Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021062147 - MODELING FIELD IRRIGATION WITH REMOTE SENSING IMAGERY

Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

[ EN ]

CLAIMS

What is claimed is:

1. A method comprising:

reading at least one time series of index rasters for a geographic region; reading a time series of weather data for the geographic region;

dividing the at least one time series of index rasters and the time series of weather data into a plurality of time windows;

compositing the at least one time series of index rasters within each of the plurality of time windows, yielding a composite index raster for each of the at least one time series of index rasters in each of the plurality of time windows; compositing the time series of weather data within each of the plurality of time windows, yielding composite weather data in each of the plurality of time windows; and

providing the composite index rasters and composite weather data to a trained classifier, and obtaining therefrom a pixel irrigation label for each pixel of the composite index rasters, each pixel irrigation label indicating the presence or absence of irrigation at the associated pixel.

2. The method of claim 1, further comprising:

reading a plurality of field regions within the geographic region; and determining a consensus irrigation label for each of the plurality of field regions based on the pixel irrigation labels within the respective field region.

3. The method of claim 2, further comprising:

determining an uncertainty of each consensus irrigation label based on the ratio of pixel irrigation labels indicating the presence of irrigation to pixel irrigation labels indicating absence of irrigation within the respective field region.

4. The method of claim 1, further comprising:

reading a time series of surface reflectance rasters for the geographic region; and determining, for each of the surface reflectance rasters, at least one index raster, yielding the at least one time series of index rasters.

5. The method of claim 1, wherein the plurality of time windows are consecutive.

6. The method of claim 1, wherein the trained classifier comprises an ensemble model.

7. The method of claim 6, wherein the ensemble model comprises a plurality of decision trees.

8. The method of claim 6, wherein the ensemble model comprises a plurality of boosted tree models.

9. The method of claim 1, wherein the time series of surface reflectance rasters comprises satellite data.

10. The method of claim 1, wherein the time series of surface reflectance rasters spans a growing season in the geographic region.

11. The method of claim 1, wherein the at least one index raster comprises a normalized difference vegetation index raster.

12. The method of claim 1, wherein the at least one index raster comprises a land surface water index raster.

13. The method of claim 1, wherein the at least one index raster comprises a mean brightness raster.

14. The method of claim 1, wherein the time series of weather data comprises accumulated precipitation.

15. The method of claim 1, wherein the time series of weather data comprises growing degree days.

16. The method of claim 1, wherein the plurality of consecutive time windows correspond to early, mid-, and late phases of a growing season in the geographic region.

17. The method of claim 1, wherein compositing comprises averaging the at least one time series of index rasters within each of the plurality of time windows.

18. A system comprising:

a computing node comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor of the computing node to cause the processor to perform a method comprising:

reading at least one time series of index rasters for a geographic region; reading a time series of weather data for the geographic region; dividing the at least one time series of index rasters and the time series of weather data into a plurality of time windows;

compositing the at least one time series of index rasters within each of the plurality of time windows, yielding a composite index raster for each of the at least one time series of index rasters in each of the plurality of time windows;

compositing the time series of weather data within each of the plurality of time windows, yielding composite weather data in each of the plurality of time windows; and

providing the composite index rasters and composite weather data to a trained classifier, and obtaining therefrom a pixel irrigation label for each pixel of the composite index rasters, each pixel irrigation label indicating the presence or absence of irrigation at the associated pixel.

19. The system of claim 18, the method further comprising:

reading a plurality of field regions within the geographic region; and determining a consensus irrigation label for each of the plurality of field regions based on the pixel irrigation labels within the respective field region.

20. The system of claim 19, the method further comprising:

determining an uncertainty of each consensus irrigation label based on the ratio of pixel irrigation labels indicating the presence of irrigation to pixel irrigation labels indicating absence of irrigation within the respective field region.

21. The system of claim 18, the method further comprising:

reading a time series of surface reflectance rasters for a geographic region; and determining, for each of the surface reflectance rasters, at least one index raster, yielding the at least one time series of index rasters.

22. The system of claim 18, wherein the plurality of time windows are consecutive.

23. The system of claim 18, wherein the trained classifier comprises an ensemble model.

24. The system of claim 23, wherein the ensemble model comprises a plurality of decision trees.

25. The system of claim 23, wherein the ensemble model comprises a plurality of boosted tree models.

26. The system of claim 18, wherein the time series of surface reflectance rasters comprises satellite data.

27. The system of claim 18, wherein the time series of surface reflectance rasters spans a growing season in the geographic region.

28. The system of claim 18, wherein the at least one index raster comprises a normalized difference vegetation index raster.

29. The system of claim 18, wherein the at least one index raster comprises a land surface water index raster.

30. The system of claim 18, wherein the at least one index raster comprises a mean brightness raster.

31. The system of claim 18, wherein the time series of weather data comprises accumulated precipitation.

32. The system of claim 18, wherein the time series of weather data comprises growing degree days.

33. The system of claim 18, wherein the plurality of consecutive time windows correspond to early, mid-, and late phases of a growing season in the geographic region.

34. The system of claim 18, wherein compositing comprises averaging the at least one time series of index rasters within each of the plurality of time windows.

35. A computer program product for irrigation labeling, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:

reading at least one time series of index rasters for a geographic region; reading a time series of weather data for the geographic region;

dividing the at least one time series of index rasters and the time series of weather data into a plurality of time windows;

compositing the at least one time series of index rasters within each of the plurality of time windows, yielding a composite index raster for each of the at least one time series of index rasters in each of the plurality of time windows; compositing the time series of weather data within each of the plurality of time windows, yielding composite weather data in each of the plurality of time windows; and

providing the composite index rasters and composite weather data to a trained classifier, and obtaining therefrom a pixel irrigation label for each pixel of the composite index rasters, each pixel irrigation label indicating the presence or absence of irrigation at the associated pixel.

36. The computer program product of claim 35, the method further comprising:

reading a plurality of field regions within the geographic region; and determining a consensus irrigation label for each of the plurality of field regions based on the pixel irrigation labels within the respective field region.

37. The computer program product of claim 36, the method further comprising:

determining an uncertainty of each consensus irrigation label based on the ratio of pixel irrigation labels indicating the presence of irrigation to pixel irrigation labels indicating absence of irrigation within the respective field region.

38. The computer program product of claim 35, further comprising:

reading a time series of surface reflectance rasters for a geographic region; and determining, for each of the surface reflectance rasters, at least one index raster, yielding the at least one time series of index rasters.

39. The computer program product of claim 35, wherein the plurality of time windows are consecutive.

40. The computer program product of claim 35, wherein the trained classifier comprises an ensemble model.

41. The computer program product of claim 40, wherein the ensemble model comprises a plurality of decision trees.

42. The computer program product of claim 40, wherein the ensemble model comprises a plurality of boosted tree models.

43. The computer program product of claim 35, wherein the time series of surface reflectance rasters comprises satellite data.

44. The computer program product of claim 35, wherein the time series of surface reflectance rasters spans a growing season in the geographic region.

45. The computer program product of claim 35, wherein the at least one index raster comprises a normalized difference vegetation index raster.

46. The computer program product of claim 35, wherein the at least one index raster comprises a land surface water index raster.

47. The computer program product of claim 35, wherein the at least one index raster comprises a mean brightness raster.

48. The computer program product of claim 35, wherein the time series of weather data comprises accumulated precipitation.

49. The computer program product of claim 35, wherein the time series of weather data comprises growing degree days.

50. The computer program product of claim 35, wherein the plurality of consecutive time windows correspond to early, mid-, and late phases of a growing season in the geographic region.

51. The computer program product of claim 35, wherein compositing comprises averaging the at least one time series of index rasters within each of the plurality of time windows.