Spatial Extremes at Scale: A Case Study of Surface Skin Temperature and Heat Risk in the United States

2026-04-20

AI Summary

This study addresses the challenge of modeling spatially heterogeneous and seasonally varying extreme heat events over complex terrain and assessing their public health risks. To this end, the authors propose a scalable Bayesian spatial extremes model that incorporates a stochastic scale mixture process and leverages an amortized inference strategy, enabling efficient Bayesian inference for the first time on large-scale, high-resolution land skin temperature data. Through both simulation studies and empirical analysis of the Four Corners region in the United States, the model demonstrates high accuracy and scalability in capturing the spatial dependence structure of extreme heat. The approach establishes a novel, data-driven paradigm for climate science and environmental health risk assessment, offering a computationally efficient framework for analyzing extreme temperature events at fine spatial scales.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Security and Privacy: Large-scale security measurements

Abstract

Understanding and mapping extreme heat is critical for risk management and public health planning, particularly in regions with complex terrain and heterogeneous climate. We present a case study of extreme heat in the Four Corners region of the United States, using high-resolution surface skin temperature data from the North American Land Data Assimilation System to characterize spatially heterogeneous and seasonally varying extremes across complex terrain, and to assess their implications for heat-related public health risks. Spatial extremes exhibit complex dependencies across geographic regions, which require sophisticated statistical models to capture. While recent advances in spatial extreme value modeling provide flexible representations of joint tail dependencies, statistical inference remains computationally demanding, especially for datasets with a large number of locations. To address this, we propose a random scale mixture process that facilitates Bayesian inference of spatial extremes, and develop scalable inference strategies that leverage advances in spatial modeling and amortized learning. We evaluate the proposed inference methods through large-scale simulation studies, representing the first such extensive study in spatial extremes, and a high-resolution surface skin temperature application in the Four Corners region. Surface skin temperature is particularly useful as a predictor for air temperature, for studying heatwaves and related environmental phenomena, and to calculate heat indices reflecting downstream health risks at any location. Our findings provide insights into efficient, data-driven approaches for modeling spatial extremes, and serve as guidelines for practitioners in the fields of climate science, environmental risk assessment, and beyond.

Problem

• spatial extremes
• extreme heat
• heat risk
• surface skin temperature
• Bayesian inference

Innovation

• spatial extremes
• Bayesian inference
• random scale mixture process
• amortized learning
• scalable inference