Electronic International Standard Serial Number (EISSN)
1872-826X
abstract
Droughts are hydrometeorological extreme events influenced by highly intricate land–atmosphere feedback mechanisms and climate variability. Deep learning models have recently succeeded in detecting extreme climate events and promise to uncover and understand droughts further. There are two main challenges of reliability and trustworthiness limiting their applications: miscalibration and inherent uncertainty. However, they remain rarely explored because deep learning models are overparameterized and seldom tractable. To address this shortcoming, we introduce methodologies for model calibration and entropy-based uncertainty quantification for deep learning-based drought detection. The calibration algorithm can deal with calibration errors by reducing distributional shifts and alleviating overconfident predictions. The uncertainty framework, in turn, decomposes and quantifies the total uncertainty according to several components: data uncertainty, procedural variability, parametric variability, and latent variability. Thus, our method identifies uncertain predictions and supports robust evaluations, benefiting the credibility of the decision-making process. Empirical evidence of performance in a wide range of European drought events is given, justifying the effectiveness of our approach. The calibration methodology yields the lowest expected calibration error (0.31%) and the precision of the uncertainty-based decision-making is improved from 72.27% to 74.06% and 76.59%, based on ensemble predictions and rejecting the predictions for the top 20% uncertain negative samples, respectively. In summary, our approach significantly enhances drought detection"s reliability and classification accuracy, constituting a key step toward more trustworthy and actionable climate decision-making.
Classification
subjects
Telecommunications
keywords
extreme climate events; drought detection; deep learning; model calibration; uncertainty quantification