Numerical investigation of carbon dioxide capture using nanofluids via machine learning

Abstract

Using nanofluids to capture CO2 is a promising method of reducing emissions. The goal of this study was to develop models that could forecast how well water-based nanofluids would absorb CO2. Several machine learning models, such as Decision Tree, Random Forest, eXtreme Gradient Boosting, and K-Nearest Neighbors, underwent training using a total of 1306 experimental datasets. These datasets contained information on the CO2 solubility in aqueous solutions for different types of nanoparticles. In terms of Average Absolute Relative Deviation (AARD%), Mean Absolute Error (MAE), Relative Absolute Error, Mean Squared Error, and Correlation Coefficient, the predictive performance on separate test data was assessed. The XGBoost model demonstrates a higher degree of accuracy in simulating the absorption capacity of aqueous nanofluid compared to other models. This is evident through the AARD value of 2.8%, MSE of 0.00084, MAE of 0.012 and an R value of 0.992. The research provides insight into the utilization of different machine learning algorithms for simulating the absorption of CO2 by nanofluids. By employing accurate data-driven models, the efficiency of nanofluid-based CO2 capture processes can be enhanced through improvements in their design and operating conditions.