Estimating soil properties within a field using hyperspectral remote sensing

Patent metadata

Field	Value
Publication number	US-10705253-B2
Application number	US-201916456883-A
Country	US
Kind code	B2
Filing date	Jun 28, 2019
Priority date	Sep 12, 2014
Publication date	Jul 7, 2020
Grant date	Jul 7, 2020

Abstract

A method for building and using soil models that determine soil properties from soil spectrum data is provided. In an embodiment, building soil model may be accomplished using soil spectrum data received via hyperspectral sensors from a land unit. A processor updates the soil spectrum data by removing interference signals from the soil spectrum data. Multiple ground sampling locations within the land unit are then determined based on the updated soil spectrum data. Soil property data are obtained from ground sampling at the ground sampling locations. Soil models that correlate the updated soil spectrum data with the soil property data are created based on the updated soil spectrum data and the soil property data. The soil models are sent to a storage for future use.

First claim

What is claimed is:

1. A computer-implemented method building and using soil models that determine soil properties from soil spectrum data, comprising:
receiving, by a processor of a server computer system, soil spectrum data for a land unit from hyperspectral sensors;
wherein the soil spectrum data represents specific continuous spectral bands having wavelength ranges of electromagnetic spectrums and captures reflectance measurements of the land unit within the wavelength ranges;
generating, by the processor, updated soil spectrum data by removing interference signals from the soil spectrum data to exclude certain interference spectral bands from the soil spectrum data;
determining ground sampling locations within the land unit based on the updated soil spectrum data;
receiving soil property data obtained from ground sampling at the ground sampling locations;
creating soil models that correlate the updated soil spectrum data with the soil property data and that indicate optimal locations for performing agricultural operations within the land unit;
controlling agricultural machines using the soil models to perform the agricultural operations within the land unit.

2. The computer-implemented method of claim 1 , wherein the hyperspectral sensors are affixed to movable equipment, and wherein the spectrum data are associated with different locations within the land unit.

3. The computer-implemented method of claim 1 , wherein removing interference signals comprises determining a prepossessing technique of a plurality of preprocessing techniques based on the soil spectrum data, type of the hyperspectral sensor used to collect the soil spectrum data, or elevation at which the soil spectrum data is received.

4. The computer-implemented method of claim 3 , wherein the plurality of preprocessing techniques comprises data smoothing, spectral derivatives, standard normal variate prepossessing, or absorbance.

5. The computer-implemented method of claim 1 , wherein determining the ground sampling locations within the land unit based on the updated soil spectrum data comprises using spatial sampling techniques on the updated soil spectrum data.

6. The computer-implemented method of claim 5 , the spatial sampling techniques including conditional Latin Hypercube Sampling.

7. The computer-implemented method of claim 1 , creating the soil models comprising discovering and calibrating latent variables during multivariate regression analysis.

8. The computer-implemented method of claim 7 , wherein discovering and calibrating latent variables comprises using one or more signature spectral band determination techniques of partial least-square regression algorithm, random forest algorithm, principal component regression, partial least squares, ridge regression, lasso regression, or decision tree statistical procedures.

9. The computer-implemented method of claim 1 , further comprising predicting soil properties for a specific geo-location within the land unit using the soil models.

10. The computer-implemented method of claim 1 , further comprising training and calibrating one or more preconfigured soil models that cover a corresponding region using the soil models.

11. The computer-implemented method of claim 1 , further comprising determining optimal locations for planting, nutrient applications, scouting, or implementing sentinel seed technology using the soil models.

12. The computer-implemented method of claim 11 , further comprising causing displaying the optimal locations in a soil map.

13. One or more non-transitory storage media storing instructions which, when executed by one or more computing devices, cause performance of a method comprising the steps of:
receiving, by a processor of a server computer system, soil spectrum data for a land unit from hyperspectral sensors;
wherein the soil spectrum data represents specific continuous spectral bands having wavelength ranges of electromagnetic spectrums and captures reflectance measurements of the land unit within the wavelength ranges;
generating, by the processor, updated soil spectrum data by removing interference signals from the soil spectrum data to exclude certain interference spectral bands from the soil spectrum data;
determining ground sampling locations within the land unit based on the updated soil spectrum data;
receiving soil property data obtained from ground sampling at the ground sampling locations;
creating soil models that correlate the updated soil spectrum data with the soil property data and that indicate optimal locations for performing agricultural operations within the land unit;
controlling agricultural machines using the soil models to perform the agricultural operations within the land unit.

14. The one or more non-transitory storage media of claim 13 , wherein the hyperspectral sensors are affixed to movable equipment, and wherein the spectrum data are associated with different locations within the land unit.

15. The one or more non-transitory storage media of claim 13 , wherein removing interference signals comprises determining a prepossessing technique of a plurality of preprocessing techniques based on the soil spectrum data, type of the hyperspectral sensor used to collect the soil spectrum data, or elevation at which the soil spectrum data is received.

16. The one or more non-transitory storage media of claim 15 , wherein the plurality of preprocessing techniques comprises data smoothing, spectral derivatives, standard normal variate prepossessing, or absorbance.

17. The one or more non-transitory storage media of claim 13 , wherein determining the ground sampling locations within the land unit based on the updated soil spectrum data comprises using spatial sampling techniques on the updated soil spectrum data.

18. The one or more non-transitory storage media of claim 17 , the spatial sampling techniques including conditional Latin Hypercube Sampling.

19. The one or more non-transitory storage media of claim 13 , creating the soil models comprising discovering and calibrating latent variables during multivariate regression analysis.

20. The one or more non-transitory storage media of claim 19 , wherein discovering and calibrating latent variables comprises using one or more signature spectral band determination techniques of partial least-square regression algorithm, random forest algorithm, principal component regression, partial least squares, ridge regression, lasso regression, or decision tree statistical procedures.

Assignees

• Climate Corp

Inventors

• Xiang Haitao
• Yang Xianyuan
• Koshnick Nick
• Cisek Nick

Classifications

• Y02A90/10

  Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation · CPC title

• G06F2111/06

  Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA] · CPC title

• G06F30/27

  using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model · CPC title

• G01N21/31

  Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry {(G01N21/72 takes precedence)} · CPC title

• A01B76/00

  Parts, details or accessories of agricultural machines or implements, not provided for in groups A01B51/00 - A01B75/00 · CPC title