« Events

Speaker: Enze Zhang, Postdoctoral Fellow, University of Texas Institute for Geophysics

Host: Ginny Catania

Title: Automate Glacier Terminus Picking from Big Data based on Deep Learning

Abstract: Ice sheet marine margins via outlet glaciers are susceptible to climate change and are expected to respond through retreat, steepening, and acceleration, although with significant spatial heterogeneity. However, research on ice-ocean interactions has continued to rely on decentralized, manual mapping of features at the ice-ocean interface, impeding progress in understanding the response of glaciers and ice sheets to climate change. The proliferation of remote sensing images lays the foundation for a better understanding of ice-ocean interactions and also necessitates the automation of terminus delineation. In this talk, I will focus on using deep learning (DL) techniques to automate the terminus delineation, proving the feasibility of using multi-sensor remote sensing imagery, and designing a fully automated pipeline that can continuously produce terminus traces. Finally, our pipeline has successfully picked 171,000 termini for 295 glaciers in Greenland from Landsat-5, -7, -8, Sentinel-1, and -2 images, spanning from 1984 to 2021 with an average uncertainty of ~37 meters. The high sampling frequency and the controlled quality of our terminus data will enable better quantification of ice sheet change and model-based parameterizations of ice-ocean interactions.