mlsanityData to 14 Oct 2026

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

arXiv 2505.17782 ↗First posted 23 May 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 63 references that are in the map. First posted on arXiv 23 May 2025.

Builds on

23 of 63 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2022A ConvNet for the 2020scited by 3,579
  5. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  6. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  7. 2019Searching for MobileNetV3cited by 1,994
  8. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  9. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  10. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  11. 2023GEO-Bench: Toward Foundation Models for Earth Monitoringcited by 124
  12. 2021BigEarthNet-MM: A Large Scale Multi-Modal Multi-Label Benchmark Archive for Remote Sensing Image Classification and Retrievalcited by 92
11 more
  1. 2020Deep Learning Meets SARcited by 60
  2. 2019Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotationscited by 32
  3. 2018Simultaneous Edge Alignment and Learningcited by 22
  4. 2023Kuro Siwo: 33 billion m2 under the water. A global multi-temporal satellite dataset for rapid flood mappingcited by 16
  5. 2019A deep learning approach to detecting volcano deformation from satellite imagery using synthetic datasetscited by 13
  6. 2022Hephaestus: A large scale multitask dataset towards InSAR understandingcited by 10
  7. 2025Probabilistic Machine Learning for Noisy Labels in Earth Observationcited by 6
  8. 2022Self-supervised Contrastive Learning for Volcanic Unrest Detectioncited by 4
  9. 2022Learning from Synthetic InSAR with Vision Transformers: The case of volcanic unrest detectioncited by 2
  10. 2024Multi-Sensor Deep Learning for Glacier Mappingcited by 2
  11. 2024Anomaly detection for the identification of volcanic unrest in satellite imagerycited by 1

Built on by

Not cited yet.