Dataset Information

Accelerating the prediction of CO₂ capture at low partial pressures in metal-organic frameworks using new machine learning descriptors.

ABSTRACT: Metal-Organic frameworks (MOFs) have been considered for various gas storage and separation applications. Theoretically, there are an infinite number of MOFs that can be created; however, a finite amount of resources are available to evaluate each one. Computational methods can be adapted to expedite the process of evaluation. In the context of CO₂ capture, this paper investigates the method of screening MOFs using machine learning trained on molecular simulation data. New descriptors are introduced to aid this process. Using all descriptors, it is shown that machine learning can predict the CO₂ adsorption, with an R² of above 0.9. The introduced Effective Point Charge (EPoCh) descriptors, which assign values to frameworks' partial charges based on the expected CO₂ uptake of an equivalent point charge in isolation, are shown to be the second most important group of descriptors, behind the Henry coefficient. Furthermore, the EPoCh descriptors are hundreds of thousands of times faster to obtain compared with the Henry coefficient, and they achieve similar results when identifying top candidates for CO₂ capture using pseudo-classification predictions.

SUBMITTER: Orhan IB

PROVIDER: S-EPMC10547688 | biostudies-literature | 2023 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Accelerating the prediction of CO<sub>2</sub> capture at low partial pressures in metal-organic frameworks using new machine learning descriptors.

Orhan Ibrahim B IB Le Tu C TC Babarao Ravichandar R Thornton Aaron W AW

Communications chemistry 20231003 1

Metal-Organic frameworks (MOFs) have been considered for various gas storage and separation applications. Theoretically, there are an infinite number of MOFs that can be created; however, a finite amount of resources are available to evaluate each one. Computational methods can be adapted to expedite the process of evaluation. In the context of CO<sub>2</sub> capture, this paper investigates the method of screening MOFs using machine learning trained on molecular simulation data. New descriptors ...[more]

PMID: 37789142

Similar Datasets

Project description:Despite the known impacts on climate change of carbon dioxide emissions, the continued use of fossil fuels for energy generation leading to the emission of carbon dioxide (CO2) into the atmosphere is evident. Therefore, innovation to address and reduce CO2 emissions from industrial operations remains an urgent and crucial priority. A viable strategy in the area is postcombustion capture mainly through absorption by aqueous alkanolamines, which focuses on the separation of CO2 from flue gas, despite its limitations. Within this context, porous materials, particularly metal-organic frameworks (MOFs), have arisen as favorable alternatives owing to their significant adsorption capacity, selectivity, and reduced regeneration energy demands. This research evaluates the engineering insights into tailored MOFs for enhanced CO2 capture, focusing on three series of MOFs (ZIF, UiO-66, and BTC) to investigate the effects of organic ligands, functional groups, and metal ions. The evaluation encompassed a range of aspects including adsorption isotherms of pure gases [CO2 and nitrogen (N2)] and mixed gas mixture (CO2 and N2 with 15:85% ratio), along with utilization of the ideal adsorbed solution theory (IAST) to simulate multicomponent gas adsorption isotherms. Moreover, the reliability of IAST for mixed gas adsorption prediction has been investigated in detail. The research offers valuable insights into the correlation between the characteristics of MOFs and their effectiveness in gas separation and how these characteristics contribute to the differences between IAST predictions and experimental results. The findings enhance the understanding of how to enhance MOF characteristics in order to reduce CO2 emissions and also highlight the need for advanced models that consider thermodynamic nonidealities to accurately predict the behavior of mixed gas adsorption in MOFs. As a result, the incorporation of MOFs with enhanced predictability and reliability into CO2 capture industrial processes is facilitated.

Dataset Information

Accelerating the prediction of CO₂ capture at low partial pressures in metal-organic frameworks using new machine learning descriptors.

Publications

Accelerating the prediction of CO<sub>2</sub> capture at low partial pressures in metal-organic frameworks using new machine learning descriptors.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Dataset Information

Accelerating the prediction of CO2 capture at low partial pressures in metal-organic frameworks using new machine learning descriptors.

Publications

Accelerating the prediction of CO<sub>2</sub> capture at low partial pressures in metal-organic frameworks using new machine learning descriptors.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Accelerating the prediction of CO₂ capture at low partial pressures in metal-organic frameworks using new machine learning descriptors.