On prediction of carbon dioxide solubility in aqueous systems of NaCl using LSSVM algorithm

ABSTRACT

In carbon dioxide-enhanced oil recovery approach, carbon dioxide-aqueous brine system is one of the noticeable fluid systems for engineers. The solubility of carbon dioxide in aqueous system is one of the effective thermophysical properties in this approach. Due to this fact, an innovative least square support vector machine algorithm is evolved to predict carbon dioxide solubility based on salinity, pressure, and temperature. The outcomes of the analyses express that evolved method has great precision in prediction of carbon dioxide solubility. Furthermore, an innovative mathematical analysis is implemented to identify the effect of input parameters on carbon dioxide solubility. This novel investigation can be a reliable source for researchers who deal with carbon dioxide phase behavior.

KEYWORDS:

• Carbon dioxide
• aqueous system
• solubility
• LSSVM
• artificial intelligence

Acknowledgments

The authors would like to gratefully acknowledge and appreciate the Department of Chemical Engineering, Faculty of Engineering, Marvdasht Islamic Azad University, Marvdasht, Iran, for the provision of the laboratory facilities necessary for completing this work.

Additional information

Funding

This work was supported by the Department of Chemical Engineering, Faculty of Engineering, Marvdasht Islamic Azad University, Marvdasht, Iran [N/A].