14 results on '"Münchmeyer, J."'
Search Results
2. PickBlue: Seismic Phase Picking for Ocean Bottom Seismometers With Deep Learning.
- Author
-
Bornstein, T., Lange, D., Münchmeyer, J., Woollam, J., Rietbrock, A., Barcheck, G., Grevemeyer, I., and Tilmann, F.
- Subjects
DEEP learning ,OCEAN bottom ,SEISMOMETERS ,SEISMIC waves ,ARTIFICIAL neural networks ,SEISMIC event location ,SEISMOGRAMS ,SOUND reverberation - Abstract
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 (OBS) data set 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 of 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 of 0.05 s for P‐waves and 0.12 s for S‐waves, and we apply the picker on the Hikurangi Ocean Bottom Tremor and Slow Slip OBS deployment offshore New Zealand. We integrate our data set and trained models into SeisBench to enable an easy and direct application in future deployments. Plain Language Summary: Ocean bottom seismometers (OBS) are seismic stations on the seafloor. Just like their counterparts on land, they record many earthquakes on three component sensors but are additionally equipped with underwater hydrophones. To determine the location of an earthquake, seismologists must precisely measure the arrival times of seismic waves. For onshore data, machine learning (ML) has been highly successful in determining earthquake arrival times. However, the noise and the signal are different in the ocean environment. For example, the recordings can contain whale songs and water layer reverberations and are disturbed by ocean bottom currents. We have assembled an extensive database of ocean bottom recordings and trained artificial neural networks to use the underwater hydrophone information and cope with the ocean noise environment. We demonstrate that the resulting ML picker picks are similar to those of human experts and outperform phase pickers based on land data only. We compare earthquake catalogs based on different pickers created from an OBS deployment offshore New Zealand and demonstrate that PICKBLUE outperforms previous pickers. We make the database and ML picker available with a standard interface so that it is easy for other scientists to apply them in their studies. Key Points: We assembled a database of ocean Bottom Seismometer (OBS) waveforms and manual P and S picks, on which we train PickBlue, a deep learning pickerOur picker significantly outperforms pickers trained with land‐based data with confidence values reflecting the likelihood of outlier picksThe picker and database are available in the SeisBench platform, allowing easy and direct application to OBS traces and hydrophone records [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
3. Catalogue of Earthquake Hypocenters for Northern Chile from 2007-2021 using IPOC (plus auxiliary) seismic stations
- Author
-
Sippl, C., Schurr, B., Münchmeyer, J., Barrientos, S., and Oncken, O.
- Abstract
The present dataset is a comprehensive earthquake catalogue for the Northern Chile subduction zone forearc covering the period 2007-2021, determined from IPOC seismic station data (GFZ and CNRS-INSU 2006; https://doi.org/10.14470/pk615318) plus some auxiliary stations (IPOC = Integrated Plate Boundary Observatory Chile; http://www.ipoc-network.org). The method of automatized earthquake catalogue retrieval, the different relocation steps as well as the different earthquake class labels, and the structures outlined by the seismicity are described in detail in Sippl et al. (2023). The catalogue builds on the one from Sippl et al. (2018; https://doi.org/10.5880/GFZ.4.1.2018.001), but uses a slightly deviating parameter set and a new event category. The columns of the data files are: year, month, day, hour, minute, second, latitude [dec. degrees], longitude [dec. degrees], depth [km], magnitude [ML], identifier The identifier term provides a first-order spatial classification of the seismicity, an explanation is given in Sippl et al. (2023).
- Published
- 2023
4. Machine learning for fast and accurate assessment of earthquake source parameters
- Author
-
Münchmeyer, J., Leser, Ulf, Tilmann, Frederik, and Beroza, Gregory
- Subjects
Deep Learning ,Erdbebenanalyse ,Machine learning ,ddc:550 ,Earthquake assessment ,ddc:004 ,Seismologie ,004 Informatik ,Maschinelles Lernen ,Seismology ,550 Geowissenschaften - Abstract
Erdbeben gehören zu den zerstörerischsten Naturgefahren auf diesem Planeten. Obwohl Erdbeben seit Jahrtausenden dokumentiert sing, bleiben viele Fragen zu Erdbeben unbeantwortet. Eine Frage ist die Vorhersagbarkeit von Brüchen: Inwieweit ist es möglich, die endgültige Größe eines Bebens zu bestimmen, bevor der zugrundeliegende Bruchprozess endet? Diese Frage ist zentral für Frühwarnsysteme. Die bisherigen Forschungsergebnisse zur Vorhersagbarkeit von Brüchen sind widersprüchlich. Die Menge an verfügbaren Daten für Erdbebenforschung wächst exponentiell und hat den Tera- bis Petabyte-Bereich erreicht. Während viele klassische Methoden, basierend auf manuellen Datenauswertungen, hier ihre Grenzen erreichen, ermöglichen diese Datenmengen den Einsatz hochparametrischer Modelle und datengetriebener Analysen. Insbesondere ermöglichen sie den Einsatz von maschinellem Lernen und deep learning. Diese Doktorarbeit befasst sich mit der Entwicklung von Methoden des maschinellen Lernens zur Untersuchung zur Erbebenanalyse. Wir untersuchen zuerst die Kalibrierung einer hochpräzisen Magnitudenskala in einem post hoc Scenario. Nachfolgend befassen wir uns mit Echtzeitanalyse von Erdbeben mittels deep learning. Wir präsentieren TEAM, eine Methode zur Frühwarnung. Auf TEAM aufbauend entwickeln wir TEAM-LM zur Echtzeitschätzung von Lokation und Magnitude eines Erdbebens. Im letzten Schritt untersuchen wir die Vorhersagbarkeit von Brüchen mittels TEAM-LM anhand eines Datensatzes von teleseismischen P-Wellen-Ankünften. Dieser Analyse stellen wir eine Untersuchung von Quellfunktionen großer Erdbeben gegenüber. Unsere Untersuchung zeigt, dass die Brüche großer Beben erst vorhersagbar sind, nachdem die Hälfte des Bebens vergangen ist. Selbst dann können weitere Subbrüche nicht vorhergesagt werden. Nichtsdestotrotz zeigen die hier entwickelten Methoden, dass deep learning die Echtzeitanalyse von Erdbeben wesentlich verbessert., Earthquakes are among the largest and most destructive natural hazards known to humankind. While records of earthquakes date back millennia, many questions about their nature remain open. One question is termed rupture predictability: to what extent is it possible to foresee the final size of an earthquake while it is still ongoing? This question is integral to earthquake early warning systems. Still, research on this question so far has reached contradictory conclusions. The amount of data available for earthquake research has grown exponentially during the last decades reaching now tera- to petabyte scale. This wealth of data, while making manual inspection infeasible, allows for data-driven analysis and complex models with high numbers of parameters, including machine and deep learning techniques. In seismology, deep learning already led to considerable improvements upon previous methods for many analysis tasks, but the application is still in its infancy. In this thesis, we develop machine learning methods for the study of rupture predictability and earthquake early warning. We first study the calibration of a high-confidence magnitude scale in a post hoc scenario. Subsequently, we focus on real-time estimation models based on deep learning and build the TEAM model for early warning. Based on TEAM, we develop TEAM-LM, a model for real-time location and magnitude estimation. In the last step, we use TEAM-LM to study rupture predictability. We complement this analysis with results obtained from a deep learning model based on moment rate functions. Our analysis shows that earthquake ruptures are not predictable early on, but only after their peak moment release, after approximately half of their duration. Even then, potential further asperities can not be foreseen. While this thesis finds no rupture predictability, the methods developed within this work demonstrate how deep learning methods make a high-quality real-time assessment of earthquakes practically feasible.
- Published
- 2022
5. The Northern Chile forearc constrained by 15 years of permanent seismic monitoring
- Author
-
Sippl, C., Schurr, B., Münchmeyer, J., Barrientos, S., and Oncken, O.
- Subjects
Geology ,Earth-Surface Processes - Abstract
In this review article, we compile seismological observations from the different constituent parts of the Northern Chile forearc: the downgoing Nazca Plate, the plate interface, the upper South American Plate as well as the mantle wedge beneath it. As Northern Chile has been monitored by a network of permanent seismic stations since late 2006, there is a wealth of observations that enables us to characterize the structure as well as ongoing processes in the forearc throughout the last 15 years. We put an emphasis on the analysis of seismicity, for which we have extended a massive earthquake catalog that now contains 180,000 events for the years 2007–2021. Moreover, we draw on published results for earthquake mechanisms, source properties, seismic velocity structure, statistical seismology and others, and discuss them in context of results from neighboring disciplines. We thus attempt to provide a comprehensive overview on the seismological knowledge about the structure and ongoing processes in the Northern Chile forearc, a breviary of which is found in the following: The Northern Chile megathrust hosted two major earthquake sequences during the analyzed time period. The 2007 7.8 Tocopilla earthquake broke the deep part of the megathrust just north of Mejillones Peninsula, whereas the 2014 8.1 Iquique earthquake ruptured the central segment in the north of the study region. The latter event has a highly interesting preparatory phase, including a significant foreshock sequence as well as aseismic slip transients. Besides these large events, background seismicity elsewhere on the megathrust may be helpful for characterizing the earthquake potential and locking state in the remaining seismic gap. The downgoing Nazca Plate in Northern Chile exhibits very high seismicity rates, with the vast majority of earthquakes occurring at depths of 80-140 km with downdip extensive mechanisms. While seismic tomography shows no sudden changes in slab geometry along strike, seismicity describes peculiar offsets that may be linked to subducted features on the oceanic plate. Upper plate seismicity likewise shows strong variations along strike, with the north and south of the study area showing only weak activity, whereas the central segment shows pervasive microseismicity throughout the upper plate, all the way to the plate interface. These earthquakes have thrust and strike-slip mechanisms with P-axes striking roughly N-S, indicating margin-parallel compression that may be connected to the concavity of the margin.
- Published
- 2023
6. Fast earthquake assessment dataset for Chile
- Author
-
Münchmeyer, J., Bindi, D., Leser, U., and Tilmann, F.
- Subjects
Data_FILES - Abstract
The data publication contains a dataset for fast assessment of earthquakes based on seismic waveforms. The dataset encompasses Northern Chile. Due to the large scale of the dataset, it is intended for use in machine learning. A similar dataset for chile has been published as Münchmeyer et al. (2020). A similar dataset for Japan can be obtained using the scripts at https://github.com/yetinam/TEAM The datasets are provided as a hdf5-file (Folk et al. 2011), a hierachical file format. Source code for reading and processing the data is available at https://github.com/yetinam/TEAM. The hdf5-file contains the two groups “metadata” and “data” that are described below. These groups are the hdf5-analog of folders in a file system.
- Published
- 2021
7. Fast earthquake assessment and earthquake early warning dataset for Italy
- Author
-
Münchmeyer, J., Bindi, D., Leser, U., and Tilmann, F.
- Abstract
The data publication contains a dataset for fast assessment of earthquakes and early warning based on seismic waveforms. The dataset encompasses Italy and surrounding refions. Due to the large scale of the dataset, it is intended for use in machine learning. A similar dataset for Japan, with the same specifications as the one provided in this data publications, can be obtained using the scripts at https://github.com/yetinam/TEAM
- Published
- 2020
8. Increasing magnitude scale consistency by combining multiple waveform features through machine learning
- Author
-
Münchmeyer, J., Bindi, D., Sippl, C., and Tilmann, F.
- Published
- 2019
9. V. 1.0
- Author
-
Münchmeyer, J., Bindi, D., Sippl, C., Leser, U., and Tilmann, F.
- Abstract
In Münchmeyer et al. 2019 magnitudes scales for Northern Chile have been derived with a focus on low uncertainties. The data set consists of three parts. First, a version of the IPOC catalog with the derived magnitude scales ML and MA and their uncertainties. Second, the attenuation functions for different waveform features. Third, the full matrix of features and the resulting single station magnitude predictions.The underlying IPOC catalog was obtained from Sippl et al. (2018). Detailed data description is provided in the README and in Münchmeyer et al. (2019) to which these data are supplementary material.
- Published
- 2019
10. How predictable are mass extinction events?
- Author
-
Foster WJ, Allen BJ, Kitzmann NH, Münchmeyer J, Rettelbach T, Witts JD, Whittle RJ, Larina E, Clapham ME, and Dunhill AM
- Abstract
Many modern extinction drivers are shared with past mass extinction events, such as rapid climate warming, habitat loss, pollution and invasive species. This commonality presents a key question: can the extinction risk of species during past mass extinction events inform our predictions for a modern biodiversity crisis? To investigate if it is possible to establish which species were more likely to go extinct during mass extinctions, we applied a functional trait-based model of extinction risk using a machine learning algorithm to datasets of marine fossils for the end-Permian, end-Triassic and end-Cretaceous mass extinctions. Extinction selectivity was inferred across each individual mass extinction event, before testing whether the selectivity patterns obtained could be used to 'predict' the extinction selectivity exhibited during the other mass extinctions. Our analyses show that, despite some similarities in extinction selectivity patterns between ancient crises, the selectivity of mass extinction events is inconsistent, which leads to a poor predictive performance. This lack of predictability is attributed to evolution in marine ecosystems, particularly during the Mesozoic Marine Revolution, associated with shifts in community structure alongside coincident Earth system changes. Our results suggest that past extinctions are unlikely to be informative for predicting extinction risk during a projected mass extinction., (© 2023 The Authors.)
- Published
- 2023
- Full Text
- View/download PDF
11. Graph Neural Networks for Learning Molecular Excitation Spectra.
- Author
-
Singh K, Münchmeyer J, Weber L, Leser U, and Bande A
- Subjects
- Machine Learning, Neural Networks, Computer
- Abstract
Machine learning (ML) approaches have demonstrated the ability to predict molecular spectra at a fraction of the computational cost of traditional theoretical chemistry methods while maintaining high accuracy. Graph neural networks (GNNs) are particularly promising in this regard, but different types of GNNs have not yet been systematically compared. In this work, we benchmark and analyze five different GNNs for the prediction of excitation spectra from the QM9 dataset of organic molecules. We compare the GNN performance in the obvious runtime measurements, prediction accuracy, and analysis of outliers in the test set. Moreover, through TMAP clustering and statistical analysis, we are able to highlight clear hotspots of high prediction errors as well as optimal spectra prediction for molecules with certain functional groups. This in-depth benchmarking and subsequent analysis protocol lays down a recipe for comparing different ML methods and evaluating dataset quality.
- Published
- 2022
- Full Text
- View/download PDF
12. HunFlair: an easy-to-use tool for state-of-the-art biomedical named entity recognition.
- Author
-
Weber L, Sänger M, Münchmeyer J, Habibi M, Leser U, and Akbik A
- Abstract
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, be highly accurate and be robust toward variations in text genre and style. We present HunFlair, a NER tagger fulfilling these requirements. HunFlair is integrated into the widely used NLP framework Flair, recognizes five biomedical entity types, reaches or overcomes state-of-the-art performance on a wide set of evaluation corpora, and is trained in a cross-corpus setting to avoid corpus-specific bias. Technically, it uses a character-level language model pretrained on roughly 24 million biomedical abstracts and three million full texts. It outperforms other off-the-shelf biomedical NER tools with an average gain of 7.26 pp over the next best tool in a cross-corpus setting and achieves on-par results with state-of-the-art research prototypes in in-corpus experiments. HunFlair can be installed with a single command and is applied with only four lines of code. Furthermore, it is accompanied by harmonized versions of 23 biomedical NER corpora., Availability and Implementation: HunFlair ist freely available through the Flair NLP framework (https://github.com/flairNLP/flair) under an MIT license and is compatible with all major operating systems., Supplementary Information: Supplementary data are available at Bioinformatics online., (© The Author(s) 2021. Published by Oxford University Press.)
- Published
- 2021
- Full Text
- View/download PDF
13. HUNER: improving biomedical NER with pretraining.
- Author
-
Weber L, Münchmeyer J, Rocktäschel T, Habibi M, and Leser U
- Subjects
- Data Analysis, Software, Computational Biology methods, Neural Networks, Computer
- Abstract
Motivation: Several recent studies showed that the application of deep neural networks advanced the state-of-the-art in named entity recognition (NER), including biomedical NER. However, the impact on performance and the robustness of improvements crucially depends on the availability of sufficiently large training corpora, which is a problem in the biomedical domain with its often rather small gold standard corpora., Results: We evaluate different methods for alleviating the data sparsity problem by pretraining a deep neural network (LSTM-CRF), followed by a rather short fine-tuning phase focusing on a particular corpus. Experiments were performed using 34 different corpora covering five different biomedical entity types, yielding an average increase in F1-score of ∼2 pp compared to learning without pretraining. We experimented both with supervised and semi-supervised pretraining, leading to interesting insights into the precision/recall trade-off. Based on our results, we created the stand-alone NER tool HUNER incorporating fully trained models for five entity types. On the independent CRAFT corpus, which was not used for creating HUNER, it outperforms the state-of-the-art tools GNormPlus and tmChem by 5-13 pp on the entity types chemicals, species and genes., Availability and Implementation: HUNER is freely available at https://hu-ner.github.io. HUNER comes in containers, making it easy to install and use, and it can be applied off-the-shelf to arbitrary texts. We also provide an integrated tool for obtaining and converting all 34 corpora used in our evaluation, including fixed training, development and test splits to enable fair comparisons in the future., Supplementary Information: Supplementary data are available at Bioinformatics online., (© The Author(s) 2019. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)
- Published
- 2020
- Full Text
- View/download PDF
14. Estimating genome-wide regulatory activity from multi-omics data sets using mathematical optimization.
- Author
-
Trescher S, Münchmeyer J, and Leser U
- Subjects
- Algorithms, Databases, Genetic, RNA, Messenger genetics, RNA, Messenger metabolism, Genomics methods
- Abstract
Background: Gene regulation is one of the most important cellular processes, indispensable for the adaptability of organisms and closely interlinked with several classes of pathogenesis and their progression. Elucidation of regulatory mechanisms can be approached by a multitude of experimental methods, yet integration of the resulting heterogeneous, large, and noisy data sets into comprehensive and tissue or disease-specific cellular models requires rigorous computational methods. Recently, several algorithms have been proposed which model genome-wide gene regulation as sets of (linear) equations over the activity and relationships of transcription factors, genes and other factors. Subsequent optimization finds those parameters that minimize the divergence of predicted and measured expression intensities. In various settings, these methods produced promising results in terms of estimating transcription factor activity and identifying key biomarkers for specific phenotypes. However, despite their common root in mathematical optimization, they vastly differ in the types of experimental data being integrated, the background knowledge necessary for their application, the granularity of their regulatory model, the concrete paradigm used for solving the optimization problem and the data sets used for evaluation., Results: Here, we review five recent methods of this class in detail and compare them with respect to several key properties. Furthermore, we quantitatively compare the results of four of the presented methods based on publicly available data sets., Conclusions: The results show that all methods seem to find biologically relevant information. However, we also observe that the mutual result overlaps are very low, which contradicts biological intuition. Our aim is to raise further awareness of the power of these methods, yet also to identify common shortcomings and necessary extensions enabling focused research on the critical points.
- Published
- 2017
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.