One of the most exciting tools that have entered the material science toolbox in recent years is machine learning. This collection of statistical methods has already proved to be capable of considerably speeding up both fundamental and applied research. At present, we are witnessing an explosion of works that develop and apply machine learning to solid-state systems. We provide a comprehensive overview and analysis of the most recent research in this topic. As a starting point, we introduce machine learning principles, algorithms, descriptors, and databases in materials science. We continue with the description of different machine learning approaches for the discovery of stable materials and the prediction of their crystal structure. Then we discuss research in numerous quantitative structure–property relationships and various approaches for the replacement of first-principle methods by machine learning. We review how active learning and surrogate-based optimization can be applied to improve the rational design process and related examples of applications. Two major questions are always the interpretability of and the physical understanding gained from machine learning models. We consider therefore the different facets of interpretability and their importance in materials science. Finally, we propose solutions and future research paths for various challenges in computational materials science.

/pdf/recent-advances-and-applications-of-machine-learning-in-55gs85xsws.pdf

Recent advances and applications of machine learning in solid-state materials science

High-throughput electronic band structure calculations: challenges and tools

Despite the intense interest in metallic glasses for a variety of engineering applications, many details of their structure remain a mystery. Here, we present the first compelling atomic structural model for metallic glasses. This structural model is based on a new sphere-packing scheme—the dense packing of atomic clusters. Random positioning of solvent atoms and medium-range atomic order of solute atoms are combined to reproduce diffraction data successfully over radial distances up to ∼1 nm. Although metallic glasses can have any number of chemically distinct solute species, this model shows that they contain no more than three topologically distinct solutes and that these solutes have specific and predictable sizes relative to the solvent atoms. Finally, this model includes defects that provide richness to the structural description of metallic glasses. The model accurately predicts the number of solute atoms in the first coordination shell of a typical solvent atom, and provides a remarkable ability to predict metallic-glass compositions accurately for a wide range of simple and complex alloys.

A structural model for metallic glasses

AFLOW: An automatic framework for high-throughput materials discovery

AFLOWLIB.ORG: A distributed materials properties repository from high-throughput ab initio calculations

The Atlas of Crystal Structure Types for Intermetallic Phases offers you pictorial detail, clearly illustratedThe Atlas is the perfect reference to keep on your shelf beside the Second Edition of Pearson's Handbook. For each structure type, you can quickly find for all atoms (point sets): A list of all coordination atoms with corresponding coordinates, the distance to its central atom, its coordination number and its polyhedron code. A histogram of the number of surrounding atoms (n) versus interatomic distances between the central atom and surrounding atoms, the interatomic distances are given relative to the shortest distance and nearest in the coordination polyhedron (dn/dnearest). The standard setting of all structure types is analagous to Pearson's Second Edition data. All point sets are numbered consistently throughout a structure type, so you can easily trace each atom in all drawings and tables. For accuracy, all drawings and tables are computer-generated directly from the database. All structure types have been checked for consistency. Published: 1991 Format: 4 Volume Set

Atlas of Crystal Structure Types for Intermetallic Phases

On the nature of the electrochemical cycling stability of non-stoichiometric LaNi5-based hydride-forming compounds Part I. crystallography and electrochemistry

Al 2 O 3

The Pauling File, Binaries Edition

On the nature of the electrochemical cycling stability of non-stoichiometric LaNi5-based hydride-forming compounds Part II. In situ x-ray diffractometry

J.L.C. Daams

Papers

Atlas of Crystal Structure Types for Intermetallic Phases

On the nature of the electrochemical cycling stability of non-stoichiometric LaNi5-based hydride-forming compounds Part I. crystallography and electrochemistry

Al 2 O 3

The Pauling File, Binaries Edition

On the nature of the electrochemical cycling stability of non-stoichiometric LaNi5-based hydride-forming compounds Part II. In situ x-ray diffractometry