Turkey Earthquake Prediction with Deep Learning Algorithms

Kas, Omer (2023) Turkey Earthquake Prediction with Deep Learning Algorithms. Masters thesis, Dublin, National College of Ireland.

Preview

PDF (Master of Science) Download (2MB) | Preview

Abstract

Earthquakes, a natural phenomenon prevalent in seismically active regions, pose a grave threat to human lives and infrastructure. Despite today’s technological advancements, a definitive earthquake prediction method remains elusive. However, researchers across diverse scientific fields are diligently studying past earthquake records in hopes of uncovering discernible patterns. To anticipate impending earthquakes, comprehensive investigations are conducted, drawing expertise from various disciplines. Notably, the rise of information technologies has steered attention towards deep learning, a subset of artificial intelligence, as a means to achieve accurate predictions in this complex process. In this research study, research is carried out on a possible future earthquake prediction model using deep learning architectures with the data of earthquakes that have occurred in Turkey. The topic of study includes a model investigated by using information such as time, latitude, longitude, magnitude and depth of the catalog data of earthquakes that have occurred in Turkey and deep learning algorithms. Long-Short Term Memory (LSTM) architecture, which is one of the Recurrent Neural Network processes, is used to predict the time of occurrence of the earthquake that may occur in the research. In the process of developing the model, the RNN model demonstrates superior prediction accuracy compared to the LSTM model. The RNN model achieves lower values for all evaluation metrics: MSE (95.13 vs. 195.54), RMSE (9.75 vs. 13.98), and MAE (4.70 vs. 5.71). This underscores the RNN model’s better performance, reflected by consistently reduced error metrics across all measures.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Shahid, Abdul UNSPECIFIED
Uncontrolled Keywords:	Earthquake; Deep Learning; LSTM; Turkey
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Algebra > Algorithms > Computer algorithms 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:	Tamara Malone
Date Deposited:	26 Nov 2024 11:30
Last Modified:	26 Nov 2024 11:30
URI:	https://norma.ncirl.ie/id/eprint/7197

Actions (login required)

View Item