ISBN-13: 9781119819752 / Angielski / Twarda / 2023 / 456 str.
List of Contributors xiiiPreface xviiAbout the Cover xxiiiAcknowledgments xxv1 The Confluence of Organo-Cations, Inorganic Species, and Molecular Modeling on the Discovery of New Zeolite Structures and Compositions 1Christopher M. Lew, Dan Xie, Joel E. Schmidt, Saleh Elomari, Tracy M. Davis, and Stacey I. Zones1.1 Introduction 11.2 Inorganic Studies 31.3 Organic Structure-Directing Agents (OSDAs) 91.3.1 Purpose and Important Properties 91.3.2 Classes of Ammonium-based OSDAs 101.3.3 Methods of Making 121.4 OSDA-Zeolite Energetics and Rational Synthesis 151.5 Role of High Throughput and Automation 221.6 Cataloguing, Archiving, Harvesting, and Mining Years of Historical Data 241.7 Concluding Remarks 25References 252 De Novo Design of Organic Structure Directing Agents for the Synthesis of Zeolites 33Frits Daeyaert and Michael Deem2.1 Introduction 332.2 De Novo Design 342.2.1 Molecular Structure Generator 352.2.2 Scoring Function 362.2.3 Optimization Algorithm 372.2.4 Practical Implementation 422.3 Scoring Functions for OSDAs 432.3.1 Stabilization Energy 432.3.2 Other Constraints 442.3.3 Multiple Objectives 452.4 Applications 482.4.1 From Drug Design to the Design of OSDAs for Zeolites 482.4.2 Experimental Confirmation: Pure Silica STW 492.4.3 Experimental Confirmation: Zeolite AEI 492.4.4 Practical Application: SSZ-52 (SFW) 492.4.5 Design of Chiral OSDAs to Direct the Synthesis of Chiral STW 492.4.6 Design of Selective OSDAs Directed Toward BEA vs. BEB 512.4.7 Design of OSDAs for Chiral Zeolite BEA 522.4.8 Application of a Machine-Learning Scoring Function in the De Novo Design of OSDAs for Zeolite Beta 522.4.9 Design of OSDAs for Zeolites for Gas Adsorption and Separation 522.4.9.1 Carbon Capture and Storage: WEI, JBW, GIS, SIV, DAC, 8124767, 8277563 522.4.9.2 Carbon Dioxide/Methane Separation: GIS, ABW, 8186909, 8198030 532.4.9.3 Separation of Ethylene-Ethane: DFT, ACO, NAT, JRY 532.4.10 Design of MOFs for Methane Storage and Delivery 542.4.11 Multi-Objective De Novo Design of OSDAs for Zeolites Using an Ant Colony Optimization Algorithm 552.5 Conclusions and Outlook 55References 563 Machine Learning Search for Suitable Structure Directing Agents for the Synthesis of Beta (BEA) Zeolite Using Molecular Topology and Monte Carlo Techniques 61María Gálvez-Llompart and German Sastre3.1 Introduction 613.2 Artificial Neural Networks for Modeling Zeolite-SDA van der Waals Energy Applied to BEA Zeolite 643.3 Virtual Screening: Identifying Novel SDA with Favorable E ZEO-SDA for the Synthesis of BEA Zeolite 693.4 Zeo-SDA Energy Calculation Using Atomic Models 713.5 Comparing Zeo-SDA Energy Calculation Using MLR, ANN, and Atomic Models 733.6 Conclusions 74Acknowledgments 77References 774 Generating, Managing, and Mining Big Data in Zeolite Simulations 81Daniel Schwalbe-Koda and Rafael Gómez-Bombarelli4.1 Introduction 814.1.1 Computational Materials Databases 824.1.2 Zeolite Databases 834.2 Database of OSDAs for Zeolites 854.2.1 Developing a Docking Algorithm 864.2.2 Calibrating Binding Energy Predictions 884.2.3 Performing and Analyzing High-Throughput Screening Calculations 914.2.4 Recalling Synthesis Outcomes from the Literature 944.2.5 Proposing OSDA Descriptors 964.2.6 Designing with Interactivity 994.3 Outlook 102References 1035 Co-templating in the Designed Synthesis of Small-pore Zeolite Catalysts 113Ruxandra G. Chitac, Mervyn D. Shannon, Paul A. Cox, James Mattock, Paul A. Wright, and Alessandro Turrina5.1 Introduction 1135.1.1 Definitions: Templates and Structure Directing Agents; Co-templating; Dual Templating; Mixed Templating 1145.2 SAPO Zeotypes: "Model" Systems for Co-templating 1165.2.1 The CHA-AEI-SAV-KFI System 1165.2.2 Development of a Retrosynthetic Co-templating Approach for ABC-6 Structure Types 1185.3 Co-templating Aluminosilicate Zeolites 1205.3.1 Inorganic/Organic Co-templates 1215.3.1.1 Targeting new phases in the RHO family using divalent cations 1215.3.1.2 Designed synthesis of the aluminosilicate SWY, STA-30 1235.3.1.3 Co-templating and the charge density mismatch approach 1245.3.2 Two Organic Templates in Zeolite Synthesis 1255.3.2.1 Applications of Dual/Mixed Organic Templating 1255.4 Intergrowth Zeolite Structures as Co-templated Materials 1275.5 Discussion 1345.6 Conclusions 138Acknowledgments 138References 1386 Computer Generation of Hypothetical Zeolites 145Estefania Argente, Soledad Valero, Alechania Misturini, Michael M.J. Treacy, Laurent Baumes, and German Sastre6.1 Introduction 1456.2 Genetic Algorithms 1466.2.1 Codification of Genetic Algorithms 1476.2.2 Selection Operators for Genetic Algorithms 1476.2.3 Crossover Operators for Genetic Algorithms 1496.2.4 Mutation Operators for Genetic Algorithms 1506.3 Algorithms for Zeolite Structure Determination and Prediction 1516.3.1 Zefsaii 1526.3.2 FraGen (Framework Generator) 1526.3.3 SCIBS (Symmetry-Constrained Intersite Bonding Search) 1536.3.4 TTL GRINSP (Geometrically Restrained Inorganic Structure Prediction) 1546.3.5 EZs (Exclusive Zones) 1556.3.6 P-GHAZ (Parallel Genetic Hybrid Algorithm for Zeolites) 1556.3.7 zeoGAsolver 1566.4 zeoGAsolver: A Specific Example of Genetic Algorithm for ZSD 1566.4.1 Setting Up and Coding Scheme 1576.4.2 Initialization 1576.4.3 Fitness Evaluation 1576.4.4 Crossover 1596.4.5 Population Reduction and Termination Criterion 1606.5 Graphics Processing Units in Zeolite Structure Determination and Prediction 1606.5.1 Quick Presentation of GPU Cards 1606.5.2 Efficient Parallelization of Evolutionary Algorithms on GPUs 1616.5.3 Genetic Algorithms on GPUs for Zeolite Structures Problem 1626.5.4 GPUs in Island Model for Interrupted Zeolitic Frameworks 1676.6 Conclusions 168Acknowledgments 169References 1697 Numerical Representations of Chemical Data for Structure-Based Machine Learning 173Gyoung S. Na7.1 Machine Readable Data Formats 1737.1.1 Feature Vectors 1737.1.2 Matrices 1747.1.3 Mathematical Graphs 1757.2 Graph-based Molecular Representations 1757.2.1 Chemical Representations of Molecular Structures 1757.2.2 Molecular Graphs 1767.2.3 XYZ File to Molecular Graph 1777.2.4 SMILES to Molecular Graph 1787.2.5 Multiple Molecular Graph 1787.3 Machine Learning with Molecular Graphs 1797.3.1 General Architecture of Graph Neural Networks 1797.3.2 Graph Convolutional Network 1817.3.3 Graph Attention Network 1827.3.4 Continuous Kernel-based Convolutional Network 1827.3.5 Crystal Graph Convolutional Neural Network 1837.4 Graph-based Machine Learning for Molecular Interactions 1837.4.1 Vector Concatenation Approach to Prediction Molecule-to-Molecule Interactions 1847.4.2 Attention Map Approach for Interpretable Prediction of Molecule-to-Molecule Interactions 1857.5 Representation Learning from Molecular Graphs 1867.5.1 Unsupervised Representation Learning 1877.5.2 Supervised Representation Learning 1877.6 Python Implementations 1897.6.1 Data Conversion: Molecular Structures to Molecular Graphs 1907.6.2 Machine Learning: Deep Learning Frameworks for Graph Neural Networks 1907.6.3 Pymatgen for Crystal Structures 1927.7 Graph-based Machine Learning for Chemical Applications 1937.7.1 Message Passing Neural Network to Predict Physical Properties of Molecules 1937.7.2 Scale-Aware Prediction of Molecular Properties 1937.7.3 Prediction of Optimal Properties From Chromophore-Solvent Interactions 1947.7.4 Drug Discovery with Reinforcement Learning 1957.7.5 Graph Neural Networks for Crystal Structures 1957.8 Conclusion 196References 1968 Extracting Metal-Organic Frameworks Data from the Cambridge Structural Database 201Aurelia Li, Rocio Bueno-Perez, and David Fairen-Jimenez8.1 Introduction 2018.2 Building the CSD MOF Subset 2038.2.1 What Is a MOF? 2038.2.2 ConQuest 2048.3 The CSD MOF Subset 2088.3.1 Removing Solvents With the CSD Python API 2098.3.2 Adding Missing Hydrogens 2098.4 Textural Properties of MOFs and Their Evolution 2108.5 Classification of MOFs 2118.5.1 Identification of Target MOF Families 2128.5.2 Identification of Surface Functionalities in MOFs 2178.5.3 Identification of Chiral MOFs 2178.5.4 Porous Network Connectivity and Framework Dimensionality 2188.5.5 An Insight into Crystal Quality of Different MOF Families 2208.6 The CSD MOF Subset Among All the MOF Databases 2238.7 Conclusions 225Acknowledgments 226References 2269 Data-Driven Approach for Rational Synthesis of Zeolites and Other Nanoporous Materials 233Watcharop Chaikittisilp9.1 Introduction 2339.2 Rationalization of the Synthesis-Structure Relationship in Zeolite Synthesis: Application Machine Learning and Graph Theory to Zeolite Synthesis 2349.3 Extraction of the Structure-Property Relationship in Nanoporous Nitrogen-Doped Carbons: Dealing with the Missing Values in Literature Data 2399.4 Acceleration of Experimental Exploration of Nanoporous Metal Alloys: An Active Learning Approach 2439.5 Summary 247Acknowledgments 248References 24810 Porous Molecular Materials: Exploring Structure and Property Space with Software and Artificial Intelligence 251Steven Bennett and Kim E. Jelfs10.1 Introduction 25110.2 Computational Modeling of Porous Molecular Materials 25510.2.1 Structure Prediction 25610.2.2 Modeling Porosity 25710.2.3 Amorphous and Liquid Phase Simulations 25910.3 Data-Driven Discovery: Applying Artificial Intelligence Methods to Materials Discovery 26010.3.1 Training Data Generation 26210.3.1.1 Hypothetical Structure Datasets 26210.3.1.2 Experimental Structure Datasets 26310.3.1.3 Extraction of Data From Scientific Literature 26310.3.1.4 Data Augmentation and Transfer Learning 26310.3.2 Descriptor Construction and Selection 26410.3.2.1 Local Environment Descriptors 26410.3.2.2 Global Environment Descriptors 26510.4 Efficient Traversal of the Chemical Space of Porous Materials 26610.4.1 Evolutionary Algorithms 26610.4.2 Reducing the Number of Experiments: Bayesian Optimization and Active Learning 26710.4.3 Chemical Space Exploration with Deep Learning 26810.5 Considering Synthetic Accessibility 26910.6 Closing the Loop: How Can High-Throughput Experimentation Feed Back into Computation? 27010.6.1 High-Throughput and Autonomous Experimentation 27110.7 Conclusions 272References 27211 Machine Learning-Aided Discovery of Nanoporous Materials for Energy- and Environmental-Related Applications 283Archit Datar, Qiang Lyu, and Li-Chiang Lin11.1 Introduction 28311.1.1 Nanoporous Materials 28311.1.2 History and Development 28311.1.3 Gas Separation and Storage Applications 28411.1.4 Large-Scale Computational Screening for Gas Separation and Storage 28411.2 Concepts and Background for Data-Driven Approaches 28611.2.1 Dimensionality Reduction 28611.2.2 Machine Learning Models 28711.2.2.1 Linear Models 28711.2.2.2 Decision Trees and Random Forests 28811.2.2.3 Support Vector Machine 28911.2.2.4 Neural Networks 28911.2.2.5 Unsupervised Learning 29011.3 Data-Driven Approaches 29011.3.1 Nanoporous Structure Datasets 29111.3.2 Identifying Feature Space of Materials to Screen 29211.3.3 Methods to Search for Optimal Structures 29511.3.4 Modeling Interatomic and Intermolecular Interactions 29711.4 Case Studies 30011.4.1 Post-Combustion CO2 Capture 30011.4.2 Methane Storage 30311.4.3 Hydrogen Storage 30511.5 Summary and Outlook 309References 31112 Big Data Science in Nanoporous Materials: Datasets and Descriptors 319Maciej Haranczyk and Giulia Lo Dico12.1 Introduction 31912.2 Repositories of Nanoporous Material Structures 32112.2.1 Experimental Crystal Structures 32112.2.2 Predicted Crystal Structures 32212.3 Descriptors 32512.3.1 Handcrafted Descriptors 32512.3.2 Toward Automatically Generated and Multi-Scale Descriptors 32812.4 Properties 32912.5 Data Analysis 33012.5.1 Material Similarity and Distance Measures 33012.5.1.1 Diversity Selection 33112.5.1.2 Cluster Analysis 33212.6 Machine Learning Models of Structure-Property Relationships 33312.7 Current and Future Applications 335References 33613 Efficient Data Utilization in Training Machine Learning Models for Nanoporous Materials Screening 343Diego A. Gómez-Gualdrón, Cory M. Simon, and Yamil J. Colón13.1 Descriptor Selection 34413.1.1 Engineering of Advanced Features 34413.1.2 Engineering of Simpler Features 34713.2 Material Selection 34913.3 Model Selection 35113.3.1 Linear Regression 35313.3.2 Supported Vector Regressors 35413.3.3 Decision Tree-based Regressors 35513.3.4 Artificial Neural Networks 35713.4 Data Usage Strategies 36013.4.1 Transfer Learning 36113.4.2 Multipurpose Models 36513.4.3 Material Recommendation Systems 36813.4.4 Active Learning 37013.4.5 Machine Learning to Speed Up Data Generation 37113.5 Summary and Outlook 374References 37514 Machine Learning and Digital Manufacturing Approaches for Solid-State Materials Development 377Lawson T. Glasby, Emily H. Whaites, and Peyman Z. Moghadam14.1 Introduction 37714.2 The Development of MOF Databases 37914.3 Natural Language Processing 38014.4 An Overview of Machine Learning Models 38314.5 Machine Learning for Synthesis and Investigation of Solid State Materials 38614.6 Machine Learning in Design and Discovery of MOFs 38814.7 Current Limitations of Machine Learning for MOFs 39214.8 Automated Synthesis and Digital Manufacturing 39414.9 Digital Manufacturing of MOFs 40114.10 The Future of Digital Manufacturing 403References 40415 Overview of AI in the Understanding and Design of Nanoporous Materials 411Seyed Mohamad Moosavi, Frits Daeyaert, Michael W. Deem, and German Sastre15.1 Introduction 41115.2 Databases 41115.2.1 Structural Databases 41215.2.2 Databases of Material Properties 41215.2.3 Databases of Synthesis Protocols 41315.3 Big-Data Science for Nanoporous Materials Design and Discovery 41315.3.1 Representations of Chemical Data 41315.3.2 Learning Algorithms 41415.4 Applications 41515.5 Zeolite Synthesis and OSDAs 41715.6 Conclusion 420References 420Index 425
German Sastre, PhD, is a member of the Structure Commission of the International Zeolite Association. His research focus is on solid state computational chemistry as applied to nanoporous materials, including zeolites and metal-organic frameworks.Frits Daeyaert, PhD, has a background in computational drug design in the pharmaceutical industry. As visiting scientist at Rice University he has developed and applied de novo design methods for the design of organic structure directing agents for zeolite synthesis. He is a co-recipient of the 2019 Donald W. Breck award in Molecular Sieve Science for his contribution to the discovery of enantiomerically enriched STW zeolite.
1997-2024 DolnySlask.com Agencja Internetowa