Earthquake Magnitude Modelling using Machine Learning Technology

Kelani, Benjamin Ayodele (2023) Earthquake Magnitude Modelling using Machine Learning Technology. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (2MB) | Preview

Abstract

One of the most frequent natural disasters with a high tendency to destroy property and lives is an earthquake (Alexander, 2018). The essence of predicting earthquake occurrence and knowledge of estimated magnitude has posed as a concern to researchers, engineers, geologists, policy makers, and the government. The limitations in existing earthquake prediction models have given rise to a surge in demand for a more sophisticated model. Due to the various factors indicating the occurrence of an earthquake relying on a single predictive model is not an effective approach to tackling the challenge of prediction and magnitude modelling (Al Banna, 2020). This research utilized an effective preprocessing strategy and machine learning technology. The research is advanced by applying artificial intelligence using various models such as support vector machine (SVM), linear regression, naïve bayes and random forest on the California earthquake dataset. The models developed utilize geological and seismic data, various exploratory data analysis techniques such as correlation matrix and plots to examine the relationship between independent data attributes and earthquake magnitude. The research provides models which would provide magnitude predictions and estimates. The research would enable improved risk management techniques for earthquake events and improve safety across the World. The result shows that under the proposed strategy the Random Forest classifier showed the highest accuracy of 99% whereas SVM showed the highest suitability with the R-square value of 0.17 which reveals a higher efficiency in the machine learning models as compared to existing models, this reveals the importance of data originality and proper data preprocessing. Predictions from the models can be used by Building Engineers to decide the strength of materials used in buildings to withstand ground shocks, can also be used by Policy makers to aid decision making as regards habitable environments to ensure safety of the People and property.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Muntean, Cristina Hava UNSPECIFIED
Subjects:	G Geography. Anthropology. Recreation > GE Environmental Sciences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence 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 Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	14 May 2025 11:28
Last Modified:	14 May 2025 11:28
URI:	https://norma.ncirl.ie/id/eprint/7545

Actions (login required)

View Item