Timely Plastic-Mulched Cropland Extraction Method from Complex Mixed Surfaces in Arid Regions

Plastic mulch is extensively applied in agricultural production arid regions. It significantly influences the interactions between land and atmosphere by altering underlying surface characteristics. An accurate timely extraction method for Plastic-Mulched Cropland (PMC) required to understand energy transfer processes, eco-hydrological cycle, climate effect of PMC, management water resources. In this study, we proposed a Timely Plastic-mulched cropland Extraction Method (TPEM) from complex mixed surfaces with multi-source remote sensing data Shiyanghe River Basin (SRB), typical representation inhomogeneous region northwest China. We defined TPEM three phases; first phase, spectral characteristic curves were drawn ground object points labeled visual interpretation data. second analysis modified index was amplify difference PMC non-PMC objects. Finally, Classification Regression Tree (CART) classifier used generate thresholds indices as rules. The results showed that it can extract boundary large-scale farmland, distinguish objects surfaces, separate desert shares same characteristics PMC. verified be efficient robust, an overall accuracy 0.9234, quantity disagreement 0.0541, allocation 0.0224, outperformed two methods, especially when satellite only during period incomplete covered plastic available. This study will provide us widely distributed surfaces.