Machine learning for volcano deformation using InSAR: moving beyond detection and classification to forecasting

This is the authors' abstract. We don't add key points for this paper.

Ground deformation is a key indicator of volcanic activity and routine acquisition by the Sentinel-1 satellite mission now allows us to monitor volcano deformation globally. We have developed a system to routinely apply radar interferometry (InSAR), whenever a new Sentinel-1 image is acquired, and extract the deformation. As there are too many images to inspect individually, we have developed an automated machine-learning approach, based on independent component analysis, to identify new deformation patterns and also any changes in rate of existing deformation patterns, both of which are key indicators of changes in activity. In addition, we have developed a deep-learning based algorithm to classify the potential source of the deformation. Our current goal is to forecast how a volcano might deform in the future, based on a time series of interferograms up to the present day. To this end, we have tested various deep-learning algorithms from the field of video prediction. Training of these networks requires a large data set of deformation time series so, in addition to processing all available SAR data acquired over volcanoes, we are simulating data using physical models of various deformation processes that can occur at volcanoes.  We aim for our forecasts to be a useful tool for volcano observatories and we also expect the resulting forecasts to highlight common deformation sequences operating at volcanoes, leading to deeper understanding of the underlying processes. Already, characterising how deformation develops in time, has led us to new discoveries about generalisable underlying processes operating at volcanoes undergoing uplift.