2021
DOI: 10.1016/j.patter.2021.100291
|View full text |Cite
|
Sign up to set email alerts
|

Predicting hydrogen storage in MOFs via machine learning

Abstract: Highlights d Accurate and general ML models for predicting H 2 storage in MOFs are developed d The models require minimal input data that are easily derived from the MOF structure d High-capacity MOFs are identified, and capacity-structure connections are revealed d The web models (https://sorbent-ml.hymarc.org) can predict the performance of new MOFs

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

5
56
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
8
2

Relationship

0
10

Authors

Journals

citations
Cited by 79 publications
(61 citation statements)
references
References 123 publications
(439 reference statements)
5
56
0
Order By: Relevance
“…Since 2012, the number of experimental and hypothetical MOFs has been increasing rapidly, and different databases including a total of nearly one million MOFs have been constructed, ready for various types of computational screening. 25 High-throughput computational screening (HTCS) has been an efficient strategy that can accelerate the discovery of the best adsorbents for various gas separations from several thousands of materials and guide experimental research. 26,27 Recently, HTCS has been used to identify the optimal MOFs for the separation of CO 2 /H 2 and other gas mixtures from the extensive MOF databases, which is an alternative to experimental synthesis and testing methods that cost a lot of manpower and material resources.…”
Section: Introductionmentioning
confidence: 99%
“…Since 2012, the number of experimental and hypothetical MOFs has been increasing rapidly, and different databases including a total of nearly one million MOFs have been constructed, ready for various types of computational screening. 25 High-throughput computational screening (HTCS) has been an efficient strategy that can accelerate the discovery of the best adsorbents for various gas separations from several thousands of materials and guide experimental research. 26,27 Recently, HTCS has been used to identify the optimal MOFs for the separation of CO 2 /H 2 and other gas mixtures from the extensive MOF databases, which is an alternative to experimental synthesis and testing methods that cost a lot of manpower and material resources.…”
Section: Introductionmentioning
confidence: 99%
“…Compared with traditional methods, ML can decrease the calculation time significantly by utilizing the cloud disk workstations and servers [ 26 ]. ML has been employed to predict the methane adsorption capacity [ 27 , 28 , 29 ], water stability [ 30 ], toxicity [ 31 , 32 ], and hydrogen storage ability [ 33 , 34 , 35 ] of MOFs. To the best of our knowledge, no study has been conducted in which ML methods are employed to predict the drug loading capacity of MOFs.…”
Section: Introductionmentioning
confidence: 99%
“…At present, the methods of hydrogen storage include high-pressure gaseous hydrogen storage, low-temperature liquid hydrogen storage, physical adsorption hydrogen storage, , chemical adsorption hydrogen storage, and liquid organic compound hydrogen storage. , Among them, physical adsorption hydrogen storage has become an important development direction because of its advantages such as low cost, high reversibility, and stability . Porous carbon materials, metal organic frameworks (MOFs), , and covalent organic frameworks are commonly used as carriers for hydrogen physical adsorption. Particularly, MOFs with a large specific surface area, high porosity, and easy adjustment of the pore structure showed better hydrogen physical adsorption capacity, and there have been several research studies on hydrogen storage of MOFs in the past 20 years. , …”
Section: Introductionmentioning
confidence: 99%