Computer-Automated Spatial Analysis

• US 20110166788A1
• Filed: 03/08/2010
• Published: 07/07/2011
• Est. Priority Date: 08/18/2009
• Status: Active Grant

• Current Assignee: TKXS LLC
• Original Assignee: Plant Health Care, Inc. (Plant Health Care Plc)
• Inventors: Griffin, Terry
• Granted Patent: US 8,306,750 B2
• Time in Patent Office: Days
• US Class Current: 702/5
• CPC Class Codes: A01B 79/005 Precision agriculture
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 50/02 Agriculture; Fishing; Forestry; Mining

Abstract

Some embodiments of the present invention automatically measure the impact of natural conditions and/or deliberate interventions on crop yields. Other embodiments automatically predict the impact of natural conditions and/or deliberate interventions on crop yields. By eliminating the need for human intervention, judgment, or discretion from the processes of measuring and predicting impact on yield, embodiments of the present invention enable such measurements and predictions to be made significantly more accurately, quickly, and inexpensively than has been possible with preexisting techniques.

Claims

1. A computer-implemented method comprising:

(A) identifying spatial yield data descriptive of crop yields associated with a plurality of spatial locations in a field;

(B) identifying at least one of the following data;

(1) experimental design data descriptive of at least one product, system, or rate associated with the plurality of locations in the field;

(2) natural condition data descriptive of natural conditions of the plurality of locations in the field;

(3) noise data descriptive of noise variables associated with the plurality of locations in the field; and

(C) deriving, from the data identified in (B), a measure of the crop yield response in the field to the data identified in (B).

2. The method of claim 1, wherein at least one product, system, or rate comprises at least one product, system, or rate previously applied to the plurality of locations in the field.

3. The method of claim 1, wherein at least one product, system, or rate comprises at least one product, system, or rate planned to be applied to the plurality of locations in the field.

4. The method of claim 1, wherein the measure of the impact on crop yield derived in (C) comprises a measure of past impact on crop yield of the data identified in (B).

5. The method of claim 1, wherein the measure of the impact on crop yield derived in (C) comprises a prediction of future impact on crop yield of the data identified in (B).

6. The method of claim 1, wherein the measure of the impact on crop yield comprises a measure of the impact of the data identified in (B) on crop yield in a particular area in the field.

7. The method of claim 1, wherein the measure of the impact on crop yield comprises a measure of:

the impact of the data identified in (B) on crop yield in a first area of the field relative to

the impact of the data identified in (B) on crop yield in a second area of the field.

8. The method of claim 1, wherein the measure of the impact on crop yield comprises a measure of:

the impact of a first subset of the data identified in (B) on crop yield in the field relative to

the impact of a second subset of the data identified in (B) on crop yield in the field.

9. The method of claim 1, further comprising:

(D) before (C), identifying a boundary of the field; and

wherein (C) comprises deriving a measure of the impact on crop yield only within the boundary of the field.

10. The method of claim 9, wherein (D) comprises retrieving raw boundary data in electronic form and identifying the boundary based on the raw boundary data.

11. The method of claim 9, wherein (D) comprises identifying the boundary by applying an automated boundary detection process to a digital image of the field.

12. The method of claim 1, further comprising:

(D) before (C), identifying a buffer region within the field; and

wherein (C) comprises deriving a measure of the impact on crop yield only within regions of the field other than the buffer region.

13. The method of claim 1, wherein (A) comprises retrieving the spatial yield data in electronic form from yield monitoring equipment.

14. The method of claim 1, wherein (B) (2) comprises retrieving the natural condition data in electronic form over an electronic communications network.

15. The method of claim 1, further comprising:

(D) before (C), correcting erroneous data within the data identified in (B) to produce corrected data; and

wherein (C) comprises deriving a measure of the impact on crop yield based on the corrected data.

16. The method of claim 1, further comprising:

(D) before (C), spatially sorting the data identified in (B) to produce sorted data; and

wherein (C) comprises deriving a measure of the impact on crop yield based on the sorted data.

17. The method of claim 16, further comprising:

(E) before (C), developing a rectangular data table based on the sorted data; and

wherein (C) comprises deriving a measure of the impact on crop yield based on the rectangular data table.

18. The method of claim 1, wherein (C) comprises

(C) (1) generating a spatial interaction structure based on the data identified in (B);

(C) (2) generating a spatial model based on the spatial interaction structure; and

(C) (3) deriving the measure of the impact on crop yield based on the spatial model.

19. The method of claim 18, wherein the spatial model comprises a spatial error process model.

21. The method of claim 1, wherein (B) comprises identifying the natural condition data and at least one of the experimental design data and the noise data.

20. The method of claim A, wherein (B) comprises identifying the experimental design data and at least one of the natural condition data and the noise data.

22. A computer-readable medium tangibly storing computer program instructions executable by a computer processor to perform a method comprising:

(A) identifying spatial yield data descriptive of crop yields associated with a plurality of spatial locations in a field;

(B) identifying at least one of the following data;

(1) experimental design data descriptive of at least one product, system, or rate associated with the plurality of locations in the field;

(2) natural condition data descriptive of natural conditions of the plurality of locations in the field;

(3) noise data descriptive of noise variables associated with the plurality of locations in the field; and

(C) deriving, from the data identified in (B), a measure of the crop yield response in the field to the data identified in (B).

23. The computer-readable medium of claim 22, wherein at least one product, system, or rate comprises at least one product, system, or rate previously applied to the plurality of locations in the field.

24. The computer-readable medium of claim 22, wherein at least one product, system, or rate comprises at least one product, system, or rate planned to be applied to the plurality of locations in the field.

25. The computer-readable medium of claim 22, wherein the measure of the impact on crop yield derived in (C) comprises a measure of past impact on crop yield of the data identified in (B).

26. The computer-readable medium of claim 22, wherein the measure of the impact on crop yield derived in (C) comprises a prediction of future impact on crop yield of the data identified in (B).

27. The computer-readable medium of claim 22, wherein the measure of the impact on crop yield comprises a measure of the impact of the data identified in (B) on crop yield in a particular area in the field.

28. The computer-readable medium of claim 22, wherein the measure of the impact on crop yield comprises a measure of:

the impact of the data identified in (B) on crop yield in a first area of the field relative to

the impact of the data identified in (B) on crop yield in a second area of the field.

29. The computer-readable medium of claim 22, wherein the measure of the impact on crop yield comprises a measure of:

the impact of a first subset of the data identified in (B) on crop yield in the field relative to

the impact of a second subset of the data identified in (B) on crop yield in the field.

30. The computer-readable medium of claim 22, further comprising:

(D) before (C), identifying a boundary of the field; and

wherein (C) comprises deriving a measure of the impact on crop yield only within the boundary of the field.

31. The computer-readable medium of claim 30, wherein (D) comprises retrieving raw boundary data in electronic form and identifying the boundary based on the raw boundary data.

32. The computer-readable medium of claim 30, wherein (D) comprises identifying the boundary by applying an automated boundary detection process to a digital image of the field.

33. The computer-readable medium of claim 22, further comprising:

(E) before (C), identifying a buffer region within the field; and

wherein (C) comprises deriving a measure of the impact on crop yield only within regions of the field other than the buffer region.

34. The computer-readable medium of claim 22, wherein (A) comprises retrieving the spatial yield data in electronic form from yield monitoring equipment.

35. The computer-readable medium of claim 22, wherein (B) (2) comprises retrieving the natural condition data in electronic form over an electronic communications network.

36. The computer-readable medium of claim 22, further comprising:

(E) before (C), correcting erroneous data within the data identified in (B) to produce corrected data; and

wherein (C) comprises deriving a measure of the impact on crop yield based on the corrected data.

37. The computer-readable medium of claim 22, further comprising:

(F) before (C), spatially sorting the data identified in (B) to produce sorted data; and

wherein (C) comprises deriving a measure of the impact on crop yield based on the sorted data.

38. The computer-readable medium of claim 37, further comprising:

(G) before (C), developing a rectangular data table based on the sorted data; and

wherein (C) comprises deriving a measure of the impact on crop yield based on the rectangular data table.

39. The computer-readable medium of claim 22, wherein (C) comprises

(C) (4) generating a spatial interaction structure based on the data identified in (B);

(C) (5) generating a spatial model based on the spatial interaction structure; and

(C) (6) deriving the measure of the impact on crop yield based on the spatial model.

40. The computer-readable medium of claim 39, wherein the spatial model comprises a spatial error process model.

41. The computer-readable medium of claim 22, wherein (B) comprises identifying the experimental design data and at least one of the natural condition data and the noise data.

42. The computer-readable medium of claim 22, wherein (B) comprises identifying the natural condition data and at least one of the experimental design data and the noise data.