Scholarlink

<p>Artificial intelligence (AI)-assisted carbon dioxide (CO₂) capture aims to optimize the collection and storage of CO₂ from power plants and industrial operations, thereby contributing to emission reduction and climate change mitigation. By leveraging AI algorithms, the efficiency of CO₂ capture processes can be significantly enhanced through the optimization of critical parameters, including temperature, pressure, flow rates, and chemical reactions. AI-driven monitoring systems facilitate large-scale CO₂ extraction from the atmosphere by utilizing models derived from experimental data, which enhances accuracy and effectiveness. Furthermore, AI enables researchers to rapidly forecast the thermodynamic properties of CO₂ in solution, expediting advancements in capture technology. Machine learning-assisted pre-combustion CO₂ capture applications have demonstrated high predictive accuracy, paving the way for more efficient and scalable solutions. Although AI-assisted CO₂ capture offers several benefits, including the ability to quantify CO₂ emissions reductions upon model deployment, it also generates emissions during AI model training. Nevertheless, AI plays a crucial role in forecasting optimal conditions for capture processes, prompting researchers to explore the capabilities of artificial neural networks (ANNs) in CO₂ collection. This study introduces a novel AI model for estimating carbon conversion efficiency and determining the importance of features in enhancing impact assessment. The results show that CO₂ conversion efficiency is primarily dependent on time, with column length and inlet pressure also playing significant roles. Notably, both inlet and outlet pressure levels and column length substantially impact the model's predictions, whereas temperature and cross-sectional area exhibit a limited influence on the AI model and conversion efficiency. These findings provide critical insights into identifying the key engineering parameters that can enhance CO₂ conversion efficiency, ultimately informing the optimization of carbon capture processes.</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

An AI-aided carbon conversion framework for efficient carbon storage

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月2日

查看全文
  • Klemens Katterbauer,
  • Abdulaziz Al Qasim,
  • Almohannad Al Ghamdi

摘要

Artificial intelligence (AI)-assisted carbon dioxide (CO₂) capture aims to optimize the collection and storage of CO₂ from power plants and industrial operations, thereby contributing to emission reduction and climate change mitigation. By leveraging AI algorithms, the efficiency of CO₂ capture processes can be significantly enhanced through the optimization of critical parameters, including temperature, pressure, flow rates, and chemical reactions. AI-driven monitoring systems facilitate large-scale CO₂ extraction from the atmosphere by utilizing models derived from experimental data, which enhances accuracy and effectiveness. Furthermore, AI enables researchers to rapidly forecast the thermodynamic properties of CO₂ in solution, expediting advancements in capture technology. Machine learning-assisted pre-combustion CO₂ capture applications have demonstrated high predictive accuracy, paving the way for more efficient and scalable solutions. Although AI-assisted CO₂ capture offers several benefits, including the ability to quantify CO₂ emissions reductions upon model deployment, it also generates emissions during AI model training. Nevertheless, AI plays a crucial role in forecasting optimal conditions for capture processes, prompting researchers to explore the capabilities of artificial neural networks (ANNs) in CO₂ collection. This study introduces a novel AI model for estimating carbon conversion efficiency and determining the importance of features in enhancing impact assessment. The results show that CO₂ conversion efficiency is primarily dependent on time, with column length and inlet pressure also playing significant roles. Notably, both inlet and outlet pressure levels and column length substantially impact the model's predictions, whereas temperature and cross-sectional area exhibit a limited influence on the AI model and conversion efficiency. These findings provide critical insights into identifying the key engineering parameters that can enhance CO₂ conversion efficiency, ultimately informing the optimization of carbon capture processes.