Modeling Spatial Extremal Dependence of Precipitation Using Distributional Neural Networks
This work addresses the challenge of modeling extreme precipitation events with spatial and temporal dependencies, which is crucial for climate risk assessment, though it appears incremental as it builds on existing max-stable process frameworks.
The authors tackled the problem of estimating spatial extremal dependence of precipitation maxima using a simulation-based approach with generative neural networks, achieving good performance in complex settings where traditional likelihood estimation is intractable, as demonstrated in a study of monthly rainfall maxima in Western Germany from 2021-2023.
In this work, we propose a simulation-based estimation approach using generative neural networks to determine dependencies of precipitation maxima and their underlying uncertainty in time and space. Within the common framework of max-stable processes for extremes under temporal and spatial dependence, our methodology allows estimating the process parameters and their respective uncertainty, but also delivers an explicit nonparametric estimate of the spatial dependence through the pairwise extremal coefficient function. We illustrate the effectiveness and robustness of our approach in a thorough finite sample study where we obtain good performance in complex settings for which closed-form likelihood estimation becomes intractable. We use the technique for studying monthly rainfall maxima in Western Germany for the period 2021-2023, which is of particular interest since it contains an extreme precipitation and consecutive flooding event in July 2021 that had a massive deadly impact. Beyond the considered setting, the presented methodology and its main generative ideas also have great potential for other applications.