Machine learning assisted rediscovery of methane storage and separation in porous carbon from material literature

•Machine learning models were trained to predict CH4 adsorption of porous carbon.•The model can be applied to build CH4 uptake performance map.•A CO2/CH4 selectivity map was further constructed by two trained models.•Mesopores may play a positive role in CO2/CH4 separation. Porous carbon (PC) has be...

Full description

Saved in:
Bibliographic Details
Published in:Fuel (Guildford) 2021-04, Vol.290 (C), p.120080, Article 120080
Main Authors: Zhang, Chi, Li, Dawei, Xie, Yunchao, Stalla, David, Hua, Peng, Nguyen, Duy Tung, Xin, Ming, Lin, Jian
Format: Article
Language:English
Subjects:
Carbon dioxide
Construction
Gas separation
Learning algorithms
Literature mining
Machine learning
Methane
Methane storage
Multilayer perceptrons
Porous carbon
Porous materials
Retraining
Selectivity
Separation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Machine learning models were trained to predict CH4 adsorption of porous carbon.•The model can be applied to build CH4 uptake performance map.•A CO2/CH4 selectivity map was further constructed by two trained models.•Mesopores may play a positive role in CO2/CH4 separation. Porous carbon (PC) has been widely regarded as one of the most promising absorbents for methane storage. Studies show that its uptake capacity and selectivity highly depend on textural structures. Although much effort has been made, unveiling their detailed structure-performance relationship remains a challenge. Here, we propose an innovative study where, with the assistance of machine learning, the hidden relationship of the textural structures of PC with the methane uptake and separation can be derived from existing data in material literature. Machine learning models were trained by the data, including specific surface area, micropore volume, mesopore volume, temperature, and pressure as the input variables and methane uptake as the output variable for prediction. Among the tested models, the multilayer perceptron (MLP) shows the highest accuracy in predicting the methane uptake. In addition, the model enables to automatically construct a uptake performance map in terms of micropore volume and mesopore volume. The obtained MLP model was also extended to explore the CO2/CH4 selectivity by retraining it with the data collected from literature of PC for the CO2 uptake. The constructed 2D selectivity map shows that the high selectivity can be achieved in the low CH4 uptake region.
ISSN:0016-2361
1873-7153
DOI:10.1016/j.fuel.2020.120080