Search

In this paper, a scalable end-to-end tree boosting system called XGBoost has been applied for predicting the magnitude of an earthquake from the early part of earthquake waveform data. This model uses the features extracted from the early P wave phase of the records as an input. The model's effectiveness has been verified by using data on earthquakes occurring in the Eurasian plate of Japan Islands from 1996 to 2021. Feature engineering has given 29 new features identified from the early P wave phase of the record, which show a high correlation with the magnitude of an earthquake. The comparison of predicted and actual magnitude shows that a trained XGboost model, which uses a single input record for magnitude prediction, gives an average prediction error of 0.004 ± 0.57 for earthquakes in the test dataset. In contrast, the average prediction error of –1.1 ± 0.80 and –0.65 ± 0.69 has been obtained for the magnitude estimated from conventional τc and Pd methods using the same test dataset. It is further seen that the average predicted magnitude of a single earthquake of magnitude 4.5 and 6.1 (MJMA) obtained by using multiple nearfield records using XGBoost model is 4.58 ± 0.33 and 6.32 ± 0.29, which is close to the actual magnitude of the earthquake. The results presented in this paper clearly show that the structured data can be effectively used by complex machine learning or deep learning models to predict earthquake magnitude from single or multiple records. [ABSTRACT FROM AUTHOR]

Earthquakes are one of nature's most devastating disasters. Earthquake prediction is critical in seismology since its success can save lives, property, and infrastructure. Numerous technologies have been proposed to address this issue, including mathematical analysis, artificial intelligence, and machine learning algorithms. Unfortunately, due to earthquakes' dynamic and spontaneous nature, they frequently fail to provide positive results. The study uses deep learning techniques to predict the magnitude of an impending earthquake using eight mathematically calculated seismic indicators derived from Japan, Indonesia, and the Hindu-Kush Karakoram Himalayan (HKKH) region's earthquake catalogs. Three deep learning techniques, including Long Short-Term Memory (LSTM), Bi-directional Long Short-Term Memory (Bi-LSTM), and self-attention-based transformer, have been implemented to model the associations between calculated seismic indicators and potential earthquake incidents. These models have been evaluated with well-known matrices such as the Mean Absolute Error (MAE), Mean Squared Error (MSE), log-cosh loss, and Mean Squared Logarithmic Error (MSLE). The value of these cost functions converges to a small number for all models, indicating that these models effectively predict earthquake magnitudes. When these models were fed with an unknown test dataset from Japan, the LSTM model performed best with the least deviation metrics (MAE = 0.060, MSE = 0.006, log cosh = 0.042 and MSLE = 0.003). Similarly, the Bi-LSTM model delivered the ideal result for the Indonesia earthquake catalog (MAE = 0.073, MSE = 0.009, log cosh = 0.016, and MSLE = 0.009), while the transformer model produced the optimal result for the HKKH region (MAE = 0.062, MSE = 0.006, log cosh = 0.043, and MSLE = 0.003). Predicting earthquake magnitude at various locations using these methodologies produces significant and positive results for magnitudes ranging from 3.5 M to 6.0 M, paving the way for the ultimate robust prediction mechanism, that has not yet been developed. [ABSTRACT FROM AUTHOR]

Earthquakes threaten people, homes, and infrastructure. Early warning systems provide prior warning of oncoming significant shaking to decrease seismic risk by providing location, magnitude, and depth information of the event. Their usefulness depends on how soon a strong shake begins after the warning. In this article, the authors implement a deep learning model for predicting earthquakes. This model is based on a graph convolutional neural network with batch normalization and attention mechanism techniques that can successfully predict the depth and magnitude of an earthquake event at any number of seismic stations in any number of locations. After preprocessing the waveform data, CNN extracts the feature map. Attention mechanism is used to focus on important features. The batch normalization technique takes place in batches for stable and faster training of the model by adding an extra layer. GNN with extracted features and event location information predicts the event information accurately. We test the proposed model on two datasets from Japan and Alaska, which have different seismic dynamics. The proposed model achieves 2.8 and 4.0 RMSE values in Alaska and Japan for magnitude prediction, and 2.87 and 2.66 RMSE values for depth prediction. Low RMSE values show that the proposed model significantly outperforms the three baseline models on both datasets to provide an accurate estimation of the depth and magnitude of small, medium, and large-magnitude events. [ABSTRACT FROM AUTHOR]