BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Monitoring the world's volcanoes from space - Prof Andy Hooper\, U
 niversity of Leeds\, School of Earth and Environment
DTSTART:20200204T120000Z
DTEND:20200204T131500Z
UID:TALK137260@talks.cam.ac.uk
CONTACT:Jonathan Rosser
DESCRIPTION:Chair: Martin Rogers\nAbstract: There are ~1500 subaerial volc
 anoes with the potential to erupt\, but less than 10% are instrumentally m
 onitored. Routine acquisition by the European Sentinel-1 radar mission now
  offers the potential to monitor most of them with at least two acquisitio
 ns every twelve days. We have developed a system to routinely apply radar 
 interferometry (InSAR) whenever a new image is acquired by Sentinel-1 over
  a volcano. Displacement of the ground between images shows up in the resu
 lting "interferograms"\, but there are too many of these to inspect indivi
 dually. We have therefore developed a machine learning approach to identif
 y signs of new deformation\, and changes in the rate of existing deformati
 on patterns\, using independent component analysis. We first use a set of 
 training interferograms to identify components associated with background 
 deformation and common atmospheric patterns. We then analyse new interfero
 grams in the context of those components\, and flag changes in rate above 
 the background variation\, and significant unexplained new signals. We dem
 onstrate this approach on a range of volcanoes\, including Sierra Negra in
  the Galapagos\, where the algorithm detects the acceleration in uplift so
 me two years prior to eruption in 2018\, as well as the eruption itself. M
 ore recently we have developed a more general alternative approach\, using
  a convolutional neural network\, which can locate deformation in interfer
 ograms and distinguish it from atmospheric signals.
LOCATION:Bullard Lab\, Seminar Room
END:VEVENT
END:VCALENDAR