Uncertainty Estimation with Deep Learning for Rainfall-Runoff Modelling
This work provides a crucial benchmarking procedure for evaluating uncertainty estimation in deep learning-based hydrological models, benefiting researchers and practitioners in hydrological forecasting.
This paper addresses the lack of standardized benchmarks for uncertainty estimation in hydrological forecasting using deep learning. It establishes a benchmarking procedure and presents four deep learning baselines, demonstrating that accurate, precise, and reliable uncertainty estimation is achievable with deep learning.
Deep Learning is becoming an increasingly important way to produce accurate hydrological predictions across a wide range of spatial and temporal scales. Uncertainty estimations are critical for actionable hydrological forecasting, and while standardized community benchmarks are becoming an increasingly important part of hydrological model development and research, similar tools for benchmarking uncertainty estimation are lacking. We establish an uncertainty estimation benchmarking procedure and present four Deep Learning baselines, out of which three are based on Mixture Density Networks and one is based on Monte Carlo dropout. Additionally, we provide a post-hoc model analysis to put forward some qualitative understanding of the resulting models. Most importantly however, we show that accurate, precise, and reliable uncertainty estimation can be achieved with Deep Learning.