Item: AUTOMATED SNOW AVALANCHE MAPPING WITH DEEP LEARNING IN AERIAL IMAGERY FROM THE EXTREME AVALANCHE WINTER OF 1999
-
-
Title: AUTOMATED SNOW AVALANCHE MAPPING WITH DEEP LEARNING IN AERIAL IMAGERY FROM THE EXTREME AVALANCHE WINTER OF 1999
Proceedings: International Snow Science Workshop 2024, Tromsø, Norway
Authors:
- Mr. Jor Fergus Dal [ WSL Institute for Snow and Avalanche Research SLF ] [ Climate Change, Extremes and Natural Hazards in Alpine Regions Research Centre CERC ]
- Mrs. Elisabeth D. Hafner [ WSL Institute for Snow and Avalanche Research SLF ] [ Climate Change, Extremes and Natural Hazards in Alpine Regions Research Centre CERC ] [ Photogrammetry and Remote Sensing, ETH Zurich ]
- Dr. Torben Peters [ Photogrammetry and Remote Sensing, ETH Zurich ]
- Dr. Dominik Narnhofer [ Photogrammetry and Remote Sensing, ETH Zurich ]
- Dr. Rodrigo Caye Daudt [ Sony Advanced Visual Sensing AG ]
- Mr. Holger Heisig [ Federal Office of Topography swisstopo ]
- Dr. Yves Bühler [ WSL Institute for Snow and Avalanche Research SLF ] [ Climate Change, Extremes and Natural Hazards in Alpine Regions Research Centre CERC ]
Date: 2024-09-23
Abstract: Snow avalanches are a major natural hazard in mountainous areas, posing a significant risk to lives and infrastructure. Knowing the location, frequency, and magnitude of past snow avalanche occurrences is vital to mitigate these risks. Avalanche mapping is therefore critical in risk mitigation. Previous research has explored various techniques to automate snow avalanche mapping from remote sensing sources, including satellite synthetic aperture radar (SAR), optical airborne, and satellite imagery. However, employing historical optical data sources for full snow avalanche delineation has received less attention. These datasets, created in the analog era, could shed light on the patterns of past avalanche activity. The winter of 1999 in the European Alps is notable for its significant avalanche activity with extreme avalanche runouts. It is well documented through aerial images covering over 12,000 square kilometers in the Swiss Alps and neighboring Austria. Our study leverages deep learning techniques to map the release, path, and deposition areas of visible snow avalanches in these historical images. Building upon previous work in deep learning for automated mapping with optical SPOT 6/7 satellite imagery, we have applied an avalanche segmentation model to historical data. The model is based on a convolutional neural network and relies on digital elevation data and orthorectified optical imagery to produce a pixel-level binary snow avalanche segmentation mask. This task requires the adaption of the methods, originally developed and trained on multi-spectral satellite data, for application on grey-scale data, a problem referred to as a domain gap. We do this by augmenting the historical training set with contemporary samples. The contemporary data is transformed to match the target data domain using a Generative Adversarial Network and coupled with the historical data to train the model. We also offer insights into the estimated uncertainty associated with labels and predictions, serving as a resource for future dataset users. Our research shows how cutting-edge mapping techniques can be adapted to historical imagery.
Object ID: ISSW2024_P9.3.pdf
Language of Article: English
Presenter(s): Jor Fergus Dal
Keywords: Avalanche mapping, remote sensing, deep learning
Page Number(s): 1264 - 1271
-