Remote-Sensing Extraction of Small Water Bodies on the Loess Plateau

The mixed pixel of low-resolution remote-sensing image makes the traditional water extraction method not effective for small body extraction. This study takes Loess Plateau with complex terrain as research area and develops a multi-index fusion threshold segmentation algorithm (MFTSA) large-scale based on GEE (Google Earth Engine). MFTSA uses AWEI (automated index), MNDWI (modified normalized difference NDVI (normalized vegetation index) EVI (enhanced synergy to extract bodies. It also slope data generated by SRTM (Shuttle Radar Topography Mission digital elevation model) NIR band reflectance eliminate suppressing high reflectivity noise shadow noise. An was proposed results showed that: (1) overall accuracy 98.14%, correct rate bodies 92.82%. (2) Compared index methods classification methods, could higher integrity clearer more accurate boundaries. (3) used total 69,900 Plateau, accounting 97.63% bodies, 482.11 square kilometers, 16.50%