FUSING MULTIPLE UNTRAINED NETWORKS FOR HYPERSPECTRAL CHANGE DETECTION

Glacier ice thickness is difficult to measure directly but is essential for glacier evolution modelling. In this work, we employ a novel approach combining physical knowledge and data-driven machine learning to estimate the ice thickness of multiple glaciers in Spitsbergen, Barentsøya, and Edgeøya in Svalbard. We identify challenges for the physics-aware machine learning model and opportunities for improving the accuracy and physical consistency that would also apply to other geophysical tasks.

Comprehensive datasets of calving-front changes are essential for studying and modeling outlet glaciers. Current records are limited in temporal resolution due to manual delineation. We use deep learning to automatically delineate calving fronts for 23 glaciers in Greenland. Resulting time series resolve long-term, seasonal, and subseasonal patterns. We discuss the implications of our results and provide the cryosphere community with a data product and an implementation of our processing system.

Our study uses deep learning to produce a new high-resolution calving front dataset for 149 marine-terminating glaciers in Svalbard from 1985 to 2023, containing 124 919 terminus traces. This dataset offers insights into understanding calving mechanisms and can help improve glacier frontal ablation estimates as a component of the integrated mass balance assessment.

Multimodal data fusion is an intuitive strategy to break the limitation of individual data in Earth observation. Here, we present a multimodal data set, named MDAS, consisting of synthetic aperture radar (SAR), multispectral, hyperspectral, digital surface model (DSM), and geographic information system (GIS) data for the city of Augsburg, Germany, along with baseline models for resolution enhancement, spectral unmixing, and land cover classification, three typical remote sensing applications.