Satellite-based vegetation datasets enable vegetation phenology detection at large scales, among which Solar-Induced Chlorophyll Fluorescence (SIF) and Enhanced Vegetation Index (EVI) are widely used proxies for detecting phenology from photosynthesis and greenness perspectives, respectively. Recent studies have revealed the divergent performances of SIF and EVI for estimating different phenology metrics, i.e., the start of season (SOS) and the end of season (EOS); however, the underlying mechanisms are unclear. In this study, we compared the SOS and EOS of natural ecosystems derived from SIF and EVI in China and explored the underlying mechanisms by investigating the relationships between the differences of phenology derived from SIF and EVI and climatic limiting factors (i.e., temperature, water and radiation). The results showed that the differences between phenology generated using SIF and EVI were diverse in space, which had a close relationship with climatic limitations. The increasing climatic limitation index could result in larger differences in phenology from SIF and EVI for each dominant climate-limited area. The phenology extracted using SIF was more correlated with climatic limiting factors than that using EVI, especially in water-limited areas, making it the main cause of the difference in phenology from SIF and EVI. These findings highlight the impact of climatic limitation on the differences of phenology from SIF and EVI and improve our understanding of land surface phenology from greenness and photosynthesis perspectives.

A high-quality remote sensing interpretation dataset has become crucial for driving an intelligent model, i.e., deep learning (DL), to produce land-use/land-cover (LULC) products. The existing remote sensing datasets face the following issues: the current studies (1) lack object-oriented fine-grained information; (2) they cannot meet national standards; (3) they lack field surveys for labeling samples; and (4) they cannot serve for geographic engineering application directly. To address these gaps, the national-standards- and DL-oriented raster and vector benchmark dataset (RVBD) is the first to be established to map LULC for conducting soil water erosion assessment (SWEA). RVBD has the following significant innovation and contributions: (1) it is the first second-level object- and DL-oriented dataset with raster and vector data for LULC mapping; (2) its classification system conforms to the national industry standards of the Ministry of Water Resources of the People’s Republic of China; (3) it has high-quality LULC interpretation accuracy assisted by field surveys rather than indoor visual interpretation; and (4) it could be applied to serve for SWEA. Our dataset is constructed as follows: (1) spatio-temporal-spectrum information is utilized to perform automatic vectorization and label LULC attributes conforming to the national standards; and (2) several remarkable DL networks (DenseNet161, HorNet, EfficientNetB7, Vision Transformer, and Swin Transformer) are chosen as the baselines to train our dataset, and five evaluation metrics are chosen to perform quantitative evaluation. Experimental results verify the reliability and effectiveness of RVBD. Each chosen network achieves a minimum overall accuracy of 0.81 and a minimum Kappa of 0.80, and Vision Transformer achieves the best classification performance with overall accuracy of 0.87 and Kappa of 0.86. It indicates that RVBD is a significant benchmark, which could lay a foundation for intelligent interpretation of relevant geographic research about SWEA in the Yangtze River Basin and promote artificial intelligence technology to enrich geographical theories and methods.