Identifying Spatio-Temporal Drivers of Extreme Events

TL;DR

This paper introduces a machine learning approach to identify spatio-temporal drivers of extreme climate events, addressing challenges like time delays and inhomogeneous spatial responses, with validation on synthetic and real datasets.

Contribution

The work presents the first end-to-end model that jointly predicts climate extremes and their drivers, providing a new benchmark for spatio-temporal analysis of extreme events.

Findings

Successfully identifies drivers correlated with extremes

Evaluated on synthetic and real climate datasets

Provides publicly available code and datasets

Abstract

The spatio-temporal relations of impacts of extreme events and their drivers in climate data are not fully understood and there is a need of machine learning approaches to identify such spatio-temporal relations from data. The task, however, is very challenging since there are time delays between extremes and their drivers, and the spatial response of such drivers is inhomogeneous. In this work, we propose a first approach and benchmarks to tackle this challenge. Our approach is trained end-to-end to predict spatio-temporally extremes and spatio-temporally drivers in the physical input variables jointly. By enforcing the network to predict extremes from spatio-temporal binary masks of identified drivers, the network successfully identifies drivers that are correlated with extremes. We evaluate our approach on three newly created synthetic benchmarks, where two of them are based on remote sensing or reanalysis climate data, and on two real-world reanalysis datasets. The source code and datasets are publicly available at the project page https://hakamshams.github.io/IDE.