The HiMIC-Monthly dataset is a 1 km high-resolution monthly atmospheric moisture index collection over China from 2003 to 2020. It is generated using the LightGBM algorithm based on observations from 2,419 weather stations and multiple covariates, including land surface temperature, vapor pressure, land cover, impervious surface proportion, population density, and topography. The dataset includes six commonly used moisture indices, enabling fine-scale assessment of moisture conditions from different perspectives. Results show that the HiMIC-Monthly dataset has high performance with R² values exceeding 0.96 for all six moisture indices and reasonable root mean square error and mean absolute error values. The dataset exhibits high consistency with in situ observations over various spatial and temporal regimes, demonstrating broad applicability and strong reliability. The dataset is freely available from Zenodo and the National Tibetan Plateau Data Center. It is stored in NetCDF and GeoTIFF formats and covers the mainland of China with a 1 km × 1 km spatial resolution. The dataset includes six moisture indices: RH, AVP, VPD, DPT, MR, and SH. The accuracy of the dataset is evaluated using R², RMSE, and MAE metrics, with high accuracy and consistency with in situ observations. The dataset is suitable for fine-scale studies and has good reliability at various time scales. The HiMIC-Monthly dataset has potential applications in various fields, including human society studies, natural systems, and environmental science. It can be used to study spatiotemporal changes of fine-resolution human heat stress, the spread of various diseases, urban dry/wet islands, plant growth, crop yield, and wildfire forecasting. The dataset is compared with existing products, such as the China Meteorological Forcing Dataset (CMFD), and shows higher accuracy and detailed spatial variations. The dataset is also compared with other datasets in different climate zones and urban agglomerations, showing good performance and reliability. The HiMIC-Monthly dataset is a high-resolution and long-term near-surface atmospheric moisture dataset that is useful in studies related to urban climate, environmental science, ecosystems, and public health. It provides detailed information on multiple moisture indicators at a fine spatial scale. The dataset is developed using a machine learning algorithm and has potential for further development and application in various fields. The dataset is available for download and use, and the code for developing the dataset is also available. The dataset has been validated and shown to have good accuracy and reliability, making it a valuable resource for research and applications in various fields.The HiMIC-Monthly dataset is a 1 km high-resolution monthly atmospheric moisture index collection over China from 2003 to 2020. It is generated using the LightGBM algorithm based on observations from 2,419 weather stations and multiple covariates, including land surface temperature, vapor pressure, land cover, impervious surface proportion, population density, and topography. The dataset includes six commonly used moisture indices, enabling fine-scale assessment of moisture conditions from different perspectives. Results show that the HiMIC-Monthly dataset has high performance with R² values exceeding 0.96 for all six moisture indices and reasonable root mean square error and mean absolute error values. The dataset exhibits high consistency with in situ observations over various spatial and temporal regimes, demonstrating broad applicability and strong reliability. The dataset is freely available from Zenodo and the National Tibetan Plateau Data Center. It is stored in NetCDF and GeoTIFF formats and covers the mainland of China with a 1 km × 1 km spatial resolution. The dataset includes six moisture indices: RH, AVP, VPD, DPT, MR, and SH. The accuracy of the dataset is evaluated using R², RMSE, and MAE metrics, with high accuracy and consistency with in situ observations. The dataset is suitable for fine-scale studies and has good reliability at various time scales. The HiMIC-Monthly dataset has potential applications in various fields, including human society studies, natural systems, and environmental science. It can be used to study spatiotemporal changes of fine-resolution human heat stress, the spread of various diseases, urban dry/wet islands, plant growth, crop yield, and wildfire forecasting. The dataset is compared with existing products, such as the China Meteorological Forcing Dataset (CMFD), and shows higher accuracy and detailed spatial variations. The dataset is also compared with other datasets in different climate zones and urban agglomerations, showing good performance and reliability. The HiMIC-Monthly dataset is a high-resolution and long-term near-surface atmospheric moisture dataset that is useful in studies related to urban climate, environmental science, ecosystems, and public health. It provides detailed information on multiple moisture indicators at a fine spatial scale. The dataset is developed using a machine learning algorithm and has potential for further development and application in various fields. The dataset is available for download and use, and the code for developing the dataset is also available. The dataset has been validated and shown to have good accuracy and reliability, making it a valuable resource for research and applications in various fields.