Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications

TL;DR

This paper introduces evidential deep learning, a method that efficiently estimates both aleatoric and epistemic uncertainty in Earth system science models, matching ensemble accuracy while reducing computational costs.

Contribution

The study demonstrates that evidential neural networks can reliably quantify uncertainty in Earth system applications, offering a simpler and more efficient alternative to ensembles.

Findings

Evidential deep learning achieves accuracy comparable to ensembles.

Models effectively quantify both aleatoric and epistemic uncertainty.

Uncertainty estimates correlate well with prediction errors.

Abstract

Robust quantification of predictive uncertainty is critical for understanding factors that drive weather and climate outcomes. Ensembles provide predictive uncertainty estimates and can be decomposed physically, but both physics and machine learning ensembles are computationally expensive. Parametric deep learning can estimate uncertainty with one model by predicting the parameters of a probability distribution but do not account for epistemic uncertainty.. Evidential deep learning, a technique that extends parametric deep learning to higher-order distributions, can account for both aleatoric and epistemic uncertainty with one model. This study compares the uncertainty derived from evidential neural networks to those obtained from ensembles. Through applications of classification of winter precipitation type and regression of surface layer fluxes, we show evidential deep learning models attaining predictive accuracy rivaling standard methods, while robustly quantifying both sources of uncertainty. We evaluate the uncertainty in terms of how well the predictions are calibrated and how well the uncertainty correlates with prediction error. Analyses of uncertainty in the context of the inputs reveal sensitivities to underlying meteorological processes, facilitating interpretation of the models. The conceptual simplicity, interpretability, and computational efficiency of evidential neural networks make them highly extensible, offering a promising approach for reliable and practical uncertainty quantification in Earth system science modeling. In order to encourage broader adoption of evidential deep learning in Earth System Science, we have developed a new Python package, MILES-GUESS (https://github.com/ai2es/miles-guess), that enables users to train and evaluate both evidential and ensemble deep learning.