Stacking ensemble learning and SHAP analysis for predicting CO2 solubility and guiding ionic liquid design
- 1School of Chemical Process Automation, Shenyang University of Technology 1 , Liaoyang, Liaoning, People's Republic of China
- 2School of Petrochemical Engineering, Shenyang University of Technology 2 , Liaoyang, Liaoning, People's Republic of China
Abstract
Excessive CO2 emissions constitute a primary driver of global climate change, creating an urgent need for efficient CO2 capture technologies. Ionic liquids (ILs) are considered highly promising absorbents. However, their vast chemical space poses significant challenges for experimental screening. In this study, Morgan fingerprint descriptors were combined with a stacking ensemble learning algorithm, and SHapley Additive exPlanations (SHAP) analysis was employed to develop an accurate and interpretable framework for predicting CO2 solubility. The stacking ensemble model employs the light gradient boosting machine and the backpropagation neural network as base learners. The dung beetle optimizer and the grey wolf optimizer were used to determine optimal hyperparameter combinations for these learners, while linear regression was adopted as the meta-learner to produce the final CO2 solubility prediction. The results demonstrate that the stacking ensemble algorithm achieves the highest predictive accuracy, attaining a test-set coefficient of determination (R2) of 0.9888, a mean absolute error of 0.0149 and a mean squared error of 0.0006. SHAP analysis further reveals that the [Tf2N] (bis(trifluoromethylsulfonyl)amide) anion exerts the most significant influence, followed by the alkyl chain length of imidazolium cations. Accordingly, combining the [Tf2N] anion with imidazolium cations bearing longer alkyl chains represents a promising strategy for synthesizing ILs with high CO2 absorption efficiency.
Related
- Predicting fluorinated gas solubility in deep eutectic solvents using machine learning and deep learning approaches
- A hybrid car-following behavior prediction framework for snowy weather based on stacking ensemble learning
- AqSol-Blend: A CPU-Trained Descriptor Ensemble for Aqueous Solubility Prediction
- Prediction of asphaltene onset pressure and precipitation amount using tree-based stacking–blending ensemble meta-learners: a flow assurance perspective
- Simultaneous hyperspectral quantitative analysis of amylose and amylopectin in foxtail millet using a heterogeneous stacking ensemble with a soft constraint on component error complementarity.
BibTeX
@article{yu2026stacking,
title = {{Stacking ensemble learning and SHAP analysis for predicting CO2 solubility and guiding ionic liquid design}},
author = {Siqi Yu and Weiyan Tong and Pengzhi Bei and Hongwei Bai},
journal = {Royal Society Open Science},
year = {2026},
month = oct,
doi = {10.1098/rsos.260335},
url = {https://royalsocietypublishing.org/rsos/article/13/10/260335/483511/Stacking-ensemble-learning-and-SHAP-analysis-for},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Stacking ensemble learning and SHAP analysis for predicting CO2 solubility and guiding ionic liquid design
AU - Siqi Yu
AU - Weiyan Tong
AU - Pengzhi Bei
AU - Hongwei Bai
PY - 2026
DA - 2026/10/07
JO - Royal Society Open Science
DO - 10.1098/rsos.260335
UR - https://royalsocietypublishing.org/rsos/article/13/10/260335/483511/Stacking-ensemble-learning-and-SHAP-analysis-for
AB - Excessive CO2 emissions constitute a primary driver of global climate change, creating an urgent need for efficient CO2 capture technologies. Ionic liquids (ILs) are considered highly promising absorbents. However, their vast chemical space poses significant challenges for experimental screening. In this study, Morgan fingerprint descriptors were combined with a stacking ensemble learning algorithm, and SHapley Additive exPlanations (SHAP) analysis was employed to develop an accurate and interpretable framework for predicting CO2 solubility. The stacking ensemble model employs the light gradient boosting machine and the backpropagation neural network as base learners. The dung beetle optimizer and the grey wolf optimizer were used to determine optimal hyperparameter combinations for these learners, while linear regression was adopted as the meta-learner to produce the final CO2 solubility prediction. The results demonstrate that the stacking ensemble algorithm achieves the highest predictive accuracy, attaining a test-set coefficient of determination (R2) of 0.9888, a mean absolute error of 0.0149 and a mean squared error of 0.0006. SHAP analysis further reveals that the [Tf2N] (bis(trifluoromethylsulfonyl)amide) anion exerts the most significant influence, followed by the alkyl chain length of imidazolium cations. Accordingly, combining the [Tf2N] anion with imidazolium cations bearing longer alkyl chains represents a promising strategy for synthesizing ILs with high CO2 absorption efficiency.
SN - 2054-5703
ER -