Abstract

We report a machine-learning strategy for design of organic structure directing agents (OSDAs) for zeolite beta. We use machine learning to replace a computationally expensive molecular dynamics evaluation of the stabilization energy of the OSDA inside zeolite beta with a neural network prediction. We train the neural network on 4,781 candidate OSDAs, spanning a range of stabilization energies. We find that the stabilization energies predicted by the neural network are highly correlated with the molecular dynamics computations. We further find that the evolutionary design algorithm samples the space of chemically feasible OSDAs thoroughly. In total, we find 469 OSDAs with verified stabilization energies below -17 kJ/(mol Si), comparable to or better than known OSDAs for zeolite beta, and greatly expanding our previous list of 152 such predicted OSDAs. We expect that these OSDAs will lead to syntheses of zeolite beta.

Highlights

  • Zeolites are crystalline nanoporous aluminosilicate minerals that have wide use in absorption, separation, and catalysis [1]

  • A de novo design or virtual combinatorial chemistry experiment typically requires on the order of 200,000 calls of the scoring function, of which around 10% reach the stage of the molecular dynamics run

  • In view of our efforts to design organic structure directing agents (OSDAs) for zeolite BEA, it is of great interest to us to speed up the evaluation of this scoring function

Read more

Summary

Introduction

Zeolites are crystalline nanoporous aluminosilicate minerals that have wide use in absorption, separation, and catalysis [1]. Its industrial uses include the alkylation of benzene [5] and the separation of organics from water [6] Synthetic zeolites such as zeolite beta are synthesized by hydrothermal synthesis from suitable amorphous aluminosilicate precursors [7]. We have successfully built upon this observation to use structure-based molecular design to obtain OSDAs for several zeolites [15,16,17], including a chiral OSDA leading to an enantiomerically enriched zeolite STW [18]. Zeolite beta is one of the top-six zeolites of commercial interest It has been synthesized through the use of a number of organic structure directing agents (OSDAs). Through de novo materials design runs, a total of 3,062 promising OSDAs were identified, and 469 OSDAs were computed to stabilize the structure of zeolite beta A better than known compounds

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call