Open AccessIDENTIFYING INFORMAL SETTLEMENTS IN SATELLITE IMAGES FOR SUSTAINABLE URBAN PLANNING: A SYSTEMATIC REVIEW OF METHODS AVAILABLE
Author(s) -
Amadu Monday Ambugadu,
Nafisa Hosni
Publication year - 2022
Publication title -
journal of information system and technology management
Language(s) - English
Resource type - Journals
ISSN - 0128-1666
DOI - 10.35631/jistm.725008
Subject(s) - human settlement , informal settlements , urban planning , urbanization , satellite imagery , environmental planning , sustainable development , remote sensing , geography , sustainability , settlement (finance) , economic shortage , computer science , environmental resource management , environmental science , civil engineering , engineering , political science , economic growth , archaeology , government (linguistics) , world wide web , law , economics , payment , biology , ecology , linguistics , philosophy
The current urbanization trend, along with a shortage of affordable housing, has led to the proliferation of informal settlements in most cities in the global south. The variance in spectral, spatial image resolution, texture, colours, and complex physical shapes of informal urban settlements has made it difficult to provide accurate evidence for urban planners to achieve sustainable urban planning. In this article, the PRISMA methodology was used to thoroughly investigate various techniques used to classify informal settlements from satellite imagery between 2010 and 2021, as well as identify the methods' strengths and weaknesses, along with image indicators used in generating adequate information for sustainable urban planning. According to the study, the dominant models and approaches used to identify or detect informal settlements in satellite imagery for urban planning purposes are remote sensing, GIS, and artificial intelligence (machine learning) applications, as well as quantitative indicators. It was also revealed that without an integrated methodology, the proposed approaches used in different studies could not accurately detect and classify informal settlements. This is due to similarities in the texture of buildings of both formal and informal settlements, as well as variations in image spectral and spatial resolutions, as reported in previous studies.