Issue |
E3S Web Conf.
Volume 633, 2025
International Forum of Global Advances in Sustainable Environment, Energy, and Earth Sciences (GASES 2025)
|
|
---|---|---|
Article Number | 07021 | |
Number of page(s) | 12 | |
Section | Geography and Spatial Planning | |
DOI | https://doi.org/10.1051/e3sconf/202563307021 | |
Published online | 04 June 2025 |
Utilization of remote sensing and GIS for land use and land cover mapping in Wasit province, Iraq
University of Baghdad, College of Engineering, Department of Surveying, Baghdad, Iraq
* Corresponding author: mina.abd2412m@coeng.uobaghdad.edu.iq
All physical components on the Earth’s surface are collectively termed land cover, such as water, vegetation, bare soil, and artificial structures made by humans. In contrast, land use refers to how humans use the land for urban growth, agricultural practices, and commerce activities. The increase in population density has resulted in changes in land use/land cover (LULC) because of urban expansion and other human activities. This study investigates the effectiveness of a supervised MLC classification algorithm to produce LULC maps of Wasit Governorate from multiple satellite images using remote sensing and GIS techniques, which is of great importance for earth observation applications, such as environmental monitoring and disaster prediction. Three Landsat 8-9/OLI satellite images were used to cover the entire study area for the year 2024. Preprocessing including radiometric and atmospheric corrections was performed using ENVI 5.3V software, and mosaicking, layer stacking, and image subsetting were performed using Arc GIS 10.8 to improve image quality. Image processing was performed using ENVI 5.3V to find LULC classes using the Maximum Likelihood (MLC) algorithm. The results indicated five LULC classifications in the study area: vegetation, water bodies, built-up areas, arid areas and saline areas. Furthermore, post-processing of the images, including accuracy assessment, was performed to assess the accuracy of the LULC mapping, yielding an overall agreement of 90.58% and a Kappa index of 88%, which measures the extent of agreement or accuracy. These results are convincing with a kappa index of more than 0.8. This study demonstrates the potential of Landsat 8-9/OLI images integrated with machine learning methods for efficient land use classification, analysis and monitoring. This study also provides broad horizons of knowledge for planners and regional authorities.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.