Articles | Volume 25, issue 12
https://doi.org/10.5194/nhess-25-4863-2025
https://doi.org/10.5194/nhess-25-4863-2025
Research article
 | 
09 Dec 2025
Research article |  | 09 Dec 2025

Deep learning-based object detection on LiDAR-derived hillshade images: insights into grain size distribution and longitudinal sorting of debris flows

Paul E. Schmid, Jacob Hirschberg, Raffaele Spielmann, and Jordan Aaron

Related authors

Updating induced seismic hazard assessments during hydraulic stimulation experiments in underground laboratories: workflow and limitations
Valentin Samuel Gischig, Antonio Pio Rinaldi, Andres Alcolea, Falko Bethman, Marco Broccardo, Kai Bröker, Raymi Castilla, Federico Ciardo, Victor Clasen Repollés, Virginie Durand, Nima Gholizadeh Doonechaly, Marian Hertrich, Rebecca Hochreutener, Philipp Kästli, Dimitrios Karvounis, Xiaodong Ma, Men-Andrin Meier, Peter Meier, Maria Mesimeri, Arnaud Mignan, Anne Obermann, Katrin Plenkers, Martina Rosskopf, Francisco Serbeto, Paul Selvadurai, Alexis Shakas, Linus Villiger, Quinn Wenning, Alba Zappone, Jordan Aaron, Hansruedi Maurer, Domenico Giardini, and Stefan Wiemer
Solid Earth, 16, 1153–1180, https://doi.org/10.5194/se-16-1153-2025,https://doi.org/10.5194/se-16-1153-2025, 2025
Short summary
Dynamic Analysis of Flowlike Landslides at Brienz/Brinzauls, Graubünden, Switzerland
Jordan Aaron, Larissa de Palézieux, Jake Langham, Valentin Gischig, Reto Thoeny, and Daniel Figi
EGUsphere, https://doi.org/10.5194/egusphere-2025-2788,https://doi.org/10.5194/egusphere-2025-2788, 2025
Short summary
Evaluating methods for debris-flow prediction based on rainfall in an Alpine catchment
Jacob Hirschberg, Alexandre Badoux, Brian W. McArdell, Elena Leonarduzzi, and Peter Molnar
Nat. Hazards Earth Syst. Sci., 21, 2773–2789, https://doi.org/10.5194/nhess-21-2773-2021,https://doi.org/10.5194/nhess-21-2773-2021, 2021
Short summary

Cited articles

Aaron, J., Spielmann, R., McArdell, B. W., and Graf, C.: High-Frequency 3D LiDAR Measurements of a Debris Flow: A Novel Method to Investigate the Dynamics of Full-Scale Events in the Field, Geophysical Research Letters, 50, e2022GL102373, https://doi.org/10.1029/2022GL102373, 2023. a, b, c, d, e, f, g
Aaron, J., Langham, J., Spielmann, R., Hirschberg, J., McArdell, B., Boss, S., Johnson, C. G., and Gray, J. M. N. T.: Detailed Observations Reveal the Genesis and Dynamics of Destructive Debris-Flow Surges, Communications Earth & Environment, 6, 556, https://doi.org/10.1038/s43247-025-02488-7, 2025. a, b, c, d, e, f, g, h, i
Aaron, J., Langham, J., Spielmann, R., Hirschberg, J., McArdell, B. W., Boss, S, Johnson, C., and Gray, N.: Data for Detailed observations reveal the genesis and dynamics of destructive debris-flow surges, ETH Research Collection [data set], https://doi.org/10.3929/ethz-b-000736836, 2025. a, b
Åberg, A., Aaron, J., McArdell, B. W., Kirchner, J., de Haas, T., and Hirschberg, J.: Field Validation of the Superelevation Method for Debris-Flow Velocity Estimation Using High-Resolution Lidar and UAV Data, Journal of Geophysical Research: Earth Surface, 129, e2024JF007857, https://doi.org/10.1029/2024JF007857, 2024. a, b
Aharon, N., Orfaig, R., and Bobrovsky, B.-Z.: BoT-SORT: Robust Associations Multi-Pedestrian Tracking, arXiv [preprint], https://doi.org/10.48550/arXiv.2206.14651, 2022. a
Download
Short summary
Debris flows are fast-moving water-sediment mixtures in steep channels, posing risks to infrastructure and lives. Traditional analysis is slow and labor-intensive. This study presents a method using laserscanners and deep learning to detect and track moving objects during active events. By converting three-dimensional data to two-dimensional images, it enables fast, accurate measurement of object speed and size. This improves debris-flow monitoring, enhancing hazard understanding and mitigation.
Share
Altmetrics
Final-revised paper
Preprint