Acceso abierto

Machine Learning and Reinforcement Learning-Driven Optimization of Carbon Capture and Storage Processes and Their Environmental Impact Assessment

  
11 abr 2025

Cite
Descargar portada

Figure 1.

Overview of the CCS optimization framework integrating ML, RL, and LCA.
Overview of the CCS optimization framework integrating ML, RL, and LCA.

Figure 2.

True vs. Predicted CO2 Capture Efficiency for Different Models
True vs. Predicted CO2 Capture Efficiency for Different Models

Figure 3.

Convergence of Different Optimization Methods
Convergence of Different Optimization Methods

Figure 4.

Comparison of Execution Time per Step for Different Optimization Methods
Comparison of Execution Time per Step for Different Optimization Methods

Comparison of Optimization Performance in CCS Process

Method CO2 Capture Efficiency (%) Energy Consumption (MJ/ton CO2)
Rule-Based Control 88.2 3.56
Gradient Descent 90.3 3.24
AI-Optimized Process 92.1 3.15

Comparison of Predictive Performance for CO2 Capture Efficiency

Model MAE RMSE R2Score
SVR 2.31 3.85 0.79
RF 1.98 3.21 0.85
DNN 1.74 2.92 0.88
GBDT 1.56 2.67 0.91
Hybrid (GBDT + DNN) 1.32 2.34 0.94

Comparison of Computational Efficiency

Method Execution Time per Step (ms) Total Optimization Time (s)
Rule-Based Control 5.6 0.56
Gradient Descent 74.2 7.42
AI-Optimized Process 52.7 5.27