AI-based Catalytic Performance Prediction for CO₂ Electrochemical Reduction using Ionic Liquids

Recently, ionic liquids (ILs) have garnered remarkable attention as electrolytes for CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> electrochemical reduction (CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>ER) due to their unique properties viz. thermal and chemical stability, good CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> solubility, and their ability to reduce the reaction overpotential. The catalytic performance of ILs in CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>ER has been explored via experimental methods which have limitations, given the unclear understanding of the complex reaction mechanisms. Recently, Artificial Intelligence (AI) methods have gained increased attention across diverse applications including chemical engineering. These methods play a pivotal role in extracting insights, understanding patterns, and mitigating uncertainty within datasets. Hence, in this study, we investigate two categories of AI models (ML and DL) for predicting the CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>ER catalytic performance using ILs via Gibbs free energy and capacity. For this task, we formulate a novel dataset (CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>ERIL) from 90 ILs in two formats using: (1) 30 electronic and geometric IL properties, (2) IL chemical structures in SMILES data format. The dataset versions are formulated using the Conductor-like Screening Model for Realistic Solvents (COSMO-RS) and TURBOMOLE software. The prediction results of the AI models on the two dataset versions depict a similar trend in the predicted target variables signifying that the dataset format does not really affect the model performance. Moreover, the best ML model outperforms the DL model for one target variable, Free energy predictions, but lags in the other target variable, capacity predictions. Our study is novel in terms of AI methodology as well as the CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>ER dataset. Our research outcomes will contribute to the more effective selection of ILs for CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>ER catalysis.