Abstract: The disclosure herein relates to identification of agro-phenological zones. Further the disclosed method and system also shares techniques for updating of the identified/existing agro-phenological zones. In a diverse geographical domain (like India), in order to maximize the crop production (avoid crop failures) from the available resources and prevailing diverse climatic conditions it necessary to use the resources and technology to infer the best agriculture approach on an individual location. The invention enables identification of the agro-phenological zones based on satellite image, weather data, soil data and cloud free historical satellite data using several techniques that includes machine learning, time series analysis, heuristic time series analysis technique and clustering. Further the invention also discloses techniques to update the identified/existing agro-phenological zones using historic data of agro-phenological zones of satellite image.

Abstract: This disclosure relates generally to root zone moisture estimation for vegetation cover using remote sensing. Conventionally, it is challenging to estimate root zone soil moisture using only satellite data. Moreover, estimation of soil moisture under vegetation cover based on bare surface soil moisture and vegetation parameters is not available. The disclosed method and system facilitate estimation of an ensemble of soil moisture under vegetation cover and root zone soil moisture using process based soil water balance for spatial estimation of root zone soil moisture. The system estimates bare surface soil moisture for different soil types/textures using the baseline bare surface model and soil properties derived from satellite data and in-situ sensors. The method further provides temporal spatially distributed soil moisture inputs to an intelligent irrigation management/information system which is very important to reduce and regulate water consumption.

Abstract: A method and system that allows on-the-fly synthesis and evaluation of services a scale has been provided. The method and system provide a mechanism where the service offering and their price points are accessible in a machine format and allow themselves to be lent to synthesize new service offerings with budgetary constraints, within the parameters of the predefined time windows. The system allows both a service provider and a service consumer to use a shared screen environment for service synthesis and valuation with the service provider playing the role of navigator. The system comprises of re-routing and navigating a plurality of nodes in the service composition graphs based on specified optimization parameters as chosen by the service consumer and tuned by the service provider. The method comprises of generation of the graph and graph traversal algorithms for along with service composition nodes and their specifications.

Abstract: A system and method for achieving auto-adaptive clustering in a sensor network has been explained. The system performs a hierarchical clustering in sensor networks to maximize the lifetime of the network. The system includes a set of sensor nodes and a sink node. The clusters in sensor networks are formed automatically from a large number of deployed nodes where the cluster characteristics are driven by the measurement requirements defined by the end-user. The system also employs a clustering algorithm to achieve adaptive clustering. The processor further includes a first level clustering module for grouping the set of sensor nodes into data level clusters based on the measurements. The processor further includes a second level clustering module for grouping the set of sensor nodes in the data level clusters into the location level clusters based on location. In another embodiment, that clustering can go on to more than two levels.

Abstract: Machine Learning models to be created for crop mapping for any region, require huge volumes of ground truth data requiring manual effort in generating region specific training dataset. Method and system for providing generalized approach for crop mapping across regions with varying characteristics is disclosed. The method provides automatic generation of a labelled pixel dataset representing cropping pattern of a Region of Interest (ROI) for building a ML crop mapping model for the ROI. The generated labelled pixel dataset captures regional dependency and localized phenological indicators for the ROI. ML crop mapping model is updated using a database, regularly updated for the set of crops and the plurality of features associated with each of the set of crops and corresponding the set of crops.

Abstract: Traditionally, forecasting models were developed using pest or disease instances collected through pest or disease surveillance. The present disclosure relates to pest forecasting using historical pesticide usage information thereby obviating need for voluminous and time consuming effort of collecting site specific data. Firstly forecasting models for different pests or diseases of different crops are generated based on historical data on pesticide usage and historical weather data collected for a geo-location under consideration. The model is validated and adapted with the current scenario of pests. Current scenario is captured using image samples sent from the field or farm through participatory sensing platform. The images are then analyzed to extract information like actual pest infestation in the field, severity, if there was infestation and the like. This analyses helps to derive the actual pest infestation instances in the field.

Abstract: Stubble burning is a serious problem resulting in pollution attributable to smog, loss of nutrients in the top soil, and risk of fires spreading out of control. Existing methodologies have attempted to predict burning areas, but have failed to do so because of inefficient sensing mechanism. Present disclosure proposes a system and method to compute burning index score pertaining to crops by detecting harvest season and predicting probable areas of burning by combining current year's crop area map along with harvesting period and historical hot spot information. Computation of the burning index score is accomplished based on inputs received from at least one of satellite imaging, multi-spectral drone based sensing devices and crowdsourcing information. This will help to prioritize the area for taking corrective measures such as training of farmers, availability of resources, optimizing the resources schedule, etc.

Abstract: This disclosure relates generally to estimating age of a leaf using morphological features extracted from segmented leaves. Traditionally, leaf age estimation requires a single leaf to be plucked from the plant and its image to be captured in a controlled environment. The method and system of the present disclosure obviates these needs and enables obtaining one or more full leaves from images captured in an uncontrolled environment. The method comprises segmenting the image to identify veins of the leaves that further enable obtaining the full leaves. The obtained leaves further enable identifying an associated plant species. The method also discloses some morphological features which are fed to a pre-trained multivariable linear regression model to estimate age of every leaf. The estimated leaf age finds application in estimation of multiple plant characteristics like photosynthetic rate, transpiration, nitrogen content and health of the plants.

Abstract: Existing techniques in precision farming comprise supervised event detection and need labeled training data which is tedious considering the large number of crops, differences therein and even larger number of diseases and pests. The present disclosure provides an unsupervised method and uses images of any size captured in an uncontrolled environment. The methods and systems disclosed find application in automatically localizing and classifying events, including health state and growth stage and also estimating an extent of manifestation of the event. Information of spatial continuity in pixels and boundaries in a given image is used to update the feature representation and label assignment to every pixel using a fully convolutional network. Back propagation of the pixel labels modified according to the output of a graph based method helps the neural network to converge and provide a time efficient solution.

Abstract: The present disclosure provides methods and systems for automated identification of agro-climatic zones. The methods deal with receiving parameters pertaining to ambience and soil from various external systems for a geographical region via one or more interaction methods. The parameters may be raw data or derived from raw data, homogenized and stored in a generic and hierarchical format for easy consumption. Inference is drawn from the parameters and associated attributes by comparing with historic attributes available in a knowledge base module for a corresponding agro-climatic zone. Inferences may also be made from parameters available in encoded form such as images, videos and ontological knowledge. Based on the comparison, a score is generated that reflects the degree of compliance with pre-defined agro-climatic zones.

Abstract: State of the art viewport design approach faces challenge in addressing customization of view port design. A method and device for dynamic view port generation providing enhanced viewport usability of text messages to be displayed on screen by considering type of user and customized typeface is provided. Determining of a customized typeface is based on user's reading capability tested during initial type face set up by the device. The customization of typeface includes applying kerning spacing and glyphs adjustment to squeeze area of the displayed text, still maintaining less ambiguity during reading. For received messages to be displayed, maximum size of window for a viewport is obtained on-the-fly with a constraint of maximum or optimal number of viewports displayed at a time on device screen. NLP is applied to each message to condense text in the message such that maximum information is conveyed while displaying minimum words.

Abstract: State of the art viewport design approach faces challenge in addressing customization of view port design. A method and device for dynamic view port generation providing enhanced viewport usability of text messages to be displayed on screen by considering type of user and customized typeface is provided. Determining of a customized typeface is based on user's reading capability tested during initial type face set up by the device. The customization of typeface includes applying kerning spacing and glyphs adjustment to squeeze area of the displayed text, still maintaining less ambiguity during reading. For received messages to be displayed, maximum size of window for a viewport is obtained on-the-fly with a constraint of maximum or optimal number of viewports displayed at a time on device screen. NLP is applied to each message to condense text in the message such that maximum information is conveyed while displaying minimum words.

Abstract: This disclosure relates to precision agriculture that relies on monitoring micro-climatic conditions of a farm to make accurate disease forecasts for better crop protection and improve yield efficiency. Conventional systems face challenge in managing energy and bandwidth of transmission considering the humongous volume of data generated in a field through IoT based sensors. The present disclosure provides energy-efficient adaptive parameter sampling from the field by optimally configuring the parameter sampling rate thereby maximizing energy-efficiency. This helps reduce unnecessary traffic to a cloud while extending network lifetime.

Abstract: The present disclosure addresses the technical problem of enabling automated inferencing of changes in spatio-temporal images by leveraging the high level robust features extracted from a Convolutional Neural Network (CNN) trained on varied contexts instead of data dependent feature methods. Unsupervised clustering on the high level features eliminates the cumbersome requirement of labeling the images. Since models are not trained on any specific context, any image may be accepted. Real time inferencing is enabled by a certain combination of unsupervised clustering and supervised classification. A cloud-edge topology ensures real time inferencing even when connectivity is not available by ensuring updated classification models are deployed on the edge. Creating a knowledge ontology based on adaptive learning enables inferencing of an incoming image with varying levels of precision. Precision farming may be an application of the present disclosure.

Abstract: Presence of natural enemies has a considerable impact on pest severity in a given geo-location. However, manually estimating pest severity or population of natural enemies is cumbersome, inaccurate and not scalable. Systems and methods of the present disclosure enable estimating effective pest severity index by receiving a first set of inputs pertaining to weather associated with a geo-location under consideration; receiving a second set of inputs pertaining to agronomic information; generating a pest forecasting model and a natural enemies forecasting model based on the received first set and the second set of inputs for each pest; and estimating the effective pest severity index based on the generated models. The timing and quantity of pesticide application can be optimized based on the estimated pest severity index. The generated models can be further enhanced continually based on one or more of historical data, participatory sensing inputs, crowdsourcing inputs and management practices.

Abstract: This disclosure relates to precision agriculture that relies on monitoring micro-climatic conditions of a farm to make accurate disease forecasts for better crop protection and improve yield efficiency. Conventional systems face challenge in managing energy and bandwidth of transmission considering the humongous volume of data generated in a field through IoT based sensors. The present disclosure provides energy-efficient adaptive parameter sampling from the field by optimally configuring the parameter sampling rate thereby maximizing energy-efficiency. This helps reduce unnecessary traffic to a cloud while extending network lifetime.

Abstract: The present disclosure addresses the technical problem of enabling automated inferencing of changes in spatio-temporal images by leveraging the high level robust features extracted from a Convolutional Neural Network (CNN) trained on varied contexts instead of data dependent feature methods. Unsupervised clustering on the high level features eliminates the cumbersome requirement of labeling the images. Since models are not trained on any specific context, any image may be accepted. Real time inferencing is enabled by a certain combination of unsupervised clustering and supervised classification. A cloud-edge topology ensures real time inferencing even when connectivity is not available by ensuring updated classification models are deployed on the edge. Creating a knowledge ontology based on adaptive learning enables inferencing of an incoming image with varying levels of precision. Precision farming may be an application of the present disclosure.

Abstract: A system and method for achieving auto-adaptive clustering in a sensor network has been explained. The system performs a hierarchical clustering in sensor networks to maximize the lifetime of the network. The system includes a set of sensor nodes and a sink node. The clusters in sensor networks are formed automatically from a large number of deployed nodes where the cluster characteristics are driven by the measurement requirements defined by the end-user. The system also employs a clustering algorithm to achieve adaptive clustering. The processor further includes a first level clustering module for grouping the set of sensor nodes into data level clusters based on the measurements. The processor further includes a second level clustering module for grouping the set of sensor nodes in the data level clusters into the location level clusters based on location. In another embodiment, that clustering can go on to more than two levels.

Abstract: The present disclosure provides methods and systems for automated identification of agro-climatic zones. The methods deal with receiving parameters pertaining to ambience and soil from various external systems for a geographical region via one or more interaction methods. The parameters may be raw data or derived from raw data, homogenized and stored in a generic and hierarchical format for easy consumption. Inference is drawn from the parameters and associated attributes by comparing with historic attributes available in a knowledge base module for a corresponding agro-climatic zone. Inferences may also be made from parameters available in encoded form such as images, videos and ontological knowledge. Based on the comparison, a score is generated that reflects the degree of compliance with pre-defined agro-climatic zones.

Abstract: Traditionally, forecasting models were developed using pest or disease instances collected through pest or disease surveillance. The present disclosure relates to pest forecasting using historical pesticide usage information thereby obviating need for voluminous and time consuming effort of collecting site specific data. Firstly forecasting models for different pests or diseases of different crops are generated based on historical data on pesticide usage and historical weather data collected for a geo-location under consideration. The model is validated and adapted with the current scenario of pests. Current scenario is captured using image samples sent from the field or farm through participatory sensing platform. The images are then analyzed to extract information like actual pest infestation in the field, severity, if there was infestation and the like. This analyses helps to derive the actual pest infestation instances in the field.