Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 20, 2025Geoscientific model developmentOpen Access

Autoencoder-based feature extraction for the automatic detection of snow avalanches in seismic data

View Full Paper
Ask AI
Bookmark
Share

Authors

ASAndri SimeonCGCristina Pérez GuillénMVMichele Volpi

Discussion

Loading...

Member takes

Overview

Machine learning improves avalanche detection in seismic data, suggesting better monitoring and mitigation measures.

Key Points

  • This research aims to automate avalanche detection using machine learning applied to seismic data.
  • Dataset compiled from 84 avalanches and 828 noise events using five seismometers in Davos.
  • Autoencoder models applied for feature extraction from 10 s seismic signals.
  • Random forest classifiers evaluated the effectiveness of extracted features.
  • Achieved avalanche recall of 0.71 using temporal autoencoder features and 0.70 with spectral autoencoder features.
  • Baseline classifiers reached an avalanche recall of 0.67.
  • Developed approach shows potential for near real-time avalanche detection despite false alarms.

Cite This Study

Simeon et al. (2025) studied this question.

synapsesocial.com/papers/6924f07ac0ce034ddc34fe55https://doi.org/10.5194/gmd-18-8751-2025
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Autoencoder-based feature extraction for the automatic detection of snow avalanches in seismic data2024
  2. 2Assessing avalanche activity in seismic data with modern machine learning methods.2024
  3. 3Seismic signal characterization of snow avalanches using distributed acoustic sensing in Grasdalen, western Norway2025 · 4 citations
  4. 4Monitoring snow avalanches from SAR data with deep learning2025
  5. 5Decennial infrasonic array analysis of snow-avalanche activity and its weather forcing in Pennine Alps: implications for forecasting2024