SeisBench—A Toolbox for Machine Learning in Seismology
Open accessThe DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
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 when the number of data are large (millions of examples). With the entire spectrum of seismological tasks, for example, seismic picking and detection, magnitude and source property estimation, ground-motion prediction, hypocenter 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—available via GitHub. SeisBench standardizes access to both models and datasets, while 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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 2×
“…datasets have been vital to rapid-progress in various classic ML application domains, most prominently computer-vision (MNIST, Deng, 2012; ImageNet Deng et al., 2009), and natural language processing (Sentiment140, Go et al., 2009), as they allow for easy assessment of which ML algorithms perform…”
BackgroundPyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
TensorFlow: A system for large-scale machine learning
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08695 · Cited by 11,822
The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]
Deng, L. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2211477 · Cited by 4,836 · cited 1×
“Labelled benchmark datasets have been vital to rapid-progress in various classic ML application domains, most prominently computer-vision (MNIST, Deng, 2012; ImageNet Deng et al., 2009), and natural language processing (Sentiment140, Go et al., 2009), as they allow for easy assessment of which ML…”
BackgroundReback, J., McKinney, W., Bossche, J. V. D., Jbrockmendel, Augspurger, T., Cloud, P., Gfyoung, Sinhrks, Klein, A., Tratner, J., et al. (2019) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.3509134 · Cited by 3,464
ObsPy: A Python Toolbox for Seismology
Beyreuther, M., Barsch, R., Krischer, L., Megies, T., Behr, Y., & Wassermann, J. (2010) · Seismological Research Letters · doi:10.1785/gssrl.81.3.530 · Cited by 1,786 · cited 1×
“The annotate and classify methods of the SeisBench models integrate with stream objects from the obspy package (Beyreuther et al., 2010), widely used within the seismological community.”
MethodPhaseNet: A Deep-Neural-Network-Based Seismic Arrival Time Picking Method
Zhu, W., & Beroza, G. C. (2018) · Geophysical Journal International · doi:10.1093/gji/ggy423 · Cited by 1,120 · cited 7×
“…et al., 2016) has driven a wave of applications of ML techniques to classical seismological problems, including earthquake phase identification (Zhu and Beroza, 2019; Ross, Meier, Hauksson and Heaton, 2018; Woollam et al., 2019; Zhou et al., 2019; Wang et al., 2019), earthquake detection…”
BackgroundMethodInfluentialMousavi, S. M., Ellsworth, W. L., Zhu, W., Chuang, L. Y., & Beroza, G. C. (2020) · Nature Communications · doi:10.1038/s41467-020-17591-w · Cited by 1,111 · cited 6×
“In terms of computational performance, we test the EQTransformer implementation on a K80 GPU and annotate 24 hours of 100 Hz data from a single station in 6 s. Scaling this process results in a months worth of data being labelled in ∼ 3 minutes.”
BackgroundMethodInfluentialConvolutional neural network for earthquake detection and location
Perol, T., Gharbi, M., & Denolle, M. (2018) · Science Advances · doi:10.1126/sciadv.1700578 · Cited by 921 · cited 2×
“, 2019), earthquake detection (Mousavi et al., 2019b, 2020; Zhou et al., 2019; Perol et al., 2018; Dokht et al., 2019; Pardo et al., 2019), magnitude estimation (Lomax et al.”
BackgroundGeneralized Seismic Phase Detection with Deep Learning
Ross, Z. E., Meier, M., Hauksson, E., & Heaton, T. H. (2018) · Bulletin of the Seismological Society of America · doi:10.1785/0120180080 · Cited by 532
An overview of the HDF5 technology suite and its applications
Folk, M., Heber, G., Koziol, Q., Pourmal, E., & Robinson, D. (2011) · Proceedings of the EDBT/ICDT 2011 Workshop on Array Databases · doi:10.1145/1966895.1966900 · Cited by 507 · cited 2×
“We use Hierarchical Data Format 5 (HDF5) to store the raw 117 waveforms (Folk et al., 2011).”
MethodP Wave Arrival Picking and First‐Motion Polarity Determination With Deep Learning
Ross, Z. E., Meier, M., & Hauksson, E. (2018) · Journal of Geophysical Research: Solid Earth · doi:10.1029/2017jb015251 · Cited by 505
STanford EArthquake Dataset (STEAD): A Global Data Set of Seismic Signals for AI
Mousavi, S. M., Sheng, Y., Zhu, W., & Beroza, G. C. (2019) · IEEE Access · doi:10.1109/access.2019.2947848 · Cited by 453 · cited 2×
“• CRED (Mousavi, Zhu, Sheng and Beroza, 2019), CNN-RNN Earthquake Detector, initially trained on 500,000 training signal and noise examples from Northern California.”
BackgroundMethodCRED: A Deep Residual Network of Convolutional and Recurrent Units for Earthquake Signal Detection
Mousavi, S. M., Zhu, W., Sheng, Y., & Beroza, G. C. (2019) · Scientific Reports · doi:10.1038/s41598-019-45748-1 · Cited by 370
MyShake: A smartphone seismic network for earthquake early warning and beyond
Kong, Q., Allen, R. M., Schreier, L., & Kwon, Y. (2016) · Science Advances · doi:10.1126/sciadv.1501055 · Cited by 360 · cited 1×
“…et al., 2018; Dokht et al., 2019; Pardo et al., 2019), magnitude estimation (Lomax et al., 2019; Mousavi and Beroza, 2020; van den Ende and Ampuero, 2020; Münchmeyer et al., 2021 a ), and earthquake early warning (Kong et al., 2016; Li et al., 2018; Münchmeyer et al., 2021 b ), amongst others.”
BackgroundA Machine‐Learning Approach for Earthquake Magnitude Estimation
Mousavi, S. M., & Beroza, G. C. (2019) · Geophysical Research Letters · doi:10.1029/2019gl085976 · Cited by 351 · cited 1×
“…Mousavi et al., 2020; Zhou et al., 2019; Perol et al., 2018; Dokht et al., 2019; Pardo et al., 2019), magnitude estimation (Lomax et al., 2019; Mousavi and Beroza, 2020; van den Ende and Ampuero, 2020; Münchmeyer et al., 2021 a ), and earthquake early warning (Kong et al., 2016; Li et al.,…”
BackgroundMachine Learning Seismic Wave Discrimination: Application to Earthquake Early Warning
Li, Z., Meier, M., Hauksson, E., Zhan, Z., & Andrews, J. (2018) · Geophysical Research Letters · doi:10.1029/2018gl077870 · Cited by 305 · cited 2×
“…et al., 2018; Dokht et al., 2019; Pardo et al., 2019), magnitude estimation (Lomax et al., 2019; Mousavi and Beroza, 2020; van den Ende and Ampuero, 2020; Münchmeyer et al., 2021 a ), and earthquake early warning (Kong et al., 2016; Li et al., 2018; Münchmeyer et al., 2021 b ), amongst others.”
BackgroundWhich Picker Fits My Data? A Quantitative Evaluation of Deep Learning Based Seismic Pickers
Münchmeyer, J., Woollam, J., Rietbrock, A., Tilmann, F., Lange, D., Bornstein, T., Diehl, T., Giunchi, C., Haslinger, F., Jozinović, D., et al. (2022) · Journal of Geophysical Research: Solid Earth · doi:10.1029/2021jb023499 · Cited by 208
Self-citationDeep Learning for Picking Seismic Arrival Times
Wang, J., Xiao, Z., Liu, C., Zhao, D., & Yao, Z. (2019) · Journal of Geophysical Research: Solid Earth · doi:10.1029/2019jb017536 · Cited by 203 · cited 2×
“of ML techniques to classical seismological problems, including earthquake phase identification (Zhu & Beroza, 2019; Ross et al., 2018b; Woollam et al., 2019; Zhou et al., 2019; Wang et al., 2019), earthquake detection (Mousavi et al.”
BackgroundMethodReliable Real‐Time Seismic Signal/Noise Discrimination With Machine Learning
Meier, M., Ross, Z. E., Ramachandran, A., Balakrishna, A., Nair, S., Kundzicz, P., Li, Z., Andrews, J. R., Hauksson, E., & Yue, Y. (2019) · Journal of Geophysical Research Solid Earth · doi:10.1029/2018jb016661 · Cited by 189
Automated Seismic Source Characterization Using Deep Graph Neural Networks
van den Ende, M., & Ampuero, J. (2020) · Geophysical Research Letters · doi:10.1029/2020gl088690 · Cited by 176
INSTANCE – the Italian seismic dataset for machine learning
Michelini, A., Cianetti, S., Gaviano, S., Giunchi, C., Jozinović, D., & Lauciani, V. (2021) · Earth system science data · doi:10.5194/essd-13-5509-2021 · Cited by 172
Self-citationHybrid Event Detection and Phase‐Picking Algorithm Using Convolutional and Recurrent Neural Networks
Zhou, Y., Yue, H., Kong, Q., & Zhou, S. (2019) · Seismological Research Letters · doi:10.1785/0220180319 · Cited by 160 · cited 4×
“…problems, including earthquake phase identification (Zhu and Beroza, 2019; Ross, Meier, Hauksson and Heaton, 2018; Woollam et al., 2019; Zhou et al., 2019; Wang et al., 2019), earthquake detection (Mousavi, Zhu, Sheng and Beroza, 2019; Mousavi et al., 2020; Zhou et al., 2019; Perol et…”
BackgroundMethodInfluentialLomax, A., Michelini, A., & Jozinović, D. (2019) · Seismological Research Letters · doi:10.1785/0220180311 · Cited by 160 · cited 2×
“, 2019), magnitude estimation (Lomax et al., 2019; Mousavi and Beroza, 2020; van den Ende 42 and Ampuero, 2020; Münchmeyer et al., 2021a), and earthquake early warning (Kong et al.”
BackgroundSelf-citationMünchmeyer, J., Bindi, D., Leser, U., & Tilmann, F. J. (2021) · Geophysical Journal International · doi:10.1093/gji/ggab139 · Cited by 135 · cited 1×
“…et al., 2018; Dokht et al., 2019; Pardo et al., 2019), magnitude estimation (Lomax et al., 2019; Mousavi and Beroza, 2020; van den Ende and Ampuero, 2020; Münchmeyer et al., 2021 a ), and earthquake early warning (Kong et al., 2016; Li et al., 2018; Münchmeyer et al., 2021 b ), amongst others.”
BackgroundSelf-citationThe transformer earthquake alerting model: a new versatile approach to earthquake early warning
Münchmeyer, J., Bindi, D., Leser, U., & Tilmann, F. J. (2020) · Geophysical Journal International · doi:10.1093/gji/ggaa609 · Cited by 129 · cited 1×
“…et al., 2018; Dokht et al., 2019; Pardo et al., 2019), magnitude estimation (Lomax et al., 2019; Mousavi and Beroza, 2020; van den Ende and Ampuero, 2020; Münchmeyer et al., 2021 a ), and earthquake early warning (Kong et al., 2016; Li et al., 2018; Münchmeyer et al., 2021 b ), amongst others.”
BackgroundSelf-citationDokht, R. M. H., Kao, H., Visser, R., & Smith, B. (2019) · Seismological Research Letters · doi:10.1785/0220180308 · Cited by 114 · cited 1×
“…2019; Wang et al., 2019), earthquake detection (Mousavi, Zhu, Sheng and Beroza, 2019; Mousavi et al., 2020; Zhou et al., 2019; Perol et al., 2018; Dokht et al., 2019; Pardo et al., 2019), magnitude estimation (Lomax et al., 2019; Mousavi and Beroza, 2020; van den Ende and Ampuero, 2020;…”
BackgroundWoollam, J., Rietbrock, A., Rodríguez, Á. B., & Angelis, S. D. (2019) · Seismological Research Letters · doi:10.1785/0220180312 · Cited by 96 · cited 2×
“• BasicPhaseAE (Woollam et al., 2019), basic CNN U-Net, initially applied to regional aftershock sequence in Chile.”
BackgroundMethodSelf-citationValentine, A. P., & Trampert, J. (2012) · Geophysical Journal International · doi:10.1111/j.1365-246x.2012.05429.x · Cited by 81 · cited 1×
“Although some pioneering works harnessed neural networks for seismological applications (e.g Wang and Teng, 1997; Valentine and Trampert, 2012), for many years such techniques did not find wider usage in seismology until approximately three years ago.”
BackgroundSoto, H., & Schurr, B. D. (2021) · Geophysical Journal International · doi:10.1093/gji/ggab266 · Cited by 76
Self-citationYeck, W. L., Patton, J. M., Ross, Z. E., Hayes, G. P., Guy, M. R., Ambruz, N., Shelly, D. R., Benz, H. M., & Earle, P. S. (2020) · Seismological Research Letters · doi:10.1785/0220200178 · Cited by 58
Seismic Phase Picking Using Convolutional Networks
Pardo, E., Garfias, C., & Malpica, N. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2911402 · Cited by 57 · cited 2×
“, 2019), earthquake detection (Mousavi et al., 2019b, 2020; Zhou et al., 2019; Perol et al., 2018; Dokht et al., 2019; Pardo et al., 2019), magnitude estimation (Lomax et al.”
BackgroundLocal earthquakes detection: A benchmark dataset of 3-component seismograms built on a global scale
Magrini, F., Jozinović, D., Cammarano, F., et al. (2020) · Artificial Intelligence in Geosciences · doi:10.1016/j.aiig.2020.04.001 · Cited by 52 · cited 1×
“The seismological benchmark datasets now emerging (e.g. LenDB, Magrini et al., 2020; INSTANCE, Michelini et al., 2021; NEIC, Yeck et al., 2021; STEAD, Mousavi, Sheng, Zhu and Beroza, 2019) already cover a wide-range of potential seismic environments (e.g. global, regional, local), essential factors…”
BackgroundSelf-citation
Cited by
Seismic Arrival-time Picking on Distributed Acoustic Sensing Data using Semi-supervised Learning
Zhu, W., Biondi, E., Li, J., Yin, J., Ross, Z. E., & Zhan, Z. (2023) · Nature Communications · doi:10.1038/s41467-023-43355-3 · Cited by 130
“…from the China Earthquake Networks; Mousavi, Sheng, et al. (2019) created a global benchmark dataset (STEAD) of ∼ 1.2 million seismic waveforms; Several other benchmark datasets are also created for developing deep learning models (Woollam et al., 2019; Yeck et al., 2020b; Woollam et al., 2022).”
BackgroundInfluential
Metadata
- Authors
- Woollam, J., Münchmeyer, J., Tilmann, F., Rietbrock, A., Lange, D., Bornstein, T., Diehl, T., Giunchi, C., Haslinger, F., Jozinović, D., Michelini, A., Saul, J., & Soto, H.
- Venue
- Seismological Research Letters
- Published
- 2022-03-16
- Volume
- 93
- Issue
- 3
- Pages
- 1695-1709
- ISSN
- 0895-0695 (ISSN-L)
- 1938-2057
- OpenAlex
- W4220904918
- Cited by
- 185
- References
- 34
- FWCI
- 10.34
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.