Award Date

May 2024

Degree Type

Thesis

Degree Name

Master of Science in Engineering (MSE)

Department

Civil and Environmental Engineering and Construction

First Committee Member

Sajjad Ahmad

Second Committee Member

Haroon Stephen

Third Committee Member

Marie-Odile Fortier

Fourth Committee Member

Ashok Singh

Number of Pages

171

Abstract

Floods are one of the most frequent and most devastating natural disasters, which cause widespread destruction and pose significant risks to human life, infrastructure, and the environment. Advancement in remote sensing technologies and methodologies have demonstrated their efficacy in disaster-related applications, such as the detection, monitoring, and analysis of floods. This study explores the utilization of Synthetic Aperture Radar (SAR) and optical imagery for flood extent mapping and studying the extent of flood over various land cover and land use classes in Pakistan's Sindh province, utilizing the cloud computing power of Google Earth Engine. The change detection method identified extensive flooding in Sindh province, covering an area of 25,229 km2 in August and 19,181 km2 in the first 19 days of September 2022. The Land Use/Land Cover dataset was developed for the pre-flood period. The study highlighted the effectiveness of Random Forest classification in distinguishing Land Use/Land Cover (LULC) types more accurately than K-means clustering. Additionally, the analysis provided insights into the spatial distribution of flood extent and vulnerability of land use/land cover classes such as urban areas, agricultural areas, and sparse natural vegetation as significant areas remained inundated in the province.

Keywords

change detection; flood extent mapping; Google Earth Engine; Land use/Land cover; LULC; Sentinel-1 Flooding

Disciplines

Remote Sensing | Water Resource Management

Degree Grantor

University of Nevada, Las Vegas

Language

English

Rights

IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/


Share

COinS