Modeling and Optimizing N/O-Enriched Bio-Derived Adsorbents for CO₂ Capture: Machine Learning and DFT Calculation Approaches

Abstract

The CO2 emission issue has triggered the promotion of carbon capture and storage (CCS), particularly bio-route CCS as a sustainable procedure to capture CO2 using biomass-based activated carbon (BAC). The well-known multi-nitrogen functional groups and microstructure features of N-doped BAC adsorbents can synergistically promote CO2 physisorption. Here, machine learning (ML) modeling was applied to the various physicochemical features of N-doped BAC as a challenge to figure out the unrevealed mechanism of CO2 capture. A radial basis function neural network (RBF-NN) was employed to estimate the in operando efficiency of microstructural and N-functionality groups at six conditions of pressures ranging from 0.15 to 1 bar at room and cryogenic temperatures. A diverse training algorithm was applied, in which trainbr illustrated the lowest mean absolute percent error (MAPE) of <3.5%. RBF-NN estimates the CO2 capture with an R 2 range of 0.97–0.99 of BACs as solid adsorbents. Also, the generalization assessment of RBF-NN observed errors, tolerating 0.5–6% of MAPE in 50–80% of total data sets. An alternative survey sensitivity analysis discloses the importance of multiple features such as specific surface area (SSA), micropore volume (%V mic), average pore diameter (AVD), and nitrogen content (N%), oxidized-N, and graphitic-N as nitrogen functional groups. A genetic algorithm (GA) optimized the physiochemical properties of N-doped ACs. It proposed the optimal CO2 capture with a value of 9.2 mmol g–1 at 1 bar and 273 K. The GA coupled with density functional theory (DFT) to optimize the geometries of exemplified BACs and adsorption energies with CO2 molecules.

A critical review on machine-learning-assisted screening and design of effective sorbents for carbon dioxide (CO2) capture

“…frontiersin.org which was generally in line with previous studies. The CO 2 adsorption behaviors of bio-derived N/O-enriched activated carbons were also simulated by a NN-based algorithm, and density functional theory (DFT) calculations were adopted as a supportive method to identify the adsorption mechanism of CO 2 (Rahimi et al, 2022). The role of different characteristics, that is, pyridinic nitrogen (N-6), pyrolytic nitrogen (N-5), oxidized nitrogen (N-X), graphitic nitrogen (N-Q), and the fraction of N-6/N-X, of N-containing functional groups was identified, evidencing that N-6, N-5, and N-X considerably functioned in the CO 2 capture.…”

Effect of the Position of Amine Groups on the CO2, CH4, and H2 Adsorption Performance of Graphene Nanoflakes

“…The mechanism responsible for the enhanced CO 2 adsorption performance by porous carbon materials following the introduction of amine groups has been investigated using quantum chemical calculations. − The dipole moment force between the nitrogen atom with abundant electron density in the amine group and the carbon atom with insufficient electron density in the CO 2 molecule increases the adsorption performance. Thus, CO 2 is preferentially adsorbed when CO 2 and N 2 are simultaneously adsorbed .…”

Machine Learning Prediction of the Yield and BET Area of Activated Carbon Quantitatively Relating to Biomass Compositions and Operating Conditions

“…More and more artificial intelligence (AI) methods are being introduced into traditional research, and some remarkable achievements have been achieved. − Among the rest, machine learning methods are the core of AI, which mainly uses the selected model to learn the input data, extracts valuable features and information from complex data sets, and summarizes reasonable change trends for data prediction. It is a method that can readjust the parameters or structures in the model after comparing the bias between the actual and predicted values to increase the accuracy and dependability of the prediction .…”