Application of Machine Learning to Determine Earthquake Hypocenter Location in Earthquake Early Warning
Changwei Yang, Kaiwen Zhang, Guangpeng Chen, Yitao Pan, Liang Zhang, Liming Qu
Abstract
We propose a novel hypocenter localization model based on machine learning in the hope of providing a feasible solution for earthquake early warning system (EEWs). The model predicts the hypocenter location using the time series of trigger stations. We compare the test results of three machine learning models: 1) random forest (RF); 2) eXtreme gradient boosting (XGBoost); and 3) light gradient boosting machine (LightGBM). LightGBM is found the most efficient and thus is applied for further testing. Moreover, considering the difference in station trigger between ocean and land earthquakes, ocean and land earthquake hypocenter prediction models are determined separately. When triggered by five stations, the mean absolute errors (MAEs) for predicting the hypocenter location in land and ocean earthquakes is 2.10 and 12.66 km, respectively. With fewer stations (three stations), the predicted MAEs for distance reaches 17.80 and 2.34 km for ocean and land earthquakes, respectively. In addition, a classification model for rapid discrimination of ocean and land earthquakes using information from three trigger stations is constructed. The proposed method in this letter can provide a more reliable solution to EEWs.