This book deals with an information-driven approach to plan materials discovery and design, iterative learning. The authors present contrasting but complementary approaches, such as those based on high throughput calculations, combinatorial experiments or data driven discovery, together with machine-learning methods. Similarly, statistical methods successfully applied in other fields, such as biosciences, are presented. The content spans from materials science to information science to reflect the cross-disciplinary nature of the field. A perspective is presented that offers a paradigm (codesign loop for materials design) to involve iteratively learning from experiments and calculations to develop materials with optimum properties. Such a loop requires the elements of incorporating domain materials knowledge, a database of descriptors (the genes), a surrogate or statistical model developed to predict a given property with uncertainties, performing adaptive experimental design to guide the next experiment or calculation and aspects of high throughput calculations as well as experiments. The book is about manufacturing with the aim to halving the time to discover and design new materials. Accelerating discovery relies on using large databases, computation, and mathematics in the material sciences in a manner similar to the way used to in the Human Genome Initiative. Novel approaches are therefore called to explore the enormous phase space presented by complex materials and processes. To achieve the desired performance gains, a predictive capability is needed to guide experiments and computations in the most fruitful directions by reducing not successful trials. Despite advances in computation and experimental techniques, generating vast arrays of data; without a clear way of linkage to models, the full value of data driven discovery cannot be realized. Hence, along with experimental, theoretical and computational materials science, we need to add a “fourth leg’’ to our toolkit to make the “Materials Genome'' a reality, the science of Materials Informatics.
This book addresses the current status, challenges and future directions of data-driven materials discovery and design. It presents the analysis and learning from data as a key theme in many science and cyber related applications. The challenging open questions as well as future directions in the application of data science to materials problems are sketched. Computational and experimental facilities today generate vast amounts of data at an unprecedented rate. The book gives guidance to discover new knowledge that enables materials innovation to address grand challenges in energy, environment and security, the clearer link needed between the data from these facilities and the theory and underlying science. The role of inference and optimization methods in distilling the data and constraining predictions using insights and results from theory is key to achieving the desired goals of real time analysis and feedback. Thus, the importance of this book lies in emphasizing that the full value of knowledge driven discovery using data can only be realized by integrating statistical and information sciences with materials science, which is increasingly dependent on high throughput and large scale computational and experimental data gathering efforts. This is especially the case as we enter a new era of big data in materials science with the planning of future experimental facilities such as the Linac Coherent Light Source at Stanford (LCLS-II), the European X-ray Free Electron Laser (EXFEL) and MaRIE (Matter Radiation in Extremes), the signature concept facility from Los Alamos National Laboratory. These facilities are expected to generate hundreds of terabytes to several petabytes of in situ spatially and temporally resolved data per sample. The questions that then arise include how we can learn from the data to accelerate the processing and analysis of reconstructed microstructure, rapidly map spatially resolved properties from high throughput data, devise diagnostics for pattern detection, and guide experiments towards desired targeted properties. The authors are an interdisciplinary group of leading experts who bring the excitement of the nascent and rapidly emerging field of materials informatics to the reader.
Typical timelines to go from discovery to impact in the advanced materials sector are between 10 to 30 years. Advances in robotics and artificial intelligence are poised to accelerate the discovery and development of new materials dramatically. This book is a primer for any materials scientist looking to future-proof their careers and get ahead of the disruption that artificial intelligence and robotic automation is just starting to unleash. It is meant to be an overview of how we can use these disruptive technologies to augment and supercharge our abilities to discover new materials that will solve world’s biggest challenges. Written by world leading experts on accelerated materials discovery from academia (UC Berkeley, Caltech, UBC, Cornell, etc.), industry (Toyota Research Institute, Citrine Informatics) and national labs (National Research Council of Canada, Lawrence Berkeley National Labs).
Given their tremendous success in commercial applications, machine learning (ML) models are increasingly being considered as alternatives to science-based models in many disciplines. Yet, these "black-box" ML models have found limited success due to their inability to work well in the presence of limited training data and generalize to unseen scenarios. As a result, there is a growing interest in the scientific community on creating a new generation of methods that integrate scientific knowledge in ML frameworks. This emerging field, called scientific knowledge-guided ML (KGML), seeks a distinct departure from existing "data-only" or "scientific knowledge-only" methods to use knowledge and data at an equal footing. Indeed, KGML involves diverse scientific and ML communities, where researchers and practitioners from various backgrounds and application domains are continually adding richness to the problem formulations and research methods in this emerging field. Knowledge Guided Machine Learning: Accelerating Discovery using Scientific Knowledge and Data provides an introduction to this rapidly growing field by discussing some of the common themes of research in KGML using illustrative examples, case studies, and reviews from diverse application domains and research communities as book chapters by leading researchers. KEY FEATURES First-of-its-kind book in an emerging area of research that is gaining widespread attention in the scientific and data science fields Accessible to a broad audience in data science and scientific and engineering fields Provides a coherent organizational structure to the problem formulations and research methods in the emerging field of KGML using illustrative examples from diverse application domains Contains chapters by leading researchers, which illustrate the cutting-edge research trends, opportunities, and challenges in KGML research from multiple perspectives Enables cross-pollination of KGML problem formulations and research methods across disciplines Highlights critical gaps that require further investigation by the broader community of researchers and practitioners to realize the full potential of KGML
Discover the power of machine learning in the physical sciences with this one-stop resource from a leading voice in the field Deep Learning for Physical Scientists: Accelerating Research with Machine Learning delivers an insightful analysis of the transformative techniques being used in deep learning within the physical sciences. The book offers readers the ability to understand, select, and apply the best deep learning techniques for their individual research problem and interpret the outcome. Designed to teach researchers to think in useful new ways about how to achieve results in their research, the book provides scientists with new avenues to attack problems and avoid common pitfalls and problems. Practical case studies and problems are presented, giving readers an opportunity to put what they have learned into practice, with exemplar coding approaches provided to assist the reader. From modelling basics to feed-forward networks, the book offers a broad cross-section of machine learning techniques to improve physical science research. Readers will also enjoy: A thorough introduction to the basic classification and regression with perceptrons An exploration of training algorithms, including back propagation and stochastic gradient descent and the parallelization of training An examination of multi-layer perceptrons for learning from descriptors and de-noising data Discussions of recurrent neural networks for learning from sequences and convolutional neural networks for learning from images A treatment of Bayesian optimization for tuning deep learning architectures Perfect for academic and industrial research professionals in the physical sciences, Deep Learning for Physical Scientists: Accelerating Research with Machine Learning will also earn a place in the libraries of industrial researchers who have access to large amounts of data but have yet to learn the techniques to fully exploit that access. Perfect for academic and industrial research professionals in the physical sciences, em style="font-family: Calibri, sans-serif; font-size: 11pt;"Deep Learning for Physical Scientists: Accelerating Research with Machine Learning will also earn a place in the libraries of industrial researchers who have access to large amounts of data but have yet to learn the techniques to fully exploit that access. This book introduces the reader to the transformative techniques involved in deep learning. A range of methodologies are addressed including: •Basic classification and regression with perceptrons •Training algorithms, such as back propagation and stochastic gradient descent and the parallelization of training •Multi-Layer Perceptrons for learning from descriptors, and de-noising data •Recurrent neural networks for learning from sequences •Convolutional neural networks for learning from images •Bayesian optimization for tuning deep learning architectures Each of these areas has direct application to physical science research, and by the end of the book, the reader should feel comfortable enough to select the methodology which is best for their situation, and be able to implement and interpret outcome of the deep learning model. The book is designed to teach researchers to think in new ways, providing them with new avenues to attack problems, and avoid roadblocks within their research. This is achieved through the inclusion of case-study like problems at the end of each chapter, which will give the reader a chance to practice what they have just learnt in a close-to-real-world setting, with example ‘solutions’ provided through an online resource. Market Description This book introduces the reader to the transformative techniques involved in deep learning. A range of methodologies are addressed including: • Basic classification and regression with perceptrons • Training algorithms, such as back propagation and stochastic gradient descent and the parallelization of training • Multi-Layer Perceptrons for learning from descriptors, and de-noising data • Recurrent neural networks for learning from sequences • Convolutional neural networks for learning from images • Bayesian optimization for tuning deep learning architectures Each of these areas has direct application to physical science research, and by the end of the book, the reader should feel comfortable enough to select the methodology which is best for their situation, and be able to implement and interpret outcome of the deep learning model. The book is designed to teach researchers to think in new ways, providing them with new avenues to attack problems, and avoid roadblocks within their research. This is achieved through the inclusion of case-study like problems at the end of each chapter, which will give the reader a chance to practice what they have just learnt in a close-to-real-world setting, with example ‘solutions’ provided through an online resource.
This book provides state-of-the-art computational approaches for accelerating materials discovery, synthesis, and processing using thermodynamics and kinetics. The authors deliver an overview of current practical computational tools for materials design in the field. They describe ways to integrate thermodynamics and kinetics and how the two can supplement each other.
Machine learning methods have lowered the cost of exploring new structures of unknown compounds, and can be used to predict reasonable expectations and subsequently validated by experimental results. As new insights and several elaborative tools have been developed for materials science and engineering in recent years, it is an appropriate time to present a book covering recent progress in this field. Searchable and interactive databases can promote research on emerging materials. Recently, databases containing a large number of high-quality materials properties for new advanced materials discovery have been developed. These approaches are set to make a significant impact on human life and, with numerous commercial developments emerging, will become a major academic topic in the coming years. This authoritative and comprehensive book will be of interest to both existing researchers in this field as well as others in the materials science community who wish to take advantage of these powerful techniques. The book offers a global spread of authors, from USA, Canada, UK, Japan, France, Russia, China and Singapore, who are all world recognized experts in their separate areas. With content relevant to both academic and commercial points of view, and offering an accessible overview of recent progress and potential future directions, the book will interest graduate students, postgraduate researchers, and consultants and industrial engineers.
The first reference of its kind in the rapidly emerging field of computational approachs to materials research, this is a compendium of perspective-providing and topical articles written to inform students and non-specialists of the current status and capabilities of modelling and simulation. From the standpoint of methodology, the development follows a multiscale approach with emphasis on electronic-structure, atomistic, and mesoscale methods, as well as mathematical analysis and rate processes. Basic models are treated across traditional disciplines, not only in the discussion of methods but also in chapters on crystal defects, microstructure, fluids, polymers and soft matter. Written by authors who are actively participating in the current development, this collection of 150 articles has the breadth and depth to be a major contributor toward defining the field of computational materials. In addition, there are 40 commentaries by highly respected researchers, presenting various views that should interest the future generations of the community. Subject Editors: Martin Bazant, MIT; Bruce Boghosian, Tufts University; Richard Catlow, Royal Institution; Long-Qing Chen, Pennsylvania State University; William Curtin, Brown University; Tomas Diaz de la Rubia, Lawrence Livermore National Laboratory; Nicolas Hadjiconstantinou, MIT; Mark F. Horstemeyer, Mississippi State University; Efthimios Kaxiras, Harvard University; L. Mahadevan, Harvard University; Dimitrios Maroudas, University of Massachusetts; Nicola Marzari, MIT; Horia Metiu, University of California Santa Barbara; Gregory C. Rutledge, MIT; David J. Srolovitz, Princeton University; Bernhardt L. Trout, MIT; Dieter Wolf, Argonne National Laboratory.
The Reviews in Computational Chemistry series brings together leading authorities in the field to teach the newcomer and update the expert on topics centered on molecular modeling, such as computer-assisted molecular design (CAMD), quantum chemistry, molecular mechanics and dynamics, and quantitative structure-activity relationships (QSAR). This volume, like those prior to it, features chapters by experts in various fields of computational chemistry. Topics in Volume 29 include: Noncovalent Interactions in Density-Functional Theory Long-Range Inter-Particle Interactions: Insights from Molecular Quantum Electrodynamics (QED) Theory Efficient Transition-State Modeling using Molecular Mechanics Force Fields for the Everyday Chemist Machine Learning in Materials Science: Recent Progress and Emerging Applications Discovering New Materials via a priori Crystal Structure Prediction Introduction to Maximally Localized Wannier Functions Methods for a Rapid and Automated Description of Proteins: Protein Structure, Protein Similarity, and Protein Folding
