Quantifying the Effects of Urban Form on Land Surface Temperature in Subtropical High-Density Urban Areas Using Machine Learning

Yanwei Sun,Run Wang,Chao Gao,Jialin Li,Jian Liu

doi:10.3390/rs11080959

Yanwei Sun, Run Wang + Show 3 more

Open Access

https://doi.org/10.3390/rs11080959

Copy DOI

Abstract

It is widely acknowledged that urban form significantly affects urban thermal environment, which is a key element to adapt and mitigate extreme high temperature weather in high-density urban areas. However, few studies have discussed the impact of physical urban form features on the land surface temperature (LST) from a perspective of comprehensive urban spatial structures. This study used the ordinary least-squares regression (OLS) and random forest regression (RF) to distinguish the relative contributions of urban form metrics on LST at three observation scales. Results of this study indicate that more than 90% of the LST variations were explained by selected urban form metrics using RF. Effects of the magnitude and direction of urban form metrics on LST varied with the changes of seasons and observation scales. Overall, building morphology and urban ecological infrastructure had dominant effects on LST variations in high-density urban centers. Urban green space and water bodies demonstrated stronger cooling effects, especially in summer. Building density (BD) exhibited significant positive effects on LST, whereas the floor area ratio (FAR) showed a negative influence on LST. The results can be applied to investigate and implement urban thermal environment mitigation planning for city managers and planners.

Highlights

An urban heat island (UHI) has been observed and recognized to exist in the most of cities around the world [1]
Taking the subtropical coastal city of Ningbo as a case study, this work quantitatively examined the relative contributions of urban form metrics on the land surface temperature (LST) variations in both summer and winter using ordinary least-squares regression (OLS) and RF ensemble models
We constructed the OLS and RF regression models for a high-density urban area with the size of 8 km × 8 km to distinguish to what degree each urban form metric influenced the LST patterns

Summary

Introduction

An urban heat island (UHI) has been observed and recognized to exist in the most of cities around the world [1]. Compared to their surrounding rural areas, an elevated temperature of urban areas directly affects urban ecological environment quality, and increases human risk of violence and mortality, impacting on mental well-being of urban residents and overall livability of cities [2,3,4,5,6,7]. An understanding of the complex relationships between features of urban form and the land surface temperature (LST) is critically important to mitigate the UHI and provide guidance for the environmentally-friendly planning of cities

Objectives

Methods

Findings

Discussion

Conclusion