ix) the one or more surface deformation related parameters;
determine (i) the amount of total surface water from rainfall infiltrated to aquifer during the predefined time period, (ii) the amount of ground water extracted from aquifer for agriculture during the predefined time period, (iii) the net amount of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period, (v) the net amount of ground water extracted from aquifer for industrial use during the predefined time period, (vi) the drought index for the predefined time period, (vii) the seismic index for the predefined time period, (viii) the amount of total surface deformation during the predefined time period, from the forecasted input parameter data; and
pass (i) the amount of total surface water from rainfall infiltrated to aquifer during the predefined time period, (ii) the amount of ground water extracted from aquifer for agriculture during the predefined time period, (iii) the net amount of ground water extracted from aquifer by population during the predefined time period, (iv) the net amount of ground water infiltrated to aquifer through one or more water sources during the predefined time period, (v) the net amount of ground water extracted from aquifer for industrial use during the predefined time period, (vi) the drought index for the predefined time period, (vii) the seismic index for the predefined time period, (viii) the amount of total surface deformation during the predefined time period, to the process-based weighted integrated forecasting model, to predict a forecasted ground water level of the predefined geographical region.
6. The system as claimed in claim 4, wherein:

(a) the one or more weather related parameters comprises (i) a daily rainfall, (ii) a daily land surface temperature, and (iii) a daily evapotranspiration rate,
(b) the one or more soil related parameters comprises (i) a soil type, (ii) a soil compaction index (SCI), (iii) a soil saturation level (SSL), and (iv) a soil infiltration capacity,
(c) the one or more agriculture related parameters comprises (i) a total agriculture area, (ii) a type of crop grown in each season, and (iii) a crop grown area in each season,
(d) the one or more population related parameters comprises (i) a year-wise population amount, (ii) a population growth rate, (iii) a year-wise number of residential establishments, (iv) a year-wise number of residential establishments with ground water recharge facilities, and (v) a year-wise area of residential establishments with ground water recharge facilities,
(e) the one or more surface water related parameters comprises (i) a total area of one or more water reserve sources, and (ii) a total water holding capacity of the one or more water reserve sources,
(f) the one or more industry related parameters comprises (i) a year-wise number of industry establishments, (ii) year-wise type of industry establishments, (iii) a year-wise total amount of ground water utilized by industry establishments, (iv) a year-wise number of industry establishments with ground water recharge facilities, (v) a year-wise area of permanent industry establishments with ground water recharge facilities, and (vi) a year-wise total amount of rain water given to aquifer by industry establishments,

(g) the one or more drought related parameters comprises (i) a season-wise spatially distributed drought affected area, and (ii) a season-wise spatially distributed drought intensity,
(h) the one or more seismic related parameters comprises (i) a region of interest (RoI) seismic zone type, and (ii) a year-wise seismic magnitude, and
(i) the one or more surface deformation related parameters comprises a year-wise amount of land surface deformation.