Automated monitoring of small grains in the Middle East and North Africa for food security early warning

摘要

This paper presents a prototype crop production monitoring pipeline which identifies agricultural fields planted with small grains over 19 countries in the Middle East and North Africa (MENA) and monitors those crops over the growing season. The technical approach employs an boundary-based image segmentation algorithm to define units of consistent land use, and clusters Sentinel-2 normalized difference vegetation index (NDVI) time series within the fields to identify small grains, without requiring labeled examples. The small grain fields are then monitored over the growing season on a monthly basis using time-integrated NDVI beginning at an interval from the planting date to the end of the target month. Classification accuracy is estimated at 82% for the test case, and crop deviations from the mean and/or reference year(s) have been detected within 1-2 months of planting, and are reliably detected several months before harvest.