Generating and improving upon agricultural maps

Patent metadata

Field	Value
Publication number	US-2022011119-A1
Application number	US-202016924279-A
Country	US
Kind code	A1
Filing date	Jul 9, 2020
Priority date	Jul 9, 2020
Publication date	Jan 13, 2022
Grant date	—

Abstract

The exemplary embodiments disclose a system and method, a computer program product, and a computer system for generating an agriculture map of a region of land. The exemplary embodiments may include collecting agricultural data of one or more sub-regions of the region of land, wherein the agricultural data includes classified data and unclassified data, extracting one or more features from the collected classified agricultural data, training one or more models based on the extracted one or more features, and generating an agricultural map of the region of land based on applying the one or more models to the collected unclassified agricultural data.

First claim

What is claimed is:

1 . A computer-implemented method for generating an agriculture map of a region of land, the method comprising:
collecting agricultural data of one or more sub-regions of the region of land, wherein the agricultural data includes classified data and unclassified data; extracting one or more features from the collected classified agricultural data; training one or more models based on the extracted one or more features; and generating an agricultural map of the region of land based on applying the one or more models to the collected unclassified agricultural data.

2 . The method of claim 1 , further comprising:
determining one or more entropy scores of the one or more sub-regions of land; determining a first sub-region of land from which to collect additional data, wherein the first sub-region of land is the sub-region of land with the highest entropy score; and collecting additional agricultural data of the first sub-region of land, wherein the collected agricultural data includes the collected additional agricultural data.

3 . The method of claim 2 , further comprising:
extracting one or more additional features from the collected additional agricultural data; and updating the generated agricultural map based on the one or more additional features.

4 . The method of claim 3 , further comprising:
based on determining that a maximum collection budget is not yet exceeded:
determining a second sub-region of land from which to collect additional data, wherein the second sub-region of land is the sub-region of land with the second highest entropy score;
collecting additional agricultural data of the second sub-region of land;
extracting one or more additional features from the collected additional agricultural data; and
updating the generated agricultural map based on the one or more additional features.

5 . The method of claim 1 , wherein:
at least one model is trained for each sub-region for which the collected classified data was collected; and the one or more trained models are applied to the one or more extracted features to calculate one or more probabilities of one or more possible classifications of the one or more sub-regions of land.

6 . The method of claim 5 , further comprising:
calculating one or more averages of the one or more probabilities of one or more possible classifications of the one or more sub-regions of land; and calculating one or more entropy scores based on the one or more averages.

7 . The method of claim 1 , wherein:
the one or more features include features from the group comprising crop samples, soil samples, pest samples, crop yield, precipitation, temperature, moisture, photos/videos of land, and classifications of land; and the agricultural data includes data from the group comprising physical access or vehicle image annotation data, remote sensing data, weather data, soil data, crop mask data, or irrigation type data.

8 . A computer program product for generating an agriculture map of a region of land, the computer program product comprising:
one or more non-transitory computer-readable storage media and program instructions stored on the one or more non-transitory computer-readable storage media capable of performing a method, the method comprising: collecting agricultural data of one or more sub-regions of the region of land, wherein the agricultural data includes classified data and unclassified data; extracting one or more features from the collected classified agricultural data; training one or more models based on the extracted one or more features; and generating an agricultural map of the region of land based on applying the one or more models to the collected unclassified agricultural data.

9 . The computer program product of claim 8 , further comprising:
determining one or more entropy scores of the one or more sub-regions of land; determining a first sub-region of land from which to collect additional data, wherein the first sub-region of land is the sub-region of land with the highest entropy score; and collecting additional agricultural data of the first sub-region of land, wherein the collected agricultural data includes the collected additional agricultural data.

10 . The computer program product of claim 9 , further comprising:
extracting one or more additional features from the collected additional agricultural data; and updating the generated agricultural map based on the one or more additional features.

11 . The computer program product of claim 10 , further comprising:
based on determining that a maximum collection budget is not yet exceeded:
determining a second sub-region of land from which to collect additional data, wherein the second sub-region of land is the sub-region of land with the second highest entropy score;
collecting additional agricultural data of the second sub-region of land;
extracting one or more additional features from the collected additional agricultural data; and
updating the generated agricultural map based on the one or more additional features.

12 . The computer program product of claim 8 , wherein:
at least one model is trained for each sub-region for which the collected classified data was collected; and the one or more trained models are applied to the one or more extracted features to calculate one or more probabilities of one or more possible classifications of the one or more sub-regions of land.

13 . The computer program product of claim 12 , further comprising:
calculating one or more averages of the one or more probabilities of one or more possible classifications of the one or more sub-regions of land; and calculating one or more entropy scores based on the one or more averages.

14 . The computer program product of claim 8 , wherein:
the one or more features include features from the group comprising crop samples, soil samples, pest samples, crop yield, precipitation, temperature, moisture, photos/videos of land, and classifications of land; and the agricultural data includes data from the group comprising physical access or vehicle image annotation data, remote sensing data, weather data, soil data, crop mask data, or irrigation type data.

15 . A computer system for generating an agriculture map of a region of land, the computer system comprising:
one or more computer processors, one or more computer-readable storage media, and program instructions stored on the one or more of the computer-readable storage media for execution by at least one of the one or more processors capable of performing a method, the method comprising: collecting agricultural data of one or more sub-regions of the region of land, wherein the agricultural data includes classified data and unclassified data; extracting one or more features from the collected classified agricultural data; training one or more models based on the extracted one or more features; and generating an agricultural map of the region of land based on applying the one or more models to the collected unclassified agricultural data.

16 . The computer system of claim 15 , further comprising:
determining one or more entropy scores of the one or more sub-regions of land; determining a first sub-region of land from which to collect additional data, wherein the first sub-region of land is the sub-region of land with the highest entropy score; and collecting additional agricultural data of the first sub-region of land, wherein the collected agricultural data includes the collected additional agricultural data.

17 . Th

Assignees

• IBM

Inventors

• Pandit Sushain
• Singh Jitendra
• Wolfson Charles Daniel
• Basu Saurav

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V10/765

  using rules for classification or partitioning the feature space · CPC title

• G06V10/803

  of input or preprocessed data · CPC title

• G06N20/20

  Ensemble learning · CPC title