Prediction of Peak Floods in Indian Rivers using Interpretable Machine-Learning

This dataset represents the predicted peak flood discharge across all Indian River stream networks. It is available at a high resolution of 30 arc-seconds (~1 km) in gridded TIFF and NetCDF formats, making it easily usable for both research and practical applications. Units of discharge in the dataset: Cumecs For detailed information about this database and its development, please refer to the original research article published in IEEE IGARSS 2025: Kuntla, S. K., & Saharia, M. (2025). Prediction of Peak Floods in Indian Rivers using Interpretable Machine-Learning. IGARSS 2025 - 2025 IEEE International Geoscience and Remote Sensing Symposium, 5773–5777. https://doi.org/10.1109/IGARSS55030.2025.11242832 Disclaimer: While every effort has been made to ensure the accuracy of the data, the authors do not assume responsibility for any errors, omissions, or misuse. Users must cite the database and the associated research article published in IEEE IGARSS 2025 when utilizing this data and acknowledge that all interpretations and conclusions drawn from the data are their own. To Be Cited: Kuntla, S. K., & Saharia, M. (2025). Prediction of Peak Floods in Indian Rivers using Interpretable Machine-Learning. IGARSS 2025 - 2025 IEEE International Geoscience and Remote Sensing Symposium, 5773–5777. https://doi.org/10.1109/IGARSS55030.2025.11242832