Mapping Annual 10-meter Evergreen Forests in China from 2017 to 2023 with Multi-Source Remote Sensing Data

Due to the complexity of China's terrain and the diversity of its climate ranging from tropical to cold temperate, mapping evergreen forests in China poses a greater challenge than those in tropical regions, and thematic fine spatio-temporal resolution evergreen forest cover maps are lacking in China. To address this issue, we developed an automatic framework to produce annual 10 m evergreen and non-evergreen forest cover maps of China from 2017 to 2023 with multi-source remote sensing data. Utilizing automatically generated high-quality training samples, integrated with the novel Dynamic World Tree FQ index and other innovative features, alongside advanced post-processing techniques, our final evergreen and non-evergreen forest classification product exhibits superior quality. This is substantiated through visual analysis, independent datasets validation (Overall Accuracy >94%), five-fold cross-validation (Overall Accuracy >98%), and consistency assessment (Kappa >0.8).