Abstract: Impervious rate is an important indicator to evaluate the urban ecological environment. Currently, there is only 1 km and 30 m resolution of impervious surface thematic information in the global scope, which cannot meet the needs of urban scale hydrological modeling, sponge city planning and construction. In this paper, an impervious surface extraction model incorporated spectral and texture information is proposed, and a new method based on deep learning is implemented to estimate imper-vious surface information. In addition the software for extracting and monitoring of impervious surface is also developed. Based on multi-source high spatial resolution imagery, impervious surface map with 2 m spatial resolution in mainland China including 31 provinces (municipalities, autonomous regions) is accomplished, just supports the high resolution data to research and monitor sponge and ecological cities.