Download Presentation Slides (649 KB)
More than 80% of the world’s farms are defined as smallholder, with field sizes < 2 hectares. This project produced a wall-to-wall cropland area map for the rain-fed residential cropland mosaic of Tigray Region, Ethiopia, which is comprised entirely of smallholder farms. Sub-meter WorldView-1 and WorldView-2 segmentation results were combined with median phenology amplitude from Landsat 8 data to map crop area. The WorldView constellation, operated by DigitalGlobe, images over 1.2 billion km2 annually at < 2 m spatial resolution, producing petabytes of data per year. Due to computation, data cost, and methodological concerns, very high resolution (VHR) satellite data has mainly been used to produce needed geospatial information for site-specific phenomena. Over 2,700 VHR WorldView-1, -2 data were obtained from the U.S. National Geospatial-Intelligence Agency (NGA) via the NextView license agreement and were processed from raw imagery to produce a smallholder crop map in ~1 week using a semi-automated method and large computing capacity of NASA’s Advanced Data Analytics Platform. This methodology is extensible to other regions with similar vegetation and can easily be expanded to country-scale.
Physical Sciences and Mathematics
McCarty-Kern, Jessica, "Mapping small(holder) farms using big data" (2017). TechTalks. 47.