Abstract
Knowledge about frequency and location of snow avalanche activity is essential for forecasting and mapping of snow avalanche hazard. Traditional field monitoring of avalanche activity has limitations, especially when surveying large and remote areas. In recent years, avalanche detection in Sentinel-1 radar satellite imagery has been developed to improve monitoring. However, the current state-of-the-art detection algorithms, based on radar signal processing techniques, are still much less accurate than human experts. To reduce this gap, we propose a deep learning architecture for detecting avalanches in Sentinel-1 radar images. We trained a neural network on 6345 manually labeled avalanches from 117 Sentinel-1 images, each one consisting of six channels that include backscatter and topographical information. Then, we tested our trained model on a new synthetic aperture radar image. Comparing to the manual labeling (the gold standard), we achieved an F 1 score above 66%, whereas the state-of-the-art detection algorithm sits at an F 1 score of only 38%. A visual inspection of the results generated by our deep learning model shows that only small avalanches are undetected, whereas some avalanches that were originally not labeled by the human expert are discovered.
Highlights
K NOWLEDGE about the spatio–temporal distribution of snow avalanche activity in a given region is critical for avalanche forecasting and hazard mapping
We considered three synthetic aperture radar (SAR) features to generate the images to be processed by the deep learning model
Following our hypothesis that the potential angle of reach (PAR) feature map can highlight areas where it is more likely to find an avalanche, we propose a neural attention mechanism [25] that generates an attention mask conditioned on the PAR
Summary
K NOWLEDGE about the spatio–temporal distribution of snow avalanche (hereafter referred to as avalanche) activity in a given region is critical for avalanche forecasting and hazard mapping. We approach avalanche detection as a saliency segmentation task, where the classification is not done at the patch level, but rather at the individual pixel level. We adopt a fully convolutional network (FCN) architecture, which generates for each input image a segmentation mask. 1) We explore, for the first time, the capability of deep learning models in detecting the presence of avalanches in SAR products at a pixel granularity and surpass the current state-of-the-art avalanche detection algorithm [2]. In the experimental section, we evaluate how much the detection performance of the deep learning model improves when providing the FCN with the PAR feature map
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
