本篇研究中提出了新的 phase picking 模型，GRADUATE，希望能達到快速且在不同環境中都能有穩定的效能表現。利用來自時域的波形資料與時頻域的頻譜圖作為輸入，參考兩個不同領域提供的特徵做出預測。實驗結果呈現出在三個資料集上，包括STEAD、INSTANCE、與 CWA，我們所提出的模型相較於其他 state-of-the-art 模型有更穩定的預測結果。同時我們也將模型整併到現有的地震預警系統中，利用即時的資料驗證其效能。最後我們也提出了首個蒐集來自臺灣周遭地區的公開地震資料集，彙整了來自中央氣象署 (CWA) 的兩個地震網的資料，超過五十萬筆具有高品質的波形，每筆皆有詳細的詮釋資料加以描述，除了用在 picking 相關研究上，也適用其他與地震相關的任務。

In this study, a new phase picking model, GRADUATE, has been proposed with the aim of achieving both speed and stable performance in different environments. It utilizes waveform data from the time domain and spectrograms from the time-frequency domain as inputs, referencing features provided by dual domains to make predictions. Experimental results demonstrate that proposed model exhibits more stable predictive results compared to other state-of-the-art models on three datasets, including STEAD, INSTANCE, and CWA. Additionally, we have integrated the model into the existing earthquake early warning (EEW) system and validated its performance using real-time data. Eventually, we introduced the first published dataset collected from the surrounding areas of Taiwan, curating data from two seismographic networks constructed by the Central Weather Administration (CWA). It contains over 500 K high-quality seismograms, described by more than 40 metadata attributes. Not only the studies about picking benefits but other earthquake related tasks.

[1] N.-C. Hsiao, Y.-M. Wu, T.-C. Shin, L. Zhao, and T.-L. Teng, “Development of earthquake early warning system in taiwan,” Geophysical research letters, vol. 36, no. 5, 2009.
[2] D.-Y. Chen, N.-C. Hsiao, and Y.-M. Wu, “The earthworm based earthquake alarm reporting system in taiwan,” Bulletin of the Seismological Society of America, vol. 105, no. 2A, pp. 568–579, 2015.
[3] D.-Y. Chen, T.-L. Lin, H.-C. Hsu, Y.-C. Hsu, N.-C. Hsiao, et al., “An approach to improve the performance of the earthquake early warning system for the 2018 hualien earthquake in taiwan,” Terr. Atmos. Ocean. Sci, vol. 30, no. 3, pp. 423–433, 2019.
[4] Y.-M. Wu, H. Mittal, D.-Y. Chen, T.-Y. Hsu, and P.-Y. Lin, “Earthquake early warning systems in taiwan: Current status,” Journal of the Geological Society of India, vol. 97, pp. 1525–1532, 2021.
[5] X. Zhou, J. Wang, Z. Cui, S. Zhang, Z. Yan, J. Zhou, and C. Zhou, “Mmspeech: Multi-modal multitask encoder-decoder pre-training for speech recognition,” arXiv preprint arXiv:2212.00500, 2022.
[6] A. Gulati, J. Qin, C.-C. Chiu, N. Parmar, Y. Zhang, J. Yu, W. Han, S. Wang, Z. Zhang, Y. Wu, et al., “Conformer: Convolution-augmented transformer for speech recognition,” arXiv preprint arXiv:2005.08100, 2020.
[7] K.-H. Lu and K.-Y. Chen, “A context-aware knowledge transferring strategy for ctc-based asr,” in 2022 IEEE Spoken Language Technology Workshop (SLT), pp. 60–67, IEEE, 2023.
[8] S. Watanabe, T. Hori, S. Kim, J. R. Hershey, and T. Hayashi, “Hybrid ctc/attention architecture for end-to-end speech recognition,” IEEE Journal of Selected Topics in Signal Processing, vol. 11, no. 8, pp. 1240–1253, 2017.
[9] Y. Liu, “Fine-tune bert for extractive summarization,” arXiv preprint arXiv:1903.10318, 2019.
[10] C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li, and P. J. Liu, “Exploring the limits of transfer learning with a unified text-to-text transformer,” The Journal of Machine Learning Research, vol. 21, no. 1, pp. 5485–5551, 2020.
[11] Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov, “Roberta: A robustly optimized bert pretraining approach,” arXiv preprint arXiv:1907.11692, 2019.
[12] L. Floridi and M. Chiriatti, “Gpt-3: Its nature, scope, limits, and consequences,” Minds and Machines, vol. 30, pp. 681–694, 2020.
[13] R. Thoppilan, D. De Freitas, J. Hall, N. Shazeer, A. Kulshreshtha, H.-T. Cheng, A. Jin, T. Bos, L. Baker, Y. Du, et al., “Lamda: Language models for dialog applications,” arXiv preprint arXiv:2201.08239, 2022. 121
[14] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017.
[15] J. Woollam, A. Rietbrock, A. Bueno, and S. De Angelis, “Convolutional neural network for seismic phase classification, performance demonstration over a local seismic network,” Seismological Research Letters, vol. 90, no. 2A, pp. 491–502, 2019.
[16] W. Zhu and G. C. Beroza, “Phasenet: a deep-neural-network-based seismic arrival-time picking method,” Geophysical Journal International, vol. 216, no. 1, pp. 261–273, 2019.
[17] S. M. Mousavi, W. Zhu, Y. Sheng, and G. C. Beroza, “Cred: A deep residual network of convolutional and recurrent units for earthquake signal detection,” Scientific reports, vol. 9, no. 1, pp. 1–14, 2019.
[18] H. Soto and B. Schurr, “Deepphasepick: a method for detecting and picking seismic phases from local earthquakes based on highly optimized convolutional and recurrent deep neural networks,” Geophysical Journal International, vol. 227, no. 2, pp. 1268–1294, 2021.
[19] Z. E. Ross, M.-A. Meier, E. Hauksson, and T. H. Heaton, “Generalized seismic phase detection with deep learning,” Bulletin of the Seismological Society of America, vol. 108, no. 5A, pp. 2894–2901, 2018.
[20] T.-L. Chin, K.-Y. Chen, D.-Y. Chen, and D.-E. Lin, “Intelligent real-time earthquake detection by recurrent neural networks,” IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 8, pp. 5440–5449, 2020.
[21] W.-Y. Liao, E.-J. Lee, D.-Y. Chen, P. Chen, D. Mu, and Y.-M. Wu, “Red-pan: Real-time earthquake detection and phase-picking with multitask attention network,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–11, 2022.
[22] W.-Y. Liao, E.-J. Lee, D. Mu, P. Chen, and R.-J. Rau, “Arru phase picker: Attention recurrent-residual u-net for picking seismic p-and s-phase arrivals,” Seismological Research Letters, vol. 92, no. 4, pp. 2410–2428, 2021.
[23] S. M. Mousavi, W. L. Ellsworth, W. Zhu, L. Y. Chuang, and G. C. Beroza, “Earthquake transformer —an attentive deep-learning model for simultaneous earthquake detection and phase picking,” Nature
communications, vol. 11, no. 1, p. 3952, 2020.
[24] R. V. Allen, “Automatic earthquake recognition and timing from single traces,” Bulletin of the seismological society of America, vol. 68, no. 5, pp. 1521–1532, 1978.
[25] J. Münchmeyer, J. Woollam, A. Rietbrock, F. Tilmann, D. Lange, T. Bornstein, T. Diehl, C. Giunchi, F. Haslinger, D. Jozinović, et al., “Which picker fits my data? a quantitative evaluation of deep learning based seismic pickers,” Journal of Geophysical Research: Solid Earth, vol. 127, no. 1,
p. e2021JB023499, 2022. 122
[26] J. Woollam, J. Münchmeyer, F. Tilmann, A. Rietbrock, D. Lange, T. Bornstein, T. Diehl, C. Giunchi, F. Haslinger, D. Jozinović, et al., “Seisbench—a toolbox for machine learning in seismology,” Seismological Society of America, vol. 93, no. 3, pp. 1695–1709, 2022.
[27] S. M. Mousavi, Y. Sheng, W. Zhu, and G. C. Beroza, “Stanford earthquake dataset (stead): A global data set of seismic signals for ai,” IEEE Access, vol. 7, pp. 179464–179476, 2019.
[28] A. Michelini, S. Cianetti, S. Gaviano, C. Giunchi, D. Jozinović, and V. Lauciani, “Instance–the italian seismic dataset for machine learning,” Earth System Science Data, vol. 13, no. 12, pp. 5509–5544, 2021.
[29] S. S. S. S. A. E. Zurich, “National seismic networks of switzerland,” ETH Zurich, 1983.
[30] D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” arXiv preprint arXiv:1409.0473, 2014.
[31] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778, 2016.
[32] J. L. Ba, J. R. Kiros, and G. E. Hinton, “Layer normalization,” arXiv preprint arXiv:1607.06450, 2016.
[33] Z. Dai, Z. Yang, Y. Yang, J. Carbonell, Q. V. Le, and R. Salakhutdinov, “Transformer-xl: Attentive language models beyond a fixed-length context,” arXiv preprint arXiv:1901.02860, 2019.
[34] Y. N. Dauphin, A. Fan, M. Auli, and D. Grangier, “Language modeling with gated convolutional networks,” in International conference on machine learning, pp. 933–941, PMLR, 2017.
[35] P. Ramachandran, B. Zoph, and Q. V. Le, “Searching for activation functions,” arXiv preprint arXiv:1710.05941, 2017.
[36] T. Q. Nguyen and J. Salazar, “Transformers without tears: Improving the normalization of selfattention,” arXiv preprint arXiv:1910.05895, 2019.
[37] Q. Wang, B. Li, T. Xiao, J. Zhu, C. Li, D. F. Wong, and L. S. Chao, “Learning deep transformer models for machine translation,” arXiv preprint arXiv:1906.01787, 2019.
[38] Y. Lu, Z. Li, D. He, Z. Sun, B. Dong, T. Qin, L. Wang, and T.-Y. Liu, “Understanding and improving transformer from a multi-particle dynamic system point of view,” arXiv preprint arXiv:1906.02762, 2019.
[39] Y. Wu, C. Chen, J. Chung, and T. Shin, “An automatic phase picker of the real-time acceleration seismic network,” Meteorol. Bull, vol. 42, pp. 103–117, 1998.
[40] M. Baer and U. Kradolfer, “An automatic phase picker for local and teleseismic events,” Bulletin of the Seismological Society of America, vol. 77, no. 4, pp. 1437–1445, 1987.
[41] O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th 123
International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp. 234–241, Springer, 2015.
[42] M. Z. Alom, M. Hasan, C. Yakopcic, T. M. Taha, and V. K. Asari, “Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation,” arXiv preprint arXiv:1802.06955, 2018.
[43] S. Liu, E. Johns, and A. J. Davison, “End-to-end multi-task learning with attention,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 1871–1880, 2019.
[44] M. Liang and X. Hu, “Recurrent convolutional neural network for object recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3367–3375, 2015.
[45] Y.-M. Wu, D.-Y. Chen, T.-L. Lin, C.-Y. Hsieh, T.-L. Chin, W.-Y. Chang, W.-S. Li, and S.-H. Ker, “A high-density seismic network for earthquake early warning in taiwan based on low cost sensors,”Seismological Research Letters, vol. 84, no. 6, pp. 1048–1054, 2013.
[46] R. Allen, “Automatic phase pickers: Their present use and future prospects,” Bulletin of the Seismological Society of America, vol. 72, no. 6B, pp. S225–S242, 1982.
[47] K. O’Shea and R. Nash, “An introduction to convolutional neural networks,” arXiv preprint arXiv:1511.08458, 2015.
[48] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997.
[49] M. Lin, Q. Chen, and S. Yan, “Network in network,” arXiv preprint arXiv:1312.4400, 2013.
[50] T. Bornstein, D. Lange, J. Münchmeyer, J. Woollam, A. Rietbrock, G. Barcheck, I. Grevemeyer, and F. Tilmann, “Pickblue: Seismic phase picking for ocean bottom seismometers with deep learning,”arXiv preprint arXiv:2304.06635, 2023.
[51] C. F. Richter, “An instrumental earthquake magnitude scale,” Bulletin of the seismological society of America, vol. 25, no. 1, pp. 1–32, 1935.
[52] M. Chakraborty, D. Fenner, W. Li, J. Faber, K. Zhou, G. Rümpker, H. Stoecker, and N. Srivastava,“Creime—a convolutional recurrent model for earthquake identification and magnitude estimation,”Journal of Geophysical Research: Solid Earth, vol. 127, no. 7, p. e2022JB024595, 2022.
[53] S. M. Mousavi and G. C. Beroza, “A machine-learning approach for earthquake magnitude estimation,” Geophysical Research Letters, vol. 47, no. 1, p. e2019GL085976, 2020.
[54] A. Lomax, A. Michelini, and D. Jozinović, “An investigation of rapid earthquake characterization using single-station waveforms and a convolutional neural network,” Seismological Research Letters,
vol. 90, no. 2A, pp. 517–529, 2019.
[55] O. M. Saad, Y. Chen, A. Savvaidis, S. Fomel, and Y. Chen, “Real-time earthquake detection and magnitude estimation using vision transformer,” Journal of Geophysical Research: Solid Earth, vol. 127, no. 5, p. e2021JB023657, 2022. 124
[56] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv preprint arXiv:2010.11929, 2020.
[57] O. Heidbach, M. Rajabi, X. Cui, K. Fuchs, B. Müller, J. Reinecker, K. Reiter, M. Tingay, F. Wenzel, F. Xie, et al., “The world stress map database release 2016: Crustal stress pattern across scales,”Tectonophysics, vol. 744, pp. 484–498, 2018.
[58] J. Zhang, Z. Li, and J. Zhang, “Simultaneous seismic phase picking and polarity determination with an attention-based neural network,” Seismological Society of America, vol. 94, no. 2A, pp. 813–828, 2023.
[59] Z. Yu and W. Wang, “Lppn: A lightweight network for fast phase picking,” Seismological Society of America, vol. 93, no. 5, pp. 2834–2846, 2022.
[60] J. Li, K. Li, and S. Tang, “Automatic arrival-time picking of p-and s-waves of microseismic events based on object detection and cnn,” Soil Dynamics and Earthquake Engineering, vol. 164, p. 107560, 2023.
[61] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “Yolov4: Optimal speed and accuracy of object detection,” arXiv preprint arXiv:2004.10934, 2020.
[62] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779–788, 2016.
[63] J. Münchmeyer, D. Bindi, U. Leser, and F. Tilmann, “The transformer earthquake alerting model: A new versatile approach to earthquake early warning,” Geophysical Journal International, vol. 225, no. 1, pp. 646–656, 2021.
[64] Y.-J. Chiang, T.-L. Chin, and D.-Y. Chen, “Neural network-based strong motion prediction for on-site earthquake early warning,” Sensors, vol. 22, no. 3, p. 704, 2022.
[65] T.-L. Chin, K.-Y. Chen, D.-Y. Chen, and T.-H. Wang, “An attention-based hypocenter estimator for earthquake localization,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–10, 2021.
[66] E. Karasözen and B. Karasözen, “Earthquake location methods,” GEM-International Journal on Geomathematics, vol. 11, pp. 1–28, 2020.
[67] J. Münchmeyer, D. Bindi, U. Leser, and F. Tilmann, “Earthquake magnitude and location estimation from real time seismic waveforms with a transformer network,” Geophysical Journal International, vol. 226, no. 2, pp. 1086–1104, 2021.
[68] Y. Ni, A. Hutko, F. Skene, M. Denolle, S. Malone, P. Bodin, R. Hartog, and A. Wright, “Curated pacific northwest ai-ready seismic dataset,” 2023. 125
[69] E. Center, “Southern california earthquake center,” Caltech. Dataset, 2013.
[70] W. L. Yeck, J. M. Patton, Z. E. Ross, G. P. Hayes, M. R. Guy, N. B. Ambruz, D. R. Shelly, H. M. Benz, and P. S. Earle, “Leveraging deep learning in global 24/7 real-time earthquake monitoring at the national earthquake information center,” Seismological Society of America, vol. 92, no. 1, pp. 469–480, 2021.
[71] F. Magrini, D. Jozinović, F. Cammarano, A. Michelini, and L. Boschi, “Local earthquakes detection: A benchmark dataset of 3-component seismograms built on a global scale,” Artificial Intelligence in Geosciences, vol. 1, pp. 1–10, 2020.
[72] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
[73] Student, “The probable error of a mean,” Biometrika, pp. 1–25, 1908.
[74] C. E. Johnson, A. Bittenbinder, B. Bogaert, L. Dietz, and W. Kohler, “Earthworm: A flexible approach to seismic network processing,” Iris newsletter, vol. 14, no. 2, pp. 1–4, 1995.
[75] A. Bapna, N. Arivazhagan, and O. Firat, “Simple, scalable adaptation for neural machine translation,”arXiv preprint arXiv:1909.08478, 2019.
[76] T. Lee, M.-J. Lee, T. G. Kang, S. Jung, M. Kwon, Y. Hong, J. Lee, K.-G. Woo, H.-G. Kim, J. Jeong, et al., “Adaptable multi-domain language model for transformer asr,” in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7358–7362, IEEE,
2021.
[77] W. Hou, Y. Wang, S. Gao, and T. Shinozaki, “Meta-adapter: Efficient cross-lingual adaptation with meta-learning,” in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7028–7032, IEEE, 2021.