Modeling Viscosity of CO₂–N₂ Gaseous Mixtures Using Robust Tree-Based Techniques: Extra Tree, Random Forest, GBoost, and LightGBM

Abstract

Carbon dioxide (CO 2 ) has an essential role in most enhanced oil recovery (EOR) methods in the oil industry. Oil swelling and viscosity reduction are the dominant mechanisms in an immiscible CO 2 -EOR process. Besides numerous CO 2 applications in EOR, most oil reservoirs do not have access to natural CO 2 , and capturing it from flue gas and other sources is costly. Flue gases are available in huge quantities at a significantly lower price and can be considered economically viable agents for EOR operations. In this work, four powerful machine learning algorithms, namely, extra tree (ET), random forest (RF), gradient boosting (GBoost), and light gradient boosted machine (LightGBM) were utilized to accurately estimate the viscosity of CO 2 −N 2 mixtures. To this aim, a databank was employed, containing 3036 data points over wide ranges of pressures and temperatures. Temperature, pressure, and CO 2 mole fraction were applied as input parameters, and the viscosity of the CO 2 −N 2 mixture was the output. The RF smart model had the highest precision with the lowest average absolute percent relative error (AAPRE) of 1.58%, root mean square error (RMSE) of 2.221, and determination coefficient (R 2 ) of 0.9993. The trend analysis showed that the RF model could precisely predict the real physical behavior of the CO 2 −N 2 viscosity variation. Finally, the outlier detection was performed using the leverage approach to demonstrate the validity of the utilized databank and the applicability area of the developed RF model. Accordingly, nearly 96% of the data points seemed to be dependable and valid, and the rest of them were located in the suspected and out-of-leverage data zones. 22

Modeling CO2 solubility in water using gradient boosting and light gradient boosting machine

“…Williams's plot is one of the outlier detection methods for examining the performance of developed models which is widely used in AI application studies 45 , 108 – 111 . The William plots of the proposed models for predicting the CO 2 solubility in water are shown in Fig.…”

On the evaluation of the carbon dioxide solubility in polymers using gene expression programming

“…The fluid adsorption process in different polymers is a vital circumstance in the oil industry concepts such as enhanced oil recovery (EOR) 1 – 3 , gas separation, imbibition of additives, and foaming processes 4 , 5 . Carbon dioxide (CO 2 ) is one of the most significant gases, which plays a noteworthy role in polymers’ structure, polymer foams, and production properties 4 , 6 . Also, CO 2 and supercritical carbon dioxide (SCCO 2 ), (a supercritical carbon dioxide is described as a fluid for which both temperature and pressure are higher than critical values) have become one of the most conventional green materials, that have been extensively used in solvent, anti-solvent or a solute in numerous field processing including material synthesis, material modification, foaming processes, polymerization and particle production 7 – 9 .…”