Ordered Logit regression model for predicting magnitude of flood along Foma River Kwara Nigeria
Flood is a natural disaster that has become a major concern to the Nigerian government. Despite the numerous hazards caused by the flood, little attention has been directed towards evaluating the flood hazards through the river condition and vulnerability components along the river areas. Hence, thi...
Saved in:
Main Author: | |
---|---|
Format: | Thesis |
Language: | eng eng eng eng |
Published: |
2021
|
Subjects: | |
Online Access: | https://etd.uum.edu.my/9335/1/s901651_01.pdf https://etd.uum.edu.my/9335/2/s901651_02.pdf https://etd.uum.edu.my/9335/3/s901651_references.docx https://etd.uum.edu.my/9335/5/depositpermission_s901651.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my-uum-etd.9335 |
---|---|
record_format |
uketd_dc |
spelling |
my-uum-etd.93352022-05-09T03:26:47Z Ordered Logit regression model for predicting magnitude of flood along Foma River Kwara Nigeria 2021 Ayinla, Chindo Abdulrasaq Mohd Shaharanee, IzwanNizal Mohd Jamil, Jastini Awang Had Salleh Graduate School of Arts & Sciences Awang Had Salleh Graduate School of Arts & Sciences DT Africa QE Geology Flood is a natural disaster that has become a major concern to the Nigerian government. Despite the numerous hazards caused by the flood, little attention has been directed towards evaluating the flood hazards through the river condition and vulnerability components along the river areas. Hence, this study examines the river condition and vulnerability components to determine the cross-sectional variables in predicting the magnitude of flood along Foma River areas. Data extracted from Geographic Information System (GIS) and site observations were used in generating the cross-sectional variables along the river areas. From the dataset, eight crosssectional variables were obtained including 530 structures of Foma River. The Ordered Logit Regression (OLR) Models were built to predict the magnitude of flood. The model was evaluated using average values of accuracy, precision, recall, and F1-score which were derived from the 10-fold cross validation procedure. The F1-score was able to harmonize and reduce the errors in regulating the imbalanced class distributions. It was also revealed that river watersheds, structure vulnerable status, vulnerable structures along the river, locations of bridges and culverts, sizes occupied by bridges and culverts, and river pollution are significantly contributing to the magnitude of the flood along the Foma River. This study produced a complementary approach to flood prediction along the Foma River, as well as provided the Nigerian government and practitioners a new source of information in addressing problems related to river flooding in Nigeria. 2021 Thesis https://etd.uum.edu.my/9335/ https://etd.uum.edu.my/9335/1/s901651_01.pdf text eng 2024-03-25 staffonly https://etd.uum.edu.my/9335/2/s901651_02.pdf text eng public https://etd.uum.edu.my/9335/3/s901651_references.docx text eng public https://etd.uum.edu.my/9335/5/depositpermission_s901651.pdf text eng staffonly other doctoral Universiti Utara Malaysia |
institution |
Universiti Utara Malaysia |
collection |
UUM ETD |
language |
eng eng eng eng |
advisor |
Mohd Shaharanee, IzwanNizal Mohd Jamil, Jastini |
topic |
DT Africa QE Geology |
spellingShingle |
DT Africa QE Geology Ayinla, Chindo Abdulrasaq Ordered Logit regression model for predicting magnitude of flood along Foma River Kwara Nigeria |
description |
Flood is a natural disaster that has become a major concern to the Nigerian government. Despite the numerous hazards caused by the flood, little attention has been directed towards evaluating the flood hazards through the river condition and vulnerability components along the river areas. Hence, this study examines the river condition and vulnerability components to determine the cross-sectional variables in predicting the magnitude of flood along Foma River areas. Data extracted from Geographic Information System (GIS) and site observations were used in generating the cross-sectional variables along the river areas. From the dataset, eight crosssectional variables were obtained including 530 structures of Foma River. The Ordered Logit Regression (OLR) Models were built to predict the magnitude of flood. The model was evaluated using average values of accuracy, precision, recall, and F1-score
which were derived from the 10-fold cross validation procedure. The F1-score was able to harmonize and reduce the errors in regulating the imbalanced class distributions. It was also revealed that river watersheds, structure vulnerable status, vulnerable structures along the river, locations of bridges and culverts, sizes occupied by bridges and culverts, and river pollution are significantly contributing to the magnitude of the flood along the Foma River. This study produced a complementary approach to flood prediction along the Foma River, as well as provided the Nigerian government and practitioners a new source of information in addressing problems related to river flooding in Nigeria. |
format |
Thesis |
qualification_name |
other |
qualification_level |
Doctorate |
author |
Ayinla, Chindo Abdulrasaq |
author_facet |
Ayinla, Chindo Abdulrasaq |
author_sort |
Ayinla, Chindo Abdulrasaq |
title |
Ordered Logit regression model for predicting magnitude of flood along Foma River Kwara Nigeria |
title_short |
Ordered Logit regression model for predicting magnitude of flood along Foma River Kwara Nigeria |
title_full |
Ordered Logit regression model for predicting magnitude of flood along Foma River Kwara Nigeria |
title_fullStr |
Ordered Logit regression model for predicting magnitude of flood along Foma River Kwara Nigeria |
title_full_unstemmed |
Ordered Logit regression model for predicting magnitude of flood along Foma River Kwara Nigeria |
title_sort |
ordered logit regression model for predicting magnitude of flood along foma river kwara nigeria |
granting_institution |
Universiti Utara Malaysia |
granting_department |
Awang Had Salleh Graduate School of Arts & Sciences |
publishDate |
2021 |
url |
https://etd.uum.edu.my/9335/1/s901651_01.pdf https://etd.uum.edu.my/9335/2/s901651_02.pdf https://etd.uum.edu.my/9335/3/s901651_references.docx https://etd.uum.edu.my/9335/5/depositpermission_s901651.pdf |
_version_ |
1747828575794364416 |