Publication Date

Spring 2025

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Engineering

Advisor

Magdalini Eirinaki; Bernardo Flores; Mahima Agumbe Suresh

Abstract

Urban areas experience the Urban Heat Island (UHI) effect, with higher temperatures than rural areas, disproportionately impacting low-income communities. Mapping UHIs is a process that usually requires significant amount of human resources, and is not scalable. The lack of accurate and detailed UHI maps makes it difficult for decision makers to design effective mitigation strategies. In this work we introduce a cost-effective, scalable, and universally applicable UHI mapping framework that leverages open-source data and AI-driven feature extraction from remote sensing imagery. Using various causative factors such as city characteristics, anthropogenic heat, city canyons, and meteorological variables, we create UHI maps for the city of San Jos´e, California. We conducted comprehensive data engineering, including the collection, cleaning, transformation, and integration of spatial and demographic datasets. Our methodology enhances traditional UHI assessment by applying clustering techniques to categorize urban areas by heat intensity, improving map interpretability. Additionally, we trained a supervised machine learning classifier to predict UHI intensity categories for census tracts, enabling scalable categorization of new data. Finally, we conducted an equity analysis to uncover disparities in UHI exposure, highlighting demographic groups disproportionately affected. Our findings show that clustering all UHI causative factors enhances holistic UHI assessment and supports more equitable urban climate resilience planning.

Download

Share

COinS