What question did this study set out to answer?

To optimize carbon capture efficiency in post-combustion amine scrubbing by combining process simulations with machine learning techniques.

April 4, 2026Open Access

Optimizing Carbon Capture Efficiency: Knowledge Extraction from Process Simulations of Post-Combustion Amine Scrubbing

Key Points

To optimize carbon capture efficiency in post-combustion amine scrubbing by combining process simulations with machine learning techniques.
Developed an integrated framework for amine scrubbing simulations and machine learning analysis.
Conducted Latin hypercube sampling to create 10,000 steady-state operational cases.
Benchmarked five regression architectures to assess prediction accuracy, selecting XGBoost for operational use.
Performed SHAP analysis to identify key factors affecting capture efficiency.
Utilized Pareto optimization to establish operational guidelines for varying capture efficiency.
Achieved R2 of 0.9729 and RMSE of 1.43% with the neural network model.
Identified liquid-to-gas ratio, inlet temperature, and MEA concentration as key efficiency determinants, explaining 85% of efficiency variation.
Demonstrated a 39% increase in specific regeneration duty penalty for maximum capture targets compared to baseline capture targets.
Established a compact control hierarchy suitable for reduced-order control architectures.

Abstract

Post-combustion amine scrubbing using monoethanolamine (MEA) remains a leading carbon capture technology, yet its deployment is constrained by high regeneration energy requirements and the computational expense of rigorous process simulation. This study presents an integrated framework coupling high-fidelity rate-based process simulation with explainable machine learning to systematically characterize a ten-dimensional operating space for MEA-based CO2 absorption. Latin hypercube sampling generated 10,000 steady-state cases, and five regression architectures were benchmarked under identical protocols. A neural network achieved the highest accuracy (R2 = 0.9729, RMSE = 1.43%), while XGBoost was selected as the operational surrogate due to its robust computational efficiency (1.5 ms inference latency) and native compatibility with exact Shapley value decomposition. SHAP analysis identified liquid-to-gas ratio as the dominant efficiency determinant, contributing 46.6% of total predictive importance, followed by inlet temperature and MEA concentration, with these three parameters collectively explaining 85% of efficiency variation and establishing a compact control hierarchy suitable for reduced-order control architectures. Bivariate interaction analysis located a high-efficiency operating region, while sensitivity analysis confirmed the strong influence of inlet temperature across the operating envelope. Pareto optimization via NSGA-II generated tiered operational guidelines spanning the 85% to 98% capture efficiency range, quantifying a 39% specific regeneration duty penalty (3.1 to 4.3 MJ/kg CO2) for pursuing maximum versus baseline capture targets. The framework demonstrates how explainable machine learning converts opaque process simulations into actionable engineering knowledge, providing a transparent and computationally efficient basis for design optimization and digital twin deployment in post-combustion carbon capture systems.

Read Full Paperexternally

Mark Helpful

Bookmark

Relay

View Full Paper