Generating a crop recommendation

• US 10,115,158 B2
• Filed: 09/10/2013
• Issued: 10/30/2018
• Est. Priority Date: 10/25/2010
• Status: Active Grant

• Current Assignee: Trimble Inc.
• Original Assignee: Trimble Inc.
• Inventors: Lindores, Robert James
• Primary Examiner(s): Ngon, Ricky
• Application Number:
  US14/023,351
• Publication Number:
  US 20140012732A1
• Time in Patent Office: 1,876 Days
• Field of Search: 702 85
• CPC Class Codes: A01B 79/005 Precision agriculture
• CPC Class Codes: A01C 21/00 Methods of fertilising , sowing or planting
• CPC Class Codes: A01C 21/007 Determining fertilization requirements
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
• CPC Class Codes: G06Q 50/02 Agriculture; Fishing; Forestry; Mining

Abstract

In a method of for generating a crop recommendation, a plurality of data sets are received by a computer system from a plurality of disparate data sources, wherein each of said plurality of data sets describes a factor affecting a crop. A benchmark is created by the computer system for each of the data sets which describes how the factor affects the market value of the crop. A model is generated by the computer system which describes the crop based upon each of said benchmarks from the plurality of data sets. A report is then generated by the computer system comprising at least one recommendation to increase the market value of the crop.

Claims

1. A method for improving crop yield, comprising:

receiving, at a receiver of a crop recommendation computer system, a plurality of data sets from a plurality of disparate data sources, wherein each of the plurality of data sets describes a factor affecting a crop, and wherein the plurality of data sets comprise a first data set describing a treatment applied to the crop or describing water use for the crop;

creating a benchmark, using a benchmark generator of the crop recommendation computer system, for each of the data sets, wherein a particular benchmark describes how a particular factor affects a yield of the crop;

generating a plurality of models, using a model generator of the crop recommendation computer system, wherein each model relates to growing conditions for the crop, and wherein each model uses different benchmarks created from the plurality of data sets;

generating a report, using a report generator of the crop recommendation computer system, wherein generating the report includes using at least one model, wherein the report comprises at least one recommendation to increase the yield of the crop, wherein the at least one recommendation corresponds to a course of action to be implemented with respect to the crop to increase crop yield, and wherein the at least one recommendation includes a treatment plan for applying the treatment to the crop or an irrigation plan for watering the crop; and

implementing one or more recommendations when growing the crop including at least the treatment plan or the irrigation plan.

2. The method of claim 1, wherein the plurality of data sets further comprise a remotely sensed data set describing a first factor, and a locally collected data set describing the first factor, wherein the remotely sensed data set corresponds to data obtained for a first location using a first sensor that is remote from the first location, and wherein the locally collected data set corresponds to data obtained for the first location using a second sensor that is present at the first location;

and wherein the method further comprises;

correlating the remotely sensed data set with the locally collected data set to generate a correlation using a data correlator of the crop recommendation computer system,

wherein creating at least one benchmark includes using the correlation, or wherein the model uses the correlation, or wherein generating the report includes using the correlation.

3. The method of claim 1, wherein the plurality of data sets further comprise a second data set describing a varietal of the crop.

4. The method of claim 3, wherein the plurality of data sets further comprise a second data set from a water use calculator for the varietal of the crop.

5. The method of claim 1, wherein the plurality of data sets further comprise a second data set from an evapotranspiration model.

6. The method of claim 1, wherein the plurality of data sets further comprise a second data set describing a ground moisture content at a location where the crop is grown.

7. The method of claim 1, wherein the plurality of data sets comprise the first data set describing the treatment applied to the crop.

8. The method of claim 1, wherein the plurality of data sets further comprise a second data set describing a soil type at a location where the crop is grown.

9. The method of claim 1, wherein the plurality of data sets further comprise a second data set corresponding to a projected weather forecast at a location where the crop is grown.

10. The method of claim 1, wherein the plurality of data sets further comprise a second data set describing a previous crop grown at a location where the crop is grown.

11. The method of claim 1, wherein generating the model comprises:

comparing at least one benchmark from a location separate from a location where the crop is grown with a corresponding benchmark from the plurality of data sets using a benchmark comparison component of the crop recommendation computer system.

12. The method of claim 1, wherein the at least one recommendation includes a crop varietal to plant.

13. The method of claim 1, wherein the at least one recommendation includes the treatment to apply to the crop.

14. The method of claim 13, wherein the at least one recommendation includes when to apply the treatment.

15. The method of claim 1, wherein the at least one recommendation includes the irrigation plan for the crop.

16. A non-transitory computer-readable storage medium comprising computer executable code, that when executed by a processor causes the processor to perform operations including:

receiving a plurality of data sets from a plurality of disparate data sources, wherein each of the plurality of data sets describes a factor affecting a crop, and wherein the plurality of data sets comprise a first data set describing a treatment applied to the crop or describing water use for the crop;

creating a benchmark for each of the data sets, wherein a particular benchmark describes how a particular factor affects a yield of the crop;

generating a model, wherein the model describes the crop, and wherein the model uses each of the benchmarks created from the plurality of data sets;

generating a report comprising at least one recommendation to increase the yield of the crop, wherein generating the report includes using at least one benchmark or using the model, wherein the at least one recommendation corresponds to a course of action to be implemented with respect to the crop to increase crop yield, and wherein the at least one recommendation includes a treatment plan for applying the treatment to the crop or an irrigation plan for watering the crop; and

implementing one or more recommendations when growing the crop including at least the treatment plan or the irrigation plan.

17. The non-transitory computer-readable storage medium of claim 16, wherein the plurality of data sets further comprise a remotely sensed data set describing a first factor, and a locally collected data set describing the first factor, wherein the remotely sensed data set corresponds to data obtained for a first location using a first sensor that is remote from the first location, and wherein the locally collected data set corresponds to data obtained for the first location using a second sensor that is present at the first location;

and wherein the operations further include;

correlating the remotely sensed data set with the locally collected data set to generate a correlation,

wherein creating at least one benchmark includes using the correlation, or wherein the model uses the correlation, or wherein generating the report includes using the correlation.

18. The non-transitory computer-readable storage medium of claim 16, wherein the plurality of data sets further comprise a second data set describing a varietal of the crop.

19. The non-transitory computer-readable storage medium of claim 18, wherein the plurality of data sets further comprise a second data set from a water use calculator for the varietal of the crop.

20. The non-transitory computer-readable storage medium of claim 16, wherein the plurality of data sets further comprise a second data set from an evapotranspiration model.

21. The non-transitory computer-readable storage medium of claim 16, wherein the plurality of data sets further comprise a second data set describing a ground moisture content at a location where the crop is grown.

22. The non-transitory computer-readable storage medium of claim 16, wherein the plurality of data sets comprise the first data set describing the treatment applied to the crop.

23. The non-transitory computer-readable storage medium of claim 16, wherein the plurality of data sets further comprise a second data set describing a soil type at a location where the crop is grown.

24. The non-transitory computer-readable storage medium of claim 16, wherein the plurality of data sets further comprise a second data set corresponding to a projected weather forecast at a location where the crop is grown.

25. The non-transitory computer-readable storage medium of claim 16, wherein the plurality of data sets further comprises a second data set describing a previous crop grown at a location where the crop is grown.

26. The non-transitory computer-readable storage medium of claim 16, wherein generating the model comprises:

comparing at least one benchmark from a location separate from a location where the crop is grown with a corresponding benchmark from the plurality of data sets.

27. The non-transitory computer-readable storage medium of claim 16, wherein the at least one recommendation includes a crop varietal to plant.

28. The non-transitory computer-readable storage medium of claim 16, wherein the at least one recommendation includes the treatment to apply to the crop.

29. The non-transitory computer-readable storage medium of claim 28, wherein the at least one recommendation includes when to apply the treatment.

30. The non-transitory computer-readable storage medium of claim 16, wherein the at least one recommendation includes the irrigation plan for watering the crop.

31. A crop recommendation computing system for generating a crop recommendation, comprising:

a memory; and

a processor coupled with the memory, wherein the memory includes processor executable code that, when executed by the processor, causes the processor to perform operations including;

receiving a plurality of data sets from a plurality of disparate data sources, wherein each of the plurality of data sets describes a factor affecting a crop, and wherein the plurality of data sets comprise a first data set describing a treatment applied to the crop or describing water use for the crop;

creating a benchmark for each of the data sets, wherein a particular benchmark describes how a particular factor affects a yield of the crop;

generating a model, wherein the model describes the crop, and wherein the model uses each of the benchmarks created from the plurality of data sets;

generating a report comprising at least one recommendation to increase the yield of the crop, wherein the at least one recommendation corresponds to a course of action to be implemented with respect to the crop, wherein at least one recommendation includes a treatment plan for applying the treatment to the crop or an irrigation plan for watering the crop, and wherein the memory and the processor are implemented as a cloud-based crop recommendation computing system;

implementing one or more recommendations when growing the crop including at least the treatment plan or the irrigation plan.

32. The crop recommendation computing system of claim 31, wherein the plurality of data sets further comprises a remotely sensed data set describing a first factor, and a locally collected data set describing the first factor, wherein the remotely sensed data set corresponds to data obtained for a first location using a first sensor that is remote from the first location, and wherein the locally collected data set corresponds to data obtained for the first location using a second sensor that is present at the first location;

and wherein the operations further include

correlating the remotely sensed data set with the locally collected data set to generate a correlation,

wherein creating at least one benchmark includes using the correlation, or wherein the model uses the correlation, or wherein generating the report includes using the correlation.

33. The crop recommendation computing system of claim 31, wherein generating the model further comprises:

comparing at least one benchmark from a location separate from a location where the crop is grown with a corresponding benchmark from the plurality of data sets.

34. The crop recommendation computing system of claim 31, wherein the at least one recommendation includes a crop varietal to plant.

35. The crop recommendation computing system of claim 31, wherein the at least one recommendation includes the treatment to apply to the crop.

36. The crop recommendation computing system of claim 31, wherein the at least one recommendation includes when to apply the treatment.

37. The crop recommendation computing system of claim 31, wherein the at least one recommendation includes the irrigation plan for watering the crop.