Urban morphology and climate vulnerability assessment in Kuwait: A spatio-temporal predictive analysis utilizing deep neural network-enhanced markov chain models for 2050 and 2100
PLOS One · 18.08.2025 · 20 (8) · e0318604
DOI: 10.1371/journal.pone.0318604 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 18.08.2025. Verfasst von Walid Al-Shaar und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Engineering and Technology, American University of the Middle East, Egaila, Kuwait. Hauptthemen laut MEDLINE: Deep Learning, Urban Renewal, Sustainable Development, Climate Change. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: American University of the Middle East.
Abstract (Originalsprache)
Rapid urban growth in Kuwait creates challenges for adapting to climate change. This study investigates the spatio-temporal dynamics of urban growth in Kuwait and assesses its climate change vulnerability using a Multi-Layer Perceptron Markov Chain Model (MLPMCM) to forecast land use and land cover (LULC) changes for the years 2050 and 2100. Utilizing historical LULC data from 1985, 2005, and 2022, along with various spatial drivers, the research predicts urban expansion patterns for 2050 and 2100. The model achieved high accuracy in predictions, indicating that proximity to coastlines, road networks, and commercial areas are the primary drivers of urban growth in Kuwait. The study projects significant urban expansion, particularly in North-Northwestern and South-Southwestern regions, with urban areas expected to increase from 819 km² in 2022–1,893 km² by 2100. Climate vulnerability analysis, based on RCP 8.5 scenario projections, is assessed using the cross-referencing approach and it suggests temperature increases of up to 17°C in urban and coastal regions by 2100. The research highlights the complex interplay between urban growth and climate change, emphasizing the need for adaptive urban planning strategies. This study contributes to the understanding of urban growth dynamics in rapidly developing, oil-rich nations with arid climates, offering insights for sustainable urban development and climate resilience in Kuwait and similar contexts.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- College of Engineering and Technology, American University of the Middle East, Egaila, Kuwait.
- LVMT (Laboratoire Ville-Mobilité-Transport), Unité commune Université Gustave Eiffel and École des Ponts, Champs-sur-Marne, Paris, France.
- Geography Department, CREEMO (Centre de Recherche en Environnement-Espace Méditer-ranée Orientale), Saint-Joseph University of Beirut, Campus des Sciences Humaines, Rue de Damas, Mar Mikhael, Beirut, Lebanon.
ORCID-Profile: Walid Al-Shaar, Gremina Elmazi
Förderung
- American University of the Middle East
Zitieren
APA
Al-Shaar, W., Lehmann, X., Saad, N., Elmazi, G., Al-Shaar, M., & Tohme, C. (2025). Urban morphology and climate vulnerability assessment in Kuwait: A spatio-temporal predictive analysis utilizing deep neural network-enhanced markov chain models for 2050 and 2100. PLOS One, 20(8), e0318604. https://doi.org/10.1371/journal.pone.0318604
Vancouver
Al-Shaar W, Lehmann X, Saad N, Elmazi G, Al-Shaar M, Tohme C. Urban morphology and climate vulnerability assessment in Kuwait: A spatio-temporal predictive analysis utilizing deep neural network-enhanced markov chain models for 2050 and 2100. PLOS One. 2025;20(8):e0318604. doi:10.1371/journal.pone.0318604
BibTeX
@article{AlShaar2025,
author = {Al-Shaar, Walid and Lehmann, Xavier and Saad, Noha and Elmazi, Gremina and Al-Shaar, Mohamad and Tohme, Christelle},
title = {Urban morphology and climate vulnerability assessment in Kuwait: A spatio-temporal predictive analysis utilizing deep neural network-enhanced markov chain models for 2050 and 2100},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {8},
pages = {e0318604},
doi = {10.1371/journal.pone.0318604}
}
EUVIMED