SeismoQuakeGNN: A Hybrid Framework for Spatio-Temporal Earthquake Prediction with Transformer-Enhanced Models

Anny Leema¹Balakrishnan P^1,2*Gladys Gnana Kiruba¹G. Rajarajan²Stuti Goel¹Prisha Aggarwal¹

• ¹VIT University, Vellore, India
• ²Vellore Institute of Technology, Vellore, India

ABSTRACT: Accurate predictions of earthquakes is crucial for disaster preparedness and risk mitigation. Conventional machine learning models like Random Forest, SVR, and XGBoost are frequently used for seismic forecasting; however, capturing the intricate spatiotemporal relationships in earthquake data remains a challenge. To overcome this issue, we propose SeismoQuakeGNN, a novel Graph Neural Network (GNN) and Transformer-based hybrid framework that integrates spatial and temporal learning for improved seismic forecasting. Unlike existing GNN-based models, SeismoQuakeGNN introduces an optimized spatial encoding mechanism to dynamically learn seismic interdependencies, coupled with a Transformer-driven attention module to capture long-range temporal correlations. Furthermore, initial experiments with XGBoost demonstrated its limitations in learning earthquake patterns, reinforcing the need for deep spatial-temporal modeling. Comparative evaluations confirm that SeismoQuakeGNN outperforms all baselines, achieving 98.00% accuracy, an R² score of 88.00%, and a minimum Mean Squared Error (MSE) of 0.07. While LSTM (97.45% accuracy, 77.19% the coefficient of determination) and XGBoost (95.54% accuracy, 72.09% the coefficient of determination) show competitive results, their capability to capture fully spatial dependencies is limited. Furthermore, the traditional GNN models namely Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) exhibit relatively poor performance, GAT being particularly unstable (R² = -120.00%). According to these findings, SeismoQuakeGNN is identified as the most efficient and reliable model for earthquake prediction, guaranteeing broad coverage for various seismic zones. The new SeismoQuakeGNN method is capable of substantial and efficient data processing of relationships in both space and time, as well as providing superior transfer to different seismic areas, thereby qualifying as a dependable starting point to extensive earthquake forecasting and hazard evaluation.