Scholarlink

<p>Accurately predicting the timing, location, and magnitude of earthquakes is a major global scientific challenge. While machine learning methods have been widely used in seismic time series analysis and outperform traditional statistical models, their predictive capability for strong earthquakes (Mw ≥ 6.5) remains limited. This study develops a new prediction method by constructing multi-timescale seismic activity features and integrating them with machine learning models.The novelty of this approach is a parameterized framework based on a historical seismic window (T_history), forecast window (T_forecast), and magnitude threshold (M_threshold). It transforms earthquake prediction into an optimization problem, using machine learning to model the relationship between these parameters and performance metrics (e.g., AUC(Area Under the (ROC) Curve)), and searches the parameter space to maximize AUC. To improve spatial prediction, clustering algorithms divide the study area into subregions with consistent seismic characteristics, and an optimization algorithm determines the optimal time-magnitude parameters for each subregion.Using earthquake catalogs from Japan and New Zealand (1973–2024), K-means +  + was selected to partition Japan into 4 and New Zealand into 3 subregions. With T_forecast set to 365&#xa0;days and time-series cross-validation applied to reduce overfitting, the method achieved average AUC values of 0.75 and 0.81 for predicting strong earthquakes within one year in Japan and New Zealand, respectively, outperforming existing models.The main contribution is a flexible and extensible prediction framework that overcomes the limitations of fixed regions, time windows, and magnitude thresholds. Future work will focus on extensible improvements, overfitting control, and integrating multi-source features to enhance generalization.</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 machine learning framework with parameter optimization and regional clustering for strong earthquake prediction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月20日

查看全文
  • Xuejian Wang,
  • Zifa Wang,
  • Zhaoyan Li,
  • Kunbo Zhou,
  • Zhaodong Wang,
  • Jianming Wang

摘要

Accurately predicting the timing, location, and magnitude of earthquakes is a major global scientific challenge. While machine learning methods have been widely used in seismic time series analysis and outperform traditional statistical models, their predictive capability for strong earthquakes (Mw ≥ 6.5) remains limited. This study develops a new prediction method by constructing multi-timescale seismic activity features and integrating them with machine learning models.The novelty of this approach is a parameterized framework based on a historical seismic window (T_history), forecast window (T_forecast), and magnitude threshold (M_threshold). It transforms earthquake prediction into an optimization problem, using machine learning to model the relationship between these parameters and performance metrics (e.g., AUC(Area Under the (ROC) Curve)), and searches the parameter space to maximize AUC. To improve spatial prediction, clustering algorithms divide the study area into subregions with consistent seismic characteristics, and an optimization algorithm determines the optimal time-magnitude parameters for each subregion.Using earthquake catalogs from Japan and New Zealand (1973–2024), K-means +  + was selected to partition Japan into 4 and New Zealand into 3 subregions. With T_forecast set to 365 days and time-series cross-validation applied to reduce overfitting, the method achieved average AUC values of 0.75 and 0.81 for predicting strong earthquakes within one year in Japan and New Zealand, respectively, outperforming existing models.The main contribution is a flexible and extensible prediction framework that overcomes the limitations of fixed regions, time windows, and magnitude thresholds. Future work will focus on extensible improvements, overfitting control, and integrating multi-source features to enhance generalization.