Satellite detection of snow avalanches using Sentinel-1 in a transitional snow climate

Keskinen, Zachary; Hendrikx, Jordy; Eckerstorfer, Markus; Birkeland, Karl W.

doi:10.1016/j.coldregions.2022.103558

Cited by 9 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These metrics provide a more detailed assessment, accounting for class imbalance and varying prediction 355 results. They have been widely used in various fields, including avalanche literature (e.g., Keskinen et al, 2022). For a more in-depth understanding of these metrics and their sources, see Liu et al ( 2014), who provides a comprehensive review of evaluation metrics for classifiers.…”

Section: Model Assessmentmentioning

confidence: 99%

AutoATES v2.0: Automated avalanche terrain exposure scale mapping

Toft,

Sykes,

Schauer

et al. 2023

Preprint

View full text Add to dashboard Cite

Abstract. This paper documents substantial improvements to the original automated avalanche terrain exposure mapping (AutoATES v1.0) algorithm. The most significant drawbacks of AutoATES v1.0 have been addressed by including forest density data, improving the avalanche runout estimations in low-angle runout zones, accounting for overhead exposure and open-source software. The algorithm also supports the new ATES v2.0 terrain class ‘extreme’ terrain. We used two benchmark maps from Bow Summit and Connaught Creek to validate the improvements from AutoATES v1.0 to v2.0. For Bow Summit, the F1 score (a measure of how well the algorithm performs) improved from 64.01 % to 77.30 %. For Connaught Creek, the F1 score improved from 39.81 % to 71.38 %. The main challenge limiting large-scale mapping is the determination of optimal input parameters for different regions and climates. In areas where AutoATES v2.0 is applied, it can be a valuable tool for avalanche risk assessment and decision. Ultimately, our goal is for AutoATES v2.0 to enable efficient, large-scale, and potentially global ATES mapping in a standardized manner rather than based solely on expert judgement.

show abstract

Section: Model Assessmentmentioning

confidence: 99%

AutoATES v2.0: Automated avalanche terrain exposure scale mapping

Toft,

Sykes,

Schauer

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…every 12 days in Switzerland) and other suitable radar data needs to be ordered and purchased as well. Additionally, with a spatial resolution of approximately 10-15 m, it is not possible to confidently map avalanches of size 3 and smaller from Sentinel-1 imagery (Hafner et al, 2021;Keskinen et al, 2022). Furthermore, the exact or even approximate time of avalanche release cannot be retrieved from satellite data and remains unknown.…”

Section: Introductionmentioning

confidence: 99%

Interactive Snow Avalanche Segmentation from Webcam Imagery: results, potential and limitations

Hafner,

Kontogianni,

Caye Daudt

et al. 2024

Preprint

View full text Add to dashboard Cite

Abstract. For many safety-related applications such as hazard mapping or road management, well documented avalanche events are crucial. Nowadays, despite research into different directions, the available data is mostly restricted to isolated locations where it is collected by observers in the field. Webcams are getting more frequent in the Alps and beyond, capturing numerous avalanche prone slopes several times a day. To complement the knowledge about avalanche occurrences, we propose to make use of this webcam imagery for avalanche mapping. For humans, avalanches are relatively easy to identify, but the manual mapping of their outlines is time intensive. Therefore, we propose to support the mapping of avalanches in images with a learned segmentation model. In interactive avalanche segmentation (IAS), a user collaborates with a deep learning model to segment the avalanche outlines, taking advantage of human expert knowledge while keeping the effort low thanks to the model's ability to delineate avalanches. The human corrections to the prediction in the form of positive clicks on the avalanche or negative clicks on the background result in avalanche outlines of good quality with little effort. Relying on IAS, we extract avalanches from the images in a flexible and efficient manner, resulting in a 90 % time saving compared to conventional manual mapping. If mounted in a stable position, the camera can be georeferenced with a mono-photogrammetry tool, allowing for exact geolocation of the avalanche outlines and subsequent use in geographical information systems (GIS). In this way all avalanches mapped in an image can be imported into a designated database, making them available for the relevant safety-related applications. For imagery, we rely on current and archive data from webcams that cover the Dischma valley near Davos, Switzerland and capture an image every 30 minutes during daytime since the winter 2019. Our model and the associated mapping pipeline represent an important step forward towards continuous and precise avalanche documentation, complementing existing databases and thereby providing a better base for safety-critical decisions and planning in avalanche-prone mountain regions.

show abstract

“…Currently, in snow cover identification research, remote sensing technology has made significant strides over the past few decades, emerging as the principal approach for large-scale and high-precision snow monitoring [3,4]. Optical remote sensing data such as Landsat [5], Sentinel-2 [6], and MODIS [7] boast a high degree of accuracy in snow identification and have become indispensable in snow research endeavors [8,9]. Common methods for snow identification using optical remote sensing data include the normalized difference snow index (NDSI) [10,11], band threshold segmentation, and image classification.…”

Section: Introductionmentioning

confidence: 99%

Avalanche Susceptibility Mapping by Investigating Spatiotemporal Characteristics of Snow Cover Based on Remote Sensing Imagery along the Pemo Highway—A Critical Transportation Road in Tibet, China

Xi,

Mei

2023

Water

View full text Add to dashboard Cite

The Pemo Highway is a critical transportation road to Medog County in the Tibet Plateau (TP). Since its completion in 2021, the Pemo Highway has been prone to frequent avalanches due to heavy rainfall and snowfall. Despite the lack of monitoring stations along the highway and limited research conducted in this area, remote sensing imagery provides valuable data for investigating avalanche hazards along the highway. In this paper, we first investigated the spatiotemporal characteristics of snow cover along the Pemo Highway over the past two years based on the GEE platform. Second, we integrated snow, topography, meteorology, and vegetation factors to assess avalanche susceptibility in January, February, and March 2023 along the highway using the AHP method. The results reveal that the exit of the Duoshungla Tunnel is particularly susceptible to avalanches during the winter months, specifically from January to March, with a significant risk observed in March. Approximately 3.7 km in the direction of the tunnel exit to Lager is prone to avalanche hazards during this period. The recent “1.17 avalanche” event along the Pemo Highway validates the accuracy of our analysis. The findings of this paper provide timely guidance for implementing effective avalanche prevention measures on the Pemo Highway.

show abstract

Satellite detection of snow avalanches using Sentinel-1 in a transitional snow climate

Cited by 9 publications

References 25 publications

AutoATES v2.0: Automated avalanche terrain exposure scale mapping

AutoATES v2.0: Automated avalanche terrain exposure scale mapping

Interactive Snow Avalanche Segmentation from Webcam Imagery: results, potential and limitations

Avalanche Susceptibility Mapping by Investigating Spatiotemporal Characteristics of Snow Cover Based on Remote Sensing Imagery along the Pemo Highway—A Critical Transportation Road in Tibet, China

Contact Info

Product

Resources

About