Machine learning to assess CO2 adsorption by biomass waste

• DOI: 10.1016/j.jcou.2023.102590
• Publication Date: 2023-10-01T03:27:15Z
• Authors: Mahmoud Maheri; Carlos Bazan; Sohrab Zendehboudi; Hamid Usefi
• Keywords: Perceptron; Gradient boosting; Python; Multilayer perceptron

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 combating air pollution and climate change issues. However, factors such as temperature, pressure, surface area can influence performance adsorbingcarbon dioxide. To maximize CO2 adsorption, vital determine the relationships among these variables. In this paper, we use several preprocessing techniques various machine learning algorithms, Gradient Boosting Regressor, Convolutional Neural Networks, Multi-Layer Perceptron, Long Short-Term Memory, explore efficacy of algorithms predicting capture capacities. We augment our datasets by generating new features turn ML models achieve better on augmented compared original dataset. Our achieved r2 score 90.7 % training set 85.73 test datasets. Furthermore, were able that ratio pressure well aspects tied physical conditions adsorbent material emerge most influential adsorption. A python implementation all experiments publicly available Github https://github.com/mmaheri/CO2_Capturing.git.