Scholarlink

<p>Understanding carbon emissions of the railway transportation industry in China is critical for effective climate action. This study applied machine learning models to analyze railway operational conditions and socio-economic driving factors of carbon emissions across four railway operational regions with different terrain, climate, and economic development characteristics in China from 2009 to 2021. This study indicates that People, Electricity Carbon Emission Factor, Tertiary Industry Gross Domestic, Railway Passenger Volume, Railway freight Volume, Research and Development Investment and Railway Infrastructure Level have a significant impact on carbon emissions. The Lasso_LR model shows strong fitting performance, as the mean absolute error is 4.98% of the average carbon emissions. By 2021, the Qinghai-Tibet Plateau, Yunnan Province, the Guangxi Zhuang Autonomous Region, and the Yangtze River Delta Region showed a decline in carbon emissions, with emission reductions of 41.1%, 36.6%, 21.4%, and 21.5% compared to their levels in 2009. Model predictions indicate that carbon emissions from railways in the Qinghai-Tibet Plateau, Yunnan Province, the Guangxi Zhuang Autonomous Region, and the Yangtze River Delta Region are projected to decline by 15.8%, 12.23%, 34.15%, and 0.03% respectively by 2030, relative to 2021 levels in the regional emission-reduction scenario. This study offers insights into the socio-economic and internal mechanisms of emissions, guiding tailored reduction targets for different railway operational regions to aid China in achieving ‘3060’ target.</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

Railway carbon emission scenario prediction in four regions of China based on machine learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月12日

查看全文
  • Yintao Lu,
  • Shuchang Liu,
  • Yuechao Wang,
  • Shengming Qiu,
  • Pengju Wang,
  • Caihong Zhang,
  • Bo Hu,
  • Jiayan Wang,
  • Jiashuai Zhao,
  • Hong Yao

摘要

Understanding carbon emissions of the railway transportation industry in China is critical for effective climate action. This study applied machine learning models to analyze railway operational conditions and socio-economic driving factors of carbon emissions across four railway operational regions with different terrain, climate, and economic development characteristics in China from 2009 to 2021. This study indicates that People, Electricity Carbon Emission Factor, Tertiary Industry Gross Domestic, Railway Passenger Volume, Railway freight Volume, Research and Development Investment and Railway Infrastructure Level have a significant impact on carbon emissions. The Lasso_LR model shows strong fitting performance, as the mean absolute error is 4.98% of the average carbon emissions. By 2021, the Qinghai-Tibet Plateau, Yunnan Province, the Guangxi Zhuang Autonomous Region, and the Yangtze River Delta Region showed a decline in carbon emissions, with emission reductions of 41.1%, 36.6%, 21.4%, and 21.5% compared to their levels in 2009. Model predictions indicate that carbon emissions from railways in the Qinghai-Tibet Plateau, Yunnan Province, the Guangxi Zhuang Autonomous Region, and the Yangtze River Delta Region are projected to decline by 15.8%, 12.23%, 34.15%, and 0.03% respectively by 2030, relative to 2021 levels in the regional emission-reduction scenario. This study offers insights into the socio-economic and internal mechanisms of emissions, guiding tailored reduction targets for different railway operational regions to aid China in achieving ‘3060’ target.