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