arXiv subjects

Jannes Münchmeyer

Publications and source records attributed to Jannes Münchmeyer.

18 recordsLinked to original sources

arXiv2026

SeisBench DAS: A machine learning framework for Distributed Acoustic Sensing

Fibre optic sensing, such as distributed acoustic sensing (DAS), has become a widespread technology for geophysical studies. To process the large-scale datasets produced by DAS, several machine learning methods have been proposed. However, without standardization of data and models, these methods lack comparability and interoperability. This introduces a gap between model developers and practitioners analyzing DAS data and inhibits adoption of deep learning for DAS. To address these limitations, here we present SeisBench DAS, an extension to the SeisBench library for machine learning in seismology. SeisBench DAS defines standard formats for DAS benchmark datasets, including standardised metadata and labels, and DAS models. It builds on the xdas framework for data ingestion and virtual array handling, and on PyTorch for reading and applying the machine learning models. Importantly, SeisBench provides an engine to efficiently apply deep learning models to diverse formats of DAS data, bridging the gap between model developers and practitioners. SeisBench DAS is designed as an open and extensible framework, allowing to easily incorporate future developments in deep learning for DAS.

physics.geo-ph↗

arXiv2025

Towards End-to-End Earthquake Monitoring Using a Multitask Deep Learning Model

Seismic waveforms contain rich information about earthquake processes, making effective data analysis crucial for earthquake monitoring, source characterization, and seismic hazard assessment. With rapid developments in deep learning, the state-of-the-art approach in artificial intelligence, many neural network models have been developed to enhance earthquake monitoring tasks, such as earthquake detection, phase picking, and phase association. However, most current efforts focus on developing separate models for each specific task, leaving the potential of an end-to-end framework relatively unexplored. To address this gap, we extend an existing phase picking model, PhaseNet, to create a multitask framework. This extended model, PhaseNet+, simultaneously performs phase arrival-time picking, first-motion polarity determination, and phase association. The outputs from these perception-based models can then be processed by specialized physics-based algorithms to accurately determine earthquake location and focal mechanism. The multitask approach is not limited to the PhaseNet model and can be applied to other state-of-the-art phase picking models, ultimately improving seismic monitoring through a more unified and efficient approach.

physics.geo-ph↗

arXiv2025

A Global-scale Database of Seismic Phases from Cloud-based Picking at Petabyte Scale

We present the first global-scale database of 4.3 billion P- and S-wave picks extracted from 1.3 PB continuous seismic data via a cloud-native workflow. Using cloud computing services on Amazon Web Services, we launched ~145,000 containerized jobs on continuous records from 47,354 stations spanning 2002-2025, completing in under three days. Phase arrivals were identified with a deep learning model, PhaseNet, through an open-source Python ecosystem for deep learning, SeisBench. To visualize and gain a global understanding of these picks, we present preliminary results about pick time series revealing Omori-law aftershock decay, seasonal variations linked to noise levels, and dense regional coverage that will enhance earthquake catalogs and machine-learning datasets. We provide all picks in a publicly queryable database, providing a powerful resource for researchers studying seismicity around the world. This report provides insights into the database and the underlying workflow, demonstrating the feasibility of petabyte-scale seismic data mining on the cloud and of providing intelligent data products to the community in an automated manner.

physics.geo-ph↗

arXiv2025

A systematic search for tectonic tremor and low-frequency earthquakes in the Atacama segment of the Chilean subduction zone (24$^\circ$S-31$^\circ$S) turns up empty

Subduction megathrusts release stress not only seismically through earthquakes, but also through creep and transient slow deformation, called slow slip events (SSEs). Understanding the interplay between fast and slow slip is essential for illuminating the deformation processes on the subduction interface. The Chilean subduction margin, while one of the most seismically active regions worldwide, has few reports of SSEs. Furthermore, there are no comprehensive reports of tectonic tremors or low-frequency earthquakes (LFEs), seismic signals typically accompanying SSEs, tracking deformation at small spatial and temporal scales. Here, we perform a systematic search for tectonic tremors and LFEs in the Atacama segment in Northern Chile, a region hosting both shallow and deep SSEs. Using dense seismic networks, we investigate 3.5 years between November 2020 and February 2024. Due to the network geometry, we focus on deep tremor and LFEs. We apply two orthogonal methods, envelope correlation for tremor search and deep learning detection for LFEs, to generate initial catalogs. To validate the potential detections, we use clustering, matched filtering, heuristics, and extensive manual inspection. While our initial search provides numerous candidates, after verification, we find no evidence for tectonic tremor or LFEs in the region. In contrast, our approaches successfully recover tremors and LFEs in two reference regions outside Chile with known tremor and LFE activity. Our observations show that tremors and LFEs in Northern Chile are either of lower moment rate than in other regions, have substantially longer recurrence rates, or are absent altogether, potentially due to the cold subduction.

physics.geo-ph↗

arXiv2025

Characterising the Atacama segment of the Chile subduction margin (24°S-31°S) with >165,000 earthquakes

The Atacama segment in Northern Chile (24°S to 31°S) is a mature seismic gap with no major event (Mw>8) since 1922. In addition to regular seismicity, around the subducting Copiapó ridge, the region hosts seismic swarms, and shallow and deep slow slip events. To characterize the fine structure of this seismic gap and its seismic-aseismic interplay, we instrumented the region with almost 200 seismic and geodetic stations. Using machine learning, we derived a dense, high-resolution seismicity catalog, encompassing over 165,000 events with double-difference relocated hypocenters. Our catalog details the outer rise, interface, intraslab, crustal and mantle wedge seismicity. We infer a detailed slab geometry, showing that the flat slab is dipping towards the south with a narrower extent along dip. The slab geometry controls the intraslab seismicity, with cross-cutting activity in the region of highest bending and a downdip limit around 105 km slab depth. Our catalogue exhibits significant seismicity in the mantle wedge upper corner between 28°S and 31°S, highlighting the brittle behavior of the cold nose. On the subduction interface, interplate locking controls the updip end of the seismicity, with seismicity extending closer to the trench in low-locking areas. On fine scales, resolved by relative uncertainties below 50 m, the subduction interface has a complex 3D structure, showing a fractal distribution of seismic patches down to a scale of tens of meters. Our results provide a holistic view of this complex subduction zone, while at the same time giving insights into fine-scale structures and processes.

physics.geo-ph↗

arXiv2025

Benchmarking seismic phase associators: Insights from synthetic scenarios

Reliable seismicity catalogs are essential for seismology. Following phase picking, phase association groups arrivals into sets with consistent origins (i.e., events), determines event counts, and identifies outlier picks. To handle the substantial increase in the quantity of seismic phase picks from improved picking methods and larger deployments, several novel phase associators have recently been proposed. This study presents a detailed benchmark analysis of five seismic phase associators, including classical and machine learning-based approaches: PhaseLink, REAL, GaMMA, GENIE, and PyOcto. We use synthetic datasets mimicking real seismicity characteristics in crustal and subduction zone scenarios. We evaluate performance for different conditions, including low- and high-noise environments, out-of-network events, very high event rates, and variable station density. The results reveal notable differences in precision, recall, and computational efficiency. GENIE and PyOcto demonstrate robust performance, with almost perfect performance for most scenarios. Only for the most challenging conditions with high noise levels and event rates, performance drops but still maintains F1 scores above 0.8. PhaseLink's performance declines with noise and event density, particularly in subduction zones, dropping to near zero in the most complex cases. GaMMA outperforms PhaseLink but struggles with accuracy and scalability in high-noise, high-density scenarios. REAL performs reasonably but loses recall under extreme conditions. PyOcto and PhaseLink show the quickest runtimes for smaller-scale datasets, while REAL and GENIE are more than an order of magnitude slower for these cases. At the highest pick rates, GENIE's runtime disadvantage diminishes, matching PyOcto and scaling effectively. Our results can guide practitioners compiling seismicity catalogs and developers designing novel associators.

physics.geo-ph↗

arXiv2024

Seismic swarms unveil the mechanisms driving shallow slow slip dynamics in the Copiapó ridge, Northern Chile

Like earthquakes, slow slip events release elastic energy stored on faults. Yet, the mechanisms behind slow slip instability and its relationship with seismicity are debated. Here, we use a seismo-geodetic deployment to document a shallow slow slip event (SSE) in 2023 on the Chile subduction. We observe dense, migrating seismic swarms accompanying the SSE, comprised of interface activity and upper plate splay faulting. Our observations suggest that the slow slip initiation is driven by structurally-confined fluid overpressure in the fluid-rich surroundings of a subducted seamount. This is consistent with an observed acceleration and expansion of the SSE after a $M_L=5.3$ earthquake likely triggering an increase in interface permeability. Historical earthquake swarms highlight the persistent structural control and recurrent nature of such slow slip events. Our observations provide insight into the interactions between slow slip and seismicity, suggesting they are controlled by creep on a fluid-infiltrated fault with fractally distributed asperities.

physics.geo-ph↗

arXiv2024

SeisLM: a Foundation Model for Seismic Waveforms

We introduce the Seismic Language Model (SeisLM), a foundational model designed to analyze seismic waveforms -- signals generated by Earth's vibrations such as the ones originating from earthquakes. SeisLM is pretrained on a large collection of open-source seismic datasets using a self-supervised contrastive loss, akin to BERT in language modeling. This approach allows the model to learn general seismic waveform patterns from unlabeled data without being tied to specific downstream tasks. When fine-tuned, SeisLM excels in seismological tasks like event detection, phase-picking, onset time regression, and foreshock-aftershock classification. The code has been made publicly available on https://github.com/liutianlin0121/seisLM.

physics.geo-ph↗

arXiv2023

Deep learning detects uncataloged low-frequency earthquakes across regions

Documenting the interplay between slow deformation and seismic ruptures is essential to understand the physics of earthquakes nucleation. However, slow deformation is often difficult to detect and characterize. The most pervasive seismic markers of slow slip are low-frequency earthquakes (LFEs) that allow resolving deformations at minute-scale. Detecting LFEs is hard, due to their emergent onsets and low signal-to-noise ratios, usually requiring region-specific template matching approaches. These approaches suffer from low flexibility and might miss LFEs as they are constrained to sources identified a priori. Here, we develop a deep learning-based workflow for LFE detection, modeled after classical earthquake detection with phase picking, phase association, and location. Across three regions with known LFE activity, we detect LFEs from both previously cataloged sources and newly identified sources. Furthermore, the approach is transferable across regions, enabling systematic studies of LFEs in regions without known LFE activity.

physics.geo-ph↗

arXiv2023

PyOcto: A high-throughput seismic phase associator

Seismic phase association is an essential task for characterising seismicity: given a collection of phase picks, identify all seismic events in the data. In recent years, machine learning pickers have lead to a rapid growth in the number of seismic phase picks. Even though new associators have been suggested, these suffer from long runtimes and sensitivity issues when faced with dense seismic sequences. Here we introduce PyOcto, a novel phase associator tackling these issues. PyOcto uses 4D space-time partitioning and can employ homogeneous and 1D velocity models. We benchmark PyOcto against popular state of the art associators on two synthetic scenarios and a real, dense aftershock sequence. PyOcto consistently achieves detection sensitivities on par or above current algorithms. Furthermore, its runtime is consistently at least 10 times lower, with many scenarios reaching speedup factors above 50. On the challenging 2014 Iquique earthquake sequence, PyOcto achieves excellent detection capability while maintaining a speedup factor of at least 70 against the other models. PyOcto is available as an open source tool for Python on Github and through PyPI.

physics.geo-ph↗

arXiv2023

PickBlue: Seismic phase picking for ocean bottom seismometers with deep learning

Detecting phase arrivals and pinpointing the arrival times of seismic phases in seismograms is crucial for many seismological analysis workflows. For land station data machine learning methods have already found widespread adoption. However, deep learning approaches are not yet commonly applied to ocean bottom data due to a lack of appropriate training data and models. Here, we compiled an extensive and labeled ocean bottom seismometer dataset from 15 deployments in different tectonic settings, comprising ~90,000 P and ~63,000 S manual picks from 13,190 events and 355 stations. We propose PickBlue, an adaptation ot the two popular deep learning networks EQTransformer and PhaseNet. PickBlue joint processes three seismometer recordings in conjunction with a hydrophone component and is trained with the waveforms in the new database. The performance is enhanced by employing transfer learning, where initial weights are derived from models trained with land earthquake data. PickBlue significantly outperforms neural networks trained with land stations and models trained without hydrophone data. The model achieves a mean absolute deviation (MAD) of 0.05 s for P waves and 0.12 s for S waves. We integrate our dataset and trained models into SeisBench to enable an easy and direct application in future deployments.

physics.geo-ph↗

arXiv2022

A probabilistic view on rupture predictability: all earthquakes evolve similarly

Ruptures of the largest earthquakes can last between a few seconds and several minutes. An early assessment of the final earthquake size is essential for early warning systems. However, it is still unclear when in the rupture history this final size can be predicted. Here we introduce a probabilistic view of rupture evolution - how likely is the event to become large - allowing for a clear and well-founded answer with implications for earthquake physics and early warning. We apply our approach to real time magnitude estimation based on either moment rate functions or broadband teleseismic P arrivals. In both cases, we find strong and principled evidence against early rupture predictability because differentiation between differently sized ruptures only occurs once half of the rupture has been observed. Even then, it is impossible to foresee future asperities. Our results hint towards a universal initiation behavior for small and large ruptures.

physics.geo-ph↗

arXiv2021

SeisBench -- A Toolbox for Machine Learning in Seismology

Machine Learning (ML) methods have seen widespread adoption in seismology in recent years. The ability of these techniques to efficiently infer the statistical properties of large datasets often provides significant improvements over traditional techniques. With the entire spectrum of seismological tasks, e.g., seismic picking, source property estimation, ground motion prediction, hypocentre determination; among others, now incorporating ML approaches, numerous models are emerging as these techniques are further adopted within seismology. To evaluate these algorithms, quality controlled benchmark datasets that contain representative class distributions are vital. In addition to this, models require implementation through a common framework to facilitate comparison. Accessing these various benchmark datasets for training and implementing the standardization of models is currently a time-consuming process, hindering further advancement of ML techniques within seismology. These development bottlenecks also affect "practitioners" seeking to deploy the latest models on seismic data, without having to necessarily learn entirely new ML frameworks to perform this task. We present SeisBench as a software package to tackle these issues. SeisBench is an open-source framework for deploying ML in seismology. SeisBench standardises access to both models and datasets, whilst also providing a range of common processing and data augmentation operations through the API. Through SeisBench, users can access several seismological ML models and benchmark datasets available in the literature via a single interface. SeisBench is built to be extensible, with community involvement encouraged to expand the package. Having such frameworks available for accessing leading ML models forms an essential tool for seismologists seeking to iterate and apply the next generation of ML techniques to seismic data.

physics.geo-ph↗

arXiv2021

Which picker fits my data? A quantitative evaluation of deep learning based seismic pickers

Seismic event detection and phase picking are the base of many seismological workflows. In recent years, several publications demonstrated that deep learning approaches significantly outperform classical approaches and even achieve human-like performance under certain circumstances. However, as most studies differ in the datasets and exact evaluation tasks studied, it is yet unclear how the different approaches compare to each other. Furthermore, there are no systematic studies how the models perform in a cross-domain scenario, i.e., when applied to data with different characteristics. Here, we address these questions by conducting a large-scale benchmark study. We compare six previously published deep learning models on eight datasets covering local to teleseismic distances and on three tasks: event detection, phase identification and onset time picking. Furthermore, we compare the results to a classical Baer-Kradolfer picker. Overall, we observe the best performance for EQTransformer, GPD and PhaseNet, with EQTransformer having a small advantage for teleseismic data. Furthermore, we conduct a cross-domain study, in which we analyze model performance on datasets they were not trained on. We show that trained models can be transferred between regions with only mild performance degradation, but not from regional to teleseismic data or vice versa. As deep learning for detection and picking is a rapidly evolving field, we ensured extensibility of our benchmark by building our code on standardized frameworks and making it openly accessible. This allows model developers to easily compare new models or evaluate performance on new datasets, beyond those presented here. Furthermore, we make all trained models available through the SeisBench framework, giving end-users an easy way to apply these models in seismological analysis.

physics.geo-ph↗

arXiv2021

Earthquake magnitude and location estimation from real time seismic waveforms with a transformer network

Precise real time estimates of earthquake magnitude and location are essential for early warning and rapid response. While recently multiple deep learning approaches for fast assessment of earthquakes have been proposed, they usually rely on either seismic records from a single station or from a fixed set of seismic stations. Here we introduce a new model for real-time magnitude and location estimation using the attention based transformer networks. Our approach incorporates waveforms from a dynamically varying set of stations and outperforms deep learning baselines in both magnitude and location estimation performance. Furthermore, it outperforms a classical magnitude estimation algorithm considerably and shows promising performance in comparison to a classical localization algorithm. In this work, we furthermore conduct a comprehensive study of the requirements on training data, the training procedures and the typical failure modes using three diverse and large scale data sets. Our analysis gives several key insights. First, we can precisely pinpoint the effect of large training data; for example, a four times larger training set reduces the required time for real time assessment by a factor of four. Second, the basic model systematically underestimates large magnitude events. This issue can be mitigated by incorporating events from other regions into the training through transfer learning. Third, location estimation is highly precise in areas with sufficient training data, but is strongly degraded for events outside the training distribution. Our analysis suggests that these characteristics are not only present for our model, but for most deep learning models for fast assessment published so far. They result from the black box modeling and their mitigation will likely require imposing physics derived constraints on the neural network.

physics.geo-ph↗

arXiv2021

The transformer earthquake alerting model: A new versatile approach to earthquake early warning

Earthquakes are major hazards to humans, buildings and infrastructure. Early warning methods aim to provide advance notice of incoming strong shaking to enable preventive action and mitigate seismic risk. Their usefulness depends on accuracy, the relation between true, missed and false alerts, and timeliness, the time between a warning and the arrival of strong shaking. Current approaches suffer from apparent aleatoric uncertainties due to simplified modelling or short warning times. Here we propose a novel early warning method, the deep-learning based transformer earthquake alerting model (TEAM), to mitigate these limitations. TEAM analyzes raw, strong motion waveforms of an arbitrary number of stations at arbitrary locations in real-time, making it easily adaptable to changing seismic networks and warning targets. We evaluate TEAM on two regions with high seismic hazard, Japan and Italy, that are complementary in their seismicity. On both datasets TEAM outperforms existing early warning methods considerably, offering accurate and timely warnings. Using domain adaptation, TEAM even provides reliable alerts for events larger than any in the training data, a property of highest importance as records from very large events are rare in many regions.

physics.geo-ph↗

arXiv2020

HunFlair: An Easy-to-Use Tool for State-of-the-Art Biomedical Named Entity Recognition

Summary: Named Entity Recognition (NER) is an important step in biomedical information extraction pipelines. Tools for NER should be easy to use, cover multiple entity types, highly accurate, and robust towards variations in text genre and style. To this end, we propose HunFlair, an NER tagger covering multiple entity types integrated into the widely used NLP framework Flair. HunFlair outperforms other state-of-the-art standalone NER tools with an average gain of 7.26 pp over the next best tool, can be installed with a single command and is applied with only four lines of code. Availability: HunFlair is freely available through the Flair framework under an MIT license: https://github.com/flairNLP/flair and is compatible with all major operating systems. Contact:{weberple,saengema,alan.akbik}@informatik.hu-berlin.de

cs.CL↗

arXiv2019

NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language

Rule-based models are attractive for various tasks because they inherently lead to interpretable and explainable decisions and can easily incorporate prior knowledge. However, such systems are difficult to apply to problems involving natural language, due to its linguistic variability. In contrast, neural models can cope very well with ambiguity by learning distributed representations of words and their composition from data, but lead to models that are difficult to interpret. In this paper, we describe a model combining neural networks with logic programming in a novel manner for solving multi-hop reasoning tasks over natural language. Specifically, we propose to use a Prolog prover which we extend to utilize a similarity function over pretrained sentence encoders. We fine-tune the representations for the similarity function via backpropagation. This leads to a system that can apply rule-based reasoning to natural language, and induce domain-specific rules from training data. We evaluate the proposed system on two different question answering tasks, showing that it outperforms two baselines -- BIDAF (Seo et al., 2016a) and FAST QA (Weissenborn et al., 2017b) on a subset of the WikiHop corpus and achieves competitive results on the MedHop data set (Welbl et al., 2017).

cs.CL↗