HYdrological Prediction with multi-model Ensemble and Reservoir computing (HYPER)

The HYdrologic Prediction with multi-model Ensemble and Reservoir computing (HYPER) model, combines ensembles of conceptual hydrological models with reservoir computing (RC) to achieve accurate, interpretable, and computationally efficient streamflow predictions. Unlike existing methods, HYPER does not require iterative calibration and remains robust even in data-scarce regions by leveraging relationships between catchment attributes and observed data. 

The HYPER.zip includes the HYPER model as well as the LSTM model used to benchmark the accuracy of the HYPER for gauged and ungauged basins. The data.zip includes the data set used in the HYPER model when tested for 87 basins in Japan.