Identification and localization of anomalous crop health patterns

Patent metadata

Field	Value
Publication number	US-11023725-B2
Application number	US-202016780111-A
Country	US
Kind code	B2
Filing date	Feb 3, 2020
Priority date	Jan 25, 2018
Publication date	Jun 1, 2021
Grant date	Jun 1, 2021

Abstract

A method and system for generating a map identifying the size and location of anomalous crop health patterns of a geographic area. Predictive crop health forecasting based historical crop health images generates expected crop health images. Statistical parametric mapping is used to model differences in the expected crop health images and current crop health images to generate a statistical parametric map. Regions of anomalous crop health based on the modeled differences are identified in the statistical parametric map. The number of the identified anomalous crop health regions and the size of each of the identified anomalous crop health regions are determined. The statistical significance of the size and number of the anomalous crop health regions relative to the expected crop health is quantified. A map of anomalous crop health patterns delineates the anomalous crop health regions and the statistical significance of the size and number of anomalous crop health regions.

First claim

What is claimed is:

1. A computer implemented method for generating a map identifying the size and location of anomalous crop health patterns of a geographic area, comprising:
storing historical crop health images of a geographic area in a computer data base;
forecasting expected crop health of regions within the geographic area based on the historical crop health images of the geographic area using a predictive crop health forecasting computer modeling module to generate expected crop health images;
obtaining current crop health images of the geographic area;
modeling differences in the expected crop health images and the current observed crop health images as a multivariate random field;
generating a statistical parametric map using properties of the multivariate random field and a distribution transform of test statistics of the expected crop health images and the current crop health images;
identifying regions of anomalous crop health based on a spatial correlation of the modeled differences in the statistical parametric map;
determining the number of the identified anomalous crop health regions;
determining the size of each of the identified anomalous crop health regions;
quantifying statistical significance of the size and number of the anomalous crop health regions relative to the expected crop health using the statistical parametric map; and
generating a geographic area map of anomalous crop health patterns, the map delineating the anomalous crop health regions and the statistical significance of the size and number of the anomalous crop health regions.

2. The computer implemented method of claim 1 , wherein the predictive crop health forecasting computer modeling module includes one of a machine learning model, a statistical model and an artificial intelligence model.

3. The computer implemented method of claim 2 , wherein the machine learning model is one of a support vector regression model, random forest model and a generalized additive model, wherein the statistical model is one of a multiple regression model, an auto-regressive model and a time series filtering model, and wherein the artificial intelligence model is one of recurrent neural networks, convolutional neural networks or other deep learning approaches.

4. The computer implemented method of claim 1 , wherein the statistical parametric mapping module utilizes an uncertainty estimate for quantifying the statistical significance of the size and number of the anomalous crop health regions.

5. The computer implemented method of claim 1 , wherein the predictive crop health forecasting computer modeling module includes a learning system to provide an uncertainty estimate in generating the expected crop health images.

6. The computer implemented method of claim 1 , wherein the statistical parametric mapping module determines spatial correlation differences between the observed crop health images and the expected crop health images.

7. A computer system for generating a map identifying the size and location of anomalous crop health patterns of a geographic area, comprising:
one or more computer processors;
one or more non-transitory computer-readable storage media;
program instructions, stored on the one or more non-transitory computer-readable storage media, which when implemented by the one or more processors, cause the computer system to perform the steps of:
storing historical crop health images of a geographic area in a computer data base;
forecasting expected crop health of regions within the geographic area based on the historical crop health images of the geographic area using a predictive crop health forecasting computer modeling module to generate expected crop health images;
obtaining current crop health images of the geographic area;
modeling differences in the expected crop health images and the current observed crop health images as a multivariate random field;
generating a statistical parametric map using properties of the multivariate random field and a distribution transform of test statistics of the expected crop health images and the current crop health images;
identifying regions of anomalous crop health based on a spatial correlation of the modeled differences in the statistical parametric map;
determining the number of the identified anomalous crop health regions;
determining the size of each of the identified anomalous crop health regions;
quantifying statistical significance of the size and number of the anomalous crop health regions relative to the expected crop health using the statistical parametric map; and
generating a geographic area map of anomalous crop health patterns, the map delineating the anomalous crop health regions and the statistical significance of the size and number of the anomalous crop health regions.

8. The computer system of claim 7 , wherein the predictive crop health forecasting computer modeling module includes one of a machine learning model, a statistical model and an artificial intelligence model.

9. The computer system of claim 8 , wherein the machine learning model is one of a support vector regression model, a random forest model and a generalized additive model, wherein the statistical model is one of a multiple regression model, an auto-regressive model and a time series filtering model, and wherein the artificial intelligence model is one of recurrent neural networks, convolutional neural networks or other deep learning approaches.

10. The computer system of claim 7 , wherein the statistical parametric mapping module utilizes an uncertainty estimate for quantifying the statistical significance of the size and number of the anomalous crop health regions.

11. The computer system of claim 7 , wherein the predictive crop health forecasting computer modeling module includes a learning system to provide an uncertainty estimate in generating the expected crop health images.

12. The computer system of claim 7 , wherein the statistical parametric mapping module determines spatial correlation differences between the observed crop health images and the expected crop health images.

13. A computer program product comprising:
program instructions on a computer-readable storage medium, where execution of the program instructions using a computer causes the computer to perform a method for generating a map identifying the size and location of anomalous crop health patterns of a geographic area, comprising:
storing historical crop health images of a geographic area in a computer data base;
forecasting expected crop health of regions within the geographic area based on the historical crop health images of the geographic area using a predictive crop health forecasting computer modeling module to generate expected crop health images;
obtaining current crop health images of the geographic area;
modeling differences in the expected crop health images and the current observed crop health images as a multivariate random field;
generating a statistical parametric map using properties of the multivariate random field and a distribution transform of test statistics of the expected crop health images and the current crop health images;
identifying regions of anomalous crop health based on a spatial correlation of the modeled differences in the statistical parametric map;
determining the number of the identified anomalous crop health regions;
determining the size of each of the identified anomalous crop health regions;
quantifying statistical significance of the size and number of the anomalous crop health regions relative to the expected crop health using the statistical parametric map; and
generating a geographic area map of

Assignees

• IBM

Inventors

• Mckenna Sean A
• Buesser Beat
• Tirupathi Seshu

Classifications

• G06V20/188 Primary

  Vegetation · CPC title

• G06T2207/20076

  Probabilistic image processing · CPC title

• G06T2207/10032

  Satellite or aerial image; Remote sensing · CPC title

• G06T2207/10024

  Color image · CPC title

• G06T2207/20081

  Training; Learning · CPC title