Characterising cropland fragmentation in post-Soviet Central Asia, using Landsat remote-sensing time series data

Abstract

Following the dissolution of the Soviet Union, agricultural reforms in Central Asia often translated into the fragmentation of large fields into smaller shares. Most remote-sensing-based land use classification approaches are categorical in nature, and thus they are unable to capture these changes. We have developed an approach to detecting the timing of land fragmentation based on textural information from a time series of Landsat images for four Central Asian countries (Uzbekistan, Turkmenistan, Kyrgyzstan and Tajikistan) between 1990 and 2019. Our results showed that detected fragmentation events correspond well with documented agrarian reform processes in the different countries, and validation yielded maximum overall accuracies between 67 and 73%. In a case study of a former collective farm in Kyrgyzstan, we demonstrate how our method can accurately detect changes on the local scale. Texture time series data have great potential for analysing the trajectories of cropland fragmentation, in particular in regions where additional information on land use is limited.