Thalia: A Global, Multi-Modal Dataset for Volcanic Activity Monitoring

TL;DR

Thalia is a comprehensive, multi-modal dataset combining satellite, topographic, and atmospheric data over 7 years, designed to improve automated volcanic activity monitoring through machine learning.

Contribution

The paper introduces Thalia, a large-scale, multi-source dataset with expert annotations, addressing previous data limitations and enabling advanced ML-based volcanic deformation analysis.

Findings

Benchmark results demonstrate state-of-the-art models effectively classify volcanic deformation.

Thalia enables improved detection and segmentation of volcanic activity signals.

The dataset fosters collaboration between machine learning and Earth science communities.

Abstract

Monitoring volcanic activity is of paramount importance to safeguarding lives, infrastructure, and ecosystems. However, only a small fraction of known volcanoes are continuously monitored. Satellite-based Interferometric Synthetic Aperture Radar (InSAR) enables systematic, global-scale deformation monitoring. However, its complex data challenge traditional remote sensing methods. Deep learning offers a powerful means to automate and enhance InSAR interpretation, advancing volcanology and geohazard assessment. Despite its promise, progress has been limited by the scarcity of well-curated datasets. In this work, we build on the existing Hephaestus dataset and introduce Thalia, addressing crucial limitations and enriching its scope with higher-resolution, multi-source, and multi-temporal data. Thalia is a global collection of 38 spatiotemporal datacubes covering 7 years and integrating InSAR products, topographic data, as well as atmospheric variables, known to introduce signal delays that can mimic ground deformation in InSAR imagery. Each sample includes expert annotations detailing the type, intensity, and extent of deformation, accompanied by descriptive text. To enable fair and consistent evaluation, we provide a comprehensive benchmark using state-of-the-art models for classification and segmentation. This work fosters collaboration between machine learning and Earth science, advancing volcanic monitoring and promoting data-driven approaches in geoscience. See https://github.com/Orion-AI-Lab/Thalia