Deep learning based uncertainty estimation techniques and benchmarking procedure for rainfall-runoff modeling.
Abstract
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. This contributions demonstrates that accurate uncertainty predictions can be obtained with Deep Learning. We establish an uncertainty estimation benchmarking procedure and present four Deep Learning baselines. Three baselines are based on Mixture Density Networks and one is based on Monte Carlo dropout. The results indicate that these approaches constitute strong baselines, especially the former ones. Additionaly, we provide a post-hoc model analysis to put forward some qualitative understanding of the resulting models. This analysis extends the notion of performance and show that learn nuanced behaviors in different situations.
Paper
Code
The results of this paper were produced with the NeuralHydrology Python package.
Citation
@Article{klotz2021uncertainty,
author = {Klotz, D. and Kratzert, F. and Gauch, M. and Keefe Sampson, A. and Brandstetter, J. and Klambauer, G. and Hochreiter, S. and Nearing, G.},
title = {Uncertainty Estimation with Deep Learning for Rainfall–Runoff Modelling},
journal = {Hydrology and Earth System Sciences Discussions},
volume = {2021},
year = {2021},
pages = {1--32},
doi = {10.5194/hess-2021-154}
}