Scholarlink

<p>Forecasting carbon dioxide (CO<sub>2</sub>) emissions has become a significant issue in recent years. International organizations have emphasized the necessity of creating a plan to gradually reduce the concentration of this pollutant in the atmosphere to combat climate change and its catastrophic consequences. The cement industry represents one of the key sectors to address this problem. The objective of this study is to predict CO<sub>2</sub> emissions in North American cement industries. To achieve this, a multi-objective mathematical model is developed, integrating various machine learning algorithms. Furthermore, a sensitivity analysis is conducted to evaluate the impacts of varying the scale of deployment of current technologies focused on reducing CO<sub>2</sub> emissions. Results demonstrate a considerable improvement in accuracy metrics, with a 48.13% reduction in Mean Absolute Error achieved through the use of the Generalized Reduced Gradient method (GRG). Forecasts reveal an increase in emissions of about 0.58 MtCO<sub>2</sub> every year between 2020 and 2050. The proposed framework can assist decision-makers and policymakers in focusing on the technical and logistical requirements to meet net-zero emission 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

Forecasting CO2 emissions to achieve net-zero emission targets for North American cement industry

  • 期刊论文

  • 发表日期：

    2026年1月22日

查看全文
  • Ángel Francisco Galaviz Román,
  • Golam Kabir,
  • Seyedmehdi Mirmohammadsadeghi

摘要

Forecasting carbon dioxide (CO2) emissions has become a significant issue in recent years. International organizations have emphasized the necessity of creating a plan to gradually reduce the concentration of this pollutant in the atmosphere to combat climate change and its catastrophic consequences. The cement industry represents one of the key sectors to address this problem. The objective of this study is to predict CO2 emissions in North American cement industries. To achieve this, a multi-objective mathematical model is developed, integrating various machine learning algorithms. Furthermore, a sensitivity analysis is conducted to evaluate the impacts of varying the scale of deployment of current technologies focused on reducing CO2 emissions. Results demonstrate a considerable improvement in accuracy metrics, with a 48.13% reduction in Mean Absolute Error achieved through the use of the Generalized Reduced Gradient method (GRG). Forecasts reveal an increase in emissions of about 0.58 MtCO2 every year between 2020 and 2050. The proposed framework can assist decision-makers and policymakers in focusing on the technical and logistical requirements to meet net-zero emission targets.