Author ORCID Identifier
https://orcid.org/0000-0002-3587-3093
Date of Award
Spring 5-4-2022
Degree Type
Thesis
Degree Name
Master of Science (MS)
Department
Geosciences
First Advisor
Hassan Babaie
Second Advisor
Luke Pangle
Third Advisor
Brian Meyer
Abstract
In this study, I compared the predictive capability of five machine learning models (logistic regression (LR), multilayer perceptron (MLP), support vector machine (SVM), k-nearest neighbor (KNN), and random forest (RF)), and used the best-performed model to construct a susceptibility map for west central Florida. A total of 9 layers were extracted from the collected data and employed as conditional factors for the correlation analysis. Factors with negligible contribution to the quality of predictions, according to the information gain ratio technique, were later discarded. The validation of the machine learning models, performed using different statistical indices and receiver operating characteristic (ROC) curves, revealed that the RF model has the highest prediction, and thus was used for constructing a susceptibility map. The susceptibility map was divided into two levels (high susceptibility (H) and low susceptibility (L)), and the result was verified by Root Mean Squared Error (RMSE) and Confusion Matrix.
DOI
https://doi.org/10.57709/28909408
Recommended Citation
Muili, Olanrewaju, "Sinkhole Susceptibility Analysis using Machine Learning for West Central Florida." Thesis, Georgia State University, 2022.
doi: https://doi.org/10.57709/28909408
File Upload Confirmation
1