Predicting the interfacial tension of CO2 and NaCl aqueous solution with machine learning

• Published in: Scientific reports Vol. 15; no. 1; pp. 25471 - 16
• Main Authors: Liaqat, Kashif, Preston, Daniel J., Schaefer, Laura
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 15.07.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166/988; 639/4077/4057; 704/172/4081; Accuracy; Algorithms; Aqueous solutions; Aquifers; Artificial neural networks; Brines; Carbon capture and storage; Carbon dioxide; Carbon dioxide emissions; Carbon dioxide fixation; Climate change; CO2-brine; Comparative analysis; Datasets; Decision trees; Emissions; Experimental methods; Experiments; Geological sequestration; Geology; Global warming; Humanities and Social Sciences; Learning algorithms; Machine learning; Monte Carlo simulation; multidisciplinary; Neural networks; Regression analysis; Research methodology; Saline water; Salinity; Science; Science (multidisciplinary); Sodium chloride; Storage capacity; Support vector machines; Support vector machines; brine; Geological sequestration; CO; Carbon capture and storage; Artificial neural networks
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-025-10274-w

Achieving carbon neutrality requires effective strategies to reduce CO 2 emissions, and geological sequestration of CO 2 is considered among the most promising and economically viable options. The interfacial tension (IFT) between the CO 2 and the surrounding liquid (underground salt water or brine, NaCl) is a key parameter that affects the storage capacity of CO 2 in saline aquifers; however, the experimental measurement of IFT is often time-consuming, labor-intensive, and reliant on expensive equipment, and empirical correlations demonstrate a low level of accuracy. Machine learning (ML) techniques have been suggested as an alternative approach, and the current literature related to interfacial phenomena utilizes a wide array of basic and advanced ML models for predicting IFT, though often without a comparative analysis, raising the question of which model is most appropriate for this specific application. In this work, multiple machine learning models, including linear regression (LR), support vector machine (SVM), decision tree regressor (DTR), random forest regressor (RFR), and multilayer perceptron (MLP), are used to predict the IFT of the CO 2 and aqueous solution of NaCl. Models are trained using an experimental dataset that covers a wide range of temperature, pressure, and salinity (NaCl) conditions for CO 2 -brine IFT. Hyperparameter tuning algorithms are utilized to optimize each model, and the performance is evaluated using metrics such as mean absolute error (MAE) and mean absolute percentage error (MAPE). The best-performing algorithms are found to be SVM and MLP, with a MAPE of 0.97% and 0.99% and a MAE of 0.39 mN/m and 0.40 mN/m, respectively. The linear regression model demonstrated the worst performance with a MAPE of 4.25% and an MAE of 1.7 mN/m. The feature importance analysis reveals that pressure is the main parameter affecting the IFT. Our findings indicate a notable enhancement in prediction accuracy over previous ML studies in this area. Moreover, the results from this study suggest that even the basic ML models that were investigated, when properly tuned and optimized, are sufficient for accurate IFT predictions. This demonstrates that ML models offer a cost-effective and efficient alternative to experimental methods, potentially optimizing designs for CO 2 sequestration.