摘要
目的利用机器学习方法,以云南省为例,分析地震发生时的各种应急相关信息,进行地震应急响应等级的预测,以协助应急救援部门与专家的决策过程,提高应对效率和效果。方法基于国家冰川冻土沙漠科学数据中心的全球自然灾害信息库中记载的云南省2014—2023年共226起地震事件,以地震烈度、震源深度、土壤含水量、前一年人口密度、前一年地区GDP、地震经济损失、受灾面积作为模型输入特征,输出结果为4种应急响应等级,构建基于贝叶斯优化(BO)的支持向量机(SVM)分类模型,用于预测地震应急响应等级。分别应用线性核、二次核、三次核和高斯核进行训练,以探索适用于地震应急响应等级预测的最佳核函数类型。结果二次核SVM模型的均匀性与整体效果较优,经贝叶斯优化后模型效果最好,构建的分类模型能较好地决策云南省地震应急响应等级,Ⅰ级响应的受试者工作特征曲线(ROC)下面积AUC值为0.8638,Ⅱ级AUC值为0.8628,Ⅲ级AUC值为0.8107,Ⅳ级AUC值为0.8740。测试集Ⅰ级响应的精确率-召回率曲线下面积(PR-AUC值)为0.3055,Ⅱ级PR-AUC值为0.7916,Ⅲ级PR-AUC值为0.8304,Ⅳ级为0.8972;模型工作点的测试集宏平均F1分数为0.7967。结论应急响应等级函数为非线性函数。贝叶斯优化二次核SVM在地震应急响应等级预测中展现出良好的应用潜力,可有效配合应急预案,为构建智能化灾害响应辅助决策系统提供了有益的方法探索。后续可通过数据增强技术、拓展数据来源,提高输入特征的全面性,以提升高级别响应判断精度。
Objective To employ machine learning methods to analyze various emergency-related information following an earthquake,taking Yunnan as an example,in order to predict emergency response levels and support decision-making by emergency rescue agencies and experts,thereby improving response efficiency and effectiveness.Methods A total of 226 earthquake events in Yunnan Province from 2014 to 2023 recorded in the Global Natural Disaster Repository of the National Cryosphere Desert Data Center(China)were used as the dataset.Model input features included seismic intensity,focal depth,soil moisture content,population density from the previous year,regional GDP from the previous year,economic losses caused by the earthquake,and affected area.The output was the classification into one of four emergency response levels.A support vector machine(SVM)classification model optimized using Bayesian optimization(BO)was constructed to predict earthquake emergency response levels.The linear,quadratic,cubic,and Gaussian kernel functions were used for training to identify the most suitable kernel for predicting earthquake emergency response levels.Results The SVM model with a quadratic kernel demonstrated superior uniformity and overall performance,achieving the best results after Bayesian optimization.The classification model accurately predicted emergency response levels in Yunnan Province.The AUC values for each level were as follows:Level I was 0.8638,LevelⅡwas 0.8628,LevelⅢwas 0.8107,and LevelⅣwas 0.8740.On the test set,the PR-AUC values were 0.3055 for Level I,0.7916 for LevelⅡ,0.8304 for LevelⅢ,and 0.8972 for LevelⅣ,with a macro-average F1-score of 0.7967 at the model’s operating point.Conclusions The emergency response level was governed by a nonlinear function.The Bayesian optimized-SVM approach with a quadratic kernel showed strong potential for application in predicting earthquake emergency response levels and can effectively support emergency preparedness plans.This approach provides a promising method for developing intelligent disaster response decision support systems.Future research should explore data augmentation techniques and expanded data sources to enhance the comprehensiveness of input features and improve the prediction accuracy for higher-level emergency responses.
作者
李辰霖
LI Chenlin(School of Environment and Resources,Southwest University of Science and Technology,Mianyang,Sichuan 621010,China)
出处
《职业卫生与应急救援》
2025年第4期530-535,共6页
Occupational Health and Emergency Rescue
基金
四川省科技计划资助项目(2023YFS0362)。
关键词
地震
应急响应等级
机器学习
支持向量机
贝叶斯优化
灾害响应
earthquake
emergency response level
machine learning
support vector machine
Bayesian optimization
disaster response
作者简介
李辰霖(2003-),男,大学本科在读。
