Global volcano deformation monitoring and forecasting from space
There are approximately 1400 subaerial volcanoes with the potential to erupt, but only a fraction of these are instrumentally monitored. Ground deformation is a key indicator of volcanic activity and routine acquisition by the Sentinel-1 radar mission now offers the ability to monitor volcano deformation globally with at least one acquisition every twelve days. We have developed a system to routinely apply radar interferometry (InSAR) whenever a new Sentinel-1 image is acquired and extract the ground deformation. For global monitoring there are too many images to inspect individually and we have therefore developed automated machine learning approaches to identify both signs of new deformation and changes in the rate of existing deformation patterns.
Forecasting how a volcano might deform in the future would be a further useful tool for volcano observatories, but this requires a different approach. We are focussing on deep learning algorithms; however, these require a larger training dataset than we currently have. We are therefore developing a deformation simulator, based on physical models of various deformation processes that occur at volcanoes. Not only will this enable us to train our forecasting algorithms but characterising how deformation develops in time has led us to interesting new discoveries about the underlying processes operating in volcano plumbing systems.
It is an open seminar, so please forward this invitation to other interested colleagues.
________________________________________________________________________________
Microsoft Teams meeting
Join on your computer, mobile app or room device
Click here to join the meeting
