Grindulu fault cloud radon data for earthquake magnitude prediction using machine learning

Abstract

The study investigates the potential of integrating radon gas concentration telemonitoring systems with machine learning techniques to enhance earthquake magnitude prediction. Conducted in Pacitan, East Java, Indonesia, where the stations are near the active Grindulu fault, the research employs random forest (RF), extreme gradient boosting (XGB), neural network (NN), AdaBoost (AB), and support vector machine (SVM) methods. The study aims to refine earthquake magnitude prediction, utilizing real-time radon gas concentration measurements, crucial for disaster preparedness. The evaluation involves multiple metrics like mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), mean squared error (MSE), symmetric mean absolute percentage error (SMAPE), and conformal normalized mean absolute percentage error (cnSMAPE). XGB and SVM emerge as top performers, showcasing superior predictive accuracy with minimal errors across various metrics. XGB achieved MAE (0.33), MAPE (6.03%), RMSE (0.51), MSE (0.26), SMAPE (0.06), and cnMAPE (0.97), while SVM recorded MAE (0.34), MAPE (6.20%), RMSE (0.51), MSE (0.26), SMAPE (0.06), and cnSMAPE (0.97). The analysis reveals XGB as the most effective method, boasting the lowest error values. The study underscores the importance of expanding data availability to enhance predictive models, ultimately contributing to more precise earthquake magnitude predictions and effective mitigation strategies.