Systems and methods for estimating effective pest severity index

Patent metadata

Field	Value
Publication number	US-10555461-B2
Application number	US-201615066891-A
Country	US
Kind code	B2
Filing date	Mar 10, 2016
Priority date	Jan 4, 2016
Publication date	Feb 11, 2020
Grant date	Feb 11, 2020

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.

First claim

What is claimed is:

1. A computer implemented method for estimating effective pest severity index, the method comprising:
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 associated with the geo-location under consideration;
generating a pest forecasting model and a natural enemies forecasting model for each pest associated with the geo-location under consideration, the pest forecasting model and the natural enemies forecasting model being based on the received first set of inputs and the second set of inputs, wherein the pest forecasting model is generated based on weather parameters derived from the first set of inputs, vegetation, soil and water indices derived from the second set of inputs, season of a year and a geographical region and wherein the natural enemies forecasting model is generated based on the pest forecasting model, the weather parameters derived from the first set of inputs, the vegetation, soil and water indices derived from the second set of inputs, the season of the year and the geographical region;
receiving participatory sensing information and crowdsourcing information associated with each pest and natural enemies in the geo-location under consideration for a period of time, wherein the participatory sensing information and crowdsourcing information comprise events from the geo-location under consideration during a life cycle of pests and natural enemies and images with geo-coordinates of pest affected areas;
dynamically updating the pest forecasting model and the natural enemies forecasting model based on the participatory sensing information and crowdsourcing information; wherein the pest forecasting model and the natural enemies forecasting model are dynamically updated based on a historical data lookup table of actual effective pest severity index detected for the corresponding first set of inputs and the second set of inputs for a given period of time; and
estimating the effective pest severity index based on the dynamically updated pest forecasting model and the natural enemies forecasting model, whereby a quantity and a timing of a pesticide application is recommended based on the estimated effective pest severity index, when the estimated effective pest severity index is greater than an Economic Threshold Level and the effective pest severity index is estimated as:
EP( n )= P ( n )−αNE( n ),

wherein, EP(n) is Effective pest severity on n th day, P(n) is Pest severity forecasted for n th day, NE(n) is Population of Natural Enemies forecasted for n th day and a is scaling factor dependent on the season and a stage of pest as well as natural enemy.

2. The computer implemented method of claim 1 further comprising:
creating the historical data lookup table based on the received first set of inputs and the second set of inputs and the estimated effective pest severity index;
appending the historical data lookup table with the actual effective pest severity index; and
updating the pest forecasting model and the natural enemies forecasting model based on the actual effective pest severity index.

3. The computer implemented method of claim 2 , wherein updating the pest forecasting model and the natural enemies forecasting model is further based on management practices deployed in the geo-location under consideration.

4. The computer implemented method of claim 1 , further comprising optimizing pesticide application based on the estimated effective pest severity index.

5. A system for estimating effective pest severity index, the system comprising:
one or more internal data storage devices comprising instructions; and one or more processors operatively coupled to the one or more internal data storage devices, the one or more processors being configured by the instructions to:
receive a first set of inputs pertaining to weather associated with a geo-location under consideration;
receive a second set of inputs pertaining to agronomic information associated with the geo-location under consideration;
generate a pest forecasting model and a natural enemies forecasting model for each pest associated with the geo-location under consideration, the pest forecasting model and the natural enemies forecasting model being based on the received first set of inputs and the second set of inputs, wherein the pest forecasting model is generated based on weather parameters derived from the first set of inputs, vegetation, soil and water indices derived from the second set of inputs, season of a year and a geographical region and wherein the natural enemies forecasting model is generated based on the pest forecasting model, the weather parameters derived from the first set of inputs, the vegetation, soil and water indices derived from the second set of inputs, the season of the year and the geographical region;
receive participatory sensing information and crowdsourcing information associated with each pest and natural enemies in the geo-location under consideration for a period of time, wherein the participatory sensing information and crowdsourcing information comprise events from the geo-location under consideration during a life cycle of pests and natural enemies and images with geo-coordinates of pest affected areas;
dynamically update the pest forecasting model and the natural enemies forecasting model based on the participatory sensing information and crowdsourcing information; wherein the pest forecasting model and the natural enemies forecasting model are dynamically updated based on a historical data lookup table of actual effective pest severity index detected for the corresponding first set of inputs and the second set of inputs for a given period of time; and

estimate the effective pest severity index based on the dynamically updated pest forecasting model and the natural enemies forecasting model, whereby a quantity and a timing of a pesticide application is recommended based on the estimated effective pest severity index, when the estimated effective pest severity index is greater than an Economic Threshold Level and the effective pest severity index is estimated as:
EP( n )= P ( n )−αNE( n ),

wherein, EP(n) is Effective pest severity on n th day, P(n) is Pest severity forecasted for n th day, NE(n) is Population of Natural Enemies forecasted for n th day and a is scaling factor dependent on the season and a stage of pest as well as natural enemy.

6. The system of claim 5 , wherein the one or more processors are further configured to:
create the historical data lookup table based on the received first set of inputs and the second set of inputs and the estimated effective pest severity index;
append the historical data lookup table with the actual effective pest severity index; and
update the pest forecasting model and the natural enemies forecasting model based on the actual effective pest severity index.

7. The system of claim 6 , wherein the one or more processors are further configured to update the pest forecasting model and the natural enemies forecasting model based on management practices deployed in the geo-location under consideration.

8. The system of claim 5 , wherein the one or more processors are further configured to optimize pesticide application based on the estimated effective pest severity index.

9. A computer program product comprising a non-transitory computer readable medium having a computer readable program embodied therein, wherein the computer readable program, when executed on a computing device, causes the computing device to:
receive a first set of inputs pertaining to weather associated with a geo-location under consideration;
receiv

Assignees

• Tata Consultancy Services Ltd

Inventors

• Jagyasi Bhushan Gurmukhdas
• Mohite Jayantrao
• Pappula Srinivasu

Classifications

• A01C14/00

  Methods or apparatus for planting not provided for in other groups of this subclass · CPC title

• G06Q50/02 Primary

  Agriculture; Fishing; Forestry; Mining · CPC title

• A01M99/00

  Subject matter not provided for in other groups of this subclass · CPC title

• G06Q10/067

  Enterprise or organisation modelling · CPC title

• A01M17/00

  Apparatus for the destruction of vermin in soil or in foodstuffs {(injecting fertilisers into the roots of trees A01G29/00)} · CPC title