journal article·2024-02-14

Accelerating In Silico Discovery of Metal–Organic Frameworks for Ethane/Ethylene and Propane/Propylene Separation: A Synergistic Approach Integrating Molecular Simulation, Machine Learning, and Active Learning

Varad Daoo, Jayant K. Singh

Publisher page

Abstract

Cryogenic distillation, a currently employed method for C 2 H 4 /C 2 H 6 and C 3 H 6 /C 3 H 8 mixture separation, is energy-intensive, prompting the research toward alternative technologies, including adsorbent-based separation. In this work, we combine machine learning (ML) technique with high-throughput screening to screen ∼23,000 hypothetical metal–organic frameworks (MOFs) for paraffin (C 2 H 6 and C 3 H 8 ) selective adsorbent separation. First, structure-based prescreening was employed to remove MOFs with undesired geometric properties. Further, a random forest model built upon the multicomponent grand canonical Monte Carlo (m-GCMC) simulation data of training set MOFs was found to be the most successful in learning the relationship between MOF features and olefin/paraffin mixture separation. Using this technique, the separation performance of the remaining (test set) MOFs was predicted, and the top-performing MOFs were identified. We also employed active learning (AL) to evaluate its effectiveness in improving the prediction of olefin/paraffin selectivity. AL was discovered to be ∼29 times more efficient than the best-supervised ML model, as it was able to identify the top materials in limited training data and at a fraction of computational cost and time as compared to ML techniques. Among the top selected materials, framework chemistry was found to be the most important parameter. Nickel and copper (as a metal node) in a tfzd and hms topological arrangement respectively, were discovered to be a prevalent attribute in high-performing MOFs, further demonstrating the prominent significance of framework chemistry. Additionally, the top MOFs discovered were studied in detail and further compared to the previously reported MOFs. These MOFs show the highest selectivity for C 2 H 4 /C 2 H 6 and C 3 H 6 /C 3 H 8 mixture separation, as reported until date. The hierarchical strategy devised in this study will facilitate the quick screening of MOFs across multiple databases toward industrially significant separation processes by leveraging molecular simulations and AL.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Metal-Organic Frameworks: Synthesis and Applications · Zeolite Catalysis and Synthesis · Machine Learning in Materials Science

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Chemical Engineering, Indian Institute of Technology Kanpur, Kanpur 208016, India

Prescience Insilico Private Limited, Bangalore 560049, India

Funding

Ministry of Education, India

References (69)

Show source-provided references
1. 10.1021/acsami.1c0247110.1021/acsami.1c02471 ↗
2. 10.1038/532435a10.1038/532435a ↗
3. 10.1016/j.micromeso.2021.11157210.1016/j.micromeso.2021.111572 ↗
4. 10.1021/acs.energyfuels.2c0142710.1021/acs.energyfuels.2c01427 ↗
5. 10.1126/science.aaf632310.1126/science.aaf6323 ↗
6. 10.1002/smll.20190005810.1002/smll.201900058 ↗
7. 10.1016/j.ces.2020.11563610.1016/j.ces.2020.115636 ↗
8. 10.1126/science.aao009210.1126/science.aao0092 ↗
9. 10.1016/j.cej.2019.12273110.1016/j.cej.2019.122731 ↗
10. 10.1016/j.micromeso.2020.11009910.1016/j.micromeso.2020.110099 ↗
11. 10.1021/ja502119z10.1021/ja502119z ↗
12. 10.1039/c3ta11205e10.1039/c3ta11205e ↗
13. 10.1126/science.106720810.1126/science.1067208 ↗
14. 10.1021/jacs.7b0639710.1021/jacs.7b06397 ↗
15. 10.1021/jacs.0c0946610.1021/jacs.0c09466 ↗
16. 10.1021/jacs.1c1042310.1021/jacs.1c10423 ↗
17. 10.1021/acsami.1c1378610.1021/acsami.1c13786 ↗
18. 10.1021/acs.iecr.2c0237410.1021/acs.iecr.2c02374 ↗
19. 10.1038/nchem.119210.1038/nchem.1192 ↗
20. 10.1021/acs.chemmater.2c0248510.1021/acs.chemmater.2c02485 ↗
21. 10.1038/natrevmats.2017.3710.1038/natrevmats.2017.37 ↗
22. 10.1021/acscentsci.0c0098810.1021/acscentsci.0c00988 ↗
23. 10.1038/s41467-019-09365-w10.1038/s41467-019-09365-w ↗
24. 10.1126/sciadv.160090910.1126/sciadv.1600909 ↗
25. 10.1021/acs.jpcc.6b0817710.1021/acs.jpcc.6b08177 ↗
26. 10.1021/acs.jpcc.0c0911710.1021/acs.jpcc.0c09117 ↗
27. 10.1021/acs.jced.9b0083510.1021/acs.jced.9b00835 ↗
28. 10.1080/08927022.2020.182252810.1080/08927022.2020.1822528 ↗
29. 10.1021/acscombsci.7b0005610.1021/acscombsci.7b00056 ↗
30. 10.1021/acs.jpcc.9b0931910.1021/acs.jpcc.9b09319 ↗
31. 10.1021/acs.jpcc.8b1064410.1021/acs.jpcc.8b10644 ↗
32. 10.1021/acs.jpcc.0c0633410.1021/acs.jpcc.0c06334 ↗
33. 10.1039/C6CE00407E10.1039/C6CE00407E ↗
34. 10.1021/acs.energyfuels.0c0306310.1021/acs.energyfuels.0c03063 ↗
35. 10.1039/C8SC05340E10.1039/C8SC05340E ↗
36. 10.1126/sciadv.abg398310.1126/sciadv.abg3983 ↗
37. 10.1039/D1ME00093D10.1039/D1ME00093D ↗
38. 10.1039/D3DD00117B10.1039/D3DD00117B ↗
39. 10.1002/aic.1785610.1002/aic.17856 ↗
40. 10.1039/D2SM01193J10.1039/D2SM01193J ↗
41. 10.1063/5.007599410.1063/5.0075994 ↗
42. 10.1021/acs.jpcc.0c0549110.1021/acs.jpcc.0c05491 ↗
43. 10.1038/s41467-021-22437-010.1038/s41467-021-22437-0 ↗
44. 10.1021/acsami.1c1622010.1021/acsami.1c16220 ↗
45. 10.1021/acs.chemmater.1c0120110.1021/acs.chemmater.1c01201 ↗
46. 10.1021/acs.energyfuels.2c0361910.1021/acs.energyfuels.2c03619 ↗
47. 10.1021/jp972543+10.1021/jp972543+ ↗
48. 10.1021/ja00051a04010.1021/ja00051a040 ↗
49. 10.1021/acs.jctc.2c0079810.1021/acs.jctc.2c00798 ↗
50. 10.1021/acs.jpcc.9b1076610.1021/acs.jpcc.9b10766 ↗
51. 10.1021/acs.jpca.9b0329010.1021/acs.jpca.9b03290 ↗
52. 10.1038/s41467-020-17755-810.1038/s41467-020-17755-8 ↗
53. 10.1021/acs.chemmater.0c0190710.1021/acs.chemmater.0c01907 ↗
54. Pedregosa F. · J. Mach. Learn. Res. · 2011 · 12 · 2825
55. Balandat M. · Adv. Neural. Inf. Process. Syst. · 2020 · 33 · 21524
56. 10.1016/j.csda.2007.08.01510.1016/j.csda.2007.08.015 ↗
57. Lundberg S. M. · 2017
58. 10.1002/aic.1702510.1002/aic.17025 ↗
59. 10.1016/j.ces.2015.09.01910.1016/j.ces.2015.09.019 ↗
60. 10.1126/science.aat058610.1126/science.aat0586 ↗
61. 10.1021/acsami.1c0980810.1021/acsami.1c09808 ↗
62. 10.1016/j.cej.2020.12642810.1016/j.cej.2020.126428 ↗
63. 10.1021/acsami.1c1039110.1021/acsami.1c10391 ↗
64. 10.1021/acsami.9b1943810.1021/acsami.9b19438 ↗
65. 10.1039/C7CE00187H10.1039/C7CE00187H ↗
66. 10.1021/la401471g10.1021/la401471g ↗
67. 10.1021/acsami.1c0247110.1021/acsami.1c02471 ↗
68. 10.1021/jp060433+10.1021/jp060433+ ↗
69. 10.1002/ange.20110753410.1002/ange.201107534 ↗