Flexible and efficient emulation of spatial extremes processes via variational autoencoders
This provides a novel computational method for researchers and practitioners in environmental science and climate modeling to analyze extreme events like marine heatwaves more efficiently, though it is incremental as it builds on existing VAE and spatial extremes frameworks.
The paper tackled the computational and modeling challenges of high-dimensional spatial extremes by integrating a flexible spatial extremes model into a variational autoencoder (XVAE), resulting in substantially improved time-efficiency over traditional Bayesian inference and outperforming stationary models in simulations.
Many real-world processes have complex tail dependence structures that cannot be characterized using classical Gaussian processes. More flexible spatial extremes models exhibit appealing extremal dependence properties but are often exceedingly prohibitive to fit and simulate from in high dimensions. In this paper, we aim to push the boundaries on computation and modeling of high-dimensional spatial extremes via integrating a new spatial extremes model that has flexible and non-stationary dependence properties in the encoding-decoding structure of a variational autoencoder called the XVAE. The XVAE can emulate spatial observations and produce outputs that have the same statistical properties as the inputs, especially in the tail. Our approach also provides a novel way of making fast inference with complex extreme-value processes. Through extensive simulation studies, we show that our XVAE is substantially more time-efficient than traditional Bayesian inference while outperforming many spatial extremes models with a stationary dependence structure. Lastly, we analyze a high-resolution satellite-derived dataset of sea surface temperature in the Red Sea, which includes 30 years of daily measurements at 16703 grid cells. We demonstrate how to use XVAE to identify regions susceptible to marine heatwaves under climate change and examine the spatial and temporal variability of the extremal dependence structure.