DESC:TECHNICAL FIELD:

[001] The present disclosure generally relates to agricultural technology, and more particularly to a system and a method for forecasting and estimating pest and disease vulnerability index for crops.

BACKGROUND:

[002] Due to population growth, world food demand is increasing every day. However, crop production is becoming challenging because of various factors such as, but not limited to, falling groundwater levels, pollution, climate change, pests, and diseases. Among these factors, pests and diseases are critical factors that always restrict the production of any crop, causing devastating damage and affecting the entire agriculture supply chain, leading to a shortage of food. In addition, globalization and climate change are adding to the emergence and spread of new diseases or known diseases to newer areas. The severity of devastation depends on multiple other factors such as the crop that is grown and its susceptibility to the diseases, and management practices. These factors account for almost an average of 40% or more loss in production [Isard et al., 2011; Devadas et al., 2015; West and Kimber, 2015; Mahlein, 2016].

[003] Many growers and farmers, especially small landholding farmers, face challenges in planning intervention and management strategy for their fields during the growing season. One of the problems faced during agriculture production is the increasing severity of pest and disease outbreaks which is further aggravated by intensifying stresses linked to the climate change. The pests and the diseases can decimate crops and can hence lead to losses in yield and productivity. As an example, the Rice Blast and Brown planthopper lead to an annual loss in yield during epidemic conditions peaking to more than 60% and sometimes more than 75%. This is because it is difficult to know in advance the kind of diseases that might affect a plot, field, or region, and the virulence of the disease, and thus plan any interventions.

[004] One of the conventional practises to deal with pests and diseases is to treat the symptoms, which is typically done by the application of chemical fertilizers and pesticides. However, the symptoms need to be detected to treat the symptoms, and such a procedure generally requires an expert to visit the field to detect the pests and diseases. Further, the conventional field scouting methods are expensive, difficult to execute, require expertise, and are also time-consuming. In addition, the injudicious use of chemical pesticides and agrochemicals to reduce crop losses, in general, has shown to increase production costs, degrade the environment and compromise grain quality, leading to a vicious cycle of food insecurity, especially in smallholder farms. Moreover, they may have a drastic impact on food security on a larger scale and can impede supply chains and international trade. The injudicious use of agrochemicals, such as pesticides, for pest and disease management, has proven to be ineffective, especially in the long run, and the conventional field scouting of plant pests and diseases is point-based and time-consuming.

[005] A few advanced methods and systems for pest risk assessment include the use of crowdsourced data from a plot and assessing the risk based on the neighbouring plots, the use of weather forecasts, the use of IoT (Internet of Things) devices for monitoring the crop, etc. However, such methods and systems rely solely on weather data or on coarse resolution optical data from satellites for predicting the occurrence of pests and diseases. The problems with such methods and systems include – (1) the optical satellite data (multispectral) lacks temporal continuity due to differential cloud cover, which can greatly affect the accuracy of early prediction of pest and disease occurrence, for example, satellite data may not coincide with a specific growth stage. (2) the coarse spectral and spatial resolution may not capture diagnostic features that can indicate the current or future risk at a field scale (1-10 hectares) and (3) the weather data alone cannot explain most of the observed variation in the prediction of pest and disease risk.

SUMMARY

[006] This summary is provided to introduce a system and a method for forecasting and estimating pest and disease vulnerability index for a crop in a simple manner that is described further in the detailed description of the disclosure. This summary is not intended to identify key or essential inventive concepts of the subject matter nor is it intended to determine the scope of the disclosure.

[007] The objective of the present disclosure is to provide a system and a method for forecasting and estimating a pest and disease vulnerability index for a crop.

[008] Another objective of present disclosure is to reduce the cost involved in agricultural inputs (both biological and chemical) and hence increase profitability.

[009] Yet another objective of the present disclosure is to reduce the amount of damage and help to reduce the spread to neighbouring villages, towns, districts, and states.

[0010] Yet another objective of the present disclosure is to increase crop yield and address the question of food security.

[0011] Yet another objective of the present disclosure is to provide weekly or fortnightly forecasts as actionable information to the farmers or decision-makers to prevent or mitigate the effects of infestation.

[0012] According to an aspect of the present disclosure, a computer implemented method is provided, for determining a pest and disease vulnerability index for a crop. The method comprising: receiving an input from a user, the input comprising at least farm data, the farm data including at least geocoordinates of the farm; obtaining remote sensing data of one or more regions of interest from one or more satellites, wherein the remote sensing data includes one or more of optical satellite images and radar satellite images; obtaining weather data, historical farm data, ground data, crop genetic data, historical and present disease and pest outbreak data of the farm and the one or more regions of interest from one or more servers; determining crop grown using the remote sensing data and a first pretrained artificial intelligence model; determining a phenological stage in which the crop is, using the remote sensing data, one or more derived features from the remote sensing data and a second pretrained artificial intelligence model; determining land utilization data in the region of interest using the remote sensing data and a third pretrained artificial intelligence model; and determining a pest and disease vulnerability index for the crop based on the crop stage, the weather data, the historical farm data, the ground data, the crop genetic data, the land utilization data and the historical and present disease and pest outbreak data.

[0013] According to another aspect of the present disclosure, a system is provided, for determining a pest and disease vulnerability index for a crop. The system comprising: at least one user device communicatively coupled to at least one forecast server via a communication network for providing an input to the at least one forecast server, the input comprising at least farm data, the farm data including at least geocoordinates of the farm; at least one server communicatively coupled to the at least one forecast server via the communication network for providing weather data, historical farm data, ground data, crop genetic data, historical and present disease and pest outbreak data of the farm and the one or more regions of interest, wherein the forecast server is configured for: receiving the input comprising at least farm data, the farm data including at least geocoordinates of the farm; obtaining remote sensing data of one or more regions of interest from one or more satellites via the communication network, wherein the remote sensing data includes one or more of optical satellite images and radar satellite images; obtaining weather data, historical farm data, ground data, crop genetic data, historical and present disease and pest outbreak data of the farm and the one or more regions of interest from one or more servers; determining crop grown using the remote sensing data and a first pretrained artificial intelligence model; determining a phenological stage in which the crop is using the remote sensing data, one or more derived features from the remote sensing data and a second pretrained artificial intelligence model; determining land utilization data in the region of interest using the remote sensing data and a third pretrained artificial intelligence model; and determining a pest and disease vulnerability index for the crop based on the crop stage, the weather data, the historical farm data, the ground data, the crop genetic data, the land utilization data and the historical and present disease and pest outbreak data.
BRIEF DESCRIPTION OF THE FIGURES

[0014] These and other features, aspects, and advantages of the example embodiments will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

[0015] Figure 1 illustrates an exemplary system for forecasting and estimating pest and disease vulnerability index for a crop in accordance with an embodiment of the present disclosure.

[0016] Figure 1A illustrates the internal components of the forecasting server as described in Figure 1 in accordance with an embodiment of the present disclosure.

[0017] Figure 1B illustrates various input data utilized by forecasting server in accordance with an embodiment of the present disclosure.

[0018] Figure 2A illustrates an exemplary framework for forecasting and estimating pest and disease vulnerability index for a crop in accordance with an embodiment of the present disclosure.

[0019] Figure 2B illustrates grid identification in accordance with an embodiment of the present disclosure.

[0020] Figure 3 illustrates the interaction of the pathogen with the host and the environment.

[0021] Figure 4 is a flowchart depicting the method of forecasting and estimating pest and disease vulnerability index for a crop in accordance with an embodiment of the present disclosure.

[0022] Figure 5 illustrates the coffee berry disease, blister blight and coffee leaf rust identified using our system and method in accordance with various embodiments of the present disclosure.

[0023] Figure 6 illustrates the blister blight for coffee vulnerability index estimates in accordance with an embodiment of the present disclosure.

[0024] Further, people skilled in the art to which this disclosure belongs will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

DETAILED DESCRIPTION

[0025] For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures, and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications to the disclosure, and such further applications of the principles of the disclosure as described herein being contemplated as would normally occur to one skilled in the art to which the disclosure relates are deemed to be a part of this disclosure.

[0026] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the disclosure and are not intended to be restrictive thereof.

[0027] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or a method. Similarly, one or more devices or sub-systems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, other sub-systems, other elements, other structures, other components, additional devices, additional sub-systems, additional elements, additional structures, or additional components. Appearances of the phrase “in an embodiment”, “in another embodiment” and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.

[0028] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. The system, methods, and examples provided herein are illustrative only and not intended to be limiting.

[0029] Embodiments of the present disclosure will be described below in detail with reference to the accompanying figures.

[0030] In addition to the illustrative aspects, exemplary embodiments, and features described above, further aspects, exemplary embodiments of the present disclosure will become apparent by reference to the drawings and the following detailed description.

[0031] Thus, with reference to the state of the art, there has been a long felt need for a system and a method for forecasting and estimating a pest and disease vulnerability index for a crop.

[0032] To overcome the problems of the state of the art, the present disclosure provides a system and a method for forecasting and estimating pest and disease vulnerability index for a crop.

[0033] Embodiments of the present disclosure disclose a system and a method for forecasting and estimating a pest and disease vulnerability index for a crop. In one embodiment, the system identifies the crop grown in the geographical region based on the plurality of intensity and temporal reflectance data values or a crop identification model learned and retrieved from memory, or a crop mask layer retrieved from memory. Then the system retrieves local regional weather data from one or more weather stations or forecast values for a time in the near future, current and historical data of a location or of the host and pest using crowd-sourced data, genetic and hybrid information of the host or pest or both, field management practices, and also retrieves other indices derived from the satellite optical or radar imaging modalities which provide an indication of the health of the soil, the crop, the effect of the biotic and abiotic stresses. By weighting each of these pluralities of parameters from the region and by using spatial spread of the pathogen, the system provides an estimate of the vulnerability index of that land or region to pests and diseases based on historical incidence values for multiple regions.

[0034] According to one embodiment of the present disclosure, a computer implemented method is provided, for determining a pest and disease vulnerability index of a crop. The method comprising: receiving an input from a user, the input comprising at least farm data, the farm data including at least geocoordinates of the farm; obtaining remote sensing data of one or more regions of interest from one or more satellites, wherein the remote sensing data includes one or more of optical satellite images and radar satellite images; obtaining weather data, historical farm data, ground data, crop genetic data, historical and present disease and pest outbreak data of the farm and the one or more regions of interest from one or more servers; determining crop grown using the remote sensing data and a first pretrained artificial intelligence model; determining a phenological stage in which the crop is using the remote sensing data, one or more derived features from the remote sensing data and a second pretrained artificial intelligence model; determining land utilization data in the region of interest using the remote sensing data and a third pretrained artificial intelligence model; and determining a pest and disease vulnerability index for the crop based on the crop stage, the weather data, the historical farm data, the ground data, the crop genetic data, the land utilization data and the historical and present disease and pest outbreak data.

[0035] According to another embodiment of the present disclosure, a system is provided, for determining a pest and disease vulnerability index for a crop. The system comprising: at least one user device communicatively coupled to at least one forecast server via a communication network for providing an input to the at least one forecast server, the input comprising at least farm data, the farm data including at least geocoordinates of the farm; at least one server communicatively coupled to the at least one forecast server via the communication network for providing weather data, historical farm data, ground data, crop genetic data, historical and present disease and pest outbreak data of the farm and the one or more regions of interest, wherein the forecast server is configured for: receiving the input comprising at least farm data, the farm data including at least geocoordinates of the farm; obtaining remote sensing data of one or more regions of interest from one or more satellites via the communication network, wherein the remote sensing data includes one or more of optical satellite images and radar satellite images; obtaining weather data, historical farm data, ground data, crop genetic data, historical and present disease and pest outbreak data of the farm and the one or more regions of interest from one or more servers; determining crop grown using the remote sensing data and a first pretrained artificial intelligence model; determining a phenological stage in which the crop is using the remote sensing data, one or more derived features from the remote sensing data and a second pretrained artificial intelligence model; determining land utilization data in the region of interest using the remote sensing data and a third pretrained artificial intelligence model; and determining a pest and disease vulnerability index for the crop based on the crop stage, the weather data, the historical farm data, the ground data, the crop genetic data, the land utilization data and the historical and present disease and pest outbreak data.

[0036] Figure 1 shows an exemplary system for forecasting and estimating pest and disease vulnerability index for a crop in accordance with an embodiment of the present disclosure. As shown, the system 100 comprises a plurality of farmer devices 105-1 to 105-N (hereafter referred as user device 105), a forecast server 110, one or more other servers 115-1 to 115-N, and a communication network 120, wherein the user device 105, the forecast server 110 and the other servers 115 are communicatively connected through the communication network 120.

[0037] The user device 105 associated with the farmer may be any computing device that often accompanies its users to perform various activities such as-making mobile telephone calls, browsing, communicating emails, etc. By way of example, the user device 105 may include a smartphone, a laptop, a notebook computer, a tablet, and the like having communication capabilities. It will be appreciated by those skilled in the art that the user device 105 comprises one or more functional elements capable of communicating through the communication network 120 to receive one or more services offered by the forecast server 110. In one embodiment of the present disclosure, a farmer may use the user device 105 for providing input to the forecast server 110 and for receiving forecast data from the forecast server 110. For the said purpose, the farmer may use a dedicated application installed on the user device 105 or may use a web browser. The input as described herein may include, but not limited to, farm details, geo coordinates, soil details, crop details, etc as shown in Figure 1B. The forecast data as described herein may include possible pest attacks, diseases, and actionable information to farmers or decision-makers to prevent or mitigate adversity due to infestation.

[0038] The forecast server 110 may include, for example, a computer server or a network of computers or a virtual server that provides functionalities or services for other programs or devices such as for the user device 105 associated with the farmer. In one implementation, the forecast server 110 is a cloud server comprising one or more processors, associated processing modules, interfaces and storage devices communicatively interconnected to one another through one or more communication means for communicating information. The storage associated with the forecast server 110 may include volatile and non-volatile memory devices for storing information and instructions to be executed by one or more processors and for storing temporary variables or other intermediate information during processing. In one embodiment of the present disclosure, the forecast server 110 is configured for providing an index of the vulnerability of a plot growing a particular crop to a particular disease based on a plurality of predefined parameters from satellite, hyperlocal weather data, historical climate data, field data, location geocoordinates and other data sources as shown in Figure 1B. Other servers 115 may include, but not limited to, weather data servers, historical climate data servers, and field data servers.

[0039] The forecast server 110 is shown in Figure 1A in accordance with one exemplary aspect of the present disclosure. In one aspect, the forecast server 110 comprises a processor 110a, a memory 110, an input interface 110c, an output interface 110d, a first module 110e, a second module 110f, and a third module 110g. The processor 110a is communicatively coupled with the memory 110, the input interface 110c, the output interface 110d, the first module 110e, the second module 110f, and the third module 110g. In one exemplary aspect, the input interface 110c receives the data from various devices such as the user device 105-1, 105-2,…105-N and the servers 115-1, 115-2,…115-N via the communication network 120. The output interface 110d sends the output data to the user device 105-1, 105-2,…105-N via the communication network 120. The memory 110 include volatile and non-volatile memory devices for storing information and instructions to be executed by the processor 110 and for storing temporary variables or other intermediate information during processing. The first module 110e, second module 110f and third module 110g may be a processor which is well known in the art. In one aspect, the first module 110e may include a first pretrained artificial intelligence (AI) model which could be used for determining the growth of crop; the second module 110f may include a second pretrained artificial intelligence (AI) model which could be used for determining a phenological stage in which the crop is; and the third module 110g may include a third pretrained artificial intelligence (AI) model which could be used for determining the land utilization data in the region of interest. In one aspect, the modules may be within the memory. The modules may include a set of instructions that may be executed to perform the required process by the processor 110. The processor 110a receives various data, analyzes the received data and outputs the analyzed data. In one aspect, the second pretrained artificial intelligence AI model may include an machine learning model which could use the time-series optical and radar satellite image using a combination of multiple indices using image processing which is well known in the art.

[0040] Figure 2A shows an exemplary framework for forecasting and estimating pest and disease vulnerability index for a crop in accordance with an embodiment of the present disclosure. The way the forecast server 110 forecasts and estimates the pest and disease vulnerability index for a crop is described, with reference to both Figure 1 and Figure 2A.

[0041] The incidence of pests and diseases in crops is most likely to occur prior to harvest and it is generally caused by the complex interactions of the host (G) with the environment (E), that is, weather – precipitation/hail, temperature, humidity, etc., and management factors (M). Management factors include date of sowing, sowing density, crop rotation, sowing area, etc. Figure 3 shows the interaction of the pathogen with the host and the environment. In one embodiment of the present disclosure, the forecast server 110 models the host, environmental and management factors, and their interactions (G x E x M) to assess the potential pest and disease risk and to provide an estimate of vulnerability. It is a known fact that the light reflected from the canopy and leaves of the infected plants show distinct spectral, spatial, and temporal characteristics, which may be related to phenological parameters (for example, stem elongation, booting, flowering, etc.) characteristics or decline in different crop morphological parameters (for example, leaf area index), biochemical parameters (for example, plant chlorophyll content), and physiological parameters (for example, plant water content). These symptoms are manifested in the crop growth characteristics and are evident much earlier in the satellite images, even before the infestation is visible to the human eye. In one embodiment of the present disclosure, the system 100 uses satellite-based remote sensing images and the weather information for early prediction of pest or disease occurrence in a plot as shown in Figure 1B.

[0042] Referring to Figure 1 and Figure 2A, initially the farmer registers with the system 100 using the user device 105 for receiving forecast data. While registering, the farmer inputs the geocoordinates of the plot and this may be done using a geotagging option provided in the application. In addition, the farmer may input other details including, but not limited to, crop data, soil data, etc. On receiving the geocoordinates data from a plurality of farmers, the forecast server 110 identifies which geographical grid the geocoordinate belongs to and groups the farmers based on the grids. The information related to each of the registered farmers is stored in a farmer database. Figure 2B shows grid identification in accordance with an embodiment of the present disclosure. As shown, based on the plot of interest (based on geocoordinates), the forecast server 110 identifies the one or more geographical grids and considered for forecasting and estimating pest and disease vulnerability index for the crop.

[0043] In one embodiment of the present disclosure, to forecast and estimate the pest and the disease vulnerability index for the crop, the forecast server 110 collects and aggregates optical satellite images or radar satellite images, or both optical and radar satellite images at the spatial and temporal resolution as shown in Figure 1B. For example, for a given plot A growing Paddy, the forecast server 110 collects and aggregates a plurality of satellite images at the spatial and temporal resolution. It is to be noted that the spatial and temporal resolution may vary with the satellite being used. For example, for the LANDSAT 8, the panchromatic channel is at 15m resolution while the other spectral channels (except the thermal infrared bands ~100m) are at 30m resolutions. LANDSAT 8 has a global revisit rate of 16 days (temporal resolution). Sentinel-2 has variable spatial resolution starting from 10m to 60m for coastal aerosol, water vapor and SWIR-Cirrus, and Sentinel-2 multispectral data has temporal resolution of about 4-5 days revisit rate.

[0044] Further, the forecast server 110 collects and aggregates hyper-local periodic historical weather data and forecast weather (for example values of humidity, precipitation, maximum temperature, minimum temperature wind speed, wind direction), historical and current field data, plant genetics information, and historical disease data from the one or more servers 115 as shown in Figure 1B. The plant genetics information as described herein refers to the parent variety details with information on variety level vulnerabilities to the diseases. In addition, the forecast server 110 collects the ground data from the region around that plot of interest, if any. The ground data as described herein may include but not limited to soil health, soil organic carbon, soil type, soil moisture conditions, nitrogen content, pH, photos of the affected plant, and field-level scales of disease infestation (like the Davis scale mentioned in references). Scale 9 being very severely affected and Scale 1 being healthy crop.

[0045] It is to be noted that the disease or pest outbreak data may be sourced from the government or publicly released data, citizen communication, or may be gathered through social media platforms, newspapers, media, or declared by farmers through networks and co-operatives. Such outbreak data is used to forecast the infestation and the likelihood of infestation based on the above covariates, that is, based on the historical and forecast weather data, historical and current field data, plant genetics, and prior disease outbreak data as shown in Figure 1B. That is, in one implementation, past disease or pest outbreak data, the weather data and a plurality of satellite images are used for forecasting and estimating the pest and the disease vulnerability index for the crop. The way in which the forecast server 110 forecasts and estimates the pest and the disease vulnerability index for the crop is described in detail further below.

[0046] For forecasting and estimating the pest and the disease vulnerability index, the forecast server 110 collects the optical satellite images or the radar satellite images, or both the optical and the radar satellite images at the spatial and temporal resolution from the one or more satellites as shown in Figure 1B. Then, the forecast server 110 processes both the optical and radar satellite data to remove any noise and artifacts and to identify the land use in past temporal samples. The land use type can be inferred using a machine learning model based on pre-trained convolutional neural network-based patch classifier or a pixel-based classifier based on one of the classes from the following set of classes, but not limited to, urban area, water body, trees, snow, flooded vegetation, bare ground, clouds, grasslands, forest, shrubs, agriculture crops. In one aspect, the third pretrained AI model may include the machine learning model.

[0047] Then the forecast server 110 identifies the crop species (host) in the plot. In one embodiment of the present disclosure, the farmer may input the crop species data through the user device 105. For example, the farmer may indicate the crop species grown (Paddy, wheat, etc.) and the areas in the plot. In another embodiment of the present disclosure, the forecast server 110 is configured for inferring the crop species based on machine learning model that looks at the time-series pattern of both the optical and radar satellite data. In addition, the forecast server 110 further identifies the stages of the crop, the stages defining the growth stage of the crop. In one aspect, the first pretrained AI model may include the machine learning model.

[0048] Then the forecast server 110 determines the rate and risk of spread of the disease based on the disease or pest outbreak data, the crop species, the current state of the crop, the health of the crop, the soil condition, soil moisture, the nutrient uptake, the historical, current, and forecast weather information, and others. The likelihood of occurrence increases if the neighbouring areas are also affected, and what is neighbouring is as per predetermined criteria. For example, disease outbreak data (fungus growth), the plant growth stage (for example, grape plant), and historical weather data may indicate that the fungus growth risk is higher than a predetermined percentage if the moisture level in the air is higher than a predetermined level and when the plant is at the flower cluster initiation. Based on such historical data and correlation, the optical and the radar satellite images, and the present and forecast weather data, the forecast server 110 determines a rate and risk of disease growth (for example, growth of fungus).

[0049] In one embodiment of the present disclosure, the forecast server 110 is also configured for determining a vulnerability index of a crop to a disease. The vulnerability index is determined by weighting and aggregating the weighted values of a plurality of causal parameters, the causal parameters including, but not limited to, crop, crop stage, present crop health, soil health, soil moisture, nutrient deficiencies and nutrient uptake, a prior percentage of cover crop in the field, the risk of vector spread from the nearby region(s), and historical disease data. Some example plant insect vectors include but not limited to aphids, thrips, leafhoppers, planthoppers and whiteflies. In one aspect, an analytical engine is provided which will be run by aggregating all the data, combined with prior risk for the particular infestation and a vulnerability risk index will be provided for different plots and villages. All the data is renormalized prior to the running of the analytical engine. In another aspect, a rule-engine is provided to define the rules based on the plurality of parameters defined above and calculate the vulnerability index by weighting all the parameters. On determining the vulnerability index, the forecast server 110 notifies the farmer through the user device 105 and provides further actionable information to the farmers or the decision-makers to prevent or mitigate adversity from infestation.

[0050] Figure 4 is a flowchart illustrating the method of forecasting and estimating pest and disease vulnerability index for a crop in accordance with an embodiment of the present disclosure. Initially, at step 405, the farmer registers with the system 100 by providing necessary details as described and geotags the plot with the forecast server 110.

[0051] At step 410, the forecast server 110 identifies which geographical grid the geocoordinate belongs to and groups the farmers based on the grids and further downloads the optical and radar satellite image tiles of the plot.

[0052] At step 415, the forecast server 110 process the image tiles and infers the cropland class and the crop grown using trained machine learning model. In one aspect, the first pretrained AI model may include the trained machine learning model. As described, the forecast server 110 may use the input provided by the farmer, the input including but not limited to crop species grown (Paddy, wheat, etc.) and the areas in the plot.

[0053] At step 420, the forecast server 110 overlays the inferred or input data with the satellite, weather, and ground data received from historical, current, and forecast weather database, and the historical and current infestation database. This is done to determine the rate and risk of spread of the disease based on the disease or pest outbreak data, the crop species, the current state of the crop, the health of the crop, the soil condition, soil moisture, the nutrient uptake, the historical, current, and forecast weather information, and others.

[0054] In one embodiment of the present disclosure, as shown at step 425, the forecast server 110 determines the causal parameters to the past infestation and uses such data to determine a vulnerability index of a crop to a disease.

[0055] At step 430, the forecast server 110 models the risk by weighing the prior risk of infestation with the likelihood of infestation based on the causal covariates. In other words, the forecast server 110 determines the vulnerability index by weighting and aggregating the weighted values of a plurality of causal parameters, the causal parameters including, but not limited to, crop, crop stage, present crop health, soil health, soil moisture, nutrient deficiencies and nutrient uptake, a prior percentage of cover crop in the field, the risk of vector spread from the nearby region(s), and historical disease data. On determining the vulnerability index, the forecast server 110 notifies the farmer through the user device 105 and provides further actionable information to the farmers or the decision-makers to prevent or mitigate adversity from infestation.

[0056] As described, the system and method disclosed in the present disclosure estimates and provides a risk of spread of the disease based on the disease or pest outbreak data, the crop species, a current state (or stage) of the crop, current health of the crop, the soil condition, soil moisture, nutrient uptake, historical, current, and forecast weather information, and others. Further, the disclosed system forecasts and estimates pest and disease vulnerability index and provides actionable information to the farmers or the decision-makers to or mitigate adversity from infestation. It is to be noted that there is a strong correlation between the crop phenological stage (germination, the development of leaves, a stem elongation stage, in some plants such as cereal-a tillering stage, through to a flowering and fruiting stage prior to senescence and death) and the pest and disease progress is closely correlated with the plant phenological stages.

[0057] Below is an exemplary list of crops that can be monitored and diseases that can be predicted using the system disclosed in the present disclosure.
Agricultural Crops
Cereals Paddy Bacterial Blight, Blast, False Smut, Sheath Blight, Red stripe, Stem Rot, Smut
Wheat Leaf Rust, Stem Rust, Stripe Rust, Powdery Mildew, Scab, Sclerotium Wilt, Bacterial Leaf Blight
Sorghum Anthracnose, Leaf spot, Rust
Maize Head Smut, Leaf Blight, Bacterial Leaf Spot, Alternaria Leaf spot, Rust, Leaf Rust, Anthracnose
Cumbu Anthracnose, Rust, Leaf Blight, Cercospora Leaf Spot, Bacterial Leaf Spot, Mosaic
Ragi/millets Blast, Leaf Blight, Wilt, Smut, Mosaic, Bacterial Leaf Spot

Pulses All Grams Stem Blight, Root rot, Powdery Mildew, Rust, Leaf Spot, Anthracnose
Cowpea Bacterial Blight, Powdery Mildew, Rust
Chickpea Fusarium Wilt, Root rot, Rust

Oil seeds and Cash crops Sunflower Alternaria Blight and Leaf Spot, Rust, Sclerotium Wilt
Sugarcane Yellow Leaf Disease, Ratoon Stunting, Grassy Shoot disease, Wilt, Smut
Cotton Fusarium Wilt, Root rot, Cercospora Leaf spot, Bacterial Blight
Groundnut Stem rot, Leaf spot, Alternaria leaf spot and Leaf blight, Rust
Castor Root rot, Cercospora Leaf spot, Bacterial Blight
Rapeseed and Mustard Alternaria leaf spot, Powdery Mildew, and Sclerotinia rot
Sesame Bacterial Blight, Bacterial Leaf Spot, Cercospora Leaf spot, Alternaria Leaf Spot, Powdery Mildew, Stem Rot, and Root rot
Horticultural Crops
Fruits Citrus Scab, Canker
Mango Anthracnose, Powdery mildew, Stem end rot, Red rust
Papaya Powdery mildew, Stem rot, Anthracnose, Leaf Curl
Banana Yellow Sigatoka, Anthracnose
Sapota/chiku Cercospora Leaf Spot, Leaf Spot, Fruit Rot
Grapes Powdery mildew, Anthracnose
Apple Scab, Powdery mildew, Bitter rot

Vegetables Onion Leaf Blight, Smut
Tomato Damping-off, Fusarium Wilt, Septoria Leaf Spot, Bacterial wilt, Bacterial Leaf Spot, Leaf curl
Beans Leaf curl, Root Rots, Rust, Bacterial Blight, Powdery Mildew, Cercospora Leaf Spot
Brinjal Bacterial Wilt, Cercospora Leaf Spot, Alternaria leaf Spot, Damping off, Fruit rot
Bhendi/ Okra/ ladies finger Cercospora Leaf Spot, Fusarium wilt, Powdery mildew, Canker
Carrot Bacterial blight, Cercospora leaf spot, Sclerotinia Rot, Rust
Potato Early blight, Late Blight, Black scurf, Scab
Beetroot Leaf Spot, Curly top virus
Chilli Damping-off, Bacterial leaf spot, Cercospora leaf spot, Fusarium wilt, Leaf curl
Gourds Powdery mildew
Cabbage Root rot, Powdery mildew
Cucumber Scab

Plantations Coffee Bacterial Blight, Coffee Berry Disease, Coffee Leaf Rust
Tea Blister blight, Bacterial Leaf Spot, Root Rot, Canker
Coconut Leaf Blight, Bud rot, Wilt
Palm Anthracnose

[0058] Figure 5 illustrates the coffee berry disease, blister blight and coffee leaf rust identified using our system and method in accordance with various embodiments of the present disclosure. The below table explains the conditions of occurring the coffee berry disease and coffee leaf rust in the crop.

Coffee Leaf Rust
Coffee Berry Disease

Spores germinate only in the
? presence of free water (rain or heavy dew);
? high humidity is favorable
? Heavy rainfall & High temperature has a negative impact
? Mild rainfall is an influential parameter
Sporulation occurs mainly with,
? high humidity conditions and the spread, responsible for new infections,
? Exclusively dependent on rain
? Moderate Day Temperature around 24 deg C are favorable for the development of the infection

[0059] Figure 6 illustrates the blister blight for coffee vulnerability index estimates in accordance with an embodiment of the present disclosure.

[0060] Below are the possible advantages of using the system disclosed in the present disclosure.
? Reducing the cost involved in agricultural inputs (both biologicals and chemical) and hence an increase in profitability.
? Reducing the amount of damage and helps to reduce the spread to neighbouring villages, towns, districts, and states.
? Increasing crop yield and addresses a major concern on food security.
? Weekly or fortnightly forecasts provide actionable information to the farmers or the decision-makers to prevent from the adversity of infestation.

[0061] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.

[0062] The figures and the foregoing description give exemplary embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible.

Reference Numbers:
System – 100
User device -105-1, 105-2,…105-N
Forecast server-110
Processor - 110a
Memory - 110
Input interface - 110c
Output interface - 110d
First module - 110e
Second module - 110f
Third module - 110g
Server - 115-1, 115-2,…115-N
Communication network – 120 ,CLAIMS:WE CLAIM:

1. A computer implemented method for determining a pest and disease vulnerability index for a crop, the method comprising:
receiving an input from a user, the input comprising at least farm data, the farm data including at least geocoordinates of the farm;
obtaining remote sensing data of one or more regions of interest from one or more satellites, wherein the remote sensing data includes one or more of optical satellite images and radar satellite images;
obtaining weather data, historical farm data, ground data, crop genetic data, historical and present disease and pest outbreak data of the farm and the one or more regions of interest from one or more servers (115-1, 115-2, …115-N);
determining crop grown using the remote sensing data and a first pretrained artificial intelligence model;
determining a phenological stage in which the crop is, using the remote sensing data, one or more derived features from the remote sensing data and a second pretrained artificial intelligence model;
determining land utilization data in the region of interest using the remote sensing data and a third pretrained artificial intelligence model; and
determining a pest and disease vulnerability index for the crop based on the crop stage, the weather data, the historical farm data, the ground data, the crop genetic data, the land utilization data and the historical and present disease and pest outbreak data.

2. The method as claimed in claim 1, wherein the remote sensing data is obtained at spatial, spectral, and temporal resolutions.

3. The method as claimed in claim 1, wherein the region of interest is determined based on the geocoordinates of the farm.

4. The method as claimed in claim 1, wherein the crop stage is determined using the one or more features derived from the remote sensing data and the second pretrained AI model.
5. The method as claimed in claim 1, wherein the weather data is retrieved for the region of interest from historical, current, and forecasts for the region of interest from one or more of weather station and meteorological database.

6. The method as claimed in claim 1, wherein the ground data comprises soil health, soil organic carbon, soil type, soil moisture conditions, nitrogen content, pH, photographs of the affected plant, and field-level scales of disease infestation in the region of interest.

7. A system (100) for determining a pest and disease vulnerability index for a crop, the system comprising:
at least one user device (105-1, 105-2,…105-N) communicatively coupled to at least one forecast server (110) via a communication network (120) for providing an input to the at least one forecast server (110), the input comprising at least farm data, the farm data including at least geocoordinates of the farm;
at least one server (115-1, 115-2,…115-N) communicatively coupled to the at least one forecast server (110) via the communication network (120) for providing weather data, historical farm data, ground data, crop genetic data, historical and present disease and pest outbreak data of the farm and the one or more regions of interest,
wherein the forecast server (110) is configured for:
receiving the input comprising at least farm data, the farm data including at least geocoordinates of the farm;
obtaining remote sensing data of one or more regions of interest from one or more satellites via the communication network (120), wherein the remote sensing data includes one or more of optical satellite images and radar satellite images;
obtaining weather data, historical farm data, ground data, crop genetic data, historical and present disease and pest outbreak data of the farm and the one or more regions of interest from one or more servers (115-1, 115-2,…115-N);
determining crop grown using the remote sensing data and a first pretrained artificial intelligence model;
determining a phenological stage in which the crop is using the remote sensing data, one or more derived features from the remote sensing data and a second pretrained artificial intelligence model;
determining land utilization data in the region of interest using the remote sensing data and a third pretrained artificial intelligence model; and
determining a pest and disease vulnerability index for the crop based on the crop stage, the weather data, the historical farm data, the ground data, the crop genetic data, the land utilization data and the historical and present disease and pest outbreak data.