Using Deep Learning to Model Elevation Differences between Radar and Laser Altimetry

• Published in: Remote Sensing
• Main Authors: Horton, Alex, Ewart, Martin, Gourmelen, Noel, Fettweis, Xavier, Storkey, Amos
• Other Authors: SPHERES - ULiège
• Format: Article in Journal/Newspaper
• Language: English
• Published: MDPI 2022
• Subjects: altimetry; artificial intelligence (AI); CryoSat; cryosphere; Greenland; IceBridge; ICESat-2; interferometry; SARIn; swath; Artificial intelligence; Green land; Interferometric radars; Earth and Planetary Sciences (all); General Earth and Planetary Sciences; Physical; chemical; mathematical & earth Sciences; Earth sciences & physical geography; Physique; chimie; mathématiques & sciences de la terre; Sciences de la terre & géographie physique
• Online Access: https://orbi.uliege.be/handle/2268/302676; https://orbi.uliege.be/bitstream/2268/302676/1/remotesensing-14-06210.pdf; https://doi.org/10.3390/rs14246210

peer reviewed Satellite and airborne observations of surface elevation are critical in understanding climatic and glaciological processes and quantifying their impact on changes in ice masses and sea level contribution. With the growing number of dedicated airborne campaigns and experimental and operational satellite missions, the science community has access to unprecedented and ever-increasing data. Combining elevation datasets allows potentially greater spatial-temporal coverage and improved accuracy; however, combining data from different sensor types and acquisition modes is difficult by differences in intrinsic sensor properties and processing methods. This study focuses on the combination of elevation measurements derived from ICESat-2 and Operation IceBridge LIDAR instruments and from CryoSat-2’s novel interferometric radar altimeter over Greenland. We develop a deep neural network based on sub-waveform information from CryoSat-2, elevation differences between radar and LIDAR, and additional inputs representing local geophysical information. A time series of maps are created showing observed LIDAR-radar differences and neural network model predictions. Mean LIDAR vs. interferometric radar adjustments and the broad spatial and temporal trends thereof are recreated by the neural network. The neural network also predicts radar-LIDAR differences with respect to waveform parameters better than a simple linear model; however, point level adjustments and the magnitudes of the spatial and temporal trends are underestimated.