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 bot...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.展开更多
We conducted a large-scale density-functional theory study on the influence of the exchange-correlation functional in the calculation of electronic band gaps of solids.First,we use the large materials data set that we...We conducted a large-scale density-functional theory study on the influence of the exchange-correlation functional in the calculation of electronic band gaps of solids.First,we use the large materials data set that we have recently proposed to benchmark 21 different functionals,with a particular focus on approximations of the meta-generalized-gradient family.Combining these data with the results for 12 functionals in our previous work,we can analyze in detail the characteristics of each approximation and identify its strong and/or weak points.Beside confirming that mBJ,HLE16 and HSE06 are the most accurate functionals for band gap calculations,we reveal several other interesting functionals,chief among which are the local Slater potential approximation,the GGA AK13LDA,and the meta-GGAs HLE17 and TASK.We also compare the computational efficiency of these different approximations.Relying on these data,we investigate the potential for improvement of a promising subset of functionals by varying their internal parameters.The identified optimal parameters yield a family of functionals fitted for the calculation of band gaps.Finally,we demonstrate how to train machine learning models for accurate band gap prediction,using as input structural and composition data,as well as approximate band gaps obtained from density-functional theory.展开更多
We present a comprehensive theoretical study of conventional superconductivity in cubic antiperovskites materials with composition XYZ_(3) where X and Z are metals,and Y is H,B,C,N,O,and P.Our starting point are elect...We present a comprehensive theoretical study of conventional superconductivity in cubic antiperovskites materials with composition XYZ_(3) where X and Z are metals,and Y is H,B,C,N,O,and P.Our starting point are electron–phonon calculations for 397 materials performed with density-functional perturbation theory.While 43%of the materials are dynamically unstable,we discovered 16 compounds close to thermodynamic stability and with T_(c) higher than 5 K.Using these results to train interpretable machine-learning models,leads us to predict a further 57(thermodynamically unstable)materials with superconducting transition temperatures above 5 K,reaching a maximum of 17.8 K for PtHBe3.Furthermore,the models give us an understanding of the mechanism of superconductivity in antiperovskites.The combination of traditional approaches with interpretable machine learning turns out to be a very efficient methodology to study and systematize whole classes of materials and is easily extendable to other families of compounds or physical properties.展开更多
Heusler compounds attract a great deal of attention from researchers thanks to a wealth of interesting properties,among which is superconductivity.Here we perform an extensive study of the superconducting and elastic ...Heusler compounds attract a great deal of attention from researchers thanks to a wealth of interesting properties,among which is superconductivity.Here we perform an extensive study of the superconducting and elastic properties of the cubic(full-)Heusler family using a mixture of ab initio methods,as well as interpretable and predictive machine-learning models.By analyzing the statistical distributions of these properties and comparing them to anti-perovskites,we recognize universal behaviors that should be common to all conventional superconductors while others turn out to be specific to the material family.In total,we discover a total of eight hypothetical materials with critical temperatures above 10 K to be compared with the current record of T_(c)=4.7 K in this family.Furthermore,we expect most of these materials to be highly ductile,making them potential candidates for the manufacture of wires and tapes for superconducting magnets.展开更多
Garnets have found important applications in modern technologies including magnetorestriction,spintronics,lithium batteries,etc.The overwhelming majority of experimentally known garnets are oxides,while explorations(e...Garnets have found important applications in modern technologies including magnetorestriction,spintronics,lithium batteries,etc.The overwhelming majority of experimentally known garnets are oxides,while explorations(experimental or theoretical)for the rest of the chemical space have been limited in scope.A key issue is that the garnet structure has a large primitive unit cell,requiring a substantial amount of computational resources.To perform a comprehensive search of the complete chemical space for new garnets,we combine recent progress in graph neural networks with high-throughput calculations.We apply the machine learning model to identify the potentially(meta-)stable garnet systems before performing systematic density-functional calculations to validate the predictions.We discover more than 600 ternary garnets with distances to the convex hull below 100 meV⋅atom−1.This includes sulfide,nitride,and halide garnets.We analyze their electronic structure and discuss the connection between the value of the electronic band gap and charge balance.展开更多
In this work,we present a large-scale study of gap deformation potentials based on density-functional theory calculations for over 5000 semiconductors.As expected,in most cases the band gap decreases for increasing vo...In this work,we present a large-scale study of gap deformation potentials based on density-functional theory calculations for over 5000 semiconductors.As expected,in most cases the band gap decreases for increasing volume with deformation potentials that can reach values of almost−15 eV.We find,however,also a sizeable number of materials with positive deformation potentials.Notorious members of this group are halide perovskites,known for their applications in photovoltaics.We then focus on understanding the physical reasons for so different values of the deformation potentials by investigating the correlations between this property and a large number of other material and compositional properties.We also train explainable machine learning models as well as graph convolutional networks to predict deformation potentials and establish simple rules to understand predicted values.Finally,we analyze in more detail a series of materials that have record positive and negative deformation potentials.展开更多
文摘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.
基金M.A.L.M.and S.B.acknowledge partial support from the DFG through the projects TRR 227,SFB 1375,FOR 2857,BO 4280/8-1,and MA 6787/9-1.
文摘We conducted a large-scale density-functional theory study on the influence of the exchange-correlation functional in the calculation of electronic band gaps of solids.First,we use the large materials data set that we have recently proposed to benchmark 21 different functionals,with a particular focus on approximations of the meta-generalized-gradient family.Combining these data with the results for 12 functionals in our previous work,we can analyze in detail the characteristics of each approximation and identify its strong and/or weak points.Beside confirming that mBJ,HLE16 and HSE06 are the most accurate functionals for band gap calculations,we reveal several other interesting functionals,chief among which are the local Slater potential approximation,the GGA AK13LDA,and the meta-GGAs HLE17 and TASK.We also compare the computational efficiency of these different approximations.Relying on these data,we investigate the potential for improvement of a promising subset of functionals by varying their internal parameters.The identified optimal parameters yield a family of functionals fitted for the calculation of band gaps.Finally,we demonstrate how to train machine learning models for accurate band gap prediction,using as input structural and composition data,as well as approximate band gaps obtained from density-functional theory.
基金T.F.T.C.acknowledges the financial support from the CFisUC through the project UIDB/04564/2020 and the Laboratory for Advanced Computing at the University of Coimbra for providing HPC resources that have contributed to the research results reported within this paper.
文摘We present a comprehensive theoretical study of conventional superconductivity in cubic antiperovskites materials with composition XYZ_(3) where X and Z are metals,and Y is H,B,C,N,O,and P.Our starting point are electron–phonon calculations for 397 materials performed with density-functional perturbation theory.While 43%of the materials are dynamically unstable,we discovered 16 compounds close to thermodynamic stability and with T_(c) higher than 5 K.Using these results to train interpretable machine-learning models,leads us to predict a further 57(thermodynamically unstable)materials with superconducting transition temperatures above 5 K,reaching a maximum of 17.8 K for PtHBe3.Furthermore,the models give us an understanding of the mechanism of superconductivity in antiperovskites.The combination of traditional approaches with interpretable machine learning turns out to be a very efficient methodology to study and systematize whole classes of materials and is easily extendable to other families of compounds or physical properties.
基金T.F.T.C.and P.B.acknowledge financial support from Fundação para a Ciência e Tecnologia(FCT),Portugal(projects UIDB/04564/2020 and 2022.09975.PTDC and contract 2020.04225.CEECIND)the Laboratory for Advanced Computing at University of Coimbra for providing HPC resources that have contributed to the research results reported within this paper.
文摘Heusler compounds attract a great deal of attention from researchers thanks to a wealth of interesting properties,among which is superconductivity.Here we perform an extensive study of the superconducting and elastic properties of the cubic(full-)Heusler family using a mixture of ab initio methods,as well as interpretable and predictive machine-learning models.By analyzing the statistical distributions of these properties and comparing them to anti-perovskites,we recognize universal behaviors that should be common to all conventional superconductors while others turn out to be specific to the material family.In total,we discover a total of eight hypothetical materials with critical temperatures above 10 K to be compared with the current record of T_(c)=4.7 K in this family.Furthermore,we expect most of these materials to be highly ductile,making them potential candidates for the manufacture of wires and tapes for superconducting magnets.
文摘Garnets have found important applications in modern technologies including magnetorestriction,spintronics,lithium batteries,etc.The overwhelming majority of experimentally known garnets are oxides,while explorations(experimental or theoretical)for the rest of the chemical space have been limited in scope.A key issue is that the garnet structure has a large primitive unit cell,requiring a substantial amount of computational resources.To perform a comprehensive search of the complete chemical space for new garnets,we combine recent progress in graph neural networks with high-throughput calculations.We apply the machine learning model to identify the potentially(meta-)stable garnet systems before performing systematic density-functional calculations to validate the predictions.We discover more than 600 ternary garnets with distances to the convex hull below 100 meV⋅atom−1.This includes sulfide,nitride,and halide garnets.We analyze their electronic structure and discuss the connection between the value of the electronic band gap and charge balance.
基金S.B.acknowledges the financial support from the Volkswagen Stiftung(Momentum)through the project“dandelion”P.B.acknowledges the financial support from the CFisUC through the project UIDB/04564/2020 and FCT under the contract 2020.04225.CEECIND.
文摘In this work,we present a large-scale study of gap deformation potentials based on density-functional theory calculations for over 5000 semiconductors.As expected,in most cases the band gap decreases for increasing volume with deformation potentials that can reach values of almost−15 eV.We find,however,also a sizeable number of materials with positive deformation potentials.Notorious members of this group are halide perovskites,known for their applications in photovoltaics.We then focus on understanding the physical reasons for so different values of the deformation potentials by investigating the correlations between this property and a large number of other material and compositional properties.We also train explainable machine learning models as well as graph convolutional networks to predict deformation potentials and establish simple rules to understand predicted values.Finally,we analyze in more detail a series of materials that have record positive and negative deformation potentials.
