AWI-ICENet1: A convolutional neural network retracker for ice altimetry

Abstract. The Greenlandic and Antarctic Ice Sheet are important indicators of climate change and major contributors to sea level rise. Hence, precise, long-term observations of surface elevation change are required to assess changes and their contribution to sea level rise. Satellite radar altimetry has been used by various missions to measure surface elevation change since 1992. It has been shown that, next to the surface slope and complex topography, one of the most challenging issues is the spatial and temporal variability of radar pulse penetration into the snow pack, especially over the vast East Antarctic plateau. This results in an inaccurate measurement of the true surface elevation and consequently affects surface elevation change (SEC) estimates. To increase the accuracy of surface elevations retrieved by retracking the radar return waveform and thus reduce the uncertainty in SEC, we developed a deep convolutional neural network architecture (AWI-ICENet1). The AWI-ICENet1 is trained using a simulated reference data set with 3.8 million waveforms, taking into account different surface slopes, topography, and attenuation. The successfully trained network is finally applied as AWI-ICENet1-retracker to the full time series of CryoSat-2 Low Resolution Mode (LRM) waveforms over both ice sheets. We compare the AWI-ICENet1 retrieved SEC with estimates of conventional retrackers like TFMRA and ESA ICE1 and ESA ICE2 products. Our results show less uncertainty and a greatly diminished effect of time variable radar penetration, reducing the need to apply corrections based on a close relationship with backscatter- and/or leading edge width, as typically done in SEC processing. This technique provides new opportunities to utilize convolutional neural networks in altimetry, waveform retracking, and processing of satellite altimetry data, which can be applied to historical, recent, and future missions.