Enhancing earthquakes and quarry blasts discrimination using machine learning based on three seismic parameters

Abstract

Explosions and other artificial seismic sources remain a major risk to human survival. Seismicity catalogs often suffer from contamination, which hinders the differentiation of tectonic and non-tectonic events. To address this issue, an automated control system is developed employing machine learning (ML) techniques to discriminate between earthquakes and quarry blasts (QBs). By using ML approaches, such as probabilistic and statistical techniques, QBs can be differentiated from natural earthquakes. The proposed method utilizes latitude, longitude, and magnitude information to improve the performance. Evaluation measures, including R2, F1-score, MCC score, and others, are employed to assess the algorithm's effectiveness. Experimental results demonstrate the superiority of the suggested method, achieving a success rate of 97.21%. The developed algorithm has significant potential for enhancing seismic hazard assessment, supporting urban development planning, and promoting safer communities by accurately discriminating between man-made and natural earthquake events.

Keywords

• Seismic hazard
• Earthquake
• Quarry blast
• Machine learning
• Seismicity contamination
• Evaluation metrics