Built environment interventions for emission mitigation: A machine learning analysis of travel-related CO2 in a developing city

Qifan Shao, Wenjia Zhang, Xinyu (Jason) Cao, Jiawen Yang

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

The transport sector accounts for more than one-fifth of global CO2 emissions. Reducing fossil fuel consumption and travel-related CO2 emissions (TCE) is a major approach to mitigating global climate change. Urban planners worldwide propose to promote low-carbon travel by changing the built environment. Therefore, understanding the relationships between built environment variables and TCE is key to the development of land use and transportation policies. Using 2019 regional household travel data from Zhongshan, a polycentric urban area in China, this study developed a gradient boosting decision trees model to estimate the relative importance of built environment variables in predicting TCE and their nonlinear associations with TCE. Built environment variables collectively contribute nearly half of the predictive power to predicting TCE, suggesting the potential of built environment interventions. Among them, location accessibility to city-level and township-level centers and population density are the top-three important features in predicting TCE. Furthermore, most built environment variables show threshold relationships with TCE. The results suggest that polycentric development, intensification of town centers, and densification of street networks are conducive to TCE mitigation. These findings inform planners of effective ranges of built environment variables to promote low-carbon travel.

Original languageEnglish (US)
Article number103632
JournalJournal of Transport Geography
Volume110
DOIs
StatePublished - Jun 2023

Bibliographical note

Funding Information:
This work was supported by the National Natural Science Foundation of China ( 42171201 ) and the Shenzhen Municipal Natural Science Foundation (Key Project) ( GXWD20201231165807007-20200811151825001 , GXWD20201231165807007-20200810223326001 ). We appreciate two anonymous reviewers and the editor Becky P.Y. Loo, for their insightful comments and helpful suggestions.

Publisher Copyright:
© 2023 Elsevier Ltd

Keywords

  • GHG emissions
  • Gradient boosting decision trees (GBDT)
  • Low-carbon travel
  • Machine learning
  • Polycentric development
  • Threshold effect

Fingerprint

Dive into the research topics of 'Built environment interventions for emission mitigation: A machine learning analysis of travel-related CO2 in a developing city'. Together they form a unique fingerprint.

Cite this