The global probability layer contains a 0-100% cropland probability for each pixel which was derived from a classification tree process using a bagging methodology. A sub-pixel training dataset was compiled from a variety of sources and covered approximately 80% of the earth's land surface, excepting Antarctica. Sources of training data included GeoCover Landsat, UN-FAO AfriCover, USDA NASS, US NLCD, Agriculture and Agri-Food Canada, South Africa State of the Environment and CORINE.

25 individual classification tree algorithms were generated using a bagging methodology, each of which included 20% of the total available training or approximately 16% of the earth's land surface. All trees were applied globally, the 25 results were ranked per-pixel and the median result was used as the final cropland probability. On average, the 25 trees explained 47.9% of the root node deviance with just 4 of the 39 available MODIS metrics accounting for 65.8% of the deviance reduction. The two best metrics were the average NDVI within the 12 warmest 16-day composite periods (of the 23 periods that make up a year), and the average red reflectance in the 12 composite periods having the lowest red reflectance.

Cropland probability data can be downloaded either by MODIS tile or global mosaic here.

These data may be used for valid scientific or educational purposes as long as proper citations are used. We ask that you credit the Global Cropland Extent data as follows:

Pittman, K., Hansen, M.C., Becker-Reshef, I., Potapov, P.V., Justice, C.O. (2010) Estimating Global Cropland Extent with Multi-year MODIS Data. Remote Sensing, in press.

For further information, please contact:

Dr. Matthew Hansen
Department of Geographical Sciences - UMD
Phone: (301) 405-9714

Dr. Peter Potapov
Department of Geographical Sciences - UMD
Phone: (301) 405-2129