ASAndri Simeon

Andri Simeon

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Andri Simeon has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Reply on RC2

    by Pascal Edme, Cristina Pérez-Guillén, Alec van Herwijnen, Johannes Aichele, Andri Simeon, Patrick Paitz, Fabian Walter, Andreas Fichtner

    We present a novel method for near real-time snow avalanche detection using Distributed Acoustic Sensing (DAS). A ∼10 km long telecommunication cable permanently installed along the avalanche-prone Flüelapass road (Swiss Alps) was continuously monitored over a full winter. Avalanches, including events that did not physically reach the cable, were clearly recorded and confirmed with photographic evidence. To discriminate avalanches from anthropogenic signals, we introduce a dual-frequency short-term over long-term average attribute that produces coherent high-value spatio-temporal signatures for avalanches, while vehicles predominantly generate negative values with pronounced move-out. The workflow consists of (1) a quasi-instantaneous threshold-based trigger to detect onset time and location, followed by (2) a rapid waterfall image analysis to estimate event extent and invalidate traffic-induced alerts. The first step issues alerts with millisecond-scale latency and meter-scale spatial resolution. The second step introduces additional latency, as it requires the event to sufficiently develop in order to assess its spatio-temporal morphology and confirm or discard the initial trigger. Our system issued alerts only 4.5 ‰ of the time when the road pass was open (i.e. 2.5 hours over 23 days), demonstrating the robustness against traffic, and 0.36 ‰ of the time when the pass was closed (i.e. 55 minutes over 108 days). Among those, a total of 73 potential avalanches were identified, most of them occurring during three independently documented avalanche episodes. These findings demonstrate that DAS represents a viable and cost-effective solution for operational real-time avalanche monitoring, with potential applicability to broader natural hazard detection.

  • Open Access

    Reply on RC1

    by Pascal Edme, Cristina Pérez-Guillén, Alec van Herwijnen, Johannes Aichele, Andri Simeon, Patrick Paitz, Fabian Walter, Andreas Fichtner

    We present a novel method for near real-time snow avalanche detection using Distributed Acoustic Sensing (DAS). A ∼10 km long telecommunication cable permanently installed along the avalanche-prone Flüelapass road (Swiss Alps) was continuously monitored over a full winter. Avalanches, including events that did not physically reach the cable, were clearly recorded and confirmed with photographic evidence. To discriminate avalanches from anthropogenic signals, we introduce a dual-frequency short-term over long-term average attribute that produces coherent high-value spatio-temporal signatures for avalanches, while vehicles predominantly generate negative values with pronounced move-out. The workflow consists of (1) a quasi-instantaneous threshold-based trigger to detect onset time and location, followed by (2) a rapid waterfall image analysis to estimate event extent and invalidate traffic-induced alerts. The first step issues alerts with millisecond-scale latency and meter-scale spatial resolution. The second step introduces additional latency, as it requires the event to sufficiently develop in order to assess its spatio-temporal morphology and confirm or discard the initial trigger. Our system issued alerts only 4.5 ‰ of the time when the road pass was open (i.e. 2.5 hours over 23 days), demonstrating the robustness against traffic, and 0.36 ‰ of the time when the pass was closed (i.e. 55 minutes over 108 days). Among those, a total of 73 potential avalanches were identified, most of them occurring during three independently documented avalanche episodes. These findings demonstrate that DAS represents a viable and cost-effective solution for operational real-time avalanche monitoring, with potential applicability to broader natural hazard detection.

  • Open Access

    Comment on egusphere-2026-2373

    by Pascal Edme, Cristina Pérez-Guillén, Alec van Herwijnen, Johannes Aichele, Andri Simeon, Patrick Paitz, Fabian Walter, Andreas Fichtner

    We present a novel method for near real-time snow avalanche detection using Distributed Acoustic Sensing (DAS). A ∼10 km long telecommunication cable permanently installed along the avalanche-prone Flüelapass road (Swiss Alps) was continuously monitored over a full winter. Avalanches, including events that did not physically reach the cable, were clearly recorded and confirmed with photographic evidence. To discriminate avalanches from anthropogenic signals, we introduce a dual-frequency short-term over long-term average attribute that produces coherent high-value spatio-temporal signatures for avalanches, while vehicles predominantly generate negative values with pronounced move-out. The workflow consists of (1) a quasi-instantaneous threshold-based trigger to detect onset time and location, followed by (2) a rapid waterfall image analysis to estimate event extent and invalidate traffic-induced alerts. The first step issues alerts with millisecond-scale latency and meter-scale spatial resolution. The second step introduces additional latency, as it requires the event to sufficiently develop in order to assess its spatio-temporal morphology and confirm or discard the initial trigger. Our system issued alerts only 4.5 ‰ of the time when the road pass was open (i.e. 2.5 hours over 23 days), demonstrating the robustness against traffic, and 0.36 ‰ of the time when the pass was closed (i.e. 55 minutes over 108 days). Among those, a total of 73 potential avalanches were identified, most of them occurring during three independently documented avalanche episodes. These findings demonstrate that DAS represents a viable and cost-effective solution for operational real-time avalanche monitoring, with potential applicability to broader natural hazard detection.

  • Open Access

    Method for near real-time detection of snow avalanches using Distributed Acoustic Sensing

    by Pascal Edme, Cristina Pérez-Guillén, Alec van Herwijnen, Johannes Aichele, Andri Simeon, Patrick Paitz, Fabian Walter, Andreas Fichtner

    We present a novel method for near real-time snow avalanche detection using Distributed Acoustic Sensing (DAS). A ∼10 km long telecommunication cable permanently installed along the avalanche-prone Flüelapass road (Swiss Alps) was continuously monitored over a full winter. Avalanches, including events that did not physically reach the cable, were clearly recorded and confirmed with photographic evidence. To discriminate avalanches from anthropogenic signals, we introduce a dual-frequency short-term over long-term average attribute that produces coherent high-value spatio-temporal signatures for avalanches, while vehicles predominantly generate negative values with pronounced move-out. The workflow consists of (1) a quasi-instantaneous threshold-based trigger to detect onset time and location, followed by (2) a rapid waterfall image analysis to estimate event extent and invalidate traffic-induced alerts. The first step issues alerts with millisecond-scale latency and meter-scale spatial resolution. The second step introduces additional latency, as it requires the event to sufficiently develop in order to assess its spatio-temporal morphology and confirm or discard the initial trigger. Our system issued alerts only 4.5 ‰ of the time when the road pass was open (i.e. 2.5 hours over 23 days), demonstrating the robustness against traffic, and 0.36 ‰ of the time when the pass was closed (i.e. 55 minutes over 108 days). Among those, a total of 73 potential avalanches were identified, most of them occurring during three independently documented avalanche episodes. These findings demonstrate that DAS represents a viable and cost-effective solution for operational real-time avalanche monitoring, with potential applicability to broader natural hazard detection.

  • Open Access

    Self-supervised learning for automated avalanche detection from seismic and infrasound data

    by Andri Simeon, Alec van Herwijnen, Johannes Aichele, Michele Volpi, Betty Sovilla, Pierre Huguenin, Johan Gaume, Andreas Fichtner, Pascal Edme, Cristina Pérez-Guillén

    Snow avalanches are among the deadliest natural hazards in mountainous regions. Yet avalanche activity is often still documented manually, and accurate avalanche release times are mostly missing. Automated monitoring systems equipped with seismic and infrasound sensors, combined with detection algorithms, could help record avalanche occurrences and provide accurate data on release time, size, and type. This comprehensive data on avalanche activity is indispensable for improving and validating avalanche forecasts and for implementing mitigation measures. At the Vallée de la Sionne (VDLS) test site in Switzerland, a combination of avalanche monitoring systems has been deployed for over two decades, including radars, cameras, seismic and infrasound stations. Additionally, avalanche researchers have manually documented and verified most avalanche events over the past 14 winter seasons to compile a unique avalanche catalogue.To facilitate and automate avalanche detection, we aimed to implement two deep learning-based methods that scan continuous seismic and infrasound data separately in (near) real-time to detect and classify avalanche signals. Therefore, we leveraged the large volume of continuous data collected every winter at VDLS by adopting concepts from recent, powerful language models. Specifically, we pre-trained transformer networks in a self-supervised manner (i.e. without using expert labels) on a wide variety of signals mined from continuous seismic and infrasound data streams. The models receive fixed-length waveforms as input, partition them into sequential patches and compute patch-wise spectrograms. By training the models to reconstruct a portion of randomly masked patches, they learn to extract meaningful representations from the data, achieving silhouette scores of up to 0.6. This indicates good separability between avalanche and non-avalanche signals. Thus, these representations can later be used to automatically detect avalanches by fine-tuning a classifier on top. Moreover, combining predictions from the seismic and infrasound models has the potential to further improve (near) real-time avalanche detection.

  • Open Access

    Tracking avalanche nucleation in situ – A real-world experiment with embedded fibre optics

    by Johannes Aichele, Pascal Edme, Simeon Andri, van Herwijnen Alec, Sovilla Betty, Huguenin Pierre, Gaume Johan, Fichtner Andreas, Perez Cristina

    Alpine mass movements pose a considerable risk to people and infrastructure. Snow avalanches pose a particularly prominent risk due to their widespread occurrence and potential catastrophic consequences. While significant advances have been made over the last decades to forecast avalanches, the spatio-temporal conditions that lead to avalanche release remain elusive. In fact, the problem of avalanche release is comparable to earthquake nucleation: An earthquake rupture and the fracture of a snow slab avalanche share the same underlying physics. As in the case of earthquakes, the observation of the rupture process of avalanches is limited to sensors in the farfield, such as seismic and infrasound arrays, and optical and radar methods, as well as laboratory experiments. While laboratory observations, far-field measurements on experimental test sites, and numerical simulations allow us to paint an ever more precise picture of the physics of avalanche nucleation, in situ measurements of crack propagation in the near-field of a real-world avalanche remain inaccessible so far.How to perform such a measurement, which would not only allow us to understand the underlying physics better, but also might open new pathways to measuring precursory processes?We designed a field experiment tackling the in situ observation of crack propagation and precursory processes. Leveraging a dense grid of seismic sensors we aim to capture the deformation in the nearfield prior, during, and after avalanche nucleation with Distributed Acoustic Sensing (DAS). In total, more than 3 km of fibreoptic cable were pulled from the top into the the steep slopes of Brämabuel near Davos (Switzerland) in autumn 2025. The cables were installed prior and during the first significant snowfall of the season, on known avalanche release slopes. Hence, they are placed centimeters below the expected weak layers, thus effectively making them an embedded strain sensor in a real-world experiment. To increase the probability of capturing the nucleation process, our DAS interrogator continuously samples at 2 m and 200 Hz, with the possibility to increase sampling rates to 1000 Hz for periods of increased avalanche risk. This continuous high spatio-temporal sampling will allow us to differentiate naturally and human-triggered slabs; in fact, skiers are easily identified in the data. In this talk, we will report on the first measurements of the 2025/2026 season and highlight the monitoring potential of our installation

  • Open Access

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

    by Andri Simeon, Cristina Pérez-Guillén, Michele Volpi, Christine Seupel, Alec van Herwijnen

    Monitoring snow avalanche activity is essential for operational avalanche forecasting and the successful implementation of mitigation measures to ensure safety in mountain regions. To facilitate and automate the monitoring process, avalanche detection systems equipped with seismic sensors can provide a cost-effective solution. Still, automatically distinguishing avalanche signals from other sources in seismic data remains challenging. This is mainly due to the complexity of seismic signals generated by avalanches, the complex signal transmission through the ground, the relatively rare occurrence of avalanches, and the presence of multiple sources in seismic data. To study and interpret the variety of these signals, we compiled a dataset of seismograms recorded with an array of five seismometers installed in an avalanche study site above Davos, Switzerland. For the winter seasons of 2020–2021 and 2021–2022, this dataset comprised 84 avalanches and 828 noise (unrelated to avalanches) events. An approach to automate the detection of avalanches in seismic data is by applying machine learning methods. So far, research in this area has mainly focused on extracting domain-specific signal attributes as input features for statistical models. In contrast, we propose a novel application of representation learning from seismograms using autoencoder models to automatically extract features from 10 s seismic signals of snow avalanches. On top of that, we applied random forest classifiers to evaluate whether these features facilitate the detection of avalanches. Concretely, we trained one random forest classifier each on a set of expert-engineered seismic attributes (baseline), temporal autoencoder features and spectral autoencoder features. The classifiers achieved an avalanche recall of 0.67 (±0.00) (baseline), 0.71 (±0.02) (temporal autoencoder) and 0.70 (±0.01) (spectral autoencoder) and macro average f1-scores of 0.78 (±0.00) (baseline), 0.70 (±0.01) (temporal autoencoder) and 0.77 (±0.01) (spectral autoencoder). The developed approach could be potentially used as an operational, near real-time avalanche detection system. Yet, the relatively high number of false alarms still needs further implementation of the current automated seismic classification algorithms for effective avalanche detection.


  • Open Access

    In Situ Snow Avalanche Monitoring and Characterization

    by Johannes Aichele, Andri Simeon, Alec van Herwijnen, Michele Volpi, Betty Sovilla, Pierre Huguenin, Johan Gaume, Andreas Fichtner, Cristina Pérez, Pascal Edme

    Snow avalanches in alpine regions pose significant risks to people and infrastructure. To mitigate these risks, early warning systems based on seismic sensors can provide real-time data on avalanche activity, crucial for avalanche forecasting. Additionally, forecasting and risk management require a thorough understanding of avalanche processes. However, avalanche release mechanism and dynamics are only partly understood due to the multi-physics processes involved, spanning from dynamic crack propagation to granular and turbulent flow. Traditional seismic monitoring systems have relied on far-field signals or sparse point measurements along the flow path, limiting our ability to fully capture the processes at play. On the one hand, this makes investigating avalanche release very challenging. For example, identifying dynamic fracture propagation through seismic sensors in the near-field is crucial to advance real-time avalanche prediction. On the other hand, far-field measures are often insufficient for effective risk mitigation. Mitigation requires a thorough characterization of avalanche flow regimes and entrainment throughout the entire heterogeneous avalanche path. To address these challenges, we deployed a unique dense array of seismic sensors at the avalanche test site Vallée de la Sionne, Valais, Switzerland, covering the release zone to the runout area. The setup consists of a Distributed Acoustic Sensing (DAS) system interrogating 14 parallel downslope fiber optic lines (~100 m in length, spaced by 2 m) within the release zone at ~2400 m a.s.l., and a quasi linear fiber optic cable down to ~1500 m a.s.l., which follows the avalanche track and covers the entire runout corridor. The ~4 km long cable is embedded beneath the first snow layer, providing innovative in situ measurements of seismic and aseismic signals in the near field. Sampled at 400 Hz, at every 2 m with 4 m gauge length, this deployment represents one of the most comprehensive in situ avalanche monitoring efforts to date. We present preliminary results from the 2024/2025 season. The avalanches act as moving seismic sources whose far and near-field seismic signals allow us to characterize the spatio-temporal avalanche evolution from release to arrest. We are able to differentiate different flow regimes along the avalanche path, and the grid will potentially capture fracture propagation in the release zone. Our DAS derived information will be benchmarked against concurrent measurements at Vallée de la Sionne which include optical and radar measurements. This makes our setup the ideal field experiment to advance avalanche characterization and lay the groundwork for real-time hazard monitoring with fibre optic cables.


  • Open Access

    Development of a deep learning-based seismic waveform classifier to automatically detect snow avalanches.

    by Andri Simeon, Alec van Herwijnen, Johannes Aichele, Michele Volpi, Betty Sovilla, Pierre Huguenin, Johan Gaume, Andreas Fichtner, Pascal Edme, Cristina Pérez-Guillén

    Avalanche forecasters mostly rely on human observations of avalanche activity, but these reports are typically incomplete during periods of poor visibility, delayed, and not automated. Automated detection systems equipped with seismic sensors can improve monitoring efficiency, providing accurate avalanche data to support avalanche forecasting, regardless of visibility and weather conditions. Additionally, such systems could be implemented as early warning tools to enhance safety measures in mountain regions. While seismic detection systems have been widely used for avalanche monitoring, there is currently no automated method to reliably identify signals originating from avalanches. To address this, we developed a deep neural network to automatically detect avalanches in real-time continuous seismic recordings. This model was trained using seismic data collected over 13 winter seasons at the avalanche test site of Vallée de la Sionne, in Switzerland. Avalanches of varying sizes and paths are monitored using four seismometers strategically placed within and outside the avalanche path. The system simultaneously acquires continuous seismic data and event alarms. The alarms are based on amplitude thresholds recorded by the two seismometers near frequent release zones. While these alarms provide preliminary insights into avalanche activity, they require manual verification to filter out false alarms caused by events such as earthquakes or other unknown sources. To overcome this limitation, we trained an end-to-end deep learning-based seismic waveform classifier on normalized, 40-second signal snippets extracted from the event database. The model architecture includes a convolutional encoder, a convolutional feature extractor with attention mechanisms, and a fully connected classification head. The network reliably distinguishes between avalanches and non-avalanche signals, achieving an accuracy of 0.97 on held-out events from the 2022/23 and 2023/24 winter seasons. The model was also deployed during the latest winter season to classify signals in near real-time, providing daily avalanche detection rates and demonstrating its feasibility as an automatic detection system. Finally, we plan to investigate the transferability of the classifier to seismic data collected by a distributed acoustic sensing (DAS) system installed on the avalanche test site, exploring its potential for broader applications.

  • Open Access

    Assessing avalanche activity in seismic data with modern machine learning methods.

    by Andri Simeon, Cristina Pérez-Guillén, Michele Volpi, Christine Seupel, Alec van Herwijnen

    Monitoring snow avalanche activity is essential for operational avalanche forecasting and the successful implementation of mitigation measures to ensure safety in mountain regions. To facilitate and automate the monitoring process, avalanche detection systems equipped with seismic sensors provide a cost-effective solution. Still, automatically differentiating avalanche signals from other sources in seismic data remains rather challenging. This is mainly due to the complexity of the seismic signals generated by avalanches, the relatively rare occurrence of avalanches and the presence of multiple sources in the continuous recordings.To discriminate avalanches from other sources in the continuous seismic recordings, we test three random forest classifiers using two feature sets extracted with two autoencoders and a set of 57 statistical features. We extract these features from 10s windows of the seismograms recorded with an array of five seismometers installed in Davos, Switzerland. The statistical feature set includes waveform, spectral and spectrogram attributes. The first autoencoder is composed of convolutional layers and a long short-term memory unit. This neuronal network automatically extracts 64 features from the raw waveform signal. The second autoencoder applies a sequence of fully connected layers to extract the same number of features from the spectrum of the signals. We assess the performance of each classifier and compare the results. To improve the predictive performance of the seismic system, we employ different post-processing, e.g. adaption of classification thresholds and ensembling the predictions from the three classifiers. The final model is tested with the continuous seismic data of the last winter season to potentially be used as an operational, near-real-time detection system.