Scholarlink

<p>Understanding the spatial distribution and future trends of industrial carbon emission efficiency (ICEE) is pivotal for achieving low-carbon urban industrial development. Despite its importance, existing studies often overlook the integration of static and dynamic evaluation indicators, the precision of clustering methods, and the necessity of tailored policy measures. This study addresses these gaps by examining 285 Chinese cities from 2000 to 2021, employing a Super-SBM model to classify ICEE into four ranks. Utilizing a dual-constrained clustering approach, the cities were divided into six regions and their spatial-temporal evolution was analyzed. The hybrid algorithm method was further employed to forecast ICEE for the next decade across these regions. The findings differentiate high-efficiency and low-efficiency regions, and the application of Extreme Gradient Boosting method for feature importance and bias dependence analysis identified key influencing factors. High-efficiency regions should continue to insist on raising the level of per capita GDP, scientific and technological innovation as the driving force. Low-efficiency regions should reduce energy consumption and open to the outside world. These insights will offer practical guidance for Chinese industries to enhance production efficiency and reduce carbon emissions, with an explicit focus on region-specific industrial structure optimization, improvements in energy efficiency, and increased investment in technological innovation. It can improve the ICEE and promote the constructive and feasible implementation of the China’s “dual-carbon” strategy, such as (1) optimizing regional industrial structure, (2) improving energy efficiency, (3) strengthening technological innovation incentives, and (4) implementing region-specific emission reduction targets.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Advancing industrial carbon emission efficiency in Chinese cities: integrating Dual-Constrained clustering with NCPSO-BP forecasting and XGBoost analysis

  • 期刊论文

  • 发表日期：

    2025年8月31日

查看全文
  • Jian Yin,
  • Xiyue Tu,
  • Yini Meng

摘要

Understanding the spatial distribution and future trends of industrial carbon emission efficiency (ICEE) is pivotal for achieving low-carbon urban industrial development. Despite its importance, existing studies often overlook the integration of static and dynamic evaluation indicators, the precision of clustering methods, and the necessity of tailored policy measures. This study addresses these gaps by examining 285 Chinese cities from 2000 to 2021, employing a Super-SBM model to classify ICEE into four ranks. Utilizing a dual-constrained clustering approach, the cities were divided into six regions and their spatial-temporal evolution was analyzed. The hybrid algorithm method was further employed to forecast ICEE for the next decade across these regions. The findings differentiate high-efficiency and low-efficiency regions, and the application of Extreme Gradient Boosting method for feature importance and bias dependence analysis identified key influencing factors. High-efficiency regions should continue to insist on raising the level of per capita GDP, scientific and technological innovation as the driving force. Low-efficiency regions should reduce energy consumption and open to the outside world. These insights will offer practical guidance for Chinese industries to enhance production efficiency and reduce carbon emissions, with an explicit focus on region-specific industrial structure optimization, improvements in energy efficiency, and increased investment in technological innovation. It can improve the ICEE and promote the constructive and feasible implementation of the China’s “dual-carbon” strategy, such as (1) optimizing regional industrial structure, (2) improving energy efficiency, (3) strengthening technological innovation incentives, and (4) implementing region-specific emission reduction targets.