%0 Journal Article
%T 集成深度学习模型在地震烈度预测中的应用&#8212;&#8212;以意大利数据为例<br>Application of an Ensemble Deep Learning Model in Earthquake Intensity Prediction&#8212;A Case Study Using Italian Data
%A 梅柏威
%J Modeling and Simulation
%P 619-630
%@ 2324-870X
%D 2025
%I Hans Publishing
%R 10.12677/mos.2025.142181
%X 本研究探讨了一种基于深度学习的集成策略来预测地震烈度的方法。通过采用意大利地震数据集(INSTANCE)的数据&#65292;研究结合了卷积神经网络(CNN)、长短期记忆网络(LSTM)和全连接网络(FCNN)&#65292;并运用Bagging算法以提高模型的泛化能力和预测精度。实验结果表明&#65292;本研究所提出的集成模型能够有效地预测地震烈度&#65292;并对不同烈度级别进行了准确区分。<br>This study explores a deep learning-based ensemble strategy for predicting earthquake intensity. Using data from the Italian earthquake dataset (INSTANCE), the research integrates Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and Fully Connected Neural Networks (FCNN), while employing the Bagging algorithm to enhance the model&#8217;s generalization ability and prediction accuracy. The experimental results demonstrate that the proposed ensemble model effectively predicts earthquake intensity and accurately distinguishes between different intensity levels.
%K 地震烈度预测&#65292
%K 深度学习&#65292
%K 集成学习&#65292
%K 意大利地震数据集<br>Earthquake Intensity Prediction
%K Deep Learning
%K Ensemble Learning
%K The Italian Seismic Dataset
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=108612