CROP YIELD FORECASTING MODELS
Methods of and computer program products for predicting crop yield of a geographic region are provided. In various embodiments, a time series of satellite imagery is received. The time series of satellite imagery covers at least the geographic region during a predetermined time period. The predetermined time period comprises one or more phenology periods. A time series of weather data is received. The time series of weather data covers at least the geographic region during the predetermined time period. At least one surface feature of the geographic region during each of the one or more phenology periods is generated from the time series of satellite imagery. At least one weather feature of the geographic region during each of the one or more phenology periods is generated from the time series of weather data. The at least one surface feature and the at least one weather feature are provided to a trained model. A prediction of crop yield for the geographical region is received from the trained model.
1 . A method for predicting crop yield of a geographic region, the method comprising:
receiving a time series of satellite imagery, the time series of satellite imagery covering at least the geographic region during a predetermined time period, the predetermined time period comprising one or more phenology periods;
receiving a time series of weather data, the time series of weather data covering at least the geographic region during the predetermined time period;
generating from the time series of satellite imagery at least one surface feature of the geographic region during each of the one or more phenology periods;
generating from the time series of weather data at least one weather feature of the geographic region during each of the one or more phenology periods;
providing the at least one surface feature and the at least one weather feature to a trained model;
receiving from the trained model a prediction of crop yield for the geographical region.
2 . The method of claim 1 , wherein generating the at least one surface feature comprises generating summary data of the satellite imagery within the geographic region.
3 . The method of claim 2 , wherein generating the at least one surface feature further comprises aggregating the summary data within each of the one or more phenology periods.
4 . The method of claim 2 , wherein generating the at least one surface feature further comprises sampling a plurality of pixels of the satellite imagery within the geographic region and generating summary data therefrom.
5 . The method of claim 4 , wherein the summary data comprises a maximum vegetation index.
6 . The method of claim 1 , wherein generating the at least one weather feature comprises generating summary data of the weather data within the geographic region.
7 . The method of claim 6 , wherein generating the at least one weather feature further comprises aggregating the summary data within each of the one or more phenology periods.
8 . The method of claim 1 , wherein the trained model comprises a linear mixed-effects model or a decision tree ensemble.
9 - 15 . (canceled)
16 . The method of claim 1 , further comprising:
determining a prediction of crop yield for at least one additional geographic region;
aggregating the prediction of crop yield for the geographical region and the prediction of crop yield for the at least one additional geographic region.
17 . The method of claim 16 , wherein aggregating comprises weighting the prediction of crop yield for the geographical region according to a size of the geographical region and weighting the prediction of crop yield for the at least one additional geographic region according to a size of the at least one additional geographic region.
18 . The method of claim 16 , wherein aggregating comprises weighting the prediction of crop yield for the geographical region according to crop production area within the geographical region and weighting the prediction of crop yield for the at least one additional geographic region according to crop production area of the at least one additional geographic region.
19 . The method of claim 16 , wherein aggregating comprises weighting the prediction of crop yield for the geographical region according to historical yield of the geographical region.
20 . (canceled)
21 . The method of claim 1 , further comprising dividing the predetermined time period into the one or more phenology periods based on the time series of satellite imagery, and wherein dividing the predetermined time period comprises
determining a time series of vegetation indices based on the time series of satellite imagery; and
locating peaks in the time series of vegetation indices.
22 . The method of claim 1 , further comprising dividing the predetermined time period into the one or more phenology periods based on the time series of satellite imagery, and wherein dividing the predetermined time period into the one or more phenology periods comprises:
sampling a plurality of pixels of the time series of satellite imagery;
determining a time series of vegetation indices based on the sampled pixels; and
locating peaks in the time series of vegetation indices.
23 . (canceled)
24 . The method of claim 1 , further comprising selecting the at least one surface feature and the at least one weather feature based on the one or more phenology periods, and wherein selecting the at least one surface feature and the at least one weather feature comprises determining a performance gain attributable to each of the at least one surface feature and the at least one weather feature each of the one or more phenology periods.
25 . The method of claim 24 , wherein determining the performance gain comprises applying a decision tree ensemble.
26 . The method of claim 1 , further comprising selecting the at least one surface feature and the at least one weather feature based on the one or more phenology periods, and wherein the one or more phenology periods comprise a plurality of phenology periods, and wherein the selection of the at least one surface feature and the at least one weather feature varies over the predetermined time period.
27 . The method of claim 1 , further comprising:
applying a crop mask to the time series of satellite imagery prior to generating the at least one surface feature.
28 . 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:
receiving a time series of satellite imagery, the time series of satellite imagery covering at least the geographic region during a predetermined time period, the predetermined time period comprising one or more phenology periods;
receiving a time series of weather data, the time series of weather data covering at least the geographic region during the predetermined time period;
generating from the time series of satellite imagery at least one surface feature of the geographic region during each of the one or more phenology periods;
generating from the time series of weather data at least one weather feature of the geographic region during each of the one or more phenology periods;
providing the at least one surface feature and the at least one weather feature to a trained model;
receiving from the trained model a prediction of crop yield for the geographical region.
29 - 54 . (canceled)
55 . A computer program product for predicting crop yield of a geographic region, 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:
receiving a time series of satellite imagery, the time series of satellite imagery covering at least the geographic region during a predetermined time period, the predetermined time period comprising one or more phenology periods;
receiving a time series of weather data, the time series of weather data covering at least the geographic region during the predetermined time period;
generating from the time series of satellite imagery at least one surface feature of the geographic region during each of the one or more phenology periods;
generating from the time series of weather data at least one weather feature of the geographic region during each of the one or more phenology periods;
providing the at least one surface feature and the at least one weather feature to a trained model;
receiving from the trained model a prediction of crop yield for the geographical region.
56 - 81 . (canceled)