A Review on Land-use and Land-change with Machine Learning Algorithm. Issue 1 (March 2021)

• Record Type: Journal Article
• Authors: Gupta, D; Sethi, D; Bathija, R
• Is Part Of: IOP conference series. Volume 1119:Issue 1(2021)
• Publication Date: 2021-03
• Subjects: SVM -- CNN -- LULC -- remote sensing -- Spatial Transformation -- Pixel-based change detection; Materials science -- Periodicals; 620.1105
• DOI: 10.1088/1757-899X/1119/1/012006
• Languages: English
• ISSNs: 1757-8981

Abstract

Abstract: A significant proportion of the planet's ground environment has changed with ground use and land-related shifts, exacerbated by both human behavior and natural feedback. Anthropogenic activities have dramatically altered natural ecosystems, in particular in areas greatly affected by population growth and climate change such as Eastern Africa. For environmental protection and successful water management practices, it is important to be aware of the trends in land use & land cover (LULC). This study centered on developments in LULC patterns in Climate Modelling, remote sensing, and field data combined to identify positive feedback circuits or negative ones using remote sensing techniques and geographic information systems (GIS). Furthermore, its findings include statements that focus on policies that display the impacts and levels of LULC transformation and the dissemination of these improvements in time and space as a central element in the current methods for environmental control of changes and the management of natural resources.