China-LID: A Comprehensive Dataset of Basic Information for Large Irrigation Districts in China

This dataset is a comprehensive GIS product covering 46 large-scale irrigation districts with designed irrigation areas exceeding 300,000 mu. By integrating multi-source remote sensing imagery, hydrological network data, digital elevation models, and historical irrigation district maps, this study employs machine learning methods such as Random Forest and U-Net alongside manual visual interpretation to extract irrigation district boundaries, ensuring high spatial accuracy. Additionally, the system systematically collected and organized key attribute information—including construction era, administrative affiliation, water source type, designed irrigation area, and crop type—from water resources statistical yearbooks and official archives.