Hephaestus Minicubes: A Global, Multi-Modal Dataset for Volcanic Unrest Monitoring

2025-05-23

AI Summary

Pre-eruptive ground deformation is a critical precursor for volcanic hazard forecasting, yet deep learning remains underutilized in InSAR-based deformation monitoring due to the scarcity of high-quality labeled data. To address this, we introduce VolcNet—the first global multimodal spatiotemporal dataset dedicated to volcanic activity monitoring—comprising 44 active volcanoes, a 7-year temporal span, and 38 high-resolution spatiotemporal cubes integrating InSAR-derived deformation, digital elevation models, and atmospheric correction variables, all accompanied by expert-annotated fine-grained deformation events and semantic descriptions. We propose the first unified spatiotemporal cube modeling framework that systematically fuses heterogeneous remote sensing modalities. On multimodal classification and semantic segmentation benchmarks, our approach establishes new state-of-the-art performance, significantly improving deformation detection during non-eruptive periods. VolcNet and the proposed framework provide foundational data and methodological advances enabling trustworthy AI deployment in geoscience.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Ground deformation is regarded in volcanology as a key precursor signal preceding volcanic eruptions. Satellite-based Interferometric Synthetic Aperture Radar (InSAR) enables consistent, global-scale deformation tracking; however, deep learning methods remain largely unexplored in this domain, mainly due to the lack of a curated machine learning dataset. In this work, we build on the existing Hephaestus dataset, and introduce Hephaestus Minicubes, a global collection of 38 spatiotemporal datacubes offering high resolution, multi-source and multi-temporal information, covering 44 of the world's most active volcanoes over a 7-year period. Each spatiotemporal datacube integrates InSAR products, topographic data, as well as atmospheric variables which are known to introduce signal delays that can mimic ground deformation in InSAR imagery. Furthermore, we provide expert annotations detailing the type, intensity and spatial extent of deformation events, along with rich text descriptions of the observed scenes. Finally, we present a comprehensive benchmark, demonstrating Hephaestus Minicubes' ability to support volcanic unrest monitoring as a multi-modal, multi-temporal classification and semantic segmentation task, establishing strong baselines with state-of-the-art architectures. This work aims to advance machine learning research in volcanic monitoring, contributing to the growing integration of data-driven methods within Earth science applications.

Problem

• Lack of curated dataset for volcanic deformation deep learning
• Need for multi-modal volcanic unrest monitoring data
• Challenges in distinguishing atmospheric noise from deformation

Innovation

• Global multi-modal dataset for volcanic monitoring
• Integrates InSAR, topographic and atmospheric data
• Supports classification and segmentation tasks