Urban Land Cover Change Modelling Using Time-Series Satellite Images: A Case Study of Urban Growth in Five Cities of Saudi Arabia

Remote Sensing

Lalit Kumar¹  Abdullah F. Alqurashi¹  Priyakant Sinha¹ 

[1] School of Environmental and Rural Science, University of New England, Armidale NSW 2351, Australia;

关键词: cellular automata;    image classification;    Landsat;    land cover;    Markov chain;    Saudi Arabia;    urban growth;    urban-growth simulation;   

DOI  :  10.3390/rs8100838

来源: DOAJ

【 摘 要 】

This study analyses the expansion of urban growth and land cover changes in five Saudi Arabian cities (Riyadh, Jeddah, Makkah, Al-Taif and the Eastern Area) using Landsat images for the 1985, 1990, 2000, 2007 and 2014 time periods. The classification was carried out using object-based image analysis (OBIA) to create land cover maps. The classified images were used to predict the land cover changes and urban growth for 2024 and 2034. The simulation model integrated the Markov chain (MC) and Cellular Automata (CA) modelling methods and the simulated maps were compared and validated to the reference maps. The simulation results indicated high accuracy of the MC–CA integrated models. The total agreement between the simulated and the reference maps was >92% for all the simulation years. The results indicated that all five cities showed a massive urban growth between 1985 and 2014 and the predicted results showed that urban expansion is likely to continue going for 2024 and 2034 periods. The transition probabilities of land cover, such as vegetation and water, are most likely to be urban areas, first through conversion to bare soil and then to urban land use. Integrating of time-series satellite images and the MC–CA models provides a better understanding of the past, current and future patterns of land cover changes and urban growth in this region. Simulation of urban growth will help planners to develop sustainable expansion policies that may reduce the future environmental impacts.

【 授权许可】

Unknown