Road network topology and machine learning integration to model urban heat patterns in Riyadh

Saeed Alqadhi () and Javed Mallick ()
Additional contact information
Saeed Alqadhi: King Khalid University, Department of Civil Engineering, College of Engineering
Javed Mallick: King Khalid University, Department of Civil Engineering, College of Engineering

Climatic Change, 2025, vol. 178, issue 12, No 21, 30 pages

Abstract: Abstract As urbanization is consolidated, increased land surface temperatures (LST) have also become an important concern for environmental quality and public health. While many studies examine the impacts of land use, vegetation, and built form on urban heat, the structural configuration of road networks remains poorly understood. The present study undertakes exploration of how road-network characteristics in Riyadh, such as intersection density, street connectivity, and the continuity of road segments, shape spatial variations in LST. Using MODIS satellite data from 2015 to 2024 within a 1 km² grid, this research analysed eight road types and described their structural forms with intuitive indicators, including average distance between intersections and prevalence of looped over linear street patterns. A Random Forest (RF) model was fitted with SHAP (Shapley Additive Explanations) interpretation to establish which feature impacted the thermal outcomes most distinctly. Results reveal a pronounced thermal gradient across the city: rapidly expanding outer districts, including Al-Manar and Al-Malqa, reached frequently over 42 °C, while central neighbourhoods cooled down to near 30 °C by 2024, following targeted greening and shading. Across most road types, shorter distances between intersections indicative of dense and more compact street networks were associated with an LST reduction of approximately 1.2–2.5 °C. In contrast, districts characterized by long and sparsely connected segments face up to 2.3 °C temperature rises. Spatial SHAP mapping has shown that looped and connected layouts dissipate heat compared to peripheral areas dominated by sparse and linear roads. In demonstrating that road-network structure meaningfully shapes urban heat patterns, this paper highlights opportunities for climate-responsive street planning.

Keywords: Land surface temperature; Road network; Machine learning; SHAP; Urban planning; Riyadh; Ensemble modelling. (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10584-025-04083-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:climat:v:178:y:2025:i:12:d:10.1007_s10584-025-04083-3

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/10584

DOI: 10.1007/s10584-025-04083-3

Access Statistics for this article

Climatic Change is currently edited by M. Oppenheimer and G. Yohe

More articles in Climatic Change from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().