A Machine Learning Approach to Zeolite Synthesis Enabled by Automatic Literature Data Extraction

Zeolites are porous, aluminosilicate materials with many industrial and “green” applications. Despite their industrial relevance, many aspects of zeolite synthesis remain poorly understood requiring costly trial and error synthesis. In this paper, we create natural language processing techniques and text markup parsing tools to automatically extract synthesis information and trends from zeolite journal articles. We further engineer a data set of germanium-containing zeolites to test the accuracy of the extracted data and to discover potential opportunities for zeolites containing germanium. We also create a regression model for a zeolite’s framework density from the synthesis conditions. This model has a cross-validated root mean squared error of 0.98 T/1000 Å3, and many of the model decision boundaries correspond to known synthesis heuristics in germanium-containing zeolites. We propose that this automatic data extraction can be applied to many different problems in zeolite synthesis and enable novel zeolite morphologies.

[1]  A. McCallum,et al.  Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning , 2017 .

[2]  S. Smeets,et al.  Structure analysis of a BEC-type germanosilicate zeolite including the location of the flexible organic cations in the channels , 2015 .

[3]  Brent M. T. Lok,et al.  Silicoaluminophosphate molecular sieves: another new class of microporous crystalline inorganic solids , 1984 .

[4]  Iosif I. Vaisman,et al.  Machine learning approach for structure-based zeolite classification , 2009 .

[5]  Avelino Corma,et al.  Jiang Meso-Microporous Zeolite ITQ-43 Synthesis and Structure Determination of the Hierarchical , 2012 .

[6]  B. Grzybowski,et al.  The 'wired' universe of organic chemistry. , 2009, Nature chemistry.

[7]  William H. Green,et al.  Computer-Assisted Retrosynthesis Based on Molecular Similarity , 2017, ACS central science.

[8]  Manuel Moliner,et al.  The ITQ-37 mesoporous chiral zeolite , 2009, Nature.

[9]  P. A. Cheeseman,et al.  Computational Discovery of New Zeolite-Like Materials , 2009 .

[10]  Ulrich Müller,et al.  Catalytic Applications of Zeolites in Chemical Industry , 2009 .

[11]  Maciej Haranczyk,et al.  Capturing chemical intuition in synthesis of metal-organic frameworks , 2019, Nature Communications.

[12]  Liping Li,et al.  Oriented control of Al locations in the framework of Al-Ge-ITQ-13 for catalyzing methanol conversion to propene , 2016 .

[13]  V. Blatov,et al.  The Zeolite Conundrum: Why Are There so Many Hypothetical Zeolites and so Few Observed? A Possible Answer from the Zeolite-Type Frameworks Perceived As Packings of Tiles , 2013 .

[14]  Mark E. Davis,et al.  Synthesis and Characterization of CIT-13, a Germanosilicate Molecular Sieve with Extra-Large Pore Openings , 2016 .

[15]  Avelino Corma,et al.  ITQ-15: the first ultralarge pore zeolite with a bi-directional pore system formed by intersecting 14- and 12-ring channels, and its catalytic implications. , 2004, Chemical communications.

[16]  Michel Waroquier,et al.  Design of zeolite by inverse sigma transformation. , 2012, Nature materials.

[17]  J. Weitkamp,et al.  Zeolites and catalysis , 2000 .

[18]  T. Degnan,et al.  Applications of zeolites in petroleum refining , 2000 .

[19]  José M. Serra,et al.  A New Mapping/Exploration Approach for HT Synthesis of Zeolites , 2006 .

[20]  Igor Rivin,et al.  Enumeration of periodic tetrahedral frameworks. II. Polynodal graphs , 2004 .

[21]  Andrew McCallum,et al.  Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks , 2018, J. Chem. Inf. Model..

[22]  Ankit Agrawal,et al.  Machine-learning-accelerated high-throughput materials screening: Discovery of novel quaternary Heusler compounds , 2018, Physical Review Materials.

[23]  D. Serrano,et al.  Heterogenous events in the crystallization of zeolites , 2001 .

[24]  Mark E. Davis,et al.  Thermodynamics of Pure-Silica Molecular Sieve Synthesis , 2002 .

[25]  Manuel Moliner,et al.  Rational design and HT techniques allow the synthesis of new IWR zeolite polymorphs. , 2006, Journal of the American Chemical Society.

[26]  Jordi Rius,et al.  A zeolite with interconnected 8-, 10- and 12-ring pores and its unique catalytic selectivity , 2003, Nature materials.

[27]  Avelino Corma,et al.  Inorganic molecular sieves: Preparation, modification and industrial application in catalytic processes , 2011 .

[28]  Muratahan Aykol,et al.  Network analysis of synthesizable materials discovery , 2018, Nature Communications.

[29]  Jose Manuel Serra,et al.  Zeolite synthesis modelling with support vector machines: a combinatorial approach. , 2007, Combinatorial chemistry & high throughput screening.

[30]  Manuel Moliner,et al.  “Ab initio” synthesis of zeolites for preestablished catalytic reactions , 2017, Science.

[31]  A. Corma,et al.  Extra-large pore zeolite (ITQ-40) with the lowest framework density containing double four- and double three-rings , 2010, Proceedings of the National Academy of Sciences.

[32]  Taylor D. Sparks,et al.  Performance and resource considerations of Li-ion battery electrode materials , 2015 .

[33]  Gilles Louppe,et al.  Independent consultant , 2013 .

[34]  Heather J. Kulik,et al.  molSimplify: A toolkit for automating discovery in inorganic chemistry , 2016, J. Comput. Chem..

[35]  Jordi Rius,et al.  Pure Polymorph C of Zeolite Beta Synthesized by Using Framework Isomorphous Substitution as a Structure-Directing Mechanism. , 2001, Angewandte Chemie.

[36]  María A. Uguina,et al.  Synthesis of ZSM-5 from Ethanol-Containing Systems. Influence of the Gel Composition , 1995 .

[37]  Stephen H. Brown.  Zeolites in Catalysis , 2010 .

[38]  A. Navrotsky,et al.  Thermochemistry of microporous and mesoporous materials. , 2009, Chemical reviews.

[39]  P. A. Barrett,et al.  Synthesis and Structure of As-Prepared ITQ-4, A Large Pore Pure Silica Zeolite: The Role and Location of Fluoride Anions and Organic Cations , 1998 .

[40]  H. Du,et al.  A Stable Extra-Large-Pore Zeolite with Intersecting 14- and 10-Membered-Ring Channels. , 2016, Chemistry.

[41]  Mark E. Davis,et al.  Enantiomerically enriched, polycrystalline molecular sieves , 2017, Proceedings of the National Academy of Sciences.

[42]  P. Cox,et al.  The hydrothermal synthesis of zeolites: Precursors, intermediates and reaction mechanism , 2005 .

[43]  S. Zones,et al.  Studies on the role of fluoride ion vs reaction concentration in zeolite synthesis. , 2005, The journal of physical chemistry. B.

[44]  Mark E. Davis,et al.  SIO-...HOSI HYDROGEN BONDS IN AS-SYNTHESIZED HIGH-SILICA ZEOLITES , 1995 .

[45]  Michael W Deem,et al.  A database of new zeolite-like materials. , 2011, Physical chemistry chemical physics : PCCP.

[46]  François-Xavier Coudert,et al.  Predicting the Mechanical Properties of Zeolite Frameworks by Machine Learning , 2017 .

[47]  Stacey I. Zones,et al.  Translating new materials discoveries in zeolite research to commercial manufacture , 2011 .

[48]  Manuel Moliner,et al.  High-throughput synthesis and catalytic properties of a molecular sieve with 18- and 10-member rings , 2006, Nature.

[49]  J. Čejka,et al.  The ADOR Mechanism for the Synthesis of New Zeolites , 2015 .

[50]  J. Hagen.  Shape‐Selective Catalysis: Zeolites , 2006 .

[51]  Callum J Court,et al.  Auto-generated materials database of Curie and Néel temperatures via semi-supervised relationship extraction , 2018, Scientific Data.

[52]  Emma Strubell,et al.  Machine-learned and codified synthesis parameters of oxide materials , 2017, Scientific Data.

[53]  Chris Morley,et al.  Open Babel: An open chemical toolbox , 2011, J. Cheminformatics.

[54]  Yi Li,et al.  Applications of Zeolites in Sustainable Chemistry , 2017 .

[55]  Mark E. Davis,et al.  Issues in the synthesis of crystalline molecular sieves: towards the crystallization of low framework-density structures. , 2004, Chemphyschem : a European journal of chemical physics and physical chemistry.

[56]  Taylor D. Sparks,et al.  Data-Driven Review of Thermoelectric Materials: Performance and Resource Considerations , 2013 .

[57]  Wolfram Stichert,et al.  High throughput experimentation for the synthesis of new crystalline microporous solids , 2001 .

[58]  William H. Green,et al.  Using Machine Learning To Predict Suitable Conditions for Organic Reactions , 2018, ACS central science.

[59]  Mark E. Davis.  Ordered Porous Materials for Emerging Applications , 2002 .

[60]  Alok Choudhary,et al.  Combinatorial screening for new materials in unconstrained composition space with machine learning , 2014 .

[61]  Mike Preuss,et al.  Planning chemical syntheses with deep neural networks and symbolic AI , 2017, Nature.

[62]  Paul Raccuglia,et al.  Machine-learning-assisted materials discovery using failed experiments , 2016, Nature.

[63]  Jordi Rius,et al.  Synthesis of a new zeolite structure ITQ-24, with intersecting 10- and 12-membered ring pores. , 2003, Journal of the American Chemical Society.

[64]  Ian Foster,et al.  Strategies for accelerating the adoption of materials informatics , 2018, MRS Bulletin.

[65]  A. Corma,et al.  Synthesis of New Zeolite Structures , 2015 .

[66]  A. Corma,et al.  Synthesis of the Ti-Silicate Form of BEC Polymorph of β-Zeolite Assisted by Molecular Modeling , 2008 .

[67]  Peter Murray-Rust,et al.  ChemicalTagger: A tool for semantic text-mining in chemistry , 2011, J. Cheminformatics.

[68]  Callum Court,et al.  ChemDataExtractor: A toolkit for automated extraction of chemical information from the scientific literature , 2017 .

[69]  Zhiqiang Liang,et al.  Germanosilicate zeolite ITQ-44 with extra-large 18-rings synthesized using a commercial quaternary ammonium as a structure-directing agent , 2015 .

[70]  Avelino Corma,et al.  The synthesis of an extra-large-pore zeolite with double three-ring building units and a low framework density. , 2010, Angewandte Chemie.

[71]  Avelino Corma,et al.  Synthesis in fluoride media and characterisation of aluminosilicate zeolite beta , 1998 .

[72]  Iosif I. Vaisman,et al.  Identifying Zeolite Frameworks with a Machine Learning Approach , 2009 .

[73]  Stefanie Jegelka,et al.  Virtual screening of inorganic materials synthesis parameters with deep learning , 2017, npj Computational Materials.

[74]  Antony J. Williams,et al.  ChemSpider:: An Online Chemical Information Resource , 2010 .

[75]  Petr Nachtigall,et al.  A family of zeolites with controlled pore size prepared using a top-down method. , 2013, Nature chemistry.