Insights into CO2/N2Selectivity in Porous Carbons from Deep Learning

Song Wang; Zihao Zhang; Sheng Dai; De En Jiang

doi:10.1021/acsmaterialslett.9b00374

Insights into CO₂/N₂Selectivity in Porous Carbons from Deep Learning

Song Wang, Zihao Zhang, Sheng Dai, De En Jiang

Nanomaterials Chemistry Group

Research output: Contribution to journal › Article › peer-review

43 Scopus citations

Abstract

Porous carbons are an important class of porous material for carbon capture. The textural properties of porous carbons greatly influence their CO2 adsorption capacities. But it is still unclear what features are most conductive to achieving high CO2/N2 selectivity. Here, we trained deep neural networks from the experimental data of CO2 and N2 uptakes in porous carbons based on textural features of micropore volume, mesopore volume, and BET surface area. We then used the model to screen porous carbons and to predict CO2 and N2 uptakes, as well as CO2/N2 selectivity. We found that the highest CO2/N2 selectivity can be achieved not at the regions of highest CO2 uptake but at the regions of lowest N2 uptake where mesopores disrupt N2 adsorption. This insight will help guide experiments to synthesize better porous carbons for post-combustion CO2 capture.

Original language	English
Pages (from-to)	558-563
Number of pages	6
Journal	ACS Materials Letters
Volume	1
Issue number	5
DOIs	https://doi.org/10.1021/acsmaterialslett.9b00374
State	Published - Nov 4 2019

Funding

This work was sponsored by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, Chemical Sciences, Geosciences, and Biosciences Division. This research used resources of the National Energy Research Scientific Computing Center, a DOE Office of Science User Facility supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231.

Funders	Funder number
U.S. Department of Energy
Office of Science	DE-AC02-05CH11231
Office of Science
Basic Energy Sciences
Chemical Sciences, Geosciences, and Biosciences Division

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1021/acsmaterialslett.9b00374

Cite this

@article{78885cf7b4634b8d895ca6641d5a9fc8,

title = "Insights into CO2/N2Selectivity in Porous Carbons from Deep Learning",

abstract = "Porous carbons are an important class of porous material for carbon capture. The textural properties of porous carbons greatly influence their CO2 adsorption capacities. But it is still unclear what features are most conductive to achieving high CO2/N2 selectivity. Here, we trained deep neural networks from the experimental data of CO2 and N2 uptakes in porous carbons based on textural features of micropore volume, mesopore volume, and BET surface area. We then used the model to screen porous carbons and to predict CO2 and N2 uptakes, as well as CO2/N2 selectivity. We found that the highest CO2/N2 selectivity can be achieved not at the regions of highest CO2 uptake but at the regions of lowest N2 uptake where mesopores disrupt N2 adsorption. This insight will help guide experiments to synthesize better porous carbons for post-combustion CO2 capture.",

author = "Song Wang and Zihao Zhang and Sheng Dai and Jiang, {De En}",

note = "Publisher Copyright: {\textcopyright} 2019 American Chemical Society.",

year = "2019",

month = nov,

day = "4",

doi = "10.1021/acsmaterialslett.9b00374",

language = "English",

volume = "1",

pages = "558--563",

journal = "ACS Materials Letters",

issn = "2639-4979",

publisher = "American Chemical Society",

number = "5",

}

TY - JOUR

T1 - Insights into CO2/N2Selectivity in Porous Carbons from Deep Learning

AU - Wang, Song

AU - Zhang, Zihao

AU - Dai, Sheng

AU - Jiang, De En

PY - 2019/11/4

Y1 - 2019/11/4

N2 - Porous carbons are an important class of porous material for carbon capture. The textural properties of porous carbons greatly influence their CO2 adsorption capacities. But it is still unclear what features are most conductive to achieving high CO2/N2 selectivity. Here, we trained deep neural networks from the experimental data of CO2 and N2 uptakes in porous carbons based on textural features of micropore volume, mesopore volume, and BET surface area. We then used the model to screen porous carbons and to predict CO2 and N2 uptakes, as well as CO2/N2 selectivity. We found that the highest CO2/N2 selectivity can be achieved not at the regions of highest CO2 uptake but at the regions of lowest N2 uptake where mesopores disrupt N2 adsorption. This insight will help guide experiments to synthesize better porous carbons for post-combustion CO2 capture.

AB - Porous carbons are an important class of porous material for carbon capture. The textural properties of porous carbons greatly influence their CO2 adsorption capacities. But it is still unclear what features are most conductive to achieving high CO2/N2 selectivity. Here, we trained deep neural networks from the experimental data of CO2 and N2 uptakes in porous carbons based on textural features of micropore volume, mesopore volume, and BET surface area. We then used the model to screen porous carbons and to predict CO2 and N2 uptakes, as well as CO2/N2 selectivity. We found that the highest CO2/N2 selectivity can be achieved not at the regions of highest CO2 uptake but at the regions of lowest N2 uptake where mesopores disrupt N2 adsorption. This insight will help guide experiments to synthesize better porous carbons for post-combustion CO2 capture.

UR - http://www.scopus.com/inward/record.url?scp=85087671546&partnerID=8YFLogxK

U2 - 10.1021/acsmaterialslett.9b00374

DO - 10.1021/acsmaterialslett.9b00374

M3 - Article

AN - SCOPUS:85087671546

SN - 2639-4979

VL - 1

SP - 558

EP - 563

JO - ACS Materials Letters

JF - ACS Materials Letters

IS - 5

ER -