Deep learning models for the prediction of earthquake magnitudes

-, Yaseen Ali Khan (2025) Deep learning models for the prediction of earthquake magnitudes. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (933kB) | Preview

Abstract

Earthquake prediction is a critical yet complex task due to the stochastic nature of seismic activities and the multitude of factors influencing tectonic movements. This study aims to leverage advanced machine learning and deep learning techniques to predict earthquake magnitudes based on spatial, temporal, and geophysical parameters. Multiple baseline models were implemented and evaluated, including Random Forest Regressor, Feedforward Neural Network, SVR, Extra Trees Regressor, and Gradient Boosting Regressor. Hyperparameter tuning using RandomizedSearchCV was employed. As part of the research, a number of deep learning architectures were studied in detail, including ones with GRU, Conv1D, Bidirectional LSTM, a hybrid Bidirectional GRU + Conv1D layers. Performance was assessed using MAE, MSE, RMSE, and R2 score. Over the course of this document, it will be shown that Gradient Boosting Regressor emerged as the best-performing model with the lowest MAE (0.2817), lowest MSE (0.1514), lowest RMSE (0.3891), and the highest R2 Score (0.1734), demonstrating its robustness and reliability. The work did not find comparable results with any deep learning technique. However, this study underscores the potential of ensemble learning models, particularly Gradient Boosting, instead of much-hyped deep learning techniques.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Estrada, Giovani UNSPECIFIED
Uncontrolled Keywords:	Earthquake Prediction; Machine Learning; Deep Learning; Random Forest Regressor; GRU (Gated Recurrent Unit)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing G Geography. Anthropology. Recreation > GE Environmental Sciences > Earth sciences > Geology > Physical geology > Sedimentation and deposition > Earth movements > Earthquakes Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	20 Nov 2025 12:51
Last Modified:	20 Nov 2025 12:56
URI:	https://norma.ncirl.ie/id/eprint/8949

Actions (login required)

View Item