Prediction of CO2 Solubility in Ionic Liquids Based on Machine Learning and Analysis of SHAP

Zian Yan; Peng Jia; Yanhong Huang; Yifan Zhang; Pengzhi Bei; Song Xue; Qianqian Xu

doi:10.54097/g1q5km82

Authors

Zian Yan
Peng Jia
Yanhong Huang
Yifan Zhang
Pengzhi Bei
Song Xue
Qianqian Xu

DOI:

https://doi.org/10.54097/g1q5km82

Keywords:

CO2 absorption, Ionic liquids, Machine learning, Transformer, SHAP.

Abstract

The combination forms of anions and cations in Ionic liquids (ILs) which was solvent for the absorption of CO₂ were extremely numerous. Consequently, a Machine Learning (ML) model of Transformer was used to measure the solubility of CO₂ in each new ILs in this study. The model used 8869 data points and encoding anions and cations based on SMILES. The r, R², RMSE and MAE were used as error indicators. Additionally, a decoding method was referenced for the first time in the field of ML predictions of CO₂ solubility in ILs, which improved the data processing results. As a result, the model achieved better predictive standards. SMILES based SHAP analysis was used on the model to understand the black box operation. The results of the SHAP analysis identified the structural factors that influenced the model's results in the solubility of CO₂ in ILs.

Downloads

Download data is not yet available.

References

[1] Das, S., et al., Carbon dioxide chemistry towards carbon-neutrality. Green Chemical Engineering, 2022 (002): p. 003.

[2] Wanlin, et al., Industrial carbon dioxide capture and utilization: state of the art and future challenges.

[3] Lozano, P., et al., Ionic Liquids for Clean Biocatalytic Processes. Current Green Chemistry, 2017 (3): p. 4.

[4] Blanchard, L.A., et al., Green processing using ionic liquids and CO2. Nature, 1999. 399 (6731): p. 28-29.

[5] Sung, J.K., S.H. Kim, and M. Cheong, Solubility of Carbon Dioxide in Strongly Basic Ionic Liquid. Bulletin of the Korean Chemical Society, 2010.

[6] Chen, Y. and T. Mu, Revisiting greenness of ionic liquids and deep eutectic solvents. Green Chemical Engineering, 2021.

[7] Mcleese, S.E., et al., Design of ionic liquids via computational molecular design. Computers & Chemical Engineering, 2010. 34 (9): p. 1476-1480.

[8] Paduszynski, K., K. Klebowski, and M. Krolikowska, Predicting melting point of ionic liquids using QSPR approach: Literature review and new models. Journal of Molecular Liquids, 2021 (344-): p. 344.

[9] Weis, D.C. and D.R. Macfarlane, Computer-Aided Molecular Design of Ionic Liquids: An Overview. Cheminform, 2013. 44 (12): p. 1478-1486.

[10] Austin, et al., Computer-aided molecular design: An introduction and review of tools, applications, and solution techniques.

[11] Karelson, M., V.S. Lobanov, and A.R. Katritzky, Quantum-Chemical Descriptors in QSAR/QSPR Studies. Chemical Reviews, 1996. 96 (3): p. 1027-1044.

[12] Ali, M., et al., Prediction of CO2solubility in Ionic liquids for CO2capture using deep learning models. Scientific Reports, 2024. 14 (1).

[13] Nakhaei-Kohani, R., S. Atashrouz, and A.M. Pourmahdi, Ahmad, Hydrogen solubility in ionic liquids: Application of a structure-based deep learning approach and equations of state. International journal of hydrogen energy, 2023. 48 (80): p. 31234-31253.

[14] Shiflett, M.B., et al., Phase Behavior of N2O and CO2 in Room-Temperature Ionic Liquids [bmim] [Tf2N], [bmim] [BF4], [bmim] [N(CN)2], [bmim] [Ac], [eam] [NO3], and [bmim] [SCN]. International Journal of Thermophysics, 2012. 33 (3): p. 412-436.

[15] Polishuk and Ilya, Implementation of CP-PC-SAFT for Predicting Thermodynamic Properties and Gas Solubility in 1-Alkyl-3-methylimidazolium Bis (trifluoromethylsulfonyl) imide Ionic Liquids without Fitting Binary Parameters. Industrial & Engineering Chemistry Research, 2017: p.acs.iecr.7b01846.

[16] Panah, H.S., Modeling H2S and CO2 solubility in ionic liquids using the CPA equation of state through a new approach. Fluid Phase Equilibria, 2017. 437: p. 155-165.

[17] Bazargani, Z. and F. Sabzi, Prediction of CO2 solubility in ionic liquids with [HMIM] and [OMIM] cations by equation of state. Journal of Molecular Liquids, 2016.

[18] Mohammadi, M.R., et al., Toward predicting SO2 solubility in ionic liquids utilizing soft computing approaches and equations of state. Journal of the Taiwan Institute of Chemical Engineers, 2022. 133: p. 104220-.

[19] Baghban, A., et al., Sulfur dioxide solubility prediction in ionic liquids by a group contribution — LSSVM model. Chemical Engineering Research and Design, 2019.

[20] Ribeiro, V.M., Sulfur dioxide emissions in Portugal: Prediction, estimation and air quality regulation using machine learning. Journal of Cleaner Production, 2021.

[21] Lei, Z., C. Dai, and B. Chen, Gas solubility in ionic liquids. Chemical Reviews, 2014. 114 (2): p. 1289-1326.

[22] Weininger and David, SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. Journal of Chemical Information & Computer Sciences, 1988. 28 (1): p. 31-36.

[23] Akrom, M., S. Rustad, and H.K. Dipojono, SMILES-based machine learning enables the prediction of corrosion inhibition capacity. MRS Communications, 2024. 14 (3): p. 379-387.

[24] Liu, X.W.P.T.X.L.X., A machine learning method and system based on SMILES. 2021.

[25] Dhar, A.C., et al., Transformer Deep Learning Model for Bangla–English Machine Translation. Algorithms for Intelligent Systems, 2022.

[26] Vaswani, A., et al., Attention Is All You Need. arXiv, 2017.

[27] Farsani, R.M., E. Pazouki, and J. Jecei, A Transformer Self-Attention Model for Time Series Forecasting. Shahid Rajaee Teacher Training University, 2021 (1).

[28] Song, Y., et al., Incorporating Morphological Compostions with Transformer to Improve BERT. Journal of Physics Conference Series, 2020. 1486: p. 072071.

[29] Zhang, Y., X. Zhuang, and M. Dai, Analysis of GPT Series Model Training Technology with Transformer Architecture. Journal of Civil Aviation Flight University of China, 2023. 34 (5): p. 16-18.

[30] Lundberg, S. and S.I. Lee, A Unified Approach to Interpreting Model Predictions. 2017.