Multi-Model Ensemble and Reservoir Computing for River Discharge Prediction in Ungauged Basins

TL;DR

HYPER combines multi-model ensemble and reservoir computing to accurately predict river discharge in ungauged basins, offering a scalable, efficient, and interpretable solution that performs well even with limited data.

Contribution

The paper introduces HYPER, a novel framework integrating Bayesian model averaging and reservoir computing for hydrological prediction without basin-specific calibration.

Findings

HYPER achieves comparable accuracy to LSTM in data-rich scenarios with much less computational time.

HYPER maintains robust performance (~0.51 NSE) in data-scarce conditions, outperforming LSTM significantly.

The method generalizes well to ungauged basins by mapping catchment attributes to model weights.

Abstract

Despite the necessity for accurate flood prediction, many regions lack sufficient river discharge observations. Although numerous models for daily river discharge prediction exist, achieving high accuracy, interpretability, and efficiency under data-scarce conditions remains a major challenge. We address this with a novel method, HYdrological Prediction with multi-model Ensemble and Reservoir computing (HYPER). Our approach applies Bayesian model averaging (BMA) to 47 "uncalibrated" catchment-based conceptual hydrological models. A reservoir computing (RC) model, a type of machine learning model, is then trained via linear regression to correct BMA output errors, a non-iterative process ensuring computational efficiency. For ungauged basins, we infer the required BMA and RC weights by mapping them to catchment attributes from gauged basins, creating a generalizable framework. Evaluated on 87 Japanese basins, in a data-rich scenario, HYPER (median Nash Sutcliffe Efficiency, NSE, of 0.59) performed comparably to a benchmark LSTM (NSE 0.64) but required only 3 % of its computational time. In a data-scarce scenario (where only ~20 % of basins are gauged), HYPER maintained robust performance (NSE 0.51) by leveraging the physical structure of the ensemble. In contrast, the LSTM's performance degraded substantially (NSE -0.61) due to data insufficiency. These results demonstrate that calibrating individual conceptual hydrological models is unnecessary when using a sufficiently large ensemble that is assembled and combined with machine-learning-based bias correction. HYPER provides a robust, efficient, and generalizable solution for discharge prediction, particularly in ungauged basins. By eliminating basin-specific calibration, HYPER offers a scalable, interpretable framework for accurate hydrological prediction in diverse data-scarce regions.