Urban Heat Island Intensity Across Global Climate Zones: A Data-Driven Comparative Analysis

Dhanya Prasad

doi:10.36948/ijfmr.2025.v07i05.59064

Urban Heat Island Intensity Across Global Climate Zones: A Data-Driven Comparative Analysis

Author(s)	Ms. Dhanya Prasad
Country	India
Abstract	Cities are heating up at an alarming pace. Not solely due to global climate change, but because of the way they are built and designed. The Urban Heat Island (UHI) effect amplifies local temperatures in densely developed areas, driving up energy demand, degrading air quality, and threatening human health. While solutions such as urban greening and reflective materials are known, their global effectiveness remains unclear because UHI behaviors differ across climates and geographies. This study employs a globally consistent dataset of over 10,000 cities spanning 2001–2021 to investigate how Urban Heat Island Intensity (UHII) varies by climate zone and latitude. Using satellite-derived DEA (Dynamic Equal Area) UHII measurements, cities were first categorized into simplified Köppen–Geiger climate zones based on geographic coordinates. Spatial visualizations were developed to illustrate UHII distribution globally. A suite of predictive models , Linear Regression, Ridge, ElasticNet, Decision Tree, Random Forest, Gradient Boosting, K-Nearest Neighbors , were developed using a standardized preprocessing pipeline (scaling and one-hot encoding). The Random Forest model produced the best predictive performance (R² ≈ 0.36). A temporal slope analysis identified the top 50 cities that exhibited UHII reduction over the study period. Visualizations and model diagnostics are provided to support interpretation. The results demonstrate that simplified climate classification derived from coordinates is a useful organizing principle for cross-city comparison, that UHII patterns are strongly climate-dependent, and that ensemble methods outperform linear baselines for UHII prediction. The paper concludes with a discussion of limitations and recommendations for incorporating remote-sensing covariates (NDVI, albedo, LST) and more advanced models in future work.
Keywords	Urban Heat Island Effect, Climate Zones, Data Science, Random Forest, UHI, Intensity, DEA, Environment
Field	Computer > Data / Information
Published In	Volume 7, Issue 5, September-October 2025
Published On	2025-10-29
DOI	https://doi.org/10.36948/ijfmr.2025.v07i05.59064

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Urban Heat Island Intensity Across Global Climate Zones: A Data-Driven Comparative Analysis

Share this