University of Twente Student Theses

Login

An urban morphology based method for estimating air temperature in informal settlements

Sampson, Sally (2024) An urban morphology based method for estimating air temperature in informal settlements.

[img] PDF
5MB
Abstract:The increasing impacts of climate change as well have reinforced concerns about heat exposure, especially in urban areas where temperatures are exaggerated due to the urban heat island effect. Specifically, informal settlements, within urban areas are attributed with these higher temperatures as compared with surrounding formal areas. Several studies have attempted to model and characterise temperature variations using both Land Surface Temperature and Air temperature and have attributed variations to differences in the urban form and fabric such as morphology and green infrastructure. Other studies have established that informal settlements can and often exhibit different urban characters including morphology. They have been characterised by dense, compact structures and limited vegetation. Despite these gaps and the understanding of the relevance of urban morphology to temperature, none of these studies have extensively included detailed morphological parameters in modelling air temperature. This study addresses the limitations of current methods by leveraging urban morphometrics and random forest to estimate air temperature within informal settlements, with a specific focus on Nairobi, Kenya. It explores the relationship between urban morphology and air temperature, hypothesizing that distinct morphological characteristics of informal settlements significantly influence local temperature variations. Through a detailed morphological analysis and advanced machine learning techniques, the study models air temperature with high spatial resolution, providing insights into the patterns and drivers of thermal variations. From this study, it was established that there are strong morphological differences between formal and informal areas in the study area. The random forest model successfully predicted air temperature with an R^2 of 0.73, revealing significant warmer temperatures within informal settlements. The model also allowed the assessment of importance of detailed morphology to air temperature. This analysis revealed urban morphology to only play a supplementary role in air temperature prediction. Urban morphometrics only influence temperature in a confounding manner, thus only at a contextual level or neighbourhood level, does it impact these variations.
Item Type:Essay (Master)
Faculty:ITC: Faculty of Geo-information Science and Earth Observation
Subject:43 environmental science, 74 (human) geography, cartography, town and country planning, demography
Programme:Geoinformation Science and Earth Observation MSc (75014)
Link to this item:https://purl.utwente.nl/essays/102483
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page