DTSIF: A machine learning-based downscaling TROPOMI solar-induced chlorophyll fluorescence dataset with high spatiotemporal resolution during 2002-2025 in Huang-Huai-Hai region, China

Currently, the spatiotemporal resolution of existing solar-induced chlorophyll fluorescence (SIF) product is relatively rough, which cannot meet the needs of precision agricultural monitoring and production, especially in Huang-Huai-Hai (HHH) region, China. Therefore, we reconstructed the TROPOMI SIF dataset with 4 days and 8 days, 500m resolution from 2002 to 2025 in the HHH region (DTSIF), using a trained ExtraTrees machine learning model based on MODIS reflectance, fraction of photosynthetically active radiation (FPAR) and leaf area index (LAI) data and ERA5 reanalysis data. The performance of DTSIF has been verified by satellite and tower-based GPP and SIF data from regional and site scales. This dataset can provide effective and high-precision data support for vegetation photosynthesis monitoring, carbon flux estimation and agrometeorological disaster monitoring in HHH region.