Show simple item record

dc.contributor.advisorGourmelen, Noel
dc.contributor.authorEwart, Martin
dc.date.accessioned2019-02-22T16:09:17Z
dc.date.available2019-02-22T16:09:17Z
dc.date.issued29/11/2018
dc.identifier.urihttp://hdl.handle.net/1842/35458
dc.description.abstractRadar altimetry is commonly used for monitoring changes within the cryosphere and its contribution to sea-level rise. Recent advances in Swath altimetry processing, using the interferometric mode of CryoSat-2, have enabled fine 500m spatial resolution surface elevation models from each satellite pass. However, there is variability in radar elevation estimates, often due to the penetration of radar waves into snow and firn, yielding differences compared to local airborne LiDAR altimeters which are less impacted by penetration. While neural networks are increasingly being used in a wide variety of domains to enhance predictions and detect changes, they have not previously been applied to radar altimetry to correct for elevation biases within the cryosphere. In this study, we present a novel approach to adjusting for elevation bias by creating a neural network that is trained to predict the elevation provided by local airborne LiDAR from CryoSat-2 radar elevation data where both data are available and then apply that model where only radar data are present. We investigate the challenges with building such models and review the variety of configurations and considerations. Finally, we present two proof of concepts that show good spatial and temporal transfer ability and compensate for 70-90% of the mean penetration, while reducing the root mean squared error by 10-17%.en
dc.language.isoenen
dc.publisherThe University of Edinburghen
dc.subjectRadar altimetryen
dc.subjectCryoSat-2en
dc.subjectGreenlanden
dc.subjectSwath processingen
dc.subjectInterferometryen
dc.subjectCryosphereen
dc.subjectIce-sheeten
dc.subjectGlaciersen
dc.subjectDEMen
dc.subjectSurface elevation changeen
dc.subjectClimate changeen
dc.subjectSea level changeen
dc.subjectOperation IceBridgeen
dc.subjectIceSat-2en
dc.subjectNeural networken
dc.subjectMachine learningen
dc.subjectDeep learningen
dc.subjectMSc Geographical Information Scienceen
dc.subjectGISen
dc.titleCompensating for penetration in radar altimetry cryosphere elevation estimates using deep learningen
dc.typeThesis or Dissertationen
dc.type.qualificationlevelMastersen
dc.type.qualificationnameMSc Master of Scienceen
dcterms.accessRightsRestricted Accessen_US


Files in this item

This item appears in the following Collection(s)

Show simple item record