Integration of Remote Sensing and GIS for Urban Sprawl Monitoring in European Cities

Urban sprawl still poses a major problem to most European cities as it causes environmental degradation, social and economic unfairness, and inefficient land utilization. This study proposes and evaluates an extensive decision-making framework that facilitates the use of remote sensing and geograph...

Full description

Saved in:
Bibliographic Details
Main Authors: Stavros Kalogiannidis, Konstantinos Spinthiropoulos, Dimitrios Kalfas, Fotios Chatzitheodoridis, Fani Tziampazi
Format: Article
Language:English
Published: European Association of Geographers 2025-04-01
Series:European Journal of Geography
Subjects:
Online Access:https://eurogeojournal.eu/index.php/egj/article/view/781
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Urban sprawl still poses a major problem to most European cities as it causes environmental degradation, social and economic unfairness, and inefficient land utilization. This study proposes and evaluates an extensive decision-making framework that facilitates the use of remote sensing and geographic information systems for assessment, analysis, and control of urban sprawl. Satellite data from Sentinel-2 and Landsat-8 were utilized to analyze land cover changes in six European cities, including London, Paris, Madrid, Berlin, Rome, and Athens, that occurred over a period of 23 years, specifically from 2000 to 2023. Supervised classification techniques, namely, Random Forest and Support Vector Machines, and spatial metrics including Shannon’s Entropy, Patch Density, Urban Compactness Ratio, and Buffer analysis were used to assess the level of sprawl. A self-administered questionnaire was completed by 125 urban planners and policymakers to get a quantitative perspective about socio-economic forces and policy efficiency. The study established that there has been extreme urban sprawl with Rome leading at 24% and Berlin at 23%, attributed to population growth, economic development and thin urban planning standards. Furthermore, green space was also reduced by 19.7%, and air pollution rose by 11.2%. Also, an increase in traffic congestion (36%) and housing costs (28%) were other socio-economic issues. The tested decision support framework proved efficient for scenario modeling and predictive spatial analysis for sustainable urban growth. Future literature should add the application of a machine learning approach and artificial intelligence for better classification of land use and quantify the cities’ sprawl. Highlights: • An integrated RS-GIS and machine learning framework to assess urban sprawl patterns across six European cities under varying urban typologies. • Combine spatial data with expert survey responses to analyze the influence of policies, socio-economic factors, and infrastructure on urban sprawl. • A multi-scalar analysis revealing spatial disparities, infrastructure access gaps, and planning challenges affecting urban expansion across Mediterranean and industrialized cities. • Evidence-based insights supporting policymakers and planners in designing sustainable urban development strategies tailored to diverse European urban contexts.
ISSN:1792-1341
2410-7433