Global volcanic unrest detection and alerting

Globally, 800 million people live within 100 km of a volcano. Improvements in monitoring and forecasting of volcanic unrest have been shown to reduce fatalities caused by eruptions, but a significant proportion of the approximately 1500 holocene volcanoes has no ground-based monitoring. However, the deformation at volcanoes, which is statistically linked to eruption, can be detected prior to the eruption event.

Interferometric Synthetic Aperture Radar (InSAR) can systematically provide ground deformation estimations over volcanic areas. Fringes detected in wrapped interferograms over volcanoes indicate the onset of deformation, which is usually due to magma chamber fill-in at depth – an activity which is considered as precursor for a potential eruption.  DeepCube will develop a fully automatic volcanic unrest alert service based on the detection of such precursor activity. This early warning is of great importance for civil protection authorities, enhancing their response effectiveness and allowing for scientists to deploy critical in-situ monitoring equipment to assess more accurately volcanic hazards.

Current access to datasets of the Geohazard Supersites and Natural Laboratory – the open access hub for satellite imagery, processed interferometric products and ground-based data – is limited to only a handful of volcanoes globally and users have to visually inspect the interferograms to decide where deformation associated with volcanic activity is present.

This DeepCube Use Case aims to research Deep Learning architectures that can automatically detect the presence of ground deformation triggered by volcanic unrest within wrapped interferograms, explore the potential of using complex SAR data, and develop a volcanic deformation alert service covering more than 900 volcanoes globally.

DeepCube will develop a global volcanic activity alert service using a GAN-based novelty detector that will detect deformation fringes hidden in a lake of Sentinel-1 wrapped interferograms.

Use Case Leader
National Observatory of Athens

Interested in learning more? Contact us!
Dr. Ioannis Papoutsis,
Nikolaos-Ioannis Bountos,