Large-area mapping of smallholder agriculture using openly available PlanetScope imagery by Philippe Rufin (ELIC & Humboldt University in Berlin)

Agricultural land use is a major driver of global climate and environmental change. Remote sensing is used to produce wall-to-wall maps of cropland, crop types, and land management indicators across consolidated agricultural systems across the globe. Cropland mapping in smallholder landscapes, however, is challenged by complex and fragmented landscapes, labor-intensive and unmechanized land management causing high within-field variability, rapid dynamics in shifting cultivation systems, and substantial proportions of short-term fallows. To overcome these challenges, we present a large-area mapping framework to identify active cropland and short-term fallows in smallholder landscapes of Northern Mozambique at 4.77 m spatial resolution. The approach is based on Google Earth Engine and monthly time series of PlanetScope mosaics made available across the world´s tropics through the NICFI data program.