在無數的自然災害中，地震能夠在轉瞬間給予人類文明造成巨大的破壞，對地震的認知不足及疏於防範將導致災難及無法抹滅的痛苦和陰影，因此，地震預測在研究主題中一直是重要焦點。而台灣位於環太平洋地震帶上，地震活動頻繁，如何預防地震成為重要的課題。本研究中嘗試對地震預測領域進行概述，並由人工智慧中機器學習領域的理論出發，以人工神經網路的深度學習模型及隨機森林模型，對中央氣象局提供桃園地區的歷史性地震資料進行訓練、預測及分析。本研究包含中央氣象局公開下載之災害性地震資料及購買之資料兩組預測組別，並且後者包含前者，分別以兩種模型預測加速度及震度；此外，本研究也探討將地震資料取對數或平方對預測結果的影響。;Among countless natural disasters, earthquakes can cause huge damage to human civilization in an instant. Insufficient understanding of earthquakes and neglect of prevention will lead to disasters and indelible pain and shadows. Therefore, earthquake prediction has always been an important research topic. Taiwan is located in the Pacific Rim seismic belt, with frequent seismic activity. Prevention of earthquakes disasters has become an important issue. This study will give an overview of the field of earthquake prediction, using machine learning methods. Here, the deep learning model of artificial neural network and random forest model were used to analyzes the historical earthquake data in Taoyuan area provided by Central Weather Bureau. This study considered two prediction data groups, the disastrous earthquake data publicly downloaded by the Central Weather Bureau and the purchased data, the latter including the former, and two models are used to predict acceleration and intensity. In addition, this study also explores the effect of taking the logarithm or square of the earthquake data on the prediction results.
