Articles | Volume 16, issue 9
https://doi.org/10.5194/tc-16-3517-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/tc-16-3517-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
02 Sep 2022
Research article |
| 02 Sep 2022
| 02 Sep 2022
Automated avalanche mapping from SPOT 6/7 satellite imagery with deep learning: results, evaluation, potential and limitations
Elisabeth D. Hafner
CORRESPONDING AUTHOR
WSL Institute for Snow and Avalanche Research SLF, Davos Dorf, 7260, Switzerland
Climate Change, Extremes, and Natural Hazards in Alpine Regions Research Center CERC¸ Davos Dorf, 7260, Switzerland
EcoVision Lab, Photogrammetry and Remote Sensing, ETH Zurich, Zurich, 8092, Switzerland
Patrick Barton
EcoVision Lab, Photogrammetry and Remote Sensing, ETH Zurich, Zurich, 8092, Switzerland
Rodrigo Caye Daudt
EcoVision Lab, Photogrammetry and Remote Sensing, ETH Zurich, Zurich, 8092, Switzerland
Jan Dirk Wegner
EcoVision Lab, Photogrammetry and Remote Sensing, ETH Zurich, Zurich, 8092, Switzerland
Institute for Computational Science, University of Zurich, Zurich, 8057, Switzerland
Konrad Schindler
EcoVision Lab, Photogrammetry and Remote Sensing, ETH Zurich, Zurich, 8092, Switzerland
Yves Bühler
WSL Institute for Snow and Avalanche Research SLF, Davos Dorf, 7260, Switzerland
Climate Change, Extremes, and Natural Hazards in Alpine Regions Research Center CERC¸ Davos Dorf, 7260, Switzerland
Related authors
Jaeyoung Lim, Elisabeth Hafner, Florian Achermann, Rik Girod, David Rohr, Nicholas R. J. Lawrance, Yves Bühler, and Roland Siegwart
EGUsphere, https://doi.org/10.5194/egusphere-2024-2728, https://doi.org/10.5194/egusphere-2024-2728, 2024
Short summary
Short summary
As avalanches occur in remote and potentially dangerous locations, data relevant to avalanche monitoring is difficult to obtain. Uncrewed fixed-wing aerial vehicles are promising platforms for gathering aerial imagery to map avalanche activity over a large area. In this work, we present an unmanned aerial system (UAS) capable of autonomously navigating and mapping avalanches in steep mountainous terrain. We expect our work to enable efficient large-scale autonomous avalanche monitoring.
Elisabeth D. Hafner, Theodora Kontogianni, Rodrigo Caye Daudt, Lucien Oberson, Jan Dirk Wegner, Konrad Schindler, and Yves Bühler
The Cryosphere, 18, 3807–3823, https://doi.org/10.5194/tc-18-3807-2024, https://doi.org/10.5194/tc-18-3807-2024, 2024
Short summary
Short summary
For many safety-related applications such as road management, well-documented avalanches are important. To enlarge the information, webcams may be used. We propose supporting the mapping of avalanches from webcams with a machine learning model that interactively works together with the human. Relying on that model, there is a 90% saving of time compared to the "traditional" mapping. This gives a better base for safety-critical decisions and planning in avalanche-prone mountain regions.
Gwendolyn Dasser, Valentin T. Bickel, Marius Rüetschi, Mylène Jacquemart, Mathias Bavay, Elisabeth D. Hafner, Alec van Herwijnen, and Andrea Manconi
EGUsphere, https://doi.org/10.5194/egusphere-2024-1510, https://doi.org/10.5194/egusphere-2024-1510, 2024
Short summary
Short summary
Understanding snowpack wetness is crucial for predicting wet snow avalanches, but detailed data is often limited to certain locations. Using satellite radar, we monitor snow wetness spatially continuously. By combining different radar tracks from Sentinel-1, we improved spatial resolution and tracked snow wetness over several seasons. Our results indicate higher snow wetness to correlate with increased wet snow avalanche activity, suggesting our method can help identify potential risk areas.
Elisabeth D. Hafner, Frank Techel, Rodrigo Caye Daudt, Jan Dirk Wegner, Konrad Schindler, and Yves Bühler
Nat. Hazards Earth Syst. Sci., 23, 2895–2914, https://doi.org/10.5194/nhess-23-2895-2023, https://doi.org/10.5194/nhess-23-2895-2023, 2023
Short summary
Short summary
Oftentimes when objective measurements are not possible, human estimates are used instead. In our study, we investigate the reproducibility of human judgement for size estimates, the mappings of avalanches from oblique photographs and remotely sensed imagery. The variability that we found in those estimates is worth considering as it may influence results and should be kept in mind for several applications.
Leon J. Bührle, Mauro Marty, Lucie A. Eberhard, Andreas Stoffel, Elisabeth D. Hafner, and Yves Bühler
The Cryosphere, 17, 3383–3408, https://doi.org/10.5194/tc-17-3383-2023, https://doi.org/10.5194/tc-17-3383-2023, 2023
Short summary
Short summary
Information on the snow depth distribution is crucial for numerous applications in high-mountain regions. However, only specific measurements can accurately map the present variability of snow depths within complex terrain. In this study, we show the reliable processing of images from aeroplane to large (> 100 km2) detailed and accurate snow depth maps around Davos (CH). We use these maps to describe the existing snow depth distribution, other special features and potential applications.
Elisabeth D. Hafner, Frank Techel, Silvan Leinss, and Yves Bühler
The Cryosphere, 15, 983–1004, https://doi.org/10.5194/tc-15-983-2021, https://doi.org/10.5194/tc-15-983-2021, 2021
Short summary
Short summary
Satellites prove to be very valuable for documentation of large-scale avalanche periods. To test reliability and completeness, which has not been satisfactorily verified before, we attempt a full validation of avalanches mapped from two optical sensors and one radar sensor. Our results demonstrate the reliability of high-spatial-resolution optical data for avalanche mapping, the suitability of radar for mapping of larger avalanches and the unsuitability of medium-spatial-resolution optical data.
Julia Glaus, Katreen Wikstrom Jones, Perry Bartelt, Marc Christen, Lukas Stoffel, Johan Gaume, and Yves Bühler
Nat. Hazards Earth Syst. Sci., 25, 2399–2419, https://doi.org/10.5194/nhess-25-2399-2025, https://doi.org/10.5194/nhess-25-2399-2025, 2025
Short summary
Short summary
This study assesses RAMMS::EXTENDED's predictive power in estimating avalanche runout distances critical for mountain road safety. Leveraging meteorological data and sensitivity analyses, it offers meaningful predictions, aiding near real-time hazard assessments and future model refinement for improved decision-making.
Ghjulia Sialelli, Torben Peters, Jan D. Wegner, and Konrad Schindler
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., X-G-2025, 829–838, https://doi.org/10.5194/isprs-annals-X-G-2025-829-2025, https://doi.org/10.5194/isprs-annals-X-G-2025-829-2025, 2025
Hongruixuan Chen, Jian Song, Olivier Dietrich, Clifford Broni-Bediako, Weihao Xuan, Junjue Wang, Xinlei Shao, Yimin Wei, Junshi Xia, Cuiling Lan, Konrad Schindler, and Naoto Yokoya
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2025-269, https://doi.org/10.5194/essd-2025-269, 2025
Revised manuscript under review for ESSD
Short summary
Short summary
Natural disasters often damage buildings and threaten lives, especially in areas with limited resources. To help improve emergency response, we created a global dataset called BRIGHT using both optical and radar images to detect building damage in any weather. We tested many artificial intelligence models and showed how well they work in real disaster scenes. This work can guide better tools for future disaster recovery and help save lives faster.
Samantha Biegel, Konrad Schindler, and Benjamin D. Stocker
EGUsphere, https://doi.org/10.5194/egusphere-2025-1617, https://doi.org/10.5194/egusphere-2025-1617, 2025
Short summary
Short summary
Our work addresses the predictability of carbon absorption by ecosystems across the globe, particularly in dry regions. We compare 3 different models, including a deep learning model that can learn from past environmental conditions, and show that this helps improve predictions. Still, challenges remain in dry areas due to varying vulnerabilities to drought. As drought conditions intensify globally, it's crucial to understand the varying impacts on ecosystem function.
Pia Ruttner, Annelies Voordendag, Thierry Hartmann, Julia Glaus, Andreas Wieser, and Yves Bühler
Nat. Hazards Earth Syst. Sci., 25, 1315–1330, https://doi.org/10.5194/nhess-25-1315-2025, https://doi.org/10.5194/nhess-25-1315-2025, 2025
Short summary
Short summary
Snow depth variations caused by wind are an important factor in avalanche danger, but detailed and up-to-date information is rarely available. We propose a monitoring system, using lidar and optical sensors, to measure the snow depth distribution at high spatial and temporal resolution. First results show that we can quantify snow depth changes with an accuracy on the low decimeter level, or better, and can identify events such as avalanches or displacement of snow during periods of strong winds.
John Sykes, Pascal Haegeli, Roger Atkins, Patrick Mair, and Yves Bühler
Nat. Hazards Earth Syst. Sci., 25, 1255–1292, https://doi.org/10.5194/nhess-25-1255-2025, https://doi.org/10.5194/nhess-25-1255-2025, 2025
Short summary
Short summary
We model the decision-making of professional ski guides and develop decision support tools to assist with determining appropriate terrain based on current conditions. Our approach compares a manually constructed Bayesian network with machine learning classification models. The models accurately capture the real-world decision-making outcomes in 85–93 % of cases. Our conclusions focus on strengths and weaknesses of each model and discuss ramifications for practical applications in ski guiding.
Jan Magnusson, Yves Bühler, Louis Quéno, Bertrand Cluzet, Giulia Mazzotti, Clare Webster, Rebecca Mott, and Tobias Jonas
Earth Syst. Sci. Data, 17, 703–717, https://doi.org/10.5194/essd-17-703-2025, https://doi.org/10.5194/essd-17-703-2025, 2025
Short summary
Short summary
In this study, we present a dataset for the Dischma catchment in eastern Switzerland, which represents a typical high-alpine watershed in the European Alps. Accurate monitoring and reliable forecasting of snow and water resources in such basins are crucial for a wide range of applications. Our dataset is valuable for improving physics-based snow, land surface, and hydrological models, with potential applications in similar high-alpine catchments.
Andrea Manconi, Yves Bühler, Andreas Stoffel, Johan Gaume, Qiaoping Zhang, and Valentyn Tolpekin
Nat. Hazards Earth Syst. Sci., 24, 3833–3839, https://doi.org/10.5194/nhess-24-3833-2024, https://doi.org/10.5194/nhess-24-3833-2024, 2024
Short summary
Short summary
Our research reveals the power of high-resolution satellite synthetic-aperture radar (SAR) imagery for slope deformation monitoring. Using ICEYE data over the Brienz/Brinzauls instability, we measured surface velocity and mapped the landslide event with unprecedented precision. This underscores the potential of satellite SAR for timely hazard assessment in remote regions and aiding disaster mitigation efforts effectively.
Jaeyoung Lim, Elisabeth Hafner, Florian Achermann, Rik Girod, David Rohr, Nicholas R. J. Lawrance, Yves Bühler, and Roland Siegwart
EGUsphere, https://doi.org/10.5194/egusphere-2024-2728, https://doi.org/10.5194/egusphere-2024-2728, 2024
Short summary
Short summary
As avalanches occur in remote and potentially dangerous locations, data relevant to avalanche monitoring is difficult to obtain. Uncrewed fixed-wing aerial vehicles are promising platforms for gathering aerial imagery to map avalanche activity over a large area. In this work, we present an unmanned aerial system (UAS) capable of autonomously navigating and mapping avalanches in steep mountainous terrain. We expect our work to enable efficient large-scale autonomous avalanche monitoring.
Elisabeth D. Hafner, Theodora Kontogianni, Rodrigo Caye Daudt, Lucien Oberson, Jan Dirk Wegner, Konrad Schindler, and Yves Bühler
The Cryosphere, 18, 3807–3823, https://doi.org/10.5194/tc-18-3807-2024, https://doi.org/10.5194/tc-18-3807-2024, 2024
Short summary
Short summary
For many safety-related applications such as road management, well-documented avalanches are important. To enlarge the information, webcams may be used. We propose supporting the mapping of avalanches from webcams with a machine learning model that interactively works together with the human. Relying on that model, there is a 90% saving of time compared to the "traditional" mapping. This gives a better base for safety-critical decisions and planning in avalanche-prone mountain regions.
Gwendolyn Dasser, Valentin T. Bickel, Marius Rüetschi, Mylène Jacquemart, Mathias Bavay, Elisabeth D. Hafner, Alec van Herwijnen, and Andrea Manconi
EGUsphere, https://doi.org/10.5194/egusphere-2024-1510, https://doi.org/10.5194/egusphere-2024-1510, 2024
Short summary
Short summary
Understanding snowpack wetness is crucial for predicting wet snow avalanches, but detailed data is often limited to certain locations. Using satellite radar, we monitor snow wetness spatially continuously. By combining different radar tracks from Sentinel-1, we improved spatial resolution and tracked snow wetness over several seasons. Our results indicate higher snow wetness to correlate with increased wet snow avalanche activity, suggesting our method can help identify potential risk areas.
B. Xiang, T. Peters, T. Kontogianni, F. Vetterli, S. Puliti, R. Astrup, and K. Schindler
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., X-1-W1-2023, 605–612, https://doi.org/10.5194/isprs-annals-X-1-W1-2023-605-2023, https://doi.org/10.5194/isprs-annals-X-1-W1-2023-605-2023, 2023
Elisabeth D. Hafner, Frank Techel, Rodrigo Caye Daudt, Jan Dirk Wegner, Konrad Schindler, and Yves Bühler
Nat. Hazards Earth Syst. Sci., 23, 2895–2914, https://doi.org/10.5194/nhess-23-2895-2023, https://doi.org/10.5194/nhess-23-2895-2023, 2023
Short summary
Short summary
Oftentimes when objective measurements are not possible, human estimates are used instead. In our study, we investigate the reproducibility of human judgement for size estimates, the mappings of avalanches from oblique photographs and remotely sensed imagery. The variability that we found in those estimates is worth considering as it may influence results and should be kept in mind for several applications.
Leon J. Bührle, Mauro Marty, Lucie A. Eberhard, Andreas Stoffel, Elisabeth D. Hafner, and Yves Bühler
The Cryosphere, 17, 3383–3408, https://doi.org/10.5194/tc-17-3383-2023, https://doi.org/10.5194/tc-17-3383-2023, 2023
Short summary
Short summary
Information on the snow depth distribution is crucial for numerous applications in high-mountain regions. However, only specific measurements can accurately map the present variability of snow depths within complex terrain. In this study, we show the reliable processing of images from aeroplane to large (> 100 km2) detailed and accurate snow depth maps around Davos (CH). We use these maps to describe the existing snow depth distribution, other special features and potential applications.
Adrian Ringenbach, Peter Bebi, Perry Bartelt, Andreas Rigling, Marc Christen, Yves Bühler, Andreas Stoffel, and Andrin Caviezel
Earth Surf. Dynam., 11, 779–801, https://doi.org/10.5194/esurf-11-779-2023, https://doi.org/10.5194/esurf-11-779-2023, 2023
Short summary
Short summary
Swiss researchers carried out repeated rockfall experiments with rocks up to human sizes in a steep mountain forest. This study focuses mainly on the effects of the rock shape and lying deadwood. In forested areas, cubic-shaped rocks showed a longer mean runout distance than platy-shaped rocks. Deadwood especially reduced the runouts of these cubic rocks. The findings enrich standard practices in modern rockfall hazard zoning assessments and strongly urge the incorporation of rock shape effects.
Gregor Ortner, Michael Bründl, Chahan M. Kropf, Thomas Röösli, Yves Bühler, and David N. Bresch
Nat. Hazards Earth Syst. Sci., 23, 2089–2110, https://doi.org/10.5194/nhess-23-2089-2023, https://doi.org/10.5194/nhess-23-2089-2023, 2023
Short summary
Short summary
This paper presents a new approach to assess avalanche risk on a large scale in mountainous regions. It combines a large-scale avalanche modeling method with a state-of-the-art probabilistic risk tool. Over 40 000 individual avalanches were simulated, and a building dataset with over 13 000 single buildings was investigated. With this new method, risk hotspots can be identified and surveyed. This enables current and future risk analysis to assist decision makers in risk reduction and adaptation.
O. Kantarcioglu, K. Schindler, and S. Kocaman
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-M-1-2023, 161–167, https://doi.org/10.5194/isprs-archives-XLVIII-M-1-2023-161-2023, https://doi.org/10.5194/isprs-archives-XLVIII-M-1-2023-161-2023, 2023
Adrian Ringenbach, Peter Bebi, Perry Bartelt, Andreas Rigling, Marc Christen, Yves Bühler, Andreas Stoffel, and Andrin Caviezel
Earth Surf. Dynam., 10, 1303–1319, https://doi.org/10.5194/esurf-10-1303-2022, https://doi.org/10.5194/esurf-10-1303-2022, 2022
Short summary
Short summary
The presented automatic deadwood generator (ADG) allows us to consider deadwood in rockfall simulations in unprecedented detail. Besides three-dimensional fresh deadwood cones, we include old woody debris in rockfall simulations based on a higher compaction rate and lower energy absorption thresholds. Simulations including different deadwood states indicate that a 10-year-old deadwood pile has a higher protective capacity than a pre-storm forest stand.
John Sykes, Pascal Haegeli, and Yves Bühler
Nat. Hazards Earth Syst. Sci., 22, 3247–3270, https://doi.org/10.5194/nhess-22-3247-2022, https://doi.org/10.5194/nhess-22-3247-2022, 2022
Short summary
Short summary
Automated snow avalanche terrain mapping provides an efficient method for large-scale assessment of avalanche hazards, which informs risk management decisions for transportation and recreation. This research reduces the cost of developing avalanche terrain maps by using satellite imagery and open-source software as well as improving performance in forested terrain. The research relies on local expertise to evaluate accuracy, so the methods are broadly applicable in mountainous regions worldwide.
Aubrey Miller, Pascal Sirguey, Simon Morris, Perry Bartelt, Nicolas Cullen, Todd Redpath, Kevin Thompson, and Yves Bühler
Nat. Hazards Earth Syst. Sci., 22, 2673–2701, https://doi.org/10.5194/nhess-22-2673-2022, https://doi.org/10.5194/nhess-22-2673-2022, 2022
Short summary
Short summary
Natural hazard modelers simulate mass movements to better anticipate the risk to people and infrastructure. These simulations require accurate digital elevation models. We test the sensitivity of a well-established snow avalanche model (RAMMS) to the source and spatial resolution of the elevation model. We find key differences in the digital representation of terrain greatly affect the simulated avalanche results, with implications for hazard planning.
Adrian Ringenbach, Elia Stihl, Yves Bühler, Peter Bebi, Perry Bartelt, Andreas Rigling, Marc Christen, Guang Lu, Andreas Stoffel, Martin Kistler, Sandro Degonda, Kevin Simmler, Daniel Mader, and Andrin Caviezel
Nat. Hazards Earth Syst. Sci., 22, 2433–2443, https://doi.org/10.5194/nhess-22-2433-2022, https://doi.org/10.5194/nhess-22-2433-2022, 2022
Short summary
Short summary
Forests have a recognized braking effect on rockfalls. The impact of lying deadwood, however, is mainly neglected. We conducted 1 : 1-scale rockfall experiments in three different states of a spruce forest to fill this knowledge gap: the original forest, the forest including lying deadwood and the cleared area. The deposition points clearly show that deadwood has a protective effect. We reproduced those experimental results numerically, considering three-dimensional cones to be deadwood.
Yves Bühler, Peter Bebi, Marc Christen, Stefan Margreth, Lukas Stoffel, Andreas Stoffel, Christoph Marty, Gregor Schmucki, Andrin Caviezel, Roderick Kühne, Stephan Wohlwend, and Perry Bartelt
Nat. Hazards Earth Syst. Sci., 22, 1825–1843, https://doi.org/10.5194/nhess-22-1825-2022, https://doi.org/10.5194/nhess-22-1825-2022, 2022
Short summary
Short summary
To calculate and visualize the potential avalanche hazard, we develop a method that automatically and efficiently pinpoints avalanche starting zones and simulate their runout for the entire canton of Grisons. The maps produced in this way highlight areas that could be endangered by avalanches and are extremely useful in multiple applications for the cantonal authorities, including the planning of new infrastructure, making alpine regions more safe.
A. Yilmaz, J. D. Wegner, R. Qin, F. Remondino, T. Fuse, and I. Toschi
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2022, 7–7, https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-7-2022, https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-7-2022, 2022
A. Yilmaz, J. D. Wegner, R. Qin, F. Remondino, T. Fuse, and I. Toschi
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2022, 7–7, https://doi.org/10.5194/isprs-annals-V-2-2022-7-2022, https://doi.org/10.5194/isprs-annals-V-2-2022-7-2022, 2022
C. Stucker, B. Ke, Y. Yue, S. Huang, I. Armeni, and K. Schindler
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2022, 193–201, https://doi.org/10.5194/isprs-annals-V-2-2022-193-2022, https://doi.org/10.5194/isprs-annals-V-2-2022-193-2022, 2022
Animesh K. Gain, Yves Bühler, Pascal Haegeli, Daniela Molinari, Mario Parise, David J. Peres, Joaquim G. Pinto, Kai Schröter, Ricardo M. Trigo, María Carmen Llasat, and Heidi Kreibich
Nat. Hazards Earth Syst. Sci., 22, 985–993, https://doi.org/10.5194/nhess-22-985-2022, https://doi.org/10.5194/nhess-22-985-2022, 2022
Short summary
Short summary
To mark the 20th anniversary of Natural Hazards and Earth System Sciences (NHESS), an interdisciplinary and international journal dedicated to the public discussion and open-access publication of high-quality studies and original research on natural hazards and their consequences, we highlight 11 key publications covering major subject areas of NHESS that stood out within the past 20 years.
Natalie Brožová, Tommaso Baggio, Vincenzo D'Agostino, Yves Bühler, and Peter Bebi
Nat. Hazards Earth Syst. Sci., 21, 3539–3562, https://doi.org/10.5194/nhess-21-3539-2021, https://doi.org/10.5194/nhess-21-3539-2021, 2021
Short summary
Short summary
Surface roughness plays a great role in natural hazard processes but is not always well implemented in natural hazard modelling. The results of our study show how surface roughness can be useful in representing vegetation and ground structures, which are currently underrated. By including surface roughness in natural hazard modelling, we could better illustrate the processes and thus improve hazard mapping, which is crucial for infrastructure and settlement planning in mountainous areas.
Nora Helbig, Michael Schirmer, Jan Magnusson, Flavia Mäder, Alec van Herwijnen, Louis Quéno, Yves Bühler, Jeff S. Deems, and Simon Gascoin
The Cryosphere, 15, 4607–4624, https://doi.org/10.5194/tc-15-4607-2021, https://doi.org/10.5194/tc-15-4607-2021, 2021
Short summary
Short summary
The snow cover spatial variability in mountains changes considerably over the course of a snow season. In applications such as weather, climate and hydrological predictions the fractional snow-covered area is therefore an essential parameter characterizing how much of the ground surface in a grid cell is currently covered by snow. We present a seasonal algorithm and a spatiotemporal evaluation suggesting that the algorithm can be applied in other geographic regions by any snow model application.
A. Yilmaz, J. D. Wegner, F. Remondino, T. Fuse, and I. Toschi
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2021, 7–7, https://doi.org/10.5194/isprs-archives-XLIII-B2-2021-7-2021, https://doi.org/10.5194/isprs-archives-XLIII-B2-2021-7-2021, 2021
Y. Xie, K. Schindler, J. Tian, and X. X. Zhu
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2021, 247–254, https://doi.org/10.5194/isprs-archives-XLIII-B2-2021-247-2021, https://doi.org/10.5194/isprs-archives-XLIII-B2-2021-247-2021, 2021
A. Yilmaz, J. D. Wegner, F. Remondino, T. Fuse, and I. Toschi
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2021, 7–7, https://doi.org/10.5194/isprs-annals-V-2-2021-7-2021, https://doi.org/10.5194/isprs-annals-V-2-2021-7-2021, 2021
Nico Lang, Andrea Irniger, Agnieszka Rozniak, Roni Hunziker, Jan Dirk Wegner, and Konrad Schindler
Hydrol. Earth Syst. Sci., 25, 2567–2597, https://doi.org/10.5194/hess-25-2567-2021, https://doi.org/10.5194/hess-25-2567-2021, 2021
Short summary
Short summary
Grain size analysis is the key to understanding the sediment dynamics of river systems and is an important indicator for mitigating flood risk and preserving biodiversity in aquatic habitats. We propose GRAINet, a data-driven approach based on deep learning, to regress grain size distributions from georeferenced UAV images. This allows for a holistic analysis of entire gravel bars, resulting in robust grading curves and high-resolution maps of spatial grain size distribution at large scale.
Elisabeth D. Hafner, Frank Techel, Silvan Leinss, and Yves Bühler
The Cryosphere, 15, 983–1004, https://doi.org/10.5194/tc-15-983-2021, https://doi.org/10.5194/tc-15-983-2021, 2021
Short summary
Short summary
Satellites prove to be very valuable for documentation of large-scale avalanche periods. To test reliability and completeness, which has not been satisfactorily verified before, we attempt a full validation of avalanches mapped from two optical sensors and one radar sensor. Our results demonstrate the reliability of high-spatial-resolution optical data for avalanche mapping, the suitability of radar for mapping of larger avalanches and the unsuitability of medium-spatial-resolution optical data.
Nora Helbig, Yves Bühler, Lucie Eberhard, César Deschamps-Berger, Simon Gascoin, Marie Dumont, Jesus Revuelto, Jeff S. Deems, and Tobias Jonas
The Cryosphere, 15, 615–632, https://doi.org/10.5194/tc-15-615-2021, https://doi.org/10.5194/tc-15-615-2021, 2021
Short summary
Short summary
The spatial variability in snow depth in mountains is driven by interactions between topography, wind, precipitation and radiation. In applications such as weather, climate and hydrological predictions, this is accounted for by the fractional snow-covered area describing the fraction of the ground surface covered by snow. We developed a new description for model grid cell sizes larger than 200 m. An evaluation suggests that the description performs similarly well in most geographical regions.
Lucie A. Eberhard, Pascal Sirguey, Aubrey Miller, Mauro Marty, Konrad Schindler, Andreas Stoffel, and Yves Bühler
The Cryosphere, 15, 69–94, https://doi.org/10.5194/tc-15-69-2021, https://doi.org/10.5194/tc-15-69-2021, 2021
Short summary
Short summary
In spring 2018 in the alpine Dischma valley (Switzerland), we tested different industrial photogrammetric platforms for snow depth mapping. These platforms were high-resolution satellites, an airplane, unmanned aerial systems and a terrestrial system. Therefore, this study gives a general overview of the accuracy and precision of the different photogrammetric platforms available in space and on earth and their use for snow depth mapping.
Cited articles
Abermann, J., Eckerstorfer, M., Malnes, E., and Hansen, B. U.: A large wet snow
avalanche cycle in West Greenland quantified using remote sensing and in
situ observations, Nat. Hazards, 97, 517–534,
https://doi.org/10.1007/s11069-019-03655-8, 2019. a, b
Barton, P. and Hafner, E. D.: aval-e/DeepLab4Avalanches: Code to automatically identify avalanches in SPOT 6/7 imagery (v1.0.0), Zenodo [code], https://doi.org/10.5281/zenodo.7014498, 2022. a
Bebi, P., Kulakowski, D., and Rixen, C.: Snow avalanche disturbances in forest
ecosystems – State of research and implications for management, Forest
Ecology Manag., 257, 1883–1892, https://doi.org/10.1016/j.foreco.2009.01.050,
2009. a
Bianchi, F. M., Grahn, J., Eckerstorfer, M., Malnes, E., and Vickers, H.: Snow
Avalanche Segmentation in SAR Images With Fully Convolutional Neural
Networks, IEEE J. Sel. Top. Appl. Earth Obs., 14, 75–82, https://doi.org/10.1109/JSTARS.2020.3036914, 2021. a
Bründl, M. and Margreth, S.: Integrative Risk Management, in: Snow and Ice-Related Hazards, edited by: Haeberli, W.
and Whiteman, C., Risks Disast.,
2015, 263–301, https://doi.org/10.1016/B978-0-12-394849-6.00009-3, 2015. a
Bühler, Y., Hüni, A., Christen, M., Meister, R., and Kellenberger, T.:
Automated detection and mapping of avalanche deposits using airborne optical
remote sensing data, Cold Reg. Sci. Technol., 57, 99–106,
https://doi.org/10.1016/j.coldregions.2009.02.007, 2009. a, b
Bühler, Y., Bebi, P., Christen, M., Margreth, S., Stoffel, L., Stoffel, A., Marty, C., Schmucki, G., Caviezel, A., Kühne, R., Wohlwend, S., and Bartelt, P.: Automated avalanche hazard indication mapping on a statewide scale, Nat. Hazards Earth Syst. Sci., 22, 1825–1843, https://doi.org/10.5194/nhess-22-1825-2022, 2022. a, b
Cai, Y., Guan, K., Peng, J., Wang, S., Seifert, C., Wardlow, B., and Li, Z.: A
high-performance and in-season classification system of field-level crop
types using time-series Landsat data and a machine learning approach,
Remote Sens. Environ., 210, 35–47,
https://doi.org/10.1016/j.rse.2018.02.045, 2018. a
Christen, M., Kowalski, J., and Bartelt, P.: RAMMS: Numerical simulation of
dense snow avalanches in three-dimensional terrain, Cold Reg. Sci.
Technol., 63, 1–14, https://doi.org/10.1016/j.coldregions.2010.04.005, 2010. a
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., and Wei, Y.: Deformable
Convolutional Networks, in: 2017 IEEE International Conference on Computer
Vision (ICCV), 764–773, https://doi.org/10.1109/ICCV.2017.89, 2017. a, b
Eckerstorfer, M., Bühler, Y., Frauenfelder, R., and Malnes, E.: Remote
sensing of snow avalanches: Recent advances, potential, and limitations, Cold
Reg. Sci. Technol., 121, 126–140,
https://doi.org/10.1016/j.coldregions.2015.11.001, 2016. a, b
Eckerstorfer, M., Vickers, H., Malnes, E., and Grahn, J.: Near-Real Time
Automatic Snow Avalanche Activity Monitoring System Using Sentinel-1 SAR
Data in Norway, Remote Sensing, 11, 2863, https://doi.org/10.3390/rs11232863, 2019. a
Eckerstorfer, M., Oterhals, H., Müller, K., Malnes, E., Grahn, J., Langeland,
S., and Velsand, P.: Performance of manual and automatic detection of dry
snow avalanches in Sentinel-1 SAR images, Cold Reg. Sci.
Technol., 198, 103549, https://doi.org/10.1016/j.coldregions.2022.103549, 2022. a, b
Fiorino, C., Reni, M., Bolognesi, A., and Calandrino, R.: Intra- and
inter-observer variability in contouring prostate and seminal vesicles:
Implications for conformal treatment planning, Radiother. Oncol., 47,
285–292, https://doi.org/10.1016/S0167-8140(98)00021-8, 1998. a
Hafner, E. and Bühler, Y.: SPOT6 Avalanche outlines 24 January 2018, EnviDat [data set], https://doi.org/10.16904/envidat.77, 2019. a, b, c, d
Hafner, E. D. and Bühler, Y.: SPOT6 Avalanche outlines 16 January 2019,
EnviDat [data set], https://doi.org/10.16904/envidat.235, 2021. a, b, c, d
Hamar, J. B., Salberg, A.-B., and Ardelean, F.: Automatic detection and mapping
of avalanches in SAR images, in: 2016 IEEE International Geoscience and
Remote Sensing Symposium (IGARSS), 689–692,
https://doi.org/10.1109/IGARSS.2016.7729173, 2016. a
He, K., Zhang, X., Ren, S., and Sun, J.: Deep Residual Learning for Image
Recognition, in: 2016 IEEE Conference on Computer Vision and Pattern
Recognition (CVPR), pp. 770–778, https://doi.org/10.1109/CVPR.2016.90, 2016. a, b
Hoffer, E., Ben-Nun, T., Hubara, I., Giladi, N., Hoefler, T., and Soudry, D.:
Augment your batch: better training with larger batches, arXiv, https://doi.org/0.48550/ARXIV.1901.09335, 2019. a
Karbou, F., Coléou, C., Lefort, M., Deschatres, M., Eckert, N., Martin, R.,
Charvet, G., and Dufour, A.: Monitoring avalanche debris in the French
mountains using SAR observations from Sentinel-1 satellites,
International Snow Science Workshop ISSW, Innsbruck, pp. 344–347, 2018. a
Kingma, D. P. and Ba, J.: Adam: A Method for Stochastic Optimization, 2017. a
Kingma, D. P. and Welling, M.: An Introduction to Variational Autoencoders,
CoRR, abs/1906.02691, http://arxiv.org/abs/1906.02691 (last access: 22 August 2022), 2019. a
Korzeniowska, K., Bühler, Y., Marty, M., and Korup, O.: Regional snow-avalanche detection using object-based image analysis of near-infrared aerial imagery, Nat. Hazards Earth Syst. Sci., 17, 1823–1836, https://doi.org/10.5194/nhess-17-1823-2017, 2017. a, b
Lato, M. J., Frauenfelder, R., and Bühler, Y.: Automated detection of snow avalanche deposits: segmentation and classification of optical remote sensing imagery, Nat. Hazards Earth Syst. Sci., 12, 2893–2906, https://doi.org/10.5194/nhess-12-2893-2012, 2012. a, b
Ma, L., Liu, Y., Zhang, X., Ye, Y., Yin, G., and Johnson, B. A.: Deep learning
in remote sensing applications: A meta-analysis and review, ISPRS J. Photogramm., 152, 166–177,
https://doi.org/10.1016/j.isprsjprs.2019.04.015, 2019. a
Meister, R.: Country-wide Avalanche Warning in Switzerland, International
Snow Science Workshop ISSW, Snowbird, Utah, USA, 58–71, 1994. a
OpenTopography: Shuttle Radar Topography Mission (SRTM) Global, OpenTopography,
https://doi.org/10.5069/G9445JDF, 2013. a
Paul, F., Barrand, N., Baumann, S., Berthier, E., Bolch, T., Casey, K., Frey,
H., Joshi, S., Konovalov, V., Le Bris, R., Mölg, N., Nosenko, G., Nuth, C., Pope, A., Racoviteanu, A., Rastner, P., Raup, B., Scharrer, K., Steffen, S., and Winsvold, So. H.: On the accuracy of
glacier outlines derived from remote-sensing data, Ann. Glaciol., 54,
171–182, https://doi.org/10.3189/2013AoG63A296, 2013. a
Prakash, N., Manconi, A., and Loew, S.: A new strategy to map landslides with a
generalized convolutional neural network, Sci. Rep.-UK, 11, 1–15,
2021. a
Robson, B. A., Bolch, T., MacDonell, S., Hölbling, D., Rastner, P., and
Schaffer, N.: Automated detection of rock glaciers using deep learning and
object-based image analysis, Remote Sens. Environ., 250, 112033,
https://doi.org/10.1016/j.rse.2020.112033, 2020. a
Rudolf-Miklau, F., Sauermoser, S., and Mears, A. (Eds.): The technical avalanche
protection handbook, Ernst & Sohn, Berlin, ISBN 978-3-433-03034-9, 2015. a
Simonyan, K. and Zisserman, A.: Very Deep Convolutional Networks for
Large-Scale Image Recognition, arXiv, https://doi.org/10.48550/arXiv.1409.1556, 2015. a, b
Sinha, S., Giffard-Roisin, S., Karbou, F., Deschatres, M., Karas, A., Eckert,
N., Coléou, C., and Monteleoni, C.: Can Avalanche Deposits be
Effectively Detected by Deep Learning on Sentinel-1 Satellite SAR
Images?, in: Climate Informatics, Paris, France,
https://hal.archives-ouvertes.fr/hal-02278230 (last access: 22 August 2022), 2019a. a
Sinha, S., Giffard-Roisin, S., Karbou, F., Deschatres, M., Karas, A., Eckert,
N., and Monteleoni, C.: Detecting Avalanche Deposits using Variational
Autoencoder on Sentinel-1 Satellite Imagery, in: NeurIPS 2019 Workshop:
Tackling Climate Change with Machine Learning NeurIPS workshop, Vancouver,
Canada, https://hal.archives-ouvertes.fr/hal-02318407 (last access: 22 August 2022), 2019b. a
Sun, K., Zhao, Y., Jiang, B., Cheng, T., Xiao, B., Liu, D., Mu, Y., Wang, X.,
Liu, W., and Wang, J.: High-Resolution Representations for Labeling Pixels
and Regions, ArXiv, https://doi.org/10.48550/ARXIV.1904.04514, 2019. a
swisstopo: swissALTI3D – Das hoch aufgelöste Terrainmodell der Schweiz, https://www.swisstopo.admin.ch/content/swisstopo-internet/de/geodata/height/alti3d/_jcr_content/contentPar/tabs_copy/items/dokumente/tabPar/downloadlist/downloadItems/846_1464690554132.download/swissALTI3D_detaillierte Produktinfo_DE_bf.pdf (last access: 20 August 2022),
2018. a
Trevethan, R.: Sensitivity, Specificity, and Predictive Values: Foundations,
Pliabilities, and Pitfalls in Research and Practice, Front. Pub.
He., 5, 307, https://doi.org/10.3389/fpubh.2017.00307, 2017. a
Waldeland, A. U., Reksten, J. H., and Salberg, A.-B.: Avalanche Detection in
SAR Images Using Deep Learning, in: IGARSS 2018–2018 IEEE International
Geoscience and Remote Sensing Symposium, 2386–2389,
https://doi.org/10.1109/IGARSS.2018.8517536, 2018. a
Wesselink, D. S., Malnes, E., Eckerstorfer, M., and Lindenbergh, R. C.:
Automatic detection of snow avalanche debris in central Svalbard using
C-band SAR data, Polar Res., 36, 1333236,
https://doi.org/10.1080/17518369.2017.1333236, 2017. a
WSL Institute for Snow and Avalanche Research SLF (Ed.): Avalanche Bulletin
Interpretation Guide, WSL Institute for Snow and Avalanche Research SLF,
Edition November 2021, 53 pp.,
https://www.slf.ch/files/user_upload/SLF/Lawinenbulletin_Schneesituation/Wissen_zum_Lawinenbulletin/Interpretationshilfe/Interpretationshilfe_EN.pdf (last access: 22 August 2022),
2021. a, b
Short summary
Knowing where avalanches occur is very important information for several disciplines, for example avalanche warning, hazard zonation and risk management. Satellite imagery can provide such data systematically over large regions. In our work we propose a machine learning model to automate the time-consuming manual mapping. Additionally, we investigate expert agreement for manual avalanche mapping, showing that our network is equally as good as the experts in identifying avalanches.
Knowing where avalanches occur is very important information for several disciplines, for...
