Reaching machine learning leverage to advance performance of electrocatalytic CO2 conversion in non-aqueous deep eutectic electrolytes

• Published in: Scientific reports 2024-10, Vol.14 (1), p.24757-18, Article 24757
• Main Authors: Halilu, Ahmed, Hadj-Kali, Mohamed Kamel, Hizaddin, Hanee Farzana, Hashim, Mohd Ali, Ali, Emad M., Bhargava, Suresh
• Format: Article
• Language: English
• Subjects: 639/166; 639/301; 639/638; 639/705; 704/172; Adiabatic; Algorithms; Artificial Intelligence; Carbon dioxide; Chemical reduction; CO2 capture and utilization; Deep eutectic electrolytes; Electrocatalysis; Electrochemistry; Electrolytes; Humanities and Social Sciences; Learning algorithms; Machine learning; multidisciplinary; Potassium carbonate; Reaction Engineering; Science; Science (multidisciplinary)
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-74893-5

Deep eutectic electrolytes (DEEs) show promise for future electrochemical systems due to their adjustable buffer capacities. This study utilizes machine learning algorithms to analyse the carbon dioxide reduction reaction (CO 2 RR) in DEEs with a buffer capacity of approximately 10.21 mol/pH. The objective is to minimize undesired hydrogen evolution reactions (HER) and render CO 2 RR dominant in a membrane cell. The CO 2 RR process was found to be non-adiabatic, as the time of nuclear motion for CO 3 2− in K 2 CO 3 product, through CO 2 ●− trapping, is 0.368 femtoseconds shorter than the 1.856 × 10 −3 s charge transfer relaxation time. Microkinetic analysis reveals that the rate of CO 2 RR to CO 2 ●− is 2.14 × 10 3 mol/cm 2 /s 2 with a rate constant of 2.1 × 10 10 cm/s. Our findings demonstrate that ensemble and k-Nearest Neighbours algorithms learn the CO 2 RR dataset, achieving a prediction accuracy of over 99%. The models were verified visually and quantitatively by overlaying predicted and experimental dataset. Diagnostic and SHAP analyses highlighted the gradient boost ensemble algorithm, predicting asymptotic current densities of -4.114 mA/cm 2 or -13.340 mA/cm 2 , with high turnover frequencies (TOF) of 3.79 × 10 10 h -1 or 12.30 × 10 10 h -1 for CO 2 ●− or K 2 CO 3 generation on silver electrodes, respectively. These results consider both accuracy and robustness against overfitting, providing an opportunity to optimize future non-aqueous electrolytes for convenient TOF measurements at industrially relevant current densities.