Machine learning to assess CO2 adsorption by biomass waste

Biomass Waste Derived Porous Carbon (BWDPC) is widely used for its ability to adsorb carbon dioxide (CO2) in large-scale industrial operations, making it a leading solution for combating air pollution and climate change issues. However, factors such as temperature, pressure, and surface area can influence its performance in adsorbing CO2. To maximize CO2 adsorption, it is vital to determine the relationships among these variables. In this paper, we use several preprocessing techniques and various Machine Learning (ML) algorithms, such as Gradient Boosting Regressor, Convolutional Neural Networks, Multi-Layer Perceptron, and Long Short-Term Memory, to explore the efficacy of these algorithms in predicting CO2 capture capacities. We augment our datasets by generating new features to achieve a better predictive performance on the augmented datasets compared to the original dataset while employing the introduced ML models. The predictive ML tools result in an r2 score of 90.7 % on the training set and 85.73 % on the testing set of the augmented datasets. Furthermore, it is found that the ratio of carbon to pressure as well as temperature, and aspects tied to the physical conditions of the adsorbent material emerge as the most influential factors in CO2 adsorption. A python implementation of all our cases/scenarios is publicly available in Github https://github.com/mmaheri/CO2_Capturing.git. •We apply various preprocessing steps and augment the original dataset by generating new features.•We compare the performance of various machine learning algorithms on the original and augmented datasets.•The machine learning algorithms show a better performance on the augmented dataset in terms of r2 score.•Convolutional Neural Network and Gradient Boosting Regression exhibit the best performance.•The ratio of carbon to pressure as well as temperature, and aspects tied to the physical conditions of the adsorbent material emerge as the most influential factors in CO2 adsorption.