Predicting Urban Heat Island Mitigation with Random Forest Regression in Belgian Cities

Mitali Yeshwant Joshi; Daniel G. Aliaga; Jacques Teller

doi:10.1007/978-3-031-31746-0_16

Predicting Urban Heat Island Mitigation with Random Forest Regression in Belgian Cities

Mitali Yeshwant Joshi, Daniel G. Aliaga, Jacques Teller

University of Liege

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review

Abstract

An abundance of impervious surfaces like building roofs in densely populated cities make green roofs a suitable solution for urban heat island (UHI) mitigation. Therefore, we employ random forest (RF) regression to predict the impact of green roofs on the surface UHI (SUHI) in Liege, Belgium. While there have been several studies identifying the impact of green roofs on UHI, fewer studies utilize a remote-sensing-based approach to measure impact on Land Surface Temperatures (LST) that are used to estimate SUHI. Moreover, the RF algorithm, can provide useful insights. In this study, we use LST obtained from Landsat-8 imagery and relate it to 2D and 3D morphological parameters that influence LST and UHI effects. Additionally, we utilise parameters that influence wind (e.g., frontal area index). We simulate the green roofs by assigning suitable values of normalised difference-vegetation index and built-up index to the buildings with flat roofs. Results suggest that green roofs decrease the average LST.

Original language	English
Title of host publication	Intelligence for Future Cities
Subtitle of host publication	Planning Through Big Data and Urban Analytics
Editors	Robert Goodspeed, Raja Sengupta, Marketta Kyttä, Christopher Pettit
Publisher	Springer
Pages	305-323
ISBN (Print)	9783031317453, 9783031317460
DOIs	https://doi.org/10.1007/978-3-031-31746-0_16
Publication status	Published - 2023
Externally published	Yes

Publication series

Name	The Urban Book Series

Keywords

Green roofs
Random forest regression
Urban heat island (UHI)
Land surface temperature (LST)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-031-31746-0_16

Cite this

Joshi, M. Y., Aliaga, D. G., & Teller, J. (2023). Predicting Urban Heat Island Mitigation with Random Forest Regression in Belgian Cities. In R. Goodspeed, R. Sengupta, M. Kyttä, & C. Pettit (Eds.), Intelligence for Future Cities: Planning Through Big Data and Urban Analytics (pp. 305-323). (The Urban Book Series). Springer. https://doi.org/10.1007/978-3-031-31746-0_16

@inbook{28e9afd5c1b44830877207d38d5f61ae,

title = "Predicting Urban Heat Island Mitigation with Random Forest Regression in Belgian Cities",

abstract = "An abundance of impervious surfaces like building roofs in densely populated cities make green roofs a suitable solution for urban heat island (UHI) mitigation. Therefore, we employ random forest (RF) regression to predict the impact of green roofs on the surface UHI (SUHI) in Liege, Belgium. While there have been several studies identifying the impact of green roofs on UHI, fewer studies utilize a remote-sensing-based approach to measure impact on Land Surface Temperatures (LST) that are used to estimate SUHI. Moreover, the RF algorithm, can provide useful insights. In this study, we use LST obtained from Landsat-8 imagery and relate it to 2D and 3D morphological parameters that influence LST and UHI effects. Additionally, we utilise parameters that influence wind (e.g., frontal area index). We simulate the green roofs by assigning suitable values of normalised difference-vegetation index and built-up index to the buildings with flat roofs. Results suggest that green roofs decrease the average LST.",

keywords = "Green roofs, Random forest regression, Urban heat island (UHI), Land surface temperature (LST)",

author = "Joshi, {Mitali Yeshwant} and Aliaga, {Daniel G.} and Jacques Teller",

year = "2023",

doi = "10.1007/978-3-031-31746-0_16",

language = "English",

isbn = "9783031317453",

series = "The Urban Book Series",

publisher = "Springer",

pages = "305--323",

editor = "Robert Goodspeed and Raja Sengupta and Marketta Kytt{\"a} and Christopher Pettit",

booktitle = "Intelligence for Future Cities",

}

Predicting Urban Heat Island Mitigation with Random Forest Regression in Belgian Cities. / Joshi, Mitali Yeshwant; Aliaga, Daniel G.; Teller, Jacques.
Intelligence for Future Cities: Planning Through Big Data and Urban Analytics. ed. / Robert Goodspeed; Raja Sengupta; Marketta Kyttä; Christopher Pettit. Springer, 2023. p. 305-323 (The Urban Book Series).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review

TY - CHAP

T1 - Predicting Urban Heat Island Mitigation with Random Forest Regression in Belgian Cities

AU - Joshi, Mitali Yeshwant

AU - Aliaga, Daniel G.

AU - Teller, Jacques

PY - 2023

Y1 - 2023

N2 - An abundance of impervious surfaces like building roofs in densely populated cities make green roofs a suitable solution for urban heat island (UHI) mitigation. Therefore, we employ random forest (RF) regression to predict the impact of green roofs on the surface UHI (SUHI) in Liege, Belgium. While there have been several studies identifying the impact of green roofs on UHI, fewer studies utilize a remote-sensing-based approach to measure impact on Land Surface Temperatures (LST) that are used to estimate SUHI. Moreover, the RF algorithm, can provide useful insights. In this study, we use LST obtained from Landsat-8 imagery and relate it to 2D and 3D morphological parameters that influence LST and UHI effects. Additionally, we utilise parameters that influence wind (e.g., frontal area index). We simulate the green roofs by assigning suitable values of normalised difference-vegetation index and built-up index to the buildings with flat roofs. Results suggest that green roofs decrease the average LST.

AB - An abundance of impervious surfaces like building roofs in densely populated cities make green roofs a suitable solution for urban heat island (UHI) mitigation. Therefore, we employ random forest (RF) regression to predict the impact of green roofs on the surface UHI (SUHI) in Liege, Belgium. While there have been several studies identifying the impact of green roofs on UHI, fewer studies utilize a remote-sensing-based approach to measure impact on Land Surface Temperatures (LST) that are used to estimate SUHI. Moreover, the RF algorithm, can provide useful insights. In this study, we use LST obtained from Landsat-8 imagery and relate it to 2D and 3D morphological parameters that influence LST and UHI effects. Additionally, we utilise parameters that influence wind (e.g., frontal area index). We simulate the green roofs by assigning suitable values of normalised difference-vegetation index and built-up index to the buildings with flat roofs. Results suggest that green roofs decrease the average LST.

KW - Green roofs

KW - Random forest regression

KW - Urban heat island (UHI)

KW - Land surface temperature (LST)

UR - http://dx.doi.org/10.1007/978-3-031-31746-0_16

U2 - 10.1007/978-3-031-31746-0_16

DO - 10.1007/978-3-031-31746-0_16

M3 - Chapter

SN - 9783031317453

SN - 9783031317460

T3 - The Urban Book Series

SP - 305

EP - 323

BT - Intelligence for Future Cities

A2 - Goodspeed, Robert

A2 - Sengupta, Raja

A2 - Kyttä, Marketta

A2 - Pettit, Christopher

PB - Springer

ER -

Predicting Urban Heat Island Mitigation with Random Forest Regression in Belgian Cities

Abstract

Publication series

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this