Mapping Spatiotemporal Dynamic Changes in Urban CO<sub>2</sub> Emissions in China by Using the Machine Learning Method and Geospatial Big Data

Accurately and objectively evaluating the spatiotemporal dynamic changes in CO<sub>2</sub> emissions is significant for human sustainable development. However, traditional CO<sub>2</sub> emissions estimates, typically derived from national or provincial energy statistics, oft...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei Guo, Yongxing Li, Ximin Cui, Xuesheng Zhao, Yongjia Teng, Andreas Rienow
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/4/611
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurately and objectively evaluating the spatiotemporal dynamic changes in CO<sub>2</sub> emissions is significant for human sustainable development. However, traditional CO<sub>2</sub> emissions estimates, typically derived from national or provincial energy statistics, often lack spatial information. To develop a more accurate spatiotemporal model for estimating CO<sub>2</sub> emissions, this research innovatively incorporates nighttime light data, vegetation cover data, land use data, and geographic big data into the study of pixel-level urban CO<sub>2</sub> emissions estimation in China. The proposed method significantly improves the precision of CO<sub>2</sub> emissions estimation, achieving an average accuracy of 83.76%. This study reveals that the type of decoupling varies according to different scales, with more negative decoupling occurring in northern cities. Factors such as the per capita GDP and urbanization contribute to the increase in CO<sub>2</sub> emissions, while the structure of industry and energy consumption play a crucial role in reducing them. The findings in this study could potentially be used to develop tailored carbon reduction strategies for different spatial scales in China.
ISSN:2072-4292