Scholarlink

<p>Major earthquake events worldwide have posed substantial threats to human security and socioeconomic stability. Accurate prediction of earthquake casualty is important for effective disaster preparedness and emergency response. However, conventional prediction methods are often constrained by multicollinearity among high-dimensional influencing factors, suboptimal computational efficiency, and inadequate consideration of critical environmental variables. Notably, the impact of meteorological conditions on post-seismic mortality remains underexplored in existing methods, despite its potential to significantly affect survival rates during secondary earthquake disaster phases. To overcome these limitations, a novel hybrid method, PCA-GA-ELM, is proposed, integrating Principal Component Analysis (PCA), Genetic Algorithm (GA), and Extreme Learning Machine (ELM). The method innovatively incorporates temperature as a key prediction variable alongside six conventional seismic and socioeconomic factors. PCA facilitates dimensionality reduction and eliminates feature redundancy, while GA enhances the prediction robustness of ELM. Rigorous validation using global seismic datasets demonstrates the superior performance of the proposed method, achieving a significant improvement in prediction accuracy compared with benchmark methods. Furthermore, owing to its promising adaptability for casualty prediction, the generalizable PCA-GA-ELM framework can also be extended to other geophysical hazards, including tsunamis and landslides, where multifactorial interactions determine outcomes. This research contributes by establishing a quantitative relationship between temperature and earthquake casualty, while its practical implementation offers substantial improvements in emergency resource allocation and mitigation strategy formulation for disaster management authorities. Nevertheless, several limitations remain and warrant further improvement: 1) the study relies on historical static data and has not yet established a dynamic mechanism integrated with real-time monitoring systems; and 2) geological environmental factors are not included in the prediction system.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A PCA-GA-ELM Method and Its Application in Earthquake Casualty Prediction

  • 期刊论文

  • 发表日期：

    2026年5月14日

查看全文
  • Hongmei Jia,
  • Zhiying Wang,
  • Hanjie Liu

摘要

Major earthquake events worldwide have posed substantial threats to human security and socioeconomic stability. Accurate prediction of earthquake casualty is important for effective disaster preparedness and emergency response. However, conventional prediction methods are often constrained by multicollinearity among high-dimensional influencing factors, suboptimal computational efficiency, and inadequate consideration of critical environmental variables. Notably, the impact of meteorological conditions on post-seismic mortality remains underexplored in existing methods, despite its potential to significantly affect survival rates during secondary earthquake disaster phases. To overcome these limitations, a novel hybrid method, PCA-GA-ELM, is proposed, integrating Principal Component Analysis (PCA), Genetic Algorithm (GA), and Extreme Learning Machine (ELM). The method innovatively incorporates temperature as a key prediction variable alongside six conventional seismic and socioeconomic factors. PCA facilitates dimensionality reduction and eliminates feature redundancy, while GA enhances the prediction robustness of ELM. Rigorous validation using global seismic datasets demonstrates the superior performance of the proposed method, achieving a significant improvement in prediction accuracy compared with benchmark methods. Furthermore, owing to its promising adaptability for casualty prediction, the generalizable PCA-GA-ELM framework can also be extended to other geophysical hazards, including tsunamis and landslides, where multifactorial interactions determine outcomes. This research contributes by establishing a quantitative relationship between temperature and earthquake casualty, while its practical implementation offers substantial improvements in emergency resource allocation and mitigation strategy formulation for disaster management authorities. Nevertheless, several limitations remain and warrant further improvement: 1) the study relies on historical static data and has not yet established a dynamic mechanism integrated with real-time monitoring systems; and 2) geological environmental factors are not included in the prediction system.