Keywords
neural network
detection
binary classification
Section
Abstract
An artificial neural network, SeisDetNet, has been developed for distinguishing seismic events from seismic noise based on waveform records. The international STEAD database, which contains minute-long records of local earthquakes and seismic noise, was used as the data source for training, validation, and testing. Specifically, we selected waveforms from 27 seismic stations located in Kyrgyzstan and surrounding areas from the KRNET, KNET, KZ, G, and TJ networks, present in the STEAD database. The model architecture is a combination of a convolutional network, designed to extract key features for class separation, and a fully connected network for the task of classifying the input record as either a seismic event or seismic noise. Evaluating the model on the test set showed good results, with the following binary classification metrics: accuracy of 0.983, precision of 0.989, recall of 0.982, and F1-score of 0.985.
References
Баталева Е.А., Мухамадеева В.А. Комплексный электромагнитный мониторинг геодинамических процессов Северного Тянь-Шаня (Бишкекский геодинамический полигон) // Геодинамика и тектонофизика. 2018. Т. 9. № 2. С. 461−487 [Bataleva E.A., Mukhamadeeva V.A. Complex electromagnetic monitoring of geodynamic processes in the Northern Tien Shan (Bishkek geodynamic test area) // Geodynamics &Tectonophysics. V. 9. № 2. P. 461–487 (in Russian)].
Гульельми А.В., Лавров И.П., Собисевич А.Л. Внезапные начала магнитных бурь и землетрясения // Солнечно-земная физика. 2015. Т. 1. № 1. С. 98–103. https://doi.org/10.12737/5694 [GuglielmiА.V., Lavrov I.P., Sobisevich A.L. Storm sudden commencements and earthquakes // Solar-Terrestrial Physics, 2015. V. 1. №. 1. P. 98–103. https://doi.org/10.12737/5694 (in Russian)].
Имашев С.А., Рыбин А.К. Сейсмические и геоакустические отклики земной коры на зондирования мощными электрическими импульсами на территории Бишкекского Геодинамического Полигона // Наука и технологические разработки. 2023. Т. 102. № 2–3. С. 63–88 [Imashev S.A., Rybin A.K. Seismic and geoacoustic responses of the earth’scrust to sensing with high energy electric pulses at the territory of the Bishkek Geodynamic Polygon // Naukaitekhnologicheskiyerazrabotki. 2023. V. 102. № 2–3. P. 63–88 (in Russian)].
Сычева Н. Солнечные вспышки, сильные магнитные бури и вариации уровня сейсмического шума на территории северного Тянь-Шаня // Гeoфизические процессы и биосфера. 2022. Т. 21. № 4. С. 93–109. https://doi.org/10.21455/GPB2022.4-7 [Sycheva N.A. Solar flares, strong magnetic storms and variations in the level of seismic noise in the northern Tien Shan // Geofizicheskiyeprotsessyibiosfera. 2022. V. 21. № 4. P. 93–109. https://doi.org/10.21455/GPB2022.4-7 (in Russian)].
Bishop C.M., Bishop H. Deep Learning: Foundations and Concepts. Cham: Springer International Publishing, 2024. 649 p. https://doi.org/10.1007/978-3-031-45468-4
Cireşan D., Meier U., Masci J. et al. Multi-column deep neural network for traffic sign classification // Neural Networks. 2012. V. 32. P. 333–338. https://doi.org/10.1016/j.neunet.2012.02.023
Glorot X., Bordes A., Bengio Y. Deep Sparse Rectifier Neural Networks // Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. Fort Lauderdale, FL, USA. 2011. V. 15. P. 315–323.
Heck S.L., Young C.J., Brogan R. Comparing Traditional and Deep Learning Signal Features for Event Detection in the Utah Region // Bulletin of the Seismological Society of America. 2022. V. 112, № 5. P. 2344–2363. https://doi.org/10.1785/0120210275
Johansson R. Numerical Python: Scientific Computing and Data Science Applications with Numpy, SciPy and Matplotlib. Berkeley. CA: Apress, 2018. 700 p. https://doi.org/10.1007/978-1-4842-4246-9
Jozinović D., Lomax A., Štajduhar I. et al. Rapid prediction of earthquake ground shaking intensity using raw waveform data and a convolutional neural network // Geophysical Journal International. 2020. V. 222, № 2. P. 1379–1389. https://doi.org/10.1093/gji/ggaa233
Kingma D., Ba J. Adam: A Method for Stochastic Optimization // International Conference on Learning Representations (ICLR). San Diego, USA, 2015. P. 13.
Kong Q., Trugman D.T., Ross Z.E. et al. Machine Learning in Seismology: Turning Data into Insights // Seismological Research Letters. 2019. V. 90. № 1. P. 3–14. https://doi.org/10.1785/0220180259
Krizhevsky A., Sutskever I., Hinton G.E. ImageNet Classification with Deep Convolutional Neural Networks // Advances in Neural Information Processing Systems. 2012. V. 25. P. 1097–1105
Kuang W., Yuan C., Zhang J. Real-time determination of earthquake focal mechanism via deep learning // Nature Communications. 2021. V. 12. № 1. P. 1432. https://doi.org/10.1038/s41467-021-21670-x
Lara F., Lara-Cueva R., Larco J.C. et al. A deep learning approach for automatic recognition of seismo-volcanic events at the Cotopaxi volcano // Journal of Volcanology and Geothermal Research. 2021. V. 409. 107142. https://doi.org/10.1016/j.jvolgeores.2020.107142
LeCun Y., Boser B., Denker J. et al. Handwritten Digit Recognition with a Back-Propagation Network // Advances in Neural Information Processing Systems, 1989. V. 2. P. 396–404.
Lecun Y., Bottou L., Bengio Y. et al. Gradient-based learning applied to document recognition // Proceedings of the IEEE. 1998. V. 86, № 11. P. 2278–2324. https://doi.org/10.1109/5.726791
LeCun Y., Bengio Y., Hinton G. Deep learning // Nature. 2015. V. 521, № 7553. P. 436–444. https://doi.org/10.1038/nature14539
Li S., Liu Z.-Q., Chan A.B. Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network // International Journal of Computer Vision. 2015. V. 113, № 1. P. 19–36. https://doi.org/10.1007/s11263-014-0767-8
Li W., Chakraborty M., Sha Y. et al. A study on small magnitude seismic phase identification using 1D deep residual neural network // Artificial Intelligence in Geosciences. 2022. V. 3. P. 115–122. https://doi.org/10.1016/j.aiig.2022.10.002
Mehta V., Kumar A., Nahar K. et al. Binary Image Classification Using Machine Learning and Deep Quantum Neural Networks // 2024 14th International Conference on Cloud Computing, Data Science & Engineering (Confluence). 2024. P. 811–816. https://doi.org/10.1109/Confluence60223.2024.10463226
Mousavi S.M., Sheng Y., Zhu W. et al. STanfordEArthquake Dataset (STEAD): A Global Data Set of Seismic Signals for AI // IEEE Access. 2019. V. 7. P. 179464–179476. https://doi.org/10.1109/ACCESS.2019.2947848
Mousavi S.M., Ellsworth W.L., Zhu W. et al. Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking // Nature Communications. 2020. V. 11. № 1. P. 3952.
Münchmeyer J., Bindi D., Leser U. et al. Earthquake magnitude and location estimation from real time seismic waveforms with a transformer network // Geophysical Journal International. 2021. V. 226, № 2. P. 1086–1104. https://doi.org/10.1093/gji/ggab139
Münchmeyer J., Woollam J., Rietbrock A. et al. Which Picker Fits My Data? A Quantitative Evaluation of Deep Learning Based Seismic Pickers // JGR Solid Earth. 2022. V. 127, № 1. P. e2021JB023499. https://doi.org/10.1029/2021JB023499
Nair V., Hinton G.E. Rectified linear units improve restricted Boltzmann machines // Proceedings of the 27th International Conference on International Conference on Machine Learning. Madison, USA: Omnipress, 2010. P. 807–814.
Ristea N.-C., Radoi A. Complex Neural Networks for Estimating Epicentral Distance, Depth, and Magnitude of Seismic Waves // IEEE Geosci. Remote Sensing Letters. 2022. V. 19. P. 1–5. https://doi.org/10.1109/LGRS.2021.3059422
Ross Z.E., Meier M., Hauksson E. P Wave arrival picking and first‐motion polarity determination with deep learning // Journal of Geophysical Research: Solid Earth. 2018а. V. 123, № 6. P. 5120–5129. https://doi.org/10.1029/2017JB015251
Ross Z.E., Meier M., Hauksson E. et al. Generalized Seismic Phase Detection with Deep Learning // Bulletin of the Seismological Society of America. 2018б. V. 108, № 5A. P. 2894–2901. https://doi.org/10.1785/0120180080
Woollam J., Rietbrock A., Bueno A. et al. Convolutional Neural Network for Seismic Phase Classification, Performance Demonstration over a Local Seismic Network // Seismological Research Letters. 2019. V. 90, № 2A. P. 491–502. https://doi.org/10.1785/0220180312
Zhu W., Beroza G.C. PhaseNet: A Deep-Neural-Network-Based Seismic Arrival Time Picking Method // Geophysical Journal International. 2018. V. 216, № 1. P. 261–273. https://doi.org/10.1093/gji/ggy423
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2024 С.А. Имашев, А.В. Аладьев