Cognitive based decision support system for agriculture

Patent metadata

Field	Value
Publication number	US-11257172-B2
Application number	US-201715497560-A
Country	US
Kind code	B2
Filing date	Apr 26, 2017
Priority date	Apr 26, 2017
Publication date	Feb 22, 2022
Grant date	Feb 22, 2022

Abstract

A method, computer program product, and system includes a processor(s) obtaining real time data related to an agricultural site by continuously monitoring remote data collection entities at the agricultural site, which include satellites, ground monitoring stations, and sensors. The processor(s) determine which data of the real time data can be utilized in subsequent decisions and accumulate a portion of the real time data in a data store, based on a timestamp of the portion indicating that the portion of the real time data is no longer current and is historical data. Based on obtaining a request for a recommendation, the processor(s) generate based on a cognitive analysis of the historical data, the real time data that can be utilized, and the agricultural data from the controlled environment, at least one agricultural model. The processor(s) determine the recommendation from the model and transmit the recommendation to the client.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
obtaining, by one or more processors, real time data related to a given agricultural site by continuously monitoring remote data collection entities at the given agricultural site, wherein the remote data collection entities comprise satellites, ground monitoring stations, and sensors at the given agricultural site, and base line data relevant to the given agricultural site comprising Normalized Difference Vegetation Index data;
determining, by the one or more processors, which data of the real time data can be utilized in subsequent agronomy decision-making;
accumulating, by the one or more processors, a portion of the real time data in a data store, based on a timestamp of the portion of the real time data indicating that the portion of the real time data is no longer current and is historical data;
in response to receiving a request for an agronomical recommendation regarding the given agricultural site from a client, querying, by the one or more processors, at least one computing resource accessible over a communications network, for agricultural data from a controlled environment, via a technology selected from the group consisting of a common gateway interface and a representational state transfer application programming interface, wherein the at least one computing resource comprises a phenotyping platform and the agricultural data comprises phenotypic data and a spectral signature of each crop grown in the controlled environment, and wherein the controlled environment comprises a laboratory;
generating, by the one or more processors, based on a cognitive analysis of the historical data, the real time data that can be utilized, the agricultural data from the controlled environment, and the base line data, at least one agricultural model, wherein the cognitive analysis comprises comparing, utilizing visual insights from at least one at least one visual recognition application programming interface, the real time data that can be utilized and the agricultural data from the controlled environment for each stage of growth for a given crop in the controlled environment and at the given agricultural site, wherein the comparing comprises comparing aspects selected from the group consisting of: crop status and crop spectral signature;
determining, by the one or more processors, based on the agricultural model, the agronomical recommendation regarding the given agricultural site;
transmitting, by the one or more processors, the agronomical recommendation to the client; and
tuning, by the one or more processors, one or more algorithms utilized in the cognitive analysis to increase accuracy of the cognitive analysis, based on applying training data generated by continuously comparing the historical data, the real time data, and the agricultural data from the controlled environment.

2. The computer-implemented method of claim 1 , wherein the agricultural model is selected from the group consisting of: a crop map, a crop growth model, a productivity map, and a weed map.

3. The computer-implemented method of claim 1 , wherein the remote data collection entities are selected from the group consisting of: one or more geographic information systems, one or more global positioning system, and one or more sensor in at least one Internet of Things device.

4. The computer-implemented method of claim 1 , wherein the generating the at least one agricultural model comprises applying a prescription map formula to generate a prescription maps for one or more of: soil type requirements, weeds regions requirements, fertilizer required region requirements, or water irrigation requirements.

5. The computer-implemented method of claim 1 , wherein the at least one agricultural model a prescription map and an exploratory agronomy model, wherein the generating the at least one agricultural model comprises:
for each one of the prescription map and the exploratory agronomy model, applying, by the one or more processors, a cognitive application programming interface to the historical data, the real time data that can be utilized, and the agricultural data.

6. The computer-implemented method of claim 5 , further comprising:
generating, by the one or more processors, from the prescription map and the exploratory agronomy model, cognitive linking templates; and
storing, by the one or more processors, the cognitive linking templates in the data store as historical data.

7. The computer-implemented method of claim 6 , wherein the at least one computing resource accessible over the communications network comprises the data store and the agricultural data from the controlled environment comprises the cognitive linking templates.

8. The computer-implemented method of claim 5 , wherein the exploratory agronomy model is specific to a given crop.

9. The computer-implemented method of claim 8 , wherein the agricultural data comprises forward looking data, and wherein the generating from the historical data, the real time data that can be utilized, and the agricultural data from the controlled environment, at least one agricultural model further comprises:
analyzing, by the one or more processors, one or more of the historical or the forward looking data to determine profitability of the given crop, wherein the exploratory agronomy model provides guidance for maximizing profitability of the given cop.

10. The computer-implemented method of claim 9 , wherein the agronomical recommendation regarding the given agricultural site comprises guidance to maximize yield and profitability of the given crop.

11. The computer-implemented method of claim 1 , wherein the generating from the historical data, the real time data that can be utilized, and the agricultural data from the controlled environment, at least one agricultural model, comprises:
deriving, by the one or more processors, relationships between the real time data that can be utilized, and the historical data; and
analyzing, by the one or more processors, phenotype data model maps in the phenotypic data retrieved from the phenotyping platform.

12. The computer-implemented method of claim 11 , wherein the agronomical recommendation comprises an instruction to adjust a planting mix based on historic yields and predicted weather patterns.

13. The computer-implemented method of claim 1 , further comprising:
utilizing, by the one or more processors, the visual recognition application programming interfaces to identify parameters from the group consisting of: sunlight intensity, water quality, carbon dioxide proportion in air, nutrients, air humidity, temperature, drought symptoms, and salinity.

14. The computer-implemented method of claim 1 , wherein the base line data further comprises data selected from a group consisting of: productivity maps, earlier analysis report, and yield maps.

15. A computer program product comprising:
a computer readable storage medium readable by one or more processors and storing instructions for execution by the one or more processors for performing a method comprising:
obtaining, by the one or more processors, real time data related to a given agricultural site by continuously monitoring remote data collection entities at the given agricultural site, wherein the remote data collection entities comprise satellites, ground monitoring stations, and sensors at the given agricultural site, and base line data relevant to the given agricultural site comprising Normalized Difference Vegetation Index data;
determining, by the one or more processors, which data of the real time data can be utilized in subsequent agron

Assignees

• IBM

Inventors

• Bender Michael
• Bhat Gautam K
• Childress Rhonda L
• Muthurajan Nalini

Classifications

• G06Q50/02 Primary

  Agriculture; Fishing; Forestry; Mining · CPC title

• A01B79/005

  Precision agriculture · CPC title

• G06N5/045

  Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence · CPC title

• G16Y10/05

  Agriculture · CPC title