Estimating Earthquake Magnitude in Sentinel-1 Imagery via Ranking

TL;DR

This paper introduces a ranking-based machine learning approach to estimate earthquake magnitudes from Sentinel-1 satellite imagery, achieving significant improvements over previous regression methods.

Contribution

It formulates earthquake magnitude estimation as a metric-learning problem, enhancing performance in low-data regimes with a ranking approach.

Findings

Up to 30%+ MAE improvement over prior methods

Transformer architectures perform particularly well

Ranking-based training enhances earthquake magnitude estimation

Abstract

Earthquakes are commonly estimated using physical seismic stations, however, due to the installation requirements and costs of these stations, global coverage quickly becomes impractical. An efficient and lower-cost alternative is to develop machine learning models to globally monitor earth observation data to pinpoint regions impacted by these natural disasters. However, due to the small amount of historically recorded earthquakes, this becomes a low-data regime problem requiring algorithmic improvements to achieve peak performance when learning to regress earthquake magnitude. In this paper, we propose to pose the estimation of earthquake magnitudes as a metric-learning problem, training models to not only estimate earthquake magnitude from Sentinel-1 satellite imagery but to additionally rank pairwise samples. Our experiments show at max a 30%+ improvement in MAE over prior regression-only based methods, particularly transformer-based architectures.