Analyzing the city-level carbon peaking in China's residential building sector with explainable machine learning

Yihui Wu, Donglan Zha, Yang Cao, Yuting Yang and Robert Lee Kong Tiong

Energy, 2025, vol. 332, issue C

Abstract: The residential building carbon emissions (BCE) in China exhibit significant spatial heterogeneity, highlighting the need to uncover the driving forces behind these disparities to develop city-specific carbon reduction strategies. This study aims to analyze the spatiotemporal evolution of BCE at the city level and detect the driving forces of different BCE peaking states. We examined BCE from 2005 to 2021 in 41 cities of the Yangtze River Delta region using a top-down and downscaling approach. By applying explainable machine learning methods, we explored the nonlinear relationships between BCE and various influencing factors, quantifying the contributions of these factors under different peaking states. The results reveal critical nonlinear dynamics in building carbon emissions (BCE), where socioeconomic drivers like floor area, population, and urbanization rate exhibit threshold effects - notably, urbanization beyond 0.72 and electrification between 0.2 and 0.5 significantly alter emission trajectories. The analysis also uncovers complex interaction effects, demonstrating how smaller floor areas combined with elevated economic-technological indicators can mitigate emissions, whereas urban expansion coupled with GDP growth amplifies BCE without proper infrastructure optimization. The analysis of differentiated peaking driving forces reveals significant variations among Yangtze River Delta cities across socioeconomic development levels, emission characteristics, and peaking states. Building upon these findings, we have developed tailored BCE reduction strategies customized for cities at different peaking states.

Keywords: Residential building carbon emissions; Driving forces; Carbon peaking; Explainable machine learning (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S036054422502835X
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:332:y:2025:i:c:s036054422502835x

DOI: 10.1016/j.energy.2025.137193

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().