Anomaly detection for the identification of volcanic unrest in satellite imagery

TL;DR

This paper presents an unsupervised deep learning framework using Patch Distribution Modeling to detect volcanic deformation in satellite imagery, addressing data noise and outperforming supervised methods.

Contribution

It introduces a novel unsupervised anomaly detection approach with weighted features and preprocessing for noisy satellite data, improving volcanic unrest detection.

Findings

Effective detection across five volcanoes with diverse deformation patterns

Outperforms supervised learning methods in identifying volcanic anomalies

Enhanced robustness to noisy and incomplete satellite data

Abstract

Satellite images have the potential to detect volcanic deformation prior to eruptions, but while a vast number of images are routinely acquired, only a small percentage contain volcanic deformation events. Manual inspection could miss these anomalies, and an automatic system modelled with supervised learning requires suitably labelled datasets. To tackle these issues, this paper explores the use of unsupervised deep learning on satellite data for the purpose of identifying volcanic deformation as anomalies. Our detector is based on Patch Distribution Modeling (PaDiM), and the detection performance is enhanced with a weighted distance, assigning greater importance to features from deeper layers. Additionally, we propose a preprocessing approach to handle noisy and incomplete data points. The final framework was tested with five volcanoes, which have different deformation characteristics and its performance was compared against the supervised learning method for volcanic deformation detection.