Description:BACKGROUND
Technical Field
[1] Embodiments herein generally relate to query processing, and more particularly, to a system and method for accelerated query processing in Integrated datasets using an optimized Indexing technique.
Description of Related Art
[2] The increasing complexity and scale of agricultural data pose significant challenges to efficient analysis and decision-making in the agricultural sector. With the advent of advanced technologies such as satellite imaging and machine learning, there is a growing opportunity to leverage these tools for adaptive analysis of agricultural regions. However, one of the primary obstacles encountered in this endeavor is the prolonged computational time across the journey of the user on a user interface, leading to delays in performing adaptive analysis.
[3] Particularly the technical challenge lies in the intricate process of gathering and analyzing diverse datasets associated with agricultural units. Agricultural data, ranging from regional records to satellite images, are often voluminous and heterogeneous in nature. Moreover, the multi-level hierarchies of geographical regions, such as state, district, and sub-district, further complicate the data retrieval process.
[4] The current methodologies for performing adaptive analysis of agricultural units involve manual or semi-automated procedures, which are inherently time-consuming and prone to errors. Users typically interact with graphical user interfaces (GUIs) to select and retrieve relevant data sets, which are then processed for adaptive analysis. However, the computational overhead associated with data retrieval, processing, and analysis significantly impacts the overall efficiency of the user journey.
[5] Furthermore, as the demand for real-time insights and decision support in agriculture continues to rise, the need for expedited adaptive analysis becomes more pressing. Delays in computational time not only impede the timely delivery of insights but also hinder the ability to make timely decisions in dynamic agricultural conditions.
[6] Therefore, there is a need to address the aforementioned technical drawbacks in existing technologies for a system and method for adaptive analysis of categorized pixels of satellite images of agricultural units.
SUMMARY
[7] In view of the foregoing, according to the first aspect, there is provided a method for accelerated query processing of anintegrated dataset of records data and satellite data to generate parameters on a Graphical User Interface. The method includes (i) collecting a first set of datasets and a second set of datasets, wherein the first set of datasets includes hierarchical user records and the second set of datasets comprises hierarchical geographical regions data, (ii) performing, based on interaction of a user on a graphical user interface (GUI), a multi-level selection of hierarchical geographical regions data including a first-level region, a second-level region, a third-level region and subsequent level region using a hybrid spatial indexing technique, where options for a subsequent selection are dynamically populated based on preceding selection from a first mapping of the hierarchical user records and the hierarchical geographical regions data,(iii) updating the GUI to present vector geometries based on the multi-level selection, where the vector geometries represent polygons and are derived from a second mapping of the vector geometries and hierarchical user records data, (iv) generating analytical data on spatial matching by associating at least one geometric boundary extracted from satellite imagery with a Survey ID and a Survey Number, based on vector geometries selected through the GUI, (v). automatically determining, using a trained artificial intelligence (AI) model, categorized pixels from one or more of satellite images associated with a group of geospatial unit, where the categorized pixels includes a crop area pixel or a non-crop area pixel for a season, (vi) assessing, using the trained AI model, the categorized pixels of the group of the geospatial unit with a score for an entity and automatically determining one or more parameters for the group of geospatial unit, where the one or more parameters are selected from irrigation condition, cropping intensity, cropping history, crop type, crop performance, crop yield, crop revenue, weather data, neighboring farm units, primary crops, and a farm centroid in the group of the geospatial unit, and (vii) performing accelerated query processing using optimized Indexing for analyzing categorized pixels of the plurality of satellite images of the group of the geospatial unit by generating data objects of the one or more parameters in a user and machine-readable format and displaying the one or more parameters at a user interface, wherein the data objects include location or geometry information.
[8] The method is of advantage that the method significantly reduces computational time, with the average duration to generate the data objects of the plurality of parameters ranging between 10 to 12 seconds. This effectively improves decision support in agricultural analysis with comprehensive parameter assessments and adaptive analysis capabilities. Moreover, the method ensures robust data integration and visualization, leveraging vector geometry-based GUI updates and satellite image analysis for grouping geometric boundaries. The method utilizes reindexing and dynamic indexing techniques to enhance query performance by restructuring outdated indexes and enabling real-time updates for efficient data retrieval.
[9] The integration of user records and vector geometries into the graphical interface enhances user experience and comprehension, enabling intuitive navigation and interpretation of agricultural data. Additionally, by utilizing the multi-level selection of hierarchical geographical regions and dynamic population of subsequent options based on preceding selections, the method offers flexibility and customization in an analysis of categorized pixels of satellite images.
[10] In some embodiments, the method further comprises the spatial indexing comprises manages queries of the spatial data in a database by integrating a GiST method for complex geometries with a tree-based method for efficiently handling point data, wherethe GiST method indexes multi-dimensional spatial data by grouping nearby objects and representing them with bounding rectangles for fast spatial queries and the tree-based method divides multi-dimensional spatial domain into nodes, wherein each nodes stores references to geospatial objects located within it.
[11] In some embodiments, the method further comprises the spatial indexing technique that utilizes a dynamic indexing technique to create, update, and maintain indexes in real-time as data changes, ensuring optimal performance.
[12] In some embodiments, the method further comprises wherein the spatial indexing employs re-indexing techniques to maintain optimal performance as the underlying spatial data evolves.
[13] In some embodiments, the method further wherein Spatial indexing supports custom geospatial functions, that comprises ST_Within function, ST_Intersects function, and ST_Contains function, which determine spatial relationships and efficiently exclude non-relevant geometries, enabling fast and efficient access to geospatial data during query execution.
[14] In some embodiments, the method further comprises the machine-readable format and employs a JSON format to structure datasets into a hierarchical format with nested levels, ensuring correct formatting of geometries and attributes, enriching the data objects with metadata such as report dates, reference IDs, and request IDs, and verifying completeness by checking that all required fields are consistently populated.
[15] In another aspect, a system for accelerated query processing in Integrated datasets using an optimized Indexing technique. The system includes a satellite image analysis server that includes a processor and a memory that are configured to perform (i) collecting a first set of datasets and a second set of datasets, wherein the first set of datasets includes hierarchical user records and the second set of datasets comprises hierarchical geographical regions data, (ii) performing, based on interaction of a user on a graphical user interface (GUI), a multi-level selection of hierarchical geographical regions data including a first-level region, a second-level region, a third-level region and subsequent level region using a hybrid spatial indexing technique, where options for a subsequent selection are dynamically populated based on preceding selection from a first mapping of the hierarchical user records and the hierarchical geographical regions data, (iii) updating the GUI to present vector geometries based on the multi-level selection, where the vector geometries represent polygons and are derived from a second mapping of the vector geometries and hierarchical user records data, (iv) generating analytical data on spatial matching by associating at least one geometric boundary extracted from satellite imagery with a Survey ID and a Survey Number, based on vector geometries selected through the GUI, (v). automatically determining, using a trained artificial intelligence (AI) model, categorized pixels from one or more of satellite images associated with a group of geospatial unit, where the categorized pixels includes a crop area pixel or a non-crop area pixel for a season, (vi) assessing, using the trained AI model, the categorized pixels of the group of the geospatial unit with a score for the entity and automatically determining one or more parameters for the group of geospatial unit, where the one or more parameters are selected from irrigation condition, cropping intensity, cropping history, crop type, crop performance, crop yield, crop revenue, weather data, neighboring farm units, primary crops, and a farm centroid in the group of the geospatial unit, and (vii) performing accelerated query processing using optimized Indexing for analyzing categorized pixels of the plurality of satellite images of the group of the geospatial unit by generating data objects of the one or more parameters in a user and machine-readable format and displaying the one or more parameters at a user interface, wherein the data objects include location or geometry information.
[16] The system significantly reduces computational time, with the average duration to generate the data objects of the plurality of parameters ranging between 10 to 12 seconds. This effectively improves decision support in agricultural analysis with comprehensive parameter assessments and adaptive analysis capabilities. Moreover, the system ensures robust data integration and visualization, leveraging shapefile-based GUI updates and satellite image analysis for grouping geometric boundaries. The system utilizes reindexing and dynamic indexing techniques to enhance query performance by restructuring outdated indexes and enabling real-time updates for efficient data retrieval.
[17] The integration of user records and vector geometries into the graphical interface enhances user experience and comprehension, enabling intuitive navigation and interpretation of agricultural data. Additionally, by utilizing the multi-level selection of hierarchical geographical regions and dynamic population of subsequent options based on preceding selections, the system offers flexibility and customization in analysis of categorized pixels of satellite images.
[18] In some embodiments, the system further comprises the spatial indexing technique manages and queries spatial data in a database by integrating a GiST method for complex geometries with a tree-based method for efficiently handling point data, wherein the GiST method indexes multi-dimensional spatial data by grouping nearby objects and representing them with bounding rectangles for fast spatial queries and the tree-based method divides multi-dimensional spatial domain into nodes, each node stores references to geospatial objects located within it.
[19] In some embodiments, the system further comprises spatial indexing and uses a dynamic technique to create, update, and maintain indexes in real-time as data changes, adding new entries and modifying existing ones to ensure optimal performance through PostgreSQL’s GiST indexing method.
[20] In some embodiments, the system further comprises the Spatial indexing supports custom geospatial functions, that comprises ST_Within function, ST_Intersects function, and ST_Contains function, which determines spatial relationships and efficiently excludes non-relevant geometries, enabling fast and efficient access to geospatial data during query execution.
[21] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.
BRIEF DESCRIPTION OF THE DRAWINGS
[22] FIG. 1 illustrates a system for accelerated query processing in Integrated datasets using an optimized Indexing technique according to some embodiments herein;
[23] FIG. 2 illustrates an exploded view of a satellite image analysis server of FIG. 1 according to some embodiments herein;
[24] FIG. 3 illustrates a block diagram of pre-processing for the accelerated query processing of categorized pixels according to some embodiments herein;
[25] FIG. 4 illustrates a flow diagram for a user flow of the dashboard and generated report according to some embodiments herein;
[26] FIG. 5 illustrates a geospatial workflow of the system according to some embodiments herein.;
[27] FIGS. 6A and 6B illustrate an exemplary view of an interface report document 600 with graphical elements and widgets based on query processing of categorized pixels according to some embodiments herein;
[28] FIGS. 7 illustrates a user interface displaying the farm location on a geographical map, along with details of adjacent land parcels in the farm region, according to some embodiments herein;
[29] FIG. 8 illustrates a graphical representation of rainfall variations at the third level region over a decade according to some embodiments herein;
[30] FIG. 9 illustrates a graphical representation of groundwater thickness trend at the third level region according to some embodiments herein;
[31] FIG. 10 illustrates a tabular representation. of regional parameters according to some embodiments herein;
[32] FIG. 11 illustrates a tabular representation. of cropping pattern and major crops according to some embodiments herein;
[33] FIG. 12 illustrates legends explaining a correlation between the parameters and categories according to some embodiments herein;
[34] FIG. 13 illustrates a tabular representation of API Latency Percentile Metrics according to some embodiments herein;
[35] FIGS 14A and 14B are flow diagram of a method for accelerated query processing in Integrated datasets using an optimized Indexing technique according to some embodiments herein;
[36] FIG. 15 is a representative cloud computing environment for practicing the embodiments herein; and
[37] FIG. 16 is a representative hardware environment for practicing the embodiments herein.
DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS
[38] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
[39] The term "entity" refers to a legal or natural person involved in agricultural activities, such as a farmer, landowner, or agricultural organization. For example, an entity represents a farmer associated with different agricultural land parcels.
[40] The term "grouped geospatial unit boundaries" refers to the aggregated boundaries of multiple land parcels that are grouped based on specific criteria such as proximity, ownership, or administrative designation. For example, grouped land boundaries may comprise several contiguous land parcels belonging to the same farmer or used for similar agricultural purposes.
[41] The term "user" refers to an individual interacting with the graphical user interface (GUI) to perform specific tasks or access information. As an example, the user may represent a credit manager who operates the GUI to gather data and make informed decisions related to agricultural lending.
[42] The term "user records" refers to a documented record containing information about land ownership, typically identified by a unique identifier known as a survey ID.
[43] The term “spatial indexing technique” refers to a method used to efficiently organize and access spatial data, such as coordinates, shapes, and regions based on their geometric properties like location and distance. It is essential in applications involving geographic information systems (GIS), mapping, and spatial databases, enabling faster querying of spatial relationships like proximity or overlap. More specifically, in some embodiments, the spatial indexing technique may include GIST, which converts remote sensing information provided by satellites and imagery into digital data.
[44] GiST stands for Generalized Search Tree. It is a flexible and extensible indexing framework used in PostgreSQL to support advanced queries on complex data types. Unlike traditional B-tree indexes that are limited to simple equality and range comparisons, GiST indexes can handle a wide range of queries, including spatial searches, full-text searches, and nearest-neighbor lookups, making them well-suited for applications involving geospatial data, custom objects, and rich search conditions.
[45] The term “vector geometries” refers to the representation of spatial features using points, lines, and polygons to model real-world objects like locations, roads, and boundaries. Each geometry type captures spatial relationships and shapes with precision, making vector data ideal for mapping, spatial analysis, and geographic information systems (GIS).
[46] The term “survey ID” refers to a unique identifier assigned to a specific survey or data collection event. It is used to track, organize, and reference survey data, ensuring each dataset can be accurately linked to its source, location, time, and other relevant attributes.
[47] The term “survey number” refers to a unique number assigned to a specific parcel of land in land records or cadastral maps. It is used by government authorities to identify, manage, and reference land for purposes like ownership, taxation, and land use planning. Each survey number corresponds to a defined region within a larger geographic area, such as a village or district.
[48] FIG. 1 illustrates a system for accelerated query processing in Integrated datasets using an optimized Indexing technique according to some embodiments herein. The system 100 includes a satellite image analysis server 102, and one or more user devices 104A-N that are communicatively connected via a data communication network 106. The satellite image analysis server 102 includes a processor and a memory. The data communication network 106 may be one or more of a wired network, a wireless network, a combination of the wired network and the wireless network, or the Internet. The one or more user devices 104A-N include but are not limited to, a mobile device, a smartphone, a smartwatch, a notebook, a Global Positioning System (GPS) device, a tablet, a desktop computer, a laptop, or any network-enabled device.
[49] The satellite image analysis server 102 collects a first set of datasets and a second set of datasets, where the first set of datasets includes hierarchical user records associated with users and the second set of datasets includes hierarchical geographical regions data. The user records may be land ownership details. The satellite image analysis server 102 performs, based on the interaction of a user on a graphical user interface (GUI), a multi-level selection of hierarchical geographical regions comprising a first-level region, a second-level region, a third-level region, and a subsequent level region using a spatial indexing technique, where options for a subsequent selection are dynamically populated based on preceding selection from a first mapping of the land ownership records and the hierarchical data of geographical regions. The first level region may be a state-level region. The second level region may be a district-level region. The third level region may be a sub-district level region. The satellite image analysis server 102 updates the GUI to present vector geometries based on the multi-level selection, wherein the vector geometries represent polygons and are derived from a second mapping of the vector geometries and hierarchical user records. The satellite image analysis server 102 generates analytical data on spatial matching by associating at least one geometric boundary extracted from satellite imagery with a survey ID and a survey number, based on vector geometries selected through the GUI.
[50] The satellite image analysis server 102 automatically determines categorized pixels from a plurality of satellite images associated with the group of agricultural using a trained AI model. The categorized pixels include a crop area pixel or a non-crop area pixel for a season. The satellite image analysis server 102 assesses the categorized pixels of the group of geospatial units with a score for the entity and automatically determines a plurality of parameters for the group of geospatial units using the trained AI model. The geospatial units may be land parcels. The plurality of parameters includes irrigation condition, cropping intensity and cropping history, crop type, crop performance, crop yield, crop revenue, weather data, neighboring farm unit, primary crops, and farm centroid in the group of land parcels. The satellite image analysis server 102 performs accelerated query processing of categorized pixels of the plurality of satellite images of the set of geospatial units by generating data objects of the plurality of parameters in a user and machine-readable format and displaying the plurality of parameters at a user interface. The geospatial units may be land parcels.
[51] The system 100 is of advantage that the system 100 significantly reduces computational time, with the average duration to generate the data objects of the plurality of parameters ranging between 10 to 12 seconds. This effectively improves decision support in agricultural analysis with comprehensive parameter assessments and capabilities. Moreover, system 100 ensures robust data integration and visualization, leveraging shapefile-based GUI updates and satellite image analysis for grouping geometric boundaries.
[52] The integration of land ownership records and vector geometries into the graphical interface enhances user experience and comprehension, enabling intuitive navigation and interpretation of agricultural data. Additionally, by utilizing the multi-level selection of hierarchical geographical regions and dynamic population of subsequent options based on preceding selections, the system 100 offers flexibility and customization in the analysis of categorized pixels of satellite images.
[53] In some embodiments, the system 100 generates an interface report document with graphical elements and widgets that are based on the data objects of the plurality of parameters.
[54] The system 100 further performs determining graphical elements and widgets representing irrigation condition, cropping intensity, and cropping history, wherein the irrigation conditionis determined using satellite data in a spatial resolution of 10 meters at an interval of one year. The cropping intensity is the number of crop cycles in a year, as identified using satellite images. For one cycle it is Once a Year, for two it is Twice a Year.
[55] In some embodiments, the system 100 further computes the cropping history parameters including historical cropping data and past weather conditions, wherein the historical cropping data is determined using satellite data obtained at a seasonal temporal resolution.
[56] In some embodiments, the system 100 further computes the plurality of parameters including vegetation and moisture indices for evaluating crop performance of the grouped land boundaries in past seasons, wherein the vegetation and moisture indices are determined using satellite data at a spatial resolution of 10 meters and a temporal resolution of 10 days.
[57] In some embodiments, the system 100 generates the farm centroid, that improves accessibility, reduces travel time for equipment and labor, and lowers operational costs by optimizing movement and resource allocation.
[58] FIG. 2 illustrates an exploded view of a satellite image analysis server 102 of FIG. 1 according to some embodiments herein. The satellite image analysis server 102 includes. a dataset collection module 202, a geographical region hierarchy selection module 204, a vector geometry visualization module 206, an analytical spatial data module 208, a categorized pixels determination module 210, a geographical region parameters determination module 212, a data object generation module 214.
[59] The dataset collection module 202 collects a first set of datasets and a second set of datasets. The first set of datasets includes hierarchical landownership records associated with users, and the second set of datasets includes hierarchical data of geographical regions.
[60] The geographical region hierarchy selection module 204 performs, based on interaction of a user on a graphical user interface (GUI), a multi-level selection of hierarchical data of geographical regions including a state region, a district region, a sub-district region and further regions using a spatial indexing technique, where options for a subsequent selection are dynamically populated based on preceding selection from a based a first mapping of hierarchical user records and hierarchical geographical regions. The spatial indexing technique manages and queries spatial data in a database by integrating the GiST method for complex geometries with a tree-based method for efficiently handling point data. The GiST method indexes multi-dimensional spatial data by grouping nearby objects and representing them with bounding rectangles for fast spatial queries and the tree-based method divides multi-dimensional spatial domain into nodes, each nodes stores references the spatial objects located within it. The spatial indexing is a method employed in databases to enhance the efficiency of storing, accessing, and querying spatial data such as geographic coordinates, shapes, and spatial features. By minimizing the volume of data that must be examined, it greatly boosts the performance of spatial queries. This technique is especially important for managing large-scale spatial datasets, as commonly found in Geographic Information Systems (GIS) and similar applications
[61] The spatial indexing technique utilizes a dynamic indexing technique to create, update, and maintain indexes in real time as data changes, ensuring optimal performance. The spatial indexing employs re-indexing techniques to maintain optimal performance as the underlying spatial data evolves over time. The spatial indexing supports custom geospatial functions, enabling fast and efficient access to geospatial data during query execution. The custom geospatial functions includes ST_Within function, ST_Intersects function, and ST_Contains function, which determine spatial relationships and efficiently exclude non-relevant geometries, enabling fast and efficient access to geospatial data during query execution. The re-indexing technique enhances data retrieval accuracy by updating the entire index to reflect the most current and consistent dataset. The dynamic indexing technique increases efficiency by dynamically organizing and indexing content without manual intervention.
[62] In some embodiments, the satellite image analysis server 102 tracks various metrics related to the user records stored in the database, including a hierarchy count that quantifies the number of user records available for performing the multi-level selection of hierarchical geographical regions.
[63] The vector geometry visualization module 206 performs updating the GUI to present shapefiles based on the multi-level selection, where the vector geometries represent polygons and are derived from a second mapping of the vector geometries and user records. The satellite image analysis server 102 performs grouping of geometric boundaries in satellite images based on the selection of vector geometries on the GUI to obtain grouped geospatial unit boundaries. Additionally, the vector geometry visualization module 206 enables the user to map the searched user records with the location of geographical boundaries, thereby enabling visualization of the geographical boundaries on a map view.
[64] In some embodiments, the database further includes (a) a database count that represents a total entries in the database that includes land ownership record details, and (b) a mapping of the vector geometries and land ownership records count, denoting the total entries in the database containing respective geometries of the land ownership records. Further, the satellite image analysis server 102 calculates a total number of matched entries between the database and the mapping of the vector geometries and land ownership records, indicating the number of land ownership records in the database that are successfully mapped or matched to geometries in the mapping of the vector geometries and land ownership records.
[65] The analytical spatial data module 208 generates analytical data on spatial matching by associating at least one geometric boundary extracted from satellite imagery with a Survey ID and a Survey Number, based on vector geometries selected through the GUI.
[66] The categorized pixels determination module 210 automatically determines, using a trained AI model, categorized pixels from of a plurality of satellite images associated with the grouped land boundaries. The categorized pixels include crop area pixels or non-crop area pixels for at least one season.
[67] The geographical region determination module 212 assesses the categorized pixels of the grouped land boundaries with a score for the entity, using the trained AI model, and determines automatically a plurality of parameters for the grouped land boundaries. The plurality of parameters includes irrigation condition, cropping intensity, cropping history, crop type, crop performance, crop yield, crop revenue, weather data, neighboring farmlands, primary crops, and farm centroid in the group of geospatial units. The following table “Table 1” describes the spatial resolution and temporal resolution for determining the plurality of parameters.
Name of the Data Product Spatial Resolution Temporal Resolution Unit
Overall Score Base Score 10m(for Satellite Data) Yearly -
Average Kharif Score 10m(for Satellite Data) Season -
Average Rabi Score 10m(for Satellite Data) Season -
Farm Details Region Details - - -
Survey Details - - -
Area - - Ha
Irrigation Condition 10m Yearly -
Cropping Intensity 10m Yearly -
Land Use type - -
Cropping History Season - - -
Crop Name - - -
Price - - Rs/100kg
Crop Performance 10m Season -
Potential Yield of Farms 10m Season Kg/Ha
Threshold Yield in District - Season Kg/Ha
Water Conditions Rainfall Trend 10km Daily Mm
Groundwater Trend 300m 1month Mm
Regional
parameters Nearest Mandi distance District-wise - Km
Nearest Mandi name District-wise - -
Proximity to nearest Road/Rail - - Km
Proximity to nearest Major Water Body - - Km
Drought Instances District-level - -
Village Population Village-level - -
Ambient Temperature 31km Daily Degree Celsius
Type of soil - - -
Agro-Ecological Sub-Zone - - -
Regional Prosperity Index - - -
Major crops in the region Season name - - -
Crop name - - -
Crop area - - Ha & %
Average crop yield - - Kg/Ha
Farm Location Survey Details - - -
Farm label - - -
Sub-farm Label - - -
Sub-farm Centroid - - -
Adjacent Land Details Adjacent Land Label - - -
Adjacent Land Survey details - - -
Direction - - Compass Directions
Phenology Crop Health 10m 10 days -
Crop Moisture 10m 10 days -
[68] The data object generation module 214 performs accelerated query processing of categorized pixels of the plurality of satellite images of the set of geospatial units by generating data objects of the plurality of parameters in a human and machine-readable format. The human and machine readable format may be JSON format. The JSON format organizes collected and processed data into a structured layout by hierarchically nesting information (e.g., state, district, sub-district), accurately formatting geometries and attributes, including metadata such as reference IDs, and request IDs to provide context and traceability.
[69] FIG. 3 illustrates a block diagram of pre-processing for accelerated query processing of categorized pixels according to some embodiments herein according to some embodiments herein. The block diagram of the pre-processing for accelerated query processing of categorized pixels includes a database 302, a dashboard generator 304, a search regional survey ID generator 306, a search result and map visualization 308, and a request with reference ID 310. It is crucial to meticulously track any modifications to ensure the accuracy and integrity of our records. The database 302 includes survey ID values for a corresponding query and the database 302 includes land boundaries for the corresponding survey ID. This dashboard generator 304 runs the queries in the buffer zone section by ensuring the appropriate "reference ID" for that specific query. Following this, proceed to process the group of Survey IDs from the database 302 against the provided reference ID at specified intervals provided by a user. The dashboard generator 304 includes a survey ID for each state and enhances the interface by integrating the survey ID alongside the information for each state based on each unique characteristics of the group of geospatial units. The regional survey ID generator module 306 is linked to the database 302 by enabling the retrieval of information about each region within the state. The association between the regional survey ID generator module 306 and the database 302 allows for accessing data specific to a multi-level selection of hierarchical geographical regions comprising a state region, a district region, a sub-district region and further regions, facilitating comprehensive analysis and decision-making based on regional insights. The search result and map visualization module 308 assists the user in correlating the survey IDs searched with the corresponding boundary locations by facilitating a seamless visualization of the boundary of the group of geospatial units on the map view for easier comprehension. The request with reference ID 310 specifies the provision of the report within the dashboard in a format that is readable by both humans and machines.
[70] FIG. 4 illustrates a flow diagram for user flow of the dashboard and generated report according to some embodiments herein. When a report request is initiated, the system 100 gathers and processes data from various modules, including farm geometry, phenology, images, major crops, ownership details, and surrounding environmental and infrastructure information such as water availability, temperature, soil type, nearest mandi, and population. These data elements are organized hierarchically (state, district, sub-district) and structured into a standardized JSON format. This format includes accurately formatted geometries, contextual attributes, and metadata like report dates and reference IDs, ensuring the output is both human- and machine-readable. The final JSON report can then be rendered on the dashboard or downloaded for use for users.
[71] FIG. 5 illustrates geospatial workflow of the system according to some embodiments herein. The geospatial workflow includes a first preprocessing module 502A, a second preprocessing module 502B, a datasets matching module 504, a survey ID matching module 506, a first QAQC module 508A, a fuzzy matching module 510, a validating module 512, a datasets integrating module 514, a parcel level matching module 516, a second QAQC checking module 508B, a matched datasets transmitting module 518, and a QAQC Hierarchy Table 520. The first set of datasets includes hierarchical land ownership records associated with users and the second set of datasets includes hierarchical data of geographical regions.
[72] The first preprocessing module 502A processes the first set of datasets by checking IDs, converting names to English, updating the name changes in the database, ensuring both original (native language) and English versions of names are present, checking for duplicates, and identifying any other survey-level errors. The second preprocessing module 502B processes the second set of datasets by adjusting scale and projection, correcting invalid geometries, identifying duplicate geometries, conducting QAQC on IDs such as District, Tehsil, and Village, cleaning attribute-level errors, and verifying the shape consistency of parcel files dissolved at the village level.
[73] The datasets matching module 504 compare datasets by performing ID matching at the village level using transliteration and SOUNDEX checks to account for spelling variations and phonetic similarities. It checks for exact matches via the Survey ID Matching Module 506; if matched, data proceeds to first QAQC Module 508A for quality assurance and control. If no exact match is found, the system uses the fuzzy matching module 510 to identify close matches, followed by the validating module 512 to ensure accuracy. If no exact match is found, the datasets integrating module 514 push the cleaned first set of datasets (dataset-1 302A) and the second set of datasets (dataset-2 302B) to the database for further processing. The parcel level matching module 516 performs data matching at the parcel level using unique identifiers such as IDs and survey numbers to ensure accurate correlation. Following this, the QAQC checking module 508B verifies the matched data for quality assurance and control before further processing.
[74] The matched datasets transmitting module 518 are configured to transmit the validated and quality-checked matched datasets received from the Second QAQC checking Module 508B. Upon successful verification, the module updates the matched data to the QAQC hierarchy Table 520 to ensure accurate hierarchical representation. Additionally, it sends the matcheddatasets-1 302A and datasets-2 302B to the database for persistent storage and further processing or analysis.
[75] The QAQC hierarchy module 520 is responsible for performing a two-level quality assurance and control check on the matched data before and after it is shared to the hierarchy table. In the first level of checks is also known as pre-sharing stage, the module verifies whether all villages are included, ensures that there are no duplicate entries in the hierarchy, and confirms that all survey numbers from the first set of datasets are added without duplication. In the second level of checks is also known as post-sharing stage, it validates whether the entire matched dataset has been successfully pushed to the hierarchy table and confirms that the has geometry columns are updated across all hierarchical levels.
[76] FIGS. 6A and 6B illustrate an exemplary view of an interface report document 600 with graphical elements and widgets based on accelerated query processing of categorized pixels according to some embodiments herein. The interface report document 600 with graphical elements and widgets based on accelerated query processing of categorized pixels includes an overall score, farm details, and a cropping history with metadata report dates, reference ID. The reference ID may be 12432542 and the report date may be 2025-03-24. The overall score, that is based on a base score, an average kharif score and an average rabi score, indicates factors that contribute to the overall score. The base score ranges from 0 to 200 and is calculated using two parameters, namely irrigation condition and cropping intensity. Irrigation condition includes irrigation status of the geospatial group and the status of either irrigated or non-irrigated is depicted by icons. Cropping intensity refers to the number of times a group of geospatial units are cultivated in one year and is determined from the crops grown in Kharif to Rabi season. For example, if a group of land parcels have been cultivated twice a year, the cropping intensity will be 2 and is also depicted by icons in the interface report document 600. The Rabi season falls between November and April whereas the Kharif Season falls between June to October. Seasonal Score ranges from 200-400 and is computed from three parameters, namely, Agricultural Condition Risk, Regional Agricultural Potential, and Revenue Score.
[77] The group of land parcels details include a region, a survey number, an area, an irrigation condition, a cropping intensity, a farm centroid, land parcels classification type. Further, the region may be a multi-level selection of hierarchical geographical regions including a state region, a district region, a sub-district region, and further regions. The survey number may be a multi-level selection of survey numbers for example a khewat, a murabba, a khasra in the state of Haryana. In 604, Farm details mention Aodo Majra village in Ambala district, state of Haryana, show two distinct agricultural regions. The first region (Khewat-1, Murabba-39, Khasra-20/2) is well-irrigated and exhibits twice a year cropping intensity, indicating active cultivation. In contrast, the second region (Khewat-1, Murabba-41, Khasra-2/1) lacks irrigation facilities and shows once a year cropping intensity. The centroid of the first region is located at 30.22892°N, 76.73652°E, and the centroid of the second region is at 30.22805°N, 76.73734°E. The farm centroids are crucial for precisely locating farms and enabling spatial analysis of their distribution and environmental context. This information supports efficient resource management and precision agriculture practices.
[78] Figure 6B shows the cropping history for three years in Ambala district, Haryana, covering the period from Dec 2021 to Nov 2024. Further, the cropping history includes a season name, crop names, price in rupee per 100 kg, crop performance, and crop yield (kg/ha). During this duration, the farmer consistently cultivated paddy during the Kharif season and wheat during the Rabi season. Paddy crops showed average performance across all three years, with market prices increasing from ₹1960 to ₹2183 per 100 kg. In contrast, wheat crops consistently underperformed despite price improvements from ₹2015 to ₹2275. Yield data indicates that farm productivity remained below the district potential in all seasons, with particularly large gaps during the Rabi seasons—most notably in 2022–2023, where wheat yielded only 1692 kg/ha compared to a district potential of 2582 kg/ha.
[79] As an example, the following table “Table 2” describes how different values of the base score, the average kharif score and the average rabi score affect the overall score and the associated risk levels.
Overall Score (out of 1000) Risk Level Base Score (out of 200) Average Kharif Score(out of 400) Average Rabi Score (out of 400)
741 Medium Risk 200 284 257
784 Medium Risk 200 285 299
754 Medium Risk 200 264 290
646 High Risk 200 217 229
669 High Risk 200 244 225
[80] FIG. 7 illustrates a user interface displaying the farm location on a geographical map, along with details of adjacent land parcels in the farm region, according to some embodiments herein. The adjacent land parcels may refer to neighboring land parcels. The first region is surrounded by adjacent lands identified through official land survey records. To the South-West, it is bound by land with Khewat No. 266, Murabba No. 41, Khasara No. 1/1; to the South-East, by Khewat No. 266, Murabba No. 41, Khasara No. 2/2; to the East, by Khewat No. 266, Murabba No. 0, Khasara No. 76/1; and to the West, by Khewat No. 1, Murabba No. 41, Khasara No. 1/2. These details ensure accurate identification and demarcation of the first region boundaries. On the South-West side, the second region is adjacent to Khewat No. 266, Murabba No. 41, Khasara No. 1/1; on the South-East side, to Khewat No. 266, Murabba No. 41, Khasara No. 2/2; on the East, to Khewat No. 266, Murabba No. 0, Khasara No. 76/1; and on the West, to Khewat No. 1, Murabba No. 41, Khasara No. 1/2. The North-West side shares boundaries with two parcels: Khewat No. 2, Murabba No. 39, Khasara No. 21 and Khewat No. 264, Murabba No. 0, Khasara No. 76/2/3. These references clearly define the location and limits of the second region for mapping and land administration purposes.
[81] FIG. 8 illustrates a graphical representation of rainfall variations at the third level region over a decade according to some embodiments herein. The third level region may be subdistrict level region. The rainfall trend in the subdistrict of Ambala from 2013 to 2022 shows significant yearly variation. The highest recorded rainfall was in 2013 at 1873 mm, while the lowest was in 2019 with a sharp dip. Most years, such as 2015, 2018, 2020, and 2021, received rainfall above the average level of 1382 mm, whereas years like 2017, 2019, and 2022 saw below-average rainfall. This indicates an inconsistent rainfall pattern across the decade.
[82] FIG. 9 illustrates a graphical representation of groundwater thickness trend at the third level region according to some embodiments herein. The third level region may be subdistrict level. The groundwater thickness is defined as an integrated estimate of water stored on and beneath the surface of Earth. Terrestrial water storage can be defined as the summation of all water on the land surface and in the subsurface. It includes surface soil moisture, root zone soil moisture, groundwater, snow, ice, water stored in the vegetation, river and lake water. The district may be Ambala. The groundwater levels have varied throughout the years, peaking in 2018 and reaching their lowest point in 2021. The years 2013, 2015, and 2018 recorded above-average groundwater thickness, whereas 2016, 2019, 2020, and 2021 remained below the average. This reflects a downward trend in groundwater availability during the latter part of the decade.
[83] FIG. 10 illustrates a tabular representation. of regional parameters according to some embodiments herein. The tabular representation. of regional parameters includes a nearest mandi, a proximity to nearest road/rail, a proximity to nearest major water body, a drought instances (at district level, since 2000), a village population (As per Census 2011), ambient temperature (annual min/max in the Year 2023, at Sub-District Level), Type of Soil, agro-ecological Sub-Zone, regional prosperity index (based on night light index and population at district level). The agro-ecological Sub-Zone Sub-agro ecological zone is a land unit represented accurately or precisely in terms of major climate and growing period, which is climatically suitable for a certain range of crops for cultivation.
[84] The regional parameters for the area indicate that the nearest mandi is located 14 km away in Lamailabad, while road or rail connectivity is very close at just 0.3 km. The proximity to the nearest major water body is 5.7 km. The region has experienced droughts in the years 2002, 2014 (twice), and 2015. As per the 2011 Census, village population data is not available. In 2023, the ambient temperature at the sub-district level ranged from a minimum of 4.2°C to a maximum of 42°C. The soil is categorized as alluvial-derived with saline phases, and the agro-ecological sub-zone is classified under the Northern Plain Hot Subhumid (Dry) Eco Region. The regional prosperity index, based on the night light index and district-level population, is 0.64 out of 1, reflecting a moderate level of economic development.
[85] FIG. 11 illustrates a tabular representation of cropping patterns and major crops in the district in which the farm lands exist according to some embodiments herein. The cropping pattern of the region is divided between the kharif and rabi seasons. During the kharif season, the major crop is paddy, which occupies the largest area of 86,967 hectares, accounting for 69.61% of the total kharif crop area, with an average yield of 3,706 kg/ha. Bajra is grown over 41,001 hectares, representing 32.82% of the area, but with a significantly lower average yield of 502 kg/ha. Moong (green gram) covers 19,161 hectares or 15.34% of the kharif area, with a relatively high yield of 3,840 kg/ha. In the rabi season, masoor is the primary crop, cultivated over 35,327 hectares, which constitutes 28.28% of the rabi crop area, and has an average yield of 2,452 kg/ha. Other oilseeds are also grown during this season, covering 17,577 hectares or 14.07% of the rabi area, with an average yield of 682 kg/ha. This data indicates a strong reliance on paddy in kharif and a diverse but lower-yielding crop profile in the rabi season.
[86] FIG. 12 illustrates a tabular representation. of agricultural parameters according to some embodiments herein. The agricultural parameters representation and guide include an overall score, a seasonal score, an irrigation condition, a cropping intensity. The overall score is based on the accelerated query processing of the categorized pixels of the plurality of satellite images of the set of land parcels and is calculated based on the agricultural parameters of the farms that belong to a farmer. It comprises of a base score (based on irrigation condition and cropping intensity of farms) and seasonal scores for the Kharif & Rabi seasons, each calculated based on the farming history in the past 3 years. Seasonal Score ranges from 200-400 and is computed from three parameters, namely, agricultural Condition Risk (a.k.a Crop performance), regional agricultural potential, and revenue Score. The seasonal score reflects the capacity of a farm/farmer to grow crops and earn based on the agricultural performance in the respective season. Cropping intensity refers to the number of times a group of geospatial units are cultivated in one year and is determined from the crops grown in Kharif to Rabi season. For one cycle it is Once a Year, for two it is Twice a Year. The irrigation condition is an agricultural water content measured by using multispectral data to classify if a land parcel is irrigated or not. For example, if a geospatial unit is used to cultivate wheat once during the rabi season, the cropping cycle is considered one. If it is followed by a kharif crop in the same year, the cropping cycle becomes two.
[87] The Overall score and seasonal score are represented using different colors to indicate the risk and productivity levels of farms, helping guide the user’s lending decisions. Poor farms (highest risk) show low productivity and limited revenue potential and should be considered unfavorable for lending. Fair farms (high risk) have average productivity and moderate revenue potential and may be considered lower priority. Good farms (medium risk) demonstrate high productivity and strong revenue potential and should be considered favorably after the very good category. Very good farms (low risk) also show high productivity and revenue potential and should be prioritized for lending immediately after excellent farms. Excellent farms (lowest risk) represent the highest productivity and revenue potential and should be given the highest priority in lending decisions.
[88] The irrigation conditions are categorized into two types: irrigated land and non-irrigated land. Widgets are used to represent these categories, with the crossed widget indicating non-irrigated land and the symbol tick mark widget representing irrigated land. The cropping intensity table includes different widgets to represent the frequency of cropping. The "single crop" widget indicates cropping intensity once a year, the "double crop" widget represents cropping intensity twice a year, and the "crossed crop" widget signifies no cropping within a year.
[89] FIG. 13 illustrates a tabular representation of API Latency Percentile Metrics according to some embodiments herein.The figure illustrates API latency percentiles, which represent the time within which a certain percentage of requests are completed. For example, P50 (the median) indicates that 50% of requests are faster and 50% are slower than this value, while P90, P95, and P99 show the response time under which 90%, 95%, and 99% of requests are served, respectively. These percentile metrics—such as P50 at 16.4s, P90 at 35.1s, and P99.9 at 56.9s—help reveal the distribution of API response times and highlight performance patterns, especially outliers, enabling better detection of delays and potential bottlenecks in the system.
[90] FIGS 14A and 14B is a flow diagram of a method for accelerated query processing in Integrated datasets using an optimized Indexing technique according to some embodiments herein. At step 1402, the method includes collecting a first set of datasets and a second set of datasets, wherein the first set of datasets comprises hierarchical user records associated with users and the second set of datasets comprises hierarchical data of geographical regions. At step 1404, the method includes performing, based on the interaction of a user on a graphical user interface (GUI), a multi-level selection of hierarchical geographical regions comprising a first-level region, a second-level region, a third-level region, and subsequent level region using a spatial indexing technique, wherein options for a subsequent selection are dynamically populated based on a preceding selection from a first mapping of the hierarchical user records and the hierarchical data of geographical regions. At step 1406, the method includes updating the GUI to present vector geometries based on the multi-level selection, wherein the vector geometries represent polygons and are derived from a second mapping of the vector geometries and hierarchical user records. At step 1408, the method includes generating analytical data on spatial matching by associating at least one geometric boundary extracted from satellite imagery with a Survey ID and a Survey Number, based on vector geometries selected through the GUI. At step 1410, the method includes automatically determining, using a trained AI model, categorized pixels from a plurality of satellite images associated with the group of geospatial units, wherein the categorized pixels comprise at least one of a crop area pixel or a non-crop area pixel for at least one season. At the step 1412, the method includes assessing, using the trained AI model, the categorized pixels of the group of geospatial units with a score for the entity and automatically determining a plurality of parameters for the group of geospatial units wherein the plurality of parameters comprises irrigation condition, cropping intensity, cropping history, crop type, crop performance, crop yield, crop revenue, weather data, neighboring farm units, primary crops, and farm centroid in the group of geospatial units. At the step 1414, the method includes performing query processing of categorized pixels of the plurality of satellite images of the set of agricultural units by generating data objects of the plurality of parameters in a user and machine-readable format and displaying the plurality of parameters at a user interface, wherein the generated data object may be a spatial object that comprises location or geometry information.
[91] The method significantly reduces computational time, with the average duration to generate the data objects of the plurality of parameters ranging between 10 to 12 seconds to process one farm, whereas the for multiple farms it takes exponentially increased. This effectively improves decision support in agricultural analysis with comprehensive parameter assessments and adaptive analysis capabilities. Moreover, the method ensures robust data integration and visualization, leveraging shapefile-based GUI updates and satellite image analysis for grouping geometric boundaries.
[92] The integration of user records and vector geometries into the graphical interface enhances user experience and comprehension, enabling intuitive navigation and interpretation of agricultural data. Additionally, by utilizing the multi-level selection of hierarchical geographical regions and dynamic population of subsequent options based on preceding selections, the method offers flexibility and customization in the analysis of categorized pixels of satellite images.
[93] Referring now to FIG. 15, a representative cloud computing environment 1500 comprising a set of functional abstraction layers are shown. It should be understood in advance that the components, layers, and functions shown in FIG. 15 are intended to be illustrative only and embodiments of the invention are not limited thereto. As depicted, the following layers and corresponding functions are provided. A hardware and software layer 60 includes hardware and software components. Examples of hardware components include mainframes 61, RISC (Reduced Instruction Set Computer) architecture-based servers 62, servers 63, blade servers 64, storage devices 65,and networks and networking components 66. In some embodiments, software components include network application server software 67 and database software 68. A virtualization layer 70 provides an abstraction layer from which the following examples of virtual entities may be provided virtual servers 71, virtual storage 72, virtual networks 73, including virtual private networks, virtual applications and operating systems 74, and virtual clients 75.
[94] In one example, management layer 80 may provide the functions described below. Resource provisioning 81 provides dynamic procurement of computing resources and other resources that are utilized to perform tasks within the cloud computing environment 1500. Metering and pricing 82 provide cost tracking as resources are utilized within the cloud computing environment 1500, and billing or invoicing for consumption of these resources. In one example, these resources may include application software licenses. Security provides identity verification for cloud consumers and tasks, as well as protection for data and other resources. User portal 83 provides access to the cloud computing environment for 1500 consumers and system administrators. Service level management 84 provides cloud computing resource allocation and management such that required service levels are met.
[95] Workloads layer 90 provides examples of functionality for which the cloud computing environment 1500 may be utilized. Examples of workloads and functions that may be provided from this layer include mapping and navigation 91, software development and lifecycle management 92, virtual classroom education delivery 93, data analytics processing 94, transaction processing 95, and microservice recipe creation 96.
[96] The embodiments herein can take the form of a computer program product accessible from a computer-usable or computer-readable medium providing program code for use by or in connection with a computer or any instruction execution system. For the purposes of this description, a 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.
[97] The medium can be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) or a propagation medium. Examples of a computer-readable medium include a semiconductor or solid-state memory, magnetic tape, a removable computer diskette, random-access memory (RAM), read-only memory (ROM), and a rigid magnetic disk.
[98] A data processing system suitable for storing and/or executing program code will include at least one processor coupled directly or indirectly to memory elements through a system bus. The memory elements can include local memory employed during actual execution of the program code, bulk storage, and cache memories which provide temporary storage of at least some program code to reduce the number of times code must be retrieved from bulk storage during execution.
[99] Input/output (I/O) devices (including but not limited to keyboards, displays, pointing devices, etc.) can be coupled to the system either directly or through intervening I/O controllers. Network adapters may also be coupled to the system to enable the data processing system to become coupled to other data processing systems or remote printers or storage devices through intervening private or public networks.
[100] FIG. 16 is a schematic diagram of the computer architecture of a pooling and decoding device user device or testing device or a molecular computer or a computing device, in accordance with the embodiments herein. A representative hardware environment for practicing the embodiments herein is depicted in FIG. 15, with reference to FIGS. 1 through 14. This schematic drawing illustrates a hardware configuration of a server/computer system/ computing device in accordance with the embodiments herein. The system 100 includes at least one processing device CPU 10 that may be interconnected via system bus 14 to various devices such as a random-access memory (RAM) 12, read-only memory (ROM) 16, and an input/output (I/O) adapter 18. The I/O adapter 18 can connect to peripheral devices, such as disk units 38 and program storage devices 40 that are readable by the system. The system can read the inventive instructions on the program storage devices 40 and follow these instructions to execute the methodology of the embodiments herein. The system further includes a user interface adapter 22 that connects a keyboard 28, mouse 30, speaker 32, microphone 34, and/or other user interface devices such as a touch screen device (not shown) to bus 14 to gather user input. Additionally, a communication adapter 20 connects the bus 14 to a data processing network 42, and a display adapter 24 connects the bus 14 to a display device 26, which provides a graphical user interface (GUI) 36 of the output data in accordance with the embodiments herein, or which may be embodied as an output device such as a monitor, printer, or transmitter, for example.
[101] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the scope.
, Claims:I/We Claim:
1. A method for accelerated query processing of an integrated dataset of records data and satellite image data to generate parameters on a Graphical User Interface, comprising:
collecting a first set of datasets and a second set of datasets, wherein the first set of datasets comprises hierarchical user records and the second set of datasets comprises hierarchical geographical regions data;
performing, based on interaction of a user on a graphical user interface (GUI), a multi-level selection of hierarchical geographical regions data comprising a first-level region, a second-level region, a third-level region and subsequent level region using a hybrid spatial indexing technique, wherein options for a subsequent selection are dynamically populated based on preceding selection from a first mapping of the hierarchical user records and the hierarchical geographical regions data;
updating the GUI to present vector geometries based on the multi-level selection, wherein the vector geometries represent polygons and are derived from a second mapping of the vector geometries and hierarchical user records data;
generating analytical data on spatial matching by associating at least one geometric boundary extracted from satellite imagery with a Survey ID and a Survey Number, based on the vector geometries selected through the GUI;
automatically determining, using a trained artificial intelligence (AI) model, categorized pixels from a plurality of satellite images associated with a group of a geospatial unit, wherein the categorized pixels comprise at least one of a crop area pixel or a non-crop area pixel for at least one season;
assessing, using the trained AI model, the categorized pixels of the group of the geospatial unit with a score for an entity and automatically determining a plurality of parameters for the group of geospatial unit, wherein the plurality of parameters are selected from irrigation condition, cropping intensity, cropping history, crop type, crop performance, crop yield, crop revenue, weather data, neighboring farm units, primary crops, and a farm centroid in the group of the geospatial unit; and
performing accelerated query processing using optimized Indexing for analyzing categorized pixels of the plurality of satellite images of the set of agricultural geospatial unit by generating data objects of the plurality of parameters in a user and machine-readable format and displaying the plurality of parameters at a user interface, wherein the data objects comprise location or geometry information.
2. The method as claimed in claim 1, wherein the spatial indexing comprises manages queries of the spatial data in a database by integrating an GiST method for complex geometries with a tree- based method for efficiently handling point data, wherein the GiST method indexes multi-dimensional spatial data by grouping nearby objects and representing them with bounding rectangles for fast spatial queries and the tree based method divides multi-dimensional spatial domain into nodes, wherein each nodes stores references to geospatial objects located within it.

3. The method as claimed in claim 1, wherein the spatial indexing technique utilizes a dynamic indexing technique to create, update, and maintain indexes in real time as data changes, ensuring optimal performance.

4. The method as claimed in claim 1, wherein the spatial indexing uses a dynamic technique to create, update, and maintain indexes in real time as data changes byadding new entries and modifying existing ones to ensure optimal performance through PostgreSQL’s GiST indexing method.

5. The method as claimed in claim 1, wherein Spatial indexing supports custom geospatial functions, thatcomprises ST_Within function, ST_Intersects function, and ST_Contains function, which determine spatial relationships and efficiently exclude non-relevant geometries, enabling fast and efficient access to geospatial data during query execution.

6. The method as claimed in claim 1, wherein the machine-readable format employs a JSON format to structure datasets into a hierarchical format with nested levels, ensuring a correct formatting of geometries and attributes, enriching the data objects with metadata such as report dates, reference IDs, and request IDs, and verifying completeness by checking that all required fields are consistently populated.

7. A system (100) for accelerated query processing in Integrated datasets using an optimized Indexing technique, the system (100) comprising:
a satellite image analysis server (102) that comprises a processor and a memory that are configured to perform:
collecting a first set of datasets and a second set of datasets, wherein the first set of datasets comprises hierarchical user record data associated with users and the second set of datasets comprises hierarchical geographical regions data;
performing, based on interaction of a user on a graphical user interface (GUI), a multi-level selection of hierarchical geographical regions data comprising a first region, a second region, a third region and further regions using a spatial indexing technique, wherein options for a subsequent selection are dynamically populated based on preceding selection from a first mapping of the hierarchical user record data and the hierarchical geographical regions data;
updating the GUI to present vector geometries based on the multi-level selection, wherein the vector geometries represent polygons and are derived from a second mapping of the vector geometries and hierarchical user record data;
generating analytical data on spatial matching by associating at least one geometric boundary extracted from satellite imagery with a Survey ID and a Survey Number, based on vector geometries selected through the GUI;
automatically determining, using a trained AI model, categorized pixels from a plurality of satellite images associated with the group of geospatial unit, wherein the categorized pixels comprise at least one of a crop area pixel or a non-crop area pixel for at least one season;
assessing, using the trained AI model, the categorized pixels of the group of geospatial units with a score for an entity and automatically determining a plurality of parameters for the group of geospatial unit, wherein the plurality of parameters comprises irrigation condition, cropping intensity, cropping history, crop type, crop performance, crop yield, crop revenue, weather data, neighboring farm units, primary crops, and farm centroid in the group of geospatial unit; and
performing accelerated query processing using the optimized Indexing technique for analyzing categorized pixels of the plurality of satellite images of the set of agricultural geospatial unit by generating data objects of the plurality of parameters in a user and machine-readable format and displaying the plurality of parameters at a user interface, wherein the generated data object may be a spatial object that comprises location or geometry information.

8. The system (100) as claimed in claim 7, wherein the spatial indexing technique manages and queries spatial data in a database by integrating a GiST method for complex geometries with a tree-based method for efficiently handling point data, wherein the GiST method indexes multi-dimensional spatial data by grouping nearby objects and representing them with bounding rectangles for fast spatial queries and the tree-based method divides multi-dimensional spatial domain into nodes, each node stores references to geospatial objects located within it.
9. The system (100) as claimed in claim 7, wherein the spatial indexing uses a dynamic technique to create, update, and maintain indexes in real time as data changes byadding new entries and modifying existing ones to ensure optimal performance through PostgreSQL’s GiST indexing method.

10. The method as claimed in claim 1, wherein Spatial indexing supports custom geospatial functions, thatcomprises ST_Within function, ST_Intersects function, and ST_Contains function, which determine spatial relationships and efficiently exclude non-relevant geometries, enabling fast and efficient access to geospatial data during query execution.
Dated this June 4th, 2025
Signature:
Name: Arjun Karthik Bala
IN/PA No. 1021