Search

Machine learning potentials (MLPs) have become indispensable for performing accurate large-scale atomistic simulations and predicting crystal structures. This study introduces the development of a polynomial MLP specifically for the ternary Cu-Ag-Au system. The MLP is formulated as a polynomial of polynomial invariants that remain unchanged under any rotation. The polynomial MLP facilitates not only comprehensive global structure searches within the Cu-Ag-Au alloy system but also reliable predictions of a wide variety of properties across the entire composition range. The developed MLP supports highly accurate and efficient atomistic simulations, thereby significantly advancing the understanding of the Cu-Ag-Au system. Furthermore, the methodology demonstrated in this study can be easily applied to other ternary alloy systems., Comment: 14 pages, 9 figures

Estimating force constants for crystal structures is crucial for calculating various phonon-related properties. However, this task becomes particularly challenging when dealing with a large number of atoms or when third- and higher-order force constants are required. In this study, we propose an efficient approach that involves constructing a complete orthonormal basis set for the force constants. We formulate this approach using projection matrices and their eigenvectors to meet the requirements for the force constants. This basis set enables precise inference of the force constants from displacement-force datasets. Our efficient algorithms for basis-set construction and force constant estimation are implemented in the symfc code. Furthermore, several applications demonstrated in this study indicate that the current approach facilitates the efficient and accurate determination of force constants., Comment: 20 pages, 11 figures

Machine learning potentials (MLPs) have become indispensable for conducting accurate large-scale atomistic simulations and for the efficient prediction of crystal structures. Polynomial MLPs, defined by polynomial rotational invariants, have been systematically developed for a wide range of elemental, alloy, and ionic systems. This study introduces a highly efficient and robust methodology for enumerating globally stable and metastable structures utilizing polynomial MLPs. To develop MLPs that are sufficiently robust for structure enumeration, an iterative process involving random structure searches and subsequent updates to the MLPs is employed. This methodology has been systematically applied to elemental systems such as As, Bi, Ga, In, La, P, Sb, Sn, and Te, where numerous local minima present significant competition with the global minimum in terms of energy. The proposed approach facilitates robust global structure searches and structure enumerations by markedly accelerating the search process and expanding the search space., Comment: 18 pages, 14 figures

The application of first-principles calculations for predicting lattice thermal conductivity (LTC) in crystalline materials, in conjunction with the linearized phonon Boltzmann equation, has gained increasing popularity. In this calculation, the determination of force constants through first-principles calculations is critical for accurate LTC predictions. For material exploration, performing first-principles LTC calculations in a high-throughput manner is now expected, although it requires significant computational resources. To reduce computational demands, we integrated polynomial machine learning potentials on-the-fly during the first-principles LTC calculations. This paper presents a systematic approach to first-principles LTC calculations. We designed and optimized an efficient workflow that integrates multiple modular software packages. We applied this approach to calculate LTCs for 103 compounds of the wurtzite, zincblende, and rocksalt types to evaluate the performance of the polynomial machine learning potentials in LTC calculations. We demonstrate a significant reduction in the computational resources required for the LTC predictions.

The polynomial machine learning potentials (MLPs) described by polynomial rotational invariants have been systematically developed for various systems and used in diverse applications in crystalline states. In this study, we systematically investigate the predictive power of the polynomial MLPs for liquid structural properties in 22 elemental systems with diverse chemical bonding properties, including those showing anomalous melting behavior, such as Si, Ge, and Bi. We compare liquid structural properties obtained from molecular dynamics simulations using the density functional theory (DFT) calculation, the polynomial MLPs, and other interatomic potentials in the literature. The current results demonstrate that the polynomial MLPs consistently exhibit high predictive power for liquid structural properties with the same accuracy as that of typical DFT calculations., Comment: REVTeX 4-2, 30 pages with 35 figures

Machine learning potentials (MLPs) developed from extensive datasets constructed from density functional theory (DFT) calculations have become increasingly appealing for many researchers. This paper presents a framework of polynomial-based MLPs, called polynomial MLPs. The systematic development of accurate and computationally efficient polynomial MLPs for many elemental and binary alloy systems and their predictive powers for various properties are also demonstrated. Consequently, many polynomial MLPs are available in a repository website. The repository will help many scientists perform accurate and efficient large-scale atomistic simulations and crystal structure searches., Comment: The article has been submitted to Journal of Applied Physics. arXiv admin note: text overlap with arXiv:2008.09750

The advanced data structure of the zero-suppressed binary decision diagram (ZDD) enables us to efficiently enumerate nonequivalent substitutional structures. Not only can the ZDD store a vast number of structures in a compressed manner, but also can a set of structures satisfying given constraints be extracted from the ZDD efficiently. Here, we present a ZDD-based efficient algorithm for exhaustively searching for special quasirandom structures (SQSs) that mimic the perfectly random substitutional structure. We demonstrate that the current approach can extract only a tiny number of SQSs from a ZDD composed of many substitutional structures (>$10^{12}$). As a result, we find SQSs that are optimized better than those proposed in the literature. A series of SQSs should be helpful for estimating the properties of substitutional solid solutions. Furthermore, the present ZDD-based algorithm should be useful for applying the ZDD to the other structure enumeration problems.

In silicon, lattice thermal conductivity plays an important role in a wide range of applications such as thermoelectric and microelectronic devices. Grain boundaries (GBs) in polycrystalline silicon can significantly reduce lattice thermal conductivity, but the impact of GB atomic structures on it remains to be elucidated. This study demonstrates accurate predictions of the GB structures, GB energies, and GB phonon properties in silicon using machine learning potentials (MLPs). The results indicate that the MLPs enable robust GB structure searches owing to the fact that the MLPs were developed from a training dataset covering a wide variety of structures. We also investigate lattice thermal conduction at four GB atomic structures using large-scale perturbed molecular dynamics and phonon wave-packet simulations. The comparison of these results indicates that the GB structure dependence of thermal conductivity stems from anharmonic vibrations at GBs rather than from the phonon transmission behavior at GBs. The advantages of the MLPs compared with a typical empirical potential of silicon are also thoroughly investigated., Comment: 16 pages with 10 figures

Machine learning potentials (MLPs) are becoming powerful tools for performing accurate atomistic simulations and crystal structure optimizations. An approach to developing MLPs employs a systematic set of polynomial invariants including high-order ones to represent the neighboring atomic density. In this study, a formulation of the polynomial invariants is extended to the case of multicomponent systems. The extended formulation is more complex than the formulation for elemental systems. This study also shows its application to Ti-Al binary system. As a result, an MLP with the lowest error and MLPs with high computational cost performance are selected from the many MLPs developed systematically. The predictive powers of the developed MLPs for many properties, such as the formation energy, elastic constants, thermodynamic properties, and mechanical properties, are examined. The MLPs exhibit high predictive power for the properties in a wide variety of ordered structures. The present scheme should be systematically applicable to other multicomponent systems., Comment: 13 pages, 6 figures

Accurate interatomic potentials are in high demand for large-scale atomistic simulations of materials that are prohibitively expensive by density functional theory (DFT) calculation. In this study, we apply machine learning potentials in a recently constructed repository to the prediction of the grain boundary energy in face-centered-cubic elemental metals, i.e., Ag, Al, Au, Cu, Pd, and Pt. The systematic application of machine learning potentials shows that they enable us to predict grain boundary structures and their energies accurately. The grain boundary energies predicted by the MLPs are in agreement with those calculated by DFT, although no grain boundary structures were included in training datasets of the present MLPs.

This paper introduces a machine learning potential repository that includes Pareto optimal machine learning potentials. It also shows the systematic development of accurate and fast machine learning potentials for a wide range of elemental systems. As a result, many Pareto optimal machine learning potentials are available in the repository from a website. Therefore, the repository will help many scientists to perform accurate and fast atomistic simulations., Comment: 9 pages, 3 figures

A derivative structure is a nonequivalent substitutional atomic configuration derived from a given primitive cell. The enumeration of derivative structures plays an essential role in searching for the ground states in multicomponent systems. However, it is computationally hard to enumerate derivative structures if the number of derivative structures of a target system becomes huge. In the present study, we introduce a novel compact data structure of the zero-suppressed binary decision diagram (ZDD) to enumerate derivative structures much more efficiently. The present study shows its simple applications to the enumeration of structures derived from the face-centered cubic and hexagonal close-packed lattices in binary, ternary, and quaternary systems. The present ZDD-based procedure should significantly contribute not only to various computational approaches based on the derivative structures but also to a wide range of combinatorial issues in physics and materials science.

Oxygen vacancy ordering in perovskite-type transition-metal oxides plays an important role in the emergence of exotic electronic properties, as typified by superconducting cuprates. In this study, we predict the stability of oxygen-deficient perovskite structures in ACuO$_{3-x}$ (A $=$ Ca, Sr, Ba, Sc, Y, La) by density functional theory calculation. We introduce a combination of the cluster expansion method, Gaussian process, and Bayesian optimization to find stable oxygen-deficient structures among a considerable number of candidates. Our calculations not only reproduce the reported structures but suggest the presence of several unknown oxygen-deficient perovskite structures, some of which are stabilized at high pressures. This work demonstrates the great applicability of the present computational procedure for the elucidation of the structural stability of strongly correlated oxides with a large tolerance to oxygen deficiency., Comment: 11 pages, 9 figures

Many rotational invariants for crystal structure representations have been used to describe the structure-property relationship by machine learning. The machine learning interatomic potential (MLIP) is one of the applications of rotational invariants, which provides the relationship between the energy and the crystal structure. Since the MLIP requires the highest accuracy among machine learning estimations of the structure-property relationship, the enumeration of rotational invariants is useful for constructing MLIPs with the desired accuracy. In this study, we introduce high-order linearly independent rotational invariants up to the sixth order based on spherical harmonics and apply them to linearized MLIPs for elemental aluminum. A set of rotational invariants is derived by the general process of reducing the Kronecker products of irreducible representations (Irreps) for the SO(3) group using a group-theoretical projector method. A high predictive power for a wide range of structures is accomplished by using high-order invariants with low-order invariants equivalent to pair and angular structural features., Comment: 15 pages, 4 figures

Structures and properties of many inorganic compounds have been collected historically. However, it only covers a very small portion of possible inorganic crystals, which implies the presence of numerous currently unknown compounds. A powerful machine-learning strategy is mandatory to discover new inorganic compounds from all chemical combinations. Herein we propose a descriptor-based recommender-system approach to estimate the relevance of chemical compositions where stable crystals can be formed [i.e., chemically relevant compositions (CRCs)]. As well as data-driven compositional similarity used in the literature, the use of compositional descriptors as a prior knowledge can accelerate the discovery of new compounds. We validate our recommender systems in two ways. Firstly, one database is used to construct a model, while another is used for the validation. Secondly, we estimate the phase stability for compounds at expected CRCs using density functional theory calculations., Comment: 8 pages, 7 figures

Machine-learning interatomic potential (MLIP) has been of growing interest as a useful method to describe the energetics of systems of interest. In the present study, we examine the accuracy of linearized pairwise MLIPs and angular-dependent MLIPs for 31 elemental metals. Using all of the optimal MLIPs for 31 elemental metals, we show the robustness of the linearized frameworks, the general trend of the predictive power of MLIPs and the limitation of pairwise MLIPs. As a result, we obtain accurate MLIPs for all 31 elements using the same linearized framework. This indicates that the use of numerous descriptors is the most important practical feature for constructing MLIPs with high accuracy. An accurate MLIP can be constructed using only pairwise descriptors for most non-transition metals, whereas it is very important to consider angular-dependent descriptors when expressing interatomic interactions of transition metals., Comment: 18 pages, 14 figures

We propose a machine-learning method for evaluating the potential barrier governing atomic transport based on the preferential selection of dominant points for the atomic transport. The proposed method generates numerous random samples of the entire potential energy surface (PES) from a probabilistic Gaussian process model of the PES, which enables defining the likelihood of the dominant points. The robustness and efficiency of the method are demonstrated on a dozen model cases for proton diffusion in oxides, in comparison with a conventional nudge elastic band method.

Chemically relevant compositions (CRCs) and atomic arrangements of inorganic compounds have been collected as inorganic crystal structure databases. Machine-learning is a unique approach to search for currently unknown CRCs from vast candidates. Herein we propose matrix- and tensor-based recommender system approaches to predict currently unknown CRCs from database entries of CRCs. Firstly, the performance of the recommender system approaches to discover currently unknown CRCs is examined. A Tucker decomposition recommender system shows the best discovery rate of CRCs as the majority of the top 100 recommended ternary and quaternary compositions correspond to CRCs. Secondly, systematic density functional theory (DFT) calculations are performed to investigate the phase stability of the recommended currently unknown CRCs. The phase stability of the 27 compositions reveals that 23 currently unknown compounds are stable. These results indicate that the recommender system has great potential to accelerate the discovery of new compounds., Comment: 9 pages, 9 figures

Descriptors, which are representations of compounds, play an essential role in machine learning of materials data. Although many representations of elements and structures of compounds are known, these representations are difficult to use as descriptors in their unchanged forms. This chapter shows how compounds in a dataset can be represented as descriptors and applied to machine-learning models for materials datasets., Comment: 12 pages, 10 figures

Machine learning interatomic potentials (MLIPs) based on a large dataset obtained by density functional theory (DFT) calculation have been developed recently. This study gives both conceptual and practical bases for the high accuracy of MLIPs, although MLIPs have been considered to be simply an accurate black-box description of atomic energy. We also construct the most accurate MLIP of the elemental Ti ever reported using a linearized MLIP framework and many angular-dependent descriptors, which also corresponds to a generalization of the modified embedded atom method (MEAM) potential.

A first-principles-based method for computing phonons of magnetic random solid solutions including thermal magnetic fluctuations is developed. The method takes fluctuations of force constants (FCs) due to magnetic excitations as well as due to chemical disorder into account. The developed approach correctly predicts the experimentally observed unusual phonon hardening of a transverse acoustic mode in Fe-Pd an Fe-Pt Invar alloys with increasing temperature. This peculiar behavior, which cannot be explained within a conventional, harmonic picture, turns out to be a consequence of thermal magnetic fluctuations.

The representations of a compound, called "descriptors" or "features", play an essential role in constructing a machine-learning model of its physical properties. In this study, we adopt a procedure for generating a systematic set of descriptors from simple elemental and structural representations. First it is applied to a large dataset composed of the cohesive energy for about 18000 compounds computed by density functional theory (DFT) calculation. As a result, we obtain a kernel ridge prediction model with a prediction error of 0.041 eV/atom, which is close to the "chemical accuracy" of 1 kcal/mol (0.043 eV/atom). The procedure is also applied to two smaller datasets, i.e., a dataset of the lattice thermal conductivity (LTC) for 110 compounds computed by DFT calculation and a dataset of the experimental melting temperature for 248 compounds. We examine the performance of the descriptor sets on the efficiency of Bayesian optimization in addition to the accuracy of the kernel ridge regression models. They exhibit good predictive performances., Comment: 11 pages, 5 figures

The band-unfolding method is widely used to calculate the effective band structures of a disordered system from its supercell model. The unfolded band structures show the crystallographic symmetry of the underlying structure, where the difference of chemical components and the local atomic relaxation are ignored. It has been, however, still difficult to decompose the unfolded band structures into the modes based on the crystallographic symmetry of the underlying structure, and therefore detailed analyses of the unfolded band structures have been restricted. In this study, we develop a procedure to decompose the unfolded band structures according to the small representations (SRs) of the little groups. For this purpose, we derive the projection operators for SRs based on the group representation theory. We also introduce another type of projection operators for chemical elements, which enables us to decompose the unfolded band structures into the contributions of different combinations of chemical elements. Using the current method, we investigate the phonon band structure of disordered face-centered cubic Cu0.75Au0.25, which has large variations of atomic masses and force constants among the atomic sites due to the chemical disorder. We find several peculiar behaviors such as discontinuous and split branches in the unfolded phonon band structure. They are found to occur because different combinations of the chemical elements contribute to different regions of frequency.

In this paper, we propose a selective sampling procedure to preferentially evaluate a potential energy surface (PES) in a part of the configuration space governing a physical property of interest. The proposed sampling procedure is based on a machine learning method called the Gaussian process (GP), which is used to construct a statistical model of the PES for identifying the region of interest in the configuration space. We demonstrate the efficacy of the proposed procedure for atomic diffusion and ionic conduction, specifically the proton conduction in a well-studied proton-conducting oxide, barium zirconate BaZrO3. The results of the demonstration study indicate that our procedure can efficiently identify the low-energy region characterizing the proton conduction in the host crystal lattice, and that the descriptors used for the statistical PES model have a great influence on the performance.

Machine learning techniques are applied to make prediction models of the G0W0 band-gaps for 156 AX binary compounds using Kohn-Sham band-gaps and other fundamental information of constituent elements and crystal structure as predictors. Ordinary least square regression (OLSR), least absolute shrinkage and selection operator (LASSO) and non-linear support vector regression (SVR) methods are applied with several levels of predictor sets. When the Kohn-Sham band-gap by GGA (PBE) or modified Becke-Johnson (mBJ) is used as a single predictor, OLSR model predicts the G0W0 band-gap of a randomly selected test data with the root mean square error (RMSE) of 0.54 eV. When Kohn-Sham band gap by PBE and mBJ methods are used together with a set of various forms of predictors representing constituent elements and crystal structures, RMSE decreases significantly. The best model by SVR yields the RMSE of 0.18 eV. A large set of band-gaps estimated in this way should be useful as predictors for materials exploration., Comment: 24 pages, 6 figures, submitted to Phys. Rev. B

Compounds of low lattice thermal conductivity (LTC) are essential for seeking thermoelectric materials with high conversion efficiency. Some strategies have been used to decrease LTC. However, such trials have yielded successes only within a limited exploration space. Here we report the virtual screening of a library containing 54,779 compounds. Our strategy is to search the library through Bayesian optimization using for the initial data the LTC obtained from first-principles anharmonic lattice dynamics calculations for a set of 101 compounds. We discovered 221 materials with very low LTC. Two of them have even an electronic band gap < 1 eV, what makes them exceptional candidates for thermoelectric applications. In addition to those newly discovered thermoelectric materials, the present strategy is believed to be powerful for many other applications in which chemistry of materials are required to be optimized., Comment: 6 pages, 4 figures

Interatomic potentials have been widely used in atomistic simulations such as molecular dynamics. Recently, frameworks to construct accurate interatomic potentials that combine a systematic set of density functional theory (DFT) calculations with machine learning techniques have been proposed. One of these methods is to use compressed sensing to derive a sparse representation for the interatomic potential. This facilitates the control of the accuracy of interatomic potentials. In this study, we demonstrate the applicability of compressed sensing to deriving the interatomic potential of ten elemental metals, namely, Ag, Al, Au, Ca, Cu, Ga, In, K, Li and Zn. For each elemental metal, the interatomic potential is obtained from DFT calculations using elastic net regression. The interatomic potentials are found to have prediction errors of less than 3.5 meV/atom, 0.03 eV/\AA\ and 0.15 GPa for the energy, force and the stress tensor, respectively, which enable the accurate prediction of physical properties such as lattice constants and the phonon dispersion relationship., Comment: 11 pages, 5 figures

Structural stability of paramagnetic (PM) body-centered cubic (bcc) Fe under pressure is investigated based on first-principles phonon calculations. Spin configurations of the PM phase are approximated using a binary special quasi-random structure (SQS) with a supercell approach. The behavior of phonon modes can be associated with pressure-induced phase transitions to the face-centered cubic (fcc) and hexagonal close-packed (hcp) structures as follows: For the PM phase, it is found that the low-frequency transverse mode at the N point (N$_4^-$ mode), which corresponds to a bcc-hcp phase transition pathway, exhibits strong softening under isotropic volume compression. The frequency of this mode becomes zero by $2\%$ volume decrease within the harmonic approximation. This result is not consistent with the experimental fact that phase transition from the PM bcc to hcp phases does not occur under volume compression. The seeming contradiction can be explained only when anharmonic behavior of the N$_4^-$ mode is taken into consideration; a potential energy curve along the N$_4^-$ mode becomes closer to a double-well shape for the PM phase under the volume compression. On the other hand, softening of the longitudinal mode at the 2/3[111] point under the volume compression is also found for the PM phase, which indicates the pressure-induced bcc-fcc phase transition along this mode. Such behaviors are not seen in ferromagnetic (FM) bcc Fe, implying that the magnetic structure plays essential roles on the phase transition mechanism.

The use of a special quasirandom structure (SQS) is a rational and efficient way to approximate random alloys. A wide variety of physical properties of metallic and semiconductor random alloys have been successfully estimated by a combination of an SQS and density functional theory (DFT) calculation. Here, we investigate the application of an SQS to the ionic multicomponent systems with configurations of heterovalent ions, including point-charge lattices, MgAl$_2$O$_4$ and ZnSnP$_2$. It is found that the physical properties do not converge with the supercell size of the SQS. This is ascribed to the fact that the correlation functions of long-range clusters larger than the period of the supercell are not optimized in the SQS. However, we demonstrate that the physical properties of the perfectly disordered structure can be estimated by linear extrapolation using the inverse of the supercell size., Comment: 7 pages, 4 figures

We propose an efficient approach to accurately finding the ground-state structures in alloys based on the cluster expansion method. In this approach, a small number of candidate ground-state structures are obtained without any information of the energy. To generate the candidates, we employ the convex hull constructed from the correlation functions of all possible structures by using an efficient algorithm. This approach is applicable to not only simple lattices but also complex lattices. Firstly, we evaluate the convex hulls for binary alloys with four types of simple lattice. Then we discuss the structures on the vertices. To examine the accuracy of this approach, we perform a set of density functional theory calculations and the cluster expansion for Ag-Au alloy and compare the formation energies of the vertex structures with those of all possible structures. As applications, the ground-state structures of the intermetallic compounds CuAu, CuAg, CuPd, AuAg, AuPd, AgPd, MoTa, MoW and TaW are similarly evaluated. Finally, the energy distribution is obtained for different cation arrangements in MgAl$_2$O$_4$ spinel, for which long-range interactions are essential for the accurate description of its energetics., Comment: 8 pages, 7 figures

We propose a simple scheme to estimate potential energy surface (PES) with which the accuracy can be easily controlled and improved up to the level of the density functional theory (DFT) calculations. It is based on a model selection within the framework of linear regression using the least absolute shrinkage and selection operator (LASSO) technique. Basis functions are selected from a systematic large set of candidate functions. The sparsity of PES significantly reduces the computational demands for evaluation of the energy and the force in molecular dynamics simulations without losing the accuracy. The usefulness of the scheme is well demonstrated for describing elemental metals of Na and Mg., Comment: 5 pages, 4 figures

A combination of systematic density functional theory (DFT) calculations and machine learning techniques has a wide range of potential applications. This study presents an application of the combination of systematic DFT calculations and regression techniques to the prediction of the melting temperature for single and binary compounds. Here we adopt the ordinary least-squares regression (OLSR), partial least-squares regression (PLSR), support vector regression (SVR) and Gaussian process regression (GPR). Among the four kinds of regression techniques, the SVR provides the best prediction. In addition, the inclusion of physical properties computed by the DFT calculation to a set of predictor variables makes the prediction better. Finally, a simulation to find the highest melting temperature toward the efficient materials design using kriging is demonstrated. The kriging design finds the compound with the highest melting temperature much faster than random designs. This result may stimulate the application of kriging to efficient materials design for a broad range of applications.

We have been examining factors determining the accuracy of cluster expansion (CE), which is used in combination with many density functional theory (DFT) calculations. With the exception of multicomponent metallic or isovalent ionic systems, the contributions of long-range effective cluster interactions (ECIs) to configurational energetics are not negligible, which is ascribed to long-range electrostatic interactions. The truncation of ECIs in such systems leads to systematic errors. A typical problem with such errors can be seen in Monte Carlo (MC) simulations since simulation supercells composed of a larger number of atoms than those of the input DFT structures are used. The prediction errors for long-period structures beyond the cell size of the input DFT structures in addition to those for short-period structures within the cell size of the input DFT structures need to be carefully examined to control the accuracy of CE. In the present study, we quantitatively discuss the contribution of the truncation of long-range ECIs to the accuracy of CE. Two types of system, namely, a point-charge spinel lattice and a real MgAl2O4 spinel crystal, are examined.