Estimating Large-Scale Interannual Dynamic Impervious Surface Percentages Based on Regional Divisions

Impervious surface information is an important indicator to describe urban development and environmental changes. The substantial increase in impervious area will have a significant impact on the regional landscape environment. Therefore, timely accurate acquisition of large-scale percentage (LISP) great significance for management ecological assessment. However, previous LISP estimation methods often ignored geographic environment climate differences remote sensing information, resulting low overall accuracy obvious estimated results. Thus, this study, based time-series characteristics multi-temporal images combined with geographical heterogeneity, method image fusion divisions was proposed. Firstly, entire region divided into several regions according spatial Köppen–Geiger data MODIS NDVI data. Subsequently, adaptive feature construction were proposed different regions. Finally, used estimate surfaces other years Asia. results indicate that R2 each better than 0.82, models good ability transfer across time can directly without using additional samples. In addition, compared existing products, has higher consistency.