Back to search

Hosted by Utah State University Libraries

Spatiotemporal Data Augmentation of MODIS-LANDSAT Water Bodies Using Generative Adversarial Networks

Abstract

dc:description.abstract

The monitoring of the shape and area of a water body is an essential component for many Earth science and Hydrological applications. For this purpose, these applications require remote sensing data which provides accurate analysis of the water bodies. In this thesis the same is being attempted, first, a model is created that can map the information from one kind of satellite that captures the data from a distance of 500m to another data that is captured by a different satellite at a distance of 30m. To achieve this, we first collected the data from both of the satellites and translated the data from one satellite to another using our proposed Hydro-GAN model. This translation gives us the accurate shape, boundary, and area of the water body. We evaluated the method by using several different similarity metrics for the area and the shape of the water body. The second part of this thesis involves augmenting the data that we obtained from the Hydro-GAN model with the original data and using this enriched data to predict the area of a water body in the future. We used the case study of Great Salt lake for this purpose. The results indicated that our proposed model was creating accurate area and shape of the water bodies. When we used our proposed model to generate data at a resolution of 30m it gave us better areal and shape accuracy. If we get more data at this resolution, we can use that data to better predict coastal lines, boundaries, as well as erosion monitoring.

Degree

thesis:*
Name thesis:degree_name
Master of Science (MS)
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
Computer Science
Grantor dc:publisher
Hosted by Utah State University Libraries

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Neema, Ashit
Contributors dc:contributor
  • Soukaina Filali Boubrahimi
  • Xiaojun Qi
  • Hamid Karimi

Subjects

dc:subject × 7

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Utah State University
Base URL
digitalcommons.usu.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Neema, Ashit. Spatiotemporal Data Augmentation of MODIS-LANDSAT Water Bodies Using Generative Adversarial Networks. Thesis thesis, Hosted by Utah State University Libraries, https://digitalcommons.usu.edu/etd/8580