地震是地球上主要的自然災害之一，當強烈地震發生時，對地震的認知不足及疏於防範，往往會造成嚴重的財產損失及人員傷亡，而臺灣位於環太平洋地震帶上，地震活動頻繁，如何預防地震已經成為不可忽視的重要課題。
本研究中嘗試對地震預警系統進行研究。研究方法為由人工智慧中機器學習領域的理論出發，使用向中央氣象局申購取得及公開下載之桃園(局部)地區地震資料，分別以隨機森林回歸與分類模型，利用取得之歷史性地震資料進行訓練及分析，擷取地震初始之加速度訊號，以對當次地震最大地動加速度(PGA)及震級進行預測，並探討不同地震地震波(P波)特徵組合及加入虛擬數據對預測結果的影響。最終目標為迅速估算當次地震震度後，系統可以決定使否需要發出地震預警警報，使收到警報的居民可以迅速逃生。

關鍵字：地震震度預測、機器學習、隨機森林、地震P波擷取

Earthquakes are one of the major natural disasters on earth. When strong earthquakes occur, insufficient awareness of earthquakes and neglect of precautions often result in serious property losses and casualties. Taiwan is located in the Pacific Rim Seismic Belt, and seismic activity is Frequently, how to prevent earthquakes has become an important issue that cannot be ignored.
This study attempts to build an earthquake early warning system. using seismic acceleration data in the Taoyuan (local) area obtained from the Central Meteorological Administration and publicly downloaded based on the theory of machine learning in artificial intelligence. The specific methods used in this thesis are random forest regression and classification models. These models capture the initial acceleration signals of the earthquake to predict the maximum ground acceleration (PGA) and magnitude of the current earthquake. This study also explores the influence of choosing different combinations of earthquake seismic wave (P wave) characteristics and adding virtual data for predicting the results.

Allen, R. M., Kanamori, H., 2003, “The potential for earthquake early warning in southern California,” Science, Vol. 300, pp. 786-789.

交通部中央氣象署, 2019, “震度新分級”, 交通部中央氣象署新聞稿.

王乾盈 (編), 2014, 基礎地球科學上, 新北市全華出版社, pp. 80.

P-Alter strong motion network, https://palert.earth.sinica.edu.tw/showallpalert.php

Wu, Y. M. and Mittal, H., 2021, “A Review on the Development of Earthquake Warning System Using Low-Cost Sensors in Taiwan” Sensor, Vol. 21, 7649.

Allen, R. V., 1978, “Automatic earthquake recognition and timing from single traces”, Bull Seism. Soc. Am., Vol. 68, pp. 1521-1532.

吳逸民, 陳承俊, 鍾仁光, 辛在勤, 1998, “即時加速度型地震觀測網之波相到時自動撿拾系統”, 氣象學報, 42:2卷, pp. 103-117.

廖炳堯, 2013, “以信號互相關運用於地震定位之P波到時偵測”, 國立台灣科技大學資工所碩士學位論文.

Zhu, W., Beroza, G. C., 2019, “ PhaseNet: a deep-neural-network-based seismic arrival-time picking method”, Geophysical Journal International, Vol. 216, pp. 261–273.

Wu, Y. M., Shin, T. C., and Tsai, Y. B., 1998, “Quick and reliable determination of magnitude for seismic early warning,” Bull. Seismol. Soc. Am., Vol. 88, pp. 1254– 1259.

Wu, Y. M., and Kanamori, H., 2005, “Rapid Assessment of Damage Potential of Earthquakes in Taiwan from the Beginning of P Waves,” Bulletin of the Seismological Society of America, Vol. 95, No. 3, pp. 1181–1185.

Wu, Y. M., Yen, H., Zhao, L., Huang, B., and Liang, W., 2006, “Magnitude determination using initial P waves: A single-station approach,” Geophysical Research Letters, Vol. 33, L05306.

Wu, Y. M. and Zhao, L., 2006, “Magnitude estimation using the first three seconds P-wave amplitude in earthquake early warning,” Geophysical Research Letters , Vol. 33(16):L16312.

Wu, Y. M., and Kanamori, H., 2008, “Development of an Earthquake Early Warning System Using Real-Time Strong Motion Signals,” Sensor, Vol. 8, pp. 1-9.

黃煒婷, 2009, “台灣地區Pd衰減關係式之分析及於地震預警之運用”, 國立臺灣大學地質科學學系碩士論文.

沈哲平, 林主潔, 黃謝恭, 林沛暘, 王冠又, 2010, “類神經網路應用於強震即時警報系統之建物受震反應分析”, 第十屆中華民國結構工程研討會.

Hsu, T. Y., Huang, S. K., Chang, Y. W., Kuo, C. H., Lin, C. M., Chang, T. M., Wen, K. L., and Loh, C. H., 2013, “Rapid on-site peak ground acceleration estimation based on support vector regression and P-wave features in Taiwan,” Soil Dynamics and Earthquake Engineering, Vol. 49, pp. 210–217.

Hsu, T.Y., Wu, R.T., Liang, C.W., Kuo, C.H., Lin, C.M., 2020, ” Peak ground acceleration estimation using P-wave parameters and horizontal-to-vertical spectral ratios,” Terr. Atmos. Ocean. Sci., Vol. 31, No. 1, pp. 1-8.

Hsu, T. Y., and Huang, C. W., 2021, “Onsite Early Prediction of PGA Using CNN With Multi-Scale and Multi-Domain P-Waves as Input,” Frontiers in Earth Science, Vol. 9, Article 626908.

10程式中, 2021, “[Day 12] 決策樹 (Decision tree), ” iT邦幫忙技術文章. https://ithelp.ithome.com.tw/articles/10271143

Breiman, L., 2001, “Random Forests,” Mach. Learn., 45(1), pp. 5–32.

Liaw, A., and Wiener, M., 2002, “Classification and Regression by Random Forest,” R News, 2(3), pp. 18–22.

10程式中, 2021, “[Day 14] 多棵決策樹更厲害：隨機森林 (Random forest),” iT邦幫忙技術文章.
https://ithelp.ithome.com.tw/articles/10272586

Krenker, A., Bešter, J. and Kos, A., 2011, “Introduction to the artificial neural networks,” Artificial Neural Networks Methodological Advances and Biomedical Applications, pp. 1-18.

“Multi-layer Perceptron in TensorFlow,” Javatpoint.
https://www.javatpoint.com/multi-layer-perceptron-in-tensorflow

Hange, A., 2021, “Target Prediction using Single-layer Perceptron and Multilayer Perceptron, ” Medium.
https://medium.com/nerd-for-tech/flux-prediction-using-single-layer-perceptron-and-multilayer-perceptron-cf82c1341c33

魏敏如, 2020, “處理不平衡資料之方法比較”, 國立中興大學統計學研究所碩士論文.

Tung, E., 2019, “SMOTE + ENN : 解決數據不平衡建模的採樣方法,” Medium.
https://medium.com/%E6%95%B8%E5%AD%B8-%E4%BA%BA%E5%B7%A5%E6%99%BA%E6%85%A7%E8%88%87%E8%9F%92%E8%9B%87/smote-enn-%E8%A7%A3%E6%B1%BA%E6%95%B8%E6%93%9A%E4%B8%8D%E5%B9%B3%E8%A1%A1%E5%BB%BA%E6%A8%A1%E7%9A%84%E6%8E%A1%E6%A8%A3%E6%96%B9%E6%B3%95-cdb6324b711e

Wikipedia contributors, 2024, “Hyperparameter optimization.,” In Wikipedia, The Free Encyclopedia. Retrieved 01:49, from
https://en.wikipedia.org/w/index.php?title=Hyperparameter_optimization&oldid=1228626700

花翊筑, 2020 , “中央山脈南段地震偵測與分析：利用山區臨時地震偵測網,” 國立臺灣師範大學地球科學學系碩士論文.

Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. , 2002, “Smote: Synthetic minority over-sampling technique,” Journal of Artificial Intelligence Research, 16, 321–357.

Mao, W., He, J., Tang, J., & Li, Y., 2018, “Predicting remaining useful life of rolling bearings based on deep feature representation and long short-term memory neural network,” Advances in Mechanical Engineering, pp. 1–18.

羅正勛, 2022, “使用深度學習及隨機森林預測地震之分析, ” 國立中央大學機械工程學系碩士論文.

洪晨訓, 2020, “以台灣地震開發的新地動數據庫, ” 國立中央大學土木工程學系碩士論文.

Raschka, S., 2018, “Model evaluation, model selection, and algorithm selection in machine learning,” arXiv preprint arXiv:1811.12808.

10程式中, 2021, “[機器學習] 交叉驗證 K-fold Cross-Validation, ” 1010Code.
https://andy6804tw.github.io/2021/07/09/k-fold-validation/

Fraj, M. B., 2017, “In Depth: Parameter tuning for Random Forest,” Medium.
https://medium.com/all-things-ai/in-depth-parameter-tuning-for-random-forest-d67bb7e920d

魏夢麗,呂秀英, 1999, “決定係數(R^2)在回歸分析中的解釋級正確使用,” 科學農業 47(11,12), pp. 341-345.
http://ilc.hk.edu.tw/c/document_library/get_file?p_l_id=260741&folderId=261080&name=DLFE-3350.pdf