Provides everything readers need to know for applying the power of informatics to materials science There is a tremendous interest in materials informatics and application of data mining to materials science. This book is a one-stop guide to the latest advances in these emerging fields. Bridging the gap between materials science and informatics, it introduces readers to up-to-date data mining and machine learning methods. It also provides an overview of state-of-the-art software and tools. Case studies illustrate the power of materials informatics in guiding the experimental discovery of new materials. Materials Informatics: Methods, Tools and Applications is presented in two parts?Methodological Aspects of Materials Informatics and Practical Aspects and Applications. The first part focuses on developments in software, databases, and high-throughput computational activities. Chapter topics include open quantum materials databases; the ICSD database; open crystallography databases; and more. The second addresses the latest developments in data mining and machine learning for materials science. Its chapters cover genetic algorithms and crystal structure prediction; MQSPR modeling in materials informatics; prediction of materials properties; amongst others. -Bridges the gap between materials science and informatics -Covers all the known methodologies and applications of materials informatics -Presents case studies that illustrate the power of materials informatics in guiding the experimental quest for new materials -Examines the state-of-the-art software and tools being used today Materials Informatics: Methods, Tools and Applications is a must-have resource for materials scientists, chemists, and engineers interested in the methods of materials informatics. Contents......Page 3 Introduction......Page 9 Open Databases for Science......Page 11 Building COD......Page 14 Use of COD......Page 22 Applications......Page 35 Perspectives......Page 40 References......Page 41 Introduction......Page 48 Content of ICSD......Page 49 Applications of ICSD......Page 53 References......Page 58 Introduction......Page 62 PAULING FILE: Crystal Structures......Page 64 PAULING FILE: Phase Diagrams......Page 79 PAULING FILE: Physical Properties......Page 82 Data Quality......Page 87 Distinct Phases......Page 88 Toward a Megadatabase......Page 91 Applications......Page 96 Lessons to Learn fromExperience......Page 106 Conclusion......Page 110 References......Page 111 Introduction......Page 114 Topological Tools for Developing Knowledge Databases......Page 115 Applications of Topological Tools in Crystal Chemistry and Materials Science......Page 138 Conclusions......Page 144 References......Page 145 Introduction......Page 155 Nature Defines Cornerstones Providing a Marvelously Rich but Still Very Rigid Systematic Framework of Restraint Conditions......Page 157 The Realization of the Fourth and Fifth Paradigms Requires Three Preconditions......Page 159 The Core Idea of the Fifth Paradigm......Page 160 Restraint Conditions Revealed by “Inorganic Solids Overview–Governing Factor Spaces (Maps)” Discovered by Data-Mining Techniques......Page 162 Quantum Simulation Strategy......Page 167 Workflows Engine in AiiDA to Carry Out High-Throughput Calculation for the Creation of the Materials Cloud, Binaries Edition......Page 170 References......Page 175 Kernel Ridge Regression......Page 177 Model Assessment......Page 179 Representations......Page 182 Recent Developments......Page 183 References......Page 184 Introduction......Page 186 Automated Computational Materials Design Frameworks......Page 187 Integrated Calculation of Materials Properties......Page 192 Online Data Repositories......Page 203 Materials Applications......Page 207 References......Page 214 Introduction......Page 228 Describing Molecules for Machine Learning Algorithms......Page 229 Building Fast and Accurate Models with Machine Learning......Page 239 Searching Through Chemical Libraries......Page 249 Conclusion......Page 253 References......Page 254 Introduction......Page 257 Machine Learning Potential for Global Optimization......Page 262 Interatomic Potential for Molecular Dynamics......Page 277 Statistical Approach for Constructing ML Potentials......Page 288 References......Page 290 Index......Page 293
