Regression modeling of multivariate precipitation extremes under regular variation

2026-02-09

AI Summary

This study addresses the challenge of predicting the frequency and intensity of multivariate extreme precipitation events at high quantile levels by proposing a two-stage regression framework grounded in regular variation theory. The approach first estimates the response variable below a moderate threshold and then extrapolates to extreme quantiles, with confidence intervals constructed via a nonparametric block bootstrap. This strategy substantially reduces the computational complexity inherent in multivariate extreme value modeling while maintaining high predictive accuracy. Applied to the CESM2 large ensemble climate data, the method achieved a tied second-place ranking in the EVA2025 Data Challenge, delivering robust predictions of extreme precipitation without revealing any statistically significant long-term trends.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• 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: Explainable and interpretable methods for personalization

Abstract

Motivated by the EVA2025 data challenge, where we participated as the team DesiBoys, we propose a regression strategy within the framework of regular variation to estimate the occurrences and intensities of high precipitation extremes derived from different climate runs of the CESM2 Large Ensemble Community Project (LENS2). Our approach first empirically estimates the target quantities at sub-asymptotic (lower threshold) levels and sets them as response variables within a simple regression framework arising from the theoretical expressions of joint regular variation. Although a seasonal pattern is evident in the data, the precipitation intensities do not exhibit any significant long-term trends across years. Besides, we can safely assume the data to be independent across different climate model runs, thereby simplifying the modeling framework. Once the regression parameters are estimated, we employ a standard prediction approach to infer precipitation levels at very high quantiles. We calculate the confidence intervals using a nonparametric block bootstrap procedure. While a likelihood-based inference grounded in multivariate extreme value theory may provide more accurate estimates and confidence intervals, it would involve a significantly higher computational burden. Our proposed simple and computationally straightforward two-stage approach provides reasonable estimates for the desired quantities, securing us a joint second position in the final rankings of the EVA2025 conference data challenge competition.

Problem

• multivariate precipitation extremes
• regular variation
• extreme value modeling
• high quantile estimation

Innovation

• regular variation
• multivariate extremes
• regression modeling
• block bootstrap
• sub-asymptotic estimation