Dataset for: Spatiotemporal changes of drought area as input for a machine-learning approach for crop yield prediction

This dataset contains the input data used in the study: “Spatiotemporal changes of drought area as input for a machine-learning approach for crop yield prediction” The dataset includes monthly time series of drought areas (DA) and seasonal rice crop yield (CY) data for three regions in eastern India:-Region 1: Bihar and Jharkhand-Region 2: West Bengal-Region 3: Odisha Drought areas are expressed as percentages (%) of the region affected by drought and were derived from the Standardised Precipitation Evapotranspiration Index (SPEI) at multiple temporal aggregation periods: 1, 3, 6, 9, and 12 months. These data represent the spatial extent of drought conditions at different time scales. Seasonal crop yield data correspond to rice yield and are expressed in kg/ha. The dataset is provided in three Excel files:-DAs_and_CY_Bihar_and_Jharkhand.xlsx-DAs_and_CY_West_Bengal.xlsx-DAs_and_CY_Odisha.xlsx Each file contains two sheets:-DA: monthly drought area time series for different aggregation periods-CY: seasonal rice crop yield time series These data were used as inputs to train and evaluate machine learning models (artificial neural networks and polynomial regression) for crop yield prediction. How to cite Please cite both this dataset and the associated article: Vitali Diaz, Ahmed A. Osman, Gerald A. Corzo Perez, Shreedhar Maskey, Dimitri Solomatine; Spatiotemporal changes of drought area as input for a machine-learning approach for crop yield prediction. Hydrology Research 2026; nh2026150. doi: https://doi.org/10.2166/nh.2026.150 Diaz, V., Osman, A. A. A., Corzo Perez, G. A., Maskey, S., & Solomatine, D. (2026). Dataset for: Spatiotemporal changes of drought area as input for a machine-learning approach for crop yield prediction [Data set]. In Hydrology Research. Zenodo. https://doi.org/10.5281/zenodo.18404801 Notes:The dataset is intended for research and educational purposes. Users are encouraged to cite the dataset when used in derivative works.