Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A comprehensive mapping of zeolite-template chemical space

  • Xie, Mingrou
  • Schwalbe-Koda, Daniel
  • Hoffman, Alexander
  • Santiago-Reyes, Omar
  • Paris, Cecilia
  • Gomez-Bombarelli, Rafael
  • Semanate-Esquivel, Yolanda Marcela|||0009-0009-0289-4267
  • Bello-Jurado, Estefanía
  • Moliner Marin, Manuel|||0000-0002-5440-716X
[EN] Zeolites are industrially important catalysts and adsorbents, typically synthesized using specific molecules known as organic structure-directing agents (OSDAs). The templating effect of the OSDAs is pivotal in determining the zeolite polymorph formed and its physicochemical properties. However, de novo design of selective OSDAs is challenging because of the diversity and size of the zeolite-OSDA chemical space. Here we present ZeoBind, a computational workflow powered by machine learning that enables an exhaustive exploration of the OSDA space. We design predictive tasks that capture zeolite-molecule matching, train predictive models for these tasks on hundreds of thousands of datapoints and curate a library of 2.3 million synthetically accessible, hypothetical OSDA-like molecules enumerated from commercially available precursors. We use ZeoBind to screen nearly 500 million zeolite-molecule pairs and identified and experimentally validated two new OSDAs that template zeolites with novel compositions. The scale of the OSDA library, along with the open-access tools and data, has the potential to accelerate OSDA design for zeolite synthesis., M.M., C.P., E.B.-J. and Y.M.S.-E. acknowledge financial support by the Spanish Government through PID2021-122755OB-I00 (funded by MCIN/AEI/10.13039/501100011033) and TED2021-130739B-I00 (funded by MCIN/AEI/10.13039/501100011033/EU/PRTR), by the Generalitat Valenciana through the Prometeo Program (CIPROM/2023/34) and CSIC through the I-link+ Program (ILINK24035). M.M., C.P., E.B.-J. and Y.M.S.-E. also thank the Severo Ochoa financial support by the Spanish Ministry of Science and Innovation (CEX2021-001230-S/funding by MCIN/AEI/10.13039/501100011033). M.X. acknowledges funding from the Agency of Science, Technology and Research (A*STAR) scholarship. D.S.-K. acknowledges funding from the MIT Energy Fellowship. E.B.-J. and Y.M.S.-E. acknowledge the Spanish Government for an FPI scholarship (PRE2019-088360) and a Severo Ochoa FPI scholarship (PRE2020-092319), respectively. R.G.-B. and A.H. acknowledge funding from MIT Deshpande Center, Alfred P. Sloan Research Fellowship (FG-2023-20026) and MISTI Inditex Fund. The Electron Microscopy Service of the UPV is also acknowledged for their help in sample characterization. Computations were executed on MIT Engaging and Supercloud clusters.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

DiffSyn: a generative diffusion approach to materials synthesis planning

  • Pan, Elton
  • Kwon, Soonhyoung
  • Liu, Sulin
  • Xie, Mingrou
  • Hoffman, Alexander J.
  • Duan, Yifei
  • Prein, Thorben
  • Sheriff, Killian
  • Roman-Leshkov, Yuriy
  • Gomez-Bombarelli, R
  • Olivetti, Elsa A.
  • Moliner Marin, Manuel|||0000-0002-5440-716X
[EN] The synthesis of crystalline materials, such as zeolites, remains a notable challenge owing to a high-dimensional synthesis space, intricate structure-synthesis relationships and time-consuming experiments. Here, considering the 'one-to-many' relationship between structure and synthesis, we propose DiffSyn, a generative diffusion model trained on over 23,000 synthesis recipes that span 50 years of literature. DiffSyn generates probable synthesis routes conditioned on a desired zeolite structure and an organic template. DiffSyn a chieves state-of-the-art performance by capturing the multi-modal nature of structure-synthesis relationships. We apply Diffsny to differentiate among competing phases and generate optimal synthesis routes. As a proof of concept, we synthesize a UFI material using DiffSyn-generated synthesis routes. These routes, rationalized by density functional theory binding energies, resulted in the successful synthesis of a UFI material with a high Si/AlICP of 19.0, which is expected to improve thermal stability., We acknowledge funding from the Generalitat Valenciana through the Prometeo Program (CIPROM/2023/34), CSIC through the I-link+ Program (ILINK24035), and MIT International Science and Technology Initiatives (MISTI) Seed Funds between MIT and CSIC. We also acknowledge partial funding from the National Science Foundation DMREF Awards 1922090, 1922311, 1922372, the Office of Naval Research (ONR) under contract N00014-20-1-2280, Kwanjeong Educational Fellowship, ExxonMobil, and the Agency for Science, Technology and Research. We thank D. Du and A. Burton for helpful discussions and suggestions.