Online citations, reference lists, and bibliographies.

Compositional Optimization Of Hard-magnetic Phases With Machine-learning Models

Johannes J. Moller, Wolfgang Korner, Georg Krugel, Daniel F. Urban, Christian Urs Elsasser
Published 2018 · Materials Science, Physics
Cite This
Download PDF
Analyze on Scholarcy
Share
Abstract Machine Learning (ML) plays an increasingly important role in the discovery and design of new materials. In this paper, we demonstrate the potential of ML for materials research using hard-magnetic phases as an illustrative case. We build kernel-based ML models to predict optimal chemical compositions for new permanent magnets, which are key components in many green-energy technologies. The magnetic-property data used for training and testing the ML models are obtained from a combinatorial high-throughput screening based on density-functional theory calculations. Our straightforward choice of describing the different configurations enables the subsequent use of the ML models for compositional optimization and thereby the prediction of promising substitutes of state-of-the-art magnetic materials like Nd2Fe14B with similar intrinsic hard-magnetic properties but a lower amount of critical rare-earth elements.
This paper references
10.1103/PhysRevB.96.014112
Efficient and accurate machine-learning interpolation of atomic energies in compositions with many species
Nongnuch Artrith (2017)
10.1016/0022-5088(88)90424-9
Some novel ternary ThMn12-type compounds
D. B. de Mooij (1988)
10.1103/PhysRevLett.98.146401
Generalized neural-network representation of high-dimensional potential-energy surfaces.
Joerg Behler (2007)
10.1103/PHYSREVLETT.114.096405
Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces.
Zhenwei Li (2015)
10.1103/PhysRevLett.104.136403
Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons.
Albert P Bartók (2010)
10.1103/PhysRevLett.114.105503
Big data of materials science: critical role of the descriptor.
Luca M. Ghiringhelli (2015)
Scikit-learn: Machine Learning in Python
Fabian Pedregosa (2011)
10.1016/c2013-0-03017-4
Calculated electronic properties of metals
V. L. Moruzzi (1978)
10.1107/S0021889804031528
FINDSYM: program for identifying the space‐group symmetry of a crystal
Harold T. Stokes (2005)
10.1103/PhysRevB.45.3161
Ab initio calculation of local magnetic moments and the crystal field in scrR2Fe14B (scrR=Gd, Tb, Dy, Ho, and Er).
Hummler (1992)
10.1002/chin.199219354
Permanent Magnet Materials Based on Tetragonal Rare Earth Compounds of the Type RFe12-xMx
K Buschow (1992)
10.1107/S2052520615013979
Classification of ABO3 perovskite solids: a machine learning study.
Ghanshyam Pilania (2015)
10.1103/PHYSREVB.93.144111
Structure–Curie temperature relationships in BaTiO 3 -based ferroelectric perovskites: Anomalous behavior of ( Ba , Cd ) TiO 3 from DFT, statistical inference, and experiments
Prasanna V. Balachandran (2016)
10.1103/PhysRevB.92.014106
Accelerated materials property predictions and design using motif-based fingerprints
Tran Doan Huan (2015)
10.1103/physrevb.90.054102
Proposed definition of crystal substructure and substructural similarity
Lusann Yang (2014)
10.1002/qua.25307
Machine Learning for Atomic Forces in a Crystalline Solid: Transferability to Various Temperatures
Teppei Suzuki (2016)
10.1016/S0081-1947(08)60543-3
The Electronic Structure of Alloys
Hannelore Ehrenreich (1976)
10.1017/CBO9780511845000
Magnetism and Magnetic Materials
John Michael David Coey (2010)
10.1002/QUA.24836
Adaptive machine learning framework to accelerate ab initio molecular dynamics
Venkatesh Botu (2015)
Discovering the Building Blocks of Atomic Systems using Machine Learning 2017;URL: http://arxiv. org/abs/1703.06236
C. W. Rosenbrock (2017)
10.1103/PhysRevLett.108.058301
Fast and accurate modeling of molecular atomization energies with machine learning.
Matthias Rupp (2012)
10.1016/c2009-0-19715-5
Data Mining Practical Machine Learning Tools and Techniques
อนิรุธ สืบสิงห์ (2014)
10.1103/PhysRevLett.108.253002
Finding Density Functionals with Machine Learning
John C. Snyder (2012)
10.1103/PhysRevB.89.235411
Modeling electronic quantum transport with machine learning
Alejandro Lopez-Bezanilla (2014)
10.1088/1367-2630/15/12/125023
Ab initio screening methodology applied to the search for new permanent magnetic materials
Nedko Drebov (2013)
10.1016/j.asoc.2012.11.025
Genetic programming through bi-objective genetic algorithms with a study of a simulated moving bed process involving multiple objectives
Brijesh Kumar Giri (2013)
10.1109/ICCI-CC.2014.6921494
Prediction of magnetic remanence of NdFeB magnets by using novel machine learning intelligence approach — Support vector regression
WenDe Cheng (2014)
10.1007/BF02985802
The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition
Trevor J. Hastie (2009)
10.7566/JPSJ.83.043702
First-Principles Study of Magnetocrystalline Anisotropy and Magnetization in NdFe12, NdFe11Ti, and NdFe11TiN
Takashi Miyake (2014)
10.1038/srep24686
Theoretical screening of intermetallic ThMn12-type phases for new hard-magnetic compounds with low rare earth content
Wolfgang Körner (2016)
10.1016/J.COMMATSCI.2016.05.034
Image driven machine learning methods for microstructure recognition
Aritra Chowdhury (2016)
10.1088/1367-2630/15/9/095003
Machine Learning of Molecular Electronic Properties in Chemical Compound Space
Gr'egoire Montavon (2013)
Bonding and Structure of Molecules and Solids
D. G. Pettifor (1995)
10.1007/BF00331219
Ab initio electron theory for hard-magnetic rare-earth-transition-metal intermetallics
Manfred Faehnle (1993)
10.1038/NPJCOMPUMATS.2015.10
The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies
Scott Kirklin (2015)
10.1016/S0925-8388(98)00409-5
Hydrogen effects on the magnetic properties of RFe11Ti compounds
Olivier Isnard (1998)
10.1103/PhysRevB.92.094306
Learning scheme to predict atomic forces and accelerate materials simulations
Venkatesh Botu (2015)
10.1007/978-1-4757-3264-1
The Nature of Statistical Learning Theory
Vladimir Naumovich Vapnik (2000)
10.1103/RevModPhys.63.819
R 2 Fe 14 B materials: Intrinsic properties and technological aspects
Jan Francis Herbst (1991)
10.1002/QUA.24917
Crystal structure representations for machine learning models of formation energies
Felix A Faber (2015)
10.1103/PhysRevB.12.3060
Linear Methods in Band Theory
Ole Krogh Andersen (1975)
10.1063/1.4812323
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
Anubhav Jain (2013)
10.1063/1.1657673
Mean Magnetic Moments in bcc Fe–Co Alloys
D. I. Bardos (1969)
10.1126/sciadv.1600746
Prediction of interface structures and energies via virtual screening
Shin Kiyohara (2016)
10.1007/BF02745311
Concise encyclopedia of magnetic and superconducting materials, 1992, (ed.) Jan Evetts
Chitaldrug Rama Nagaraja Rao (1993)
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learn
M. Rupp (2015)
10.1002/QUA.24912
Fourier series of atomic radial distribution functions: A molecular fingerprint for machine learning models of quantum chemical properties
O. Anatole von Lilienfeld (2013)
10.1016/J.SCRIPTAMAT.2014.10.016
NdFe12Nx hard-magnetic compound with high magnetization and anisotropy field
Yusuke Hirayama (2015)
10.1016/J.JMMM.2017.05.011
Dependence of magnetisation and magnetocrystalline anisotropy on site distribution of alloying elements in RE-TM phases with ThMn12 structure
Tim Butcher (2017)
10.1023/B:STCO.0000035301.49549.88
A tutorial on support vector regression
Alexander J. Smola (2004)
10.1039/c1cp00051a
Support vector machine regression (LS-SVM)--an alternative to artificial neural networks (ANNs) for the analysis of quantum chemistry data?
Roman M. Balabin (2011)
10.1038/srep06367
On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets
Aaron Gilad Kusne (2014)
10.7567/JJAP.55.045502
Acceleration of stable interface structure searching using a kriging approach
Shin Kiyohara (2016)
10.1038/srep02810
Accelerating materials property predictions using machine learning
Ghanshyam Pilania (2013)
10.1063/1.3079326
How to quantify energy landscapes of solids.
Artem R. Oganov (2009)
R2Fe14B materials: Intrinsic properties and technological aspects
Herbst (1991)
Machine - learning approach for one - and two - body corrections to density functional theory : Applications to molecular and condensed wa
A. P. Bartók (2011)
10.1080/10426914.2016.1269923
A data-driven surrogate-assisted evolutionary algorithm applied to a many-objective blast furnace optimization problem
Tinkle Chugh (2017)
10.1007/S11837-013-0755-4
Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD)
James E. Saal (2013)
10.1103/PHYSREVB.88.054104
Machine-learning approach for one- and two-body corrections to density functional theory: Applications to molecular and condensed water
Albert P. Bartók (2013)
10.1063/1.4862156
Data mining for materials design: a computational study of single molecule magnet.
Hieu Chi Dam (2014)
Pattern recognition using generalized portrait method
Vladimir Vapnik (1963)
10.1103/PhysRevLett.117.135502
Machine Learning Energies of 2 Million Elpasolite (ABC_{2}D_{6}) Crystals.
Felix A Faber (2016)
SciPy: Open Source Scientific Tools for Python
Eric Daniel Jones (2001)
Model - ing electronic quantum transport with machine learn
A. Lopez-Bezanilla (2014)



This paper is referenced by
10.1016/J.CERAMINT.2019.06.076
Ultra-high temperature ceramics melting temperature prediction via machine learning
Nan Qu (2019)
10.1016/j.promfg.2019.12.051
The phase selection via machine learning in high entropy alloys
Nan Qu (2019)
Towards Digitizing Physical Entities in Materials Science
Mehwish Alam (2020)
10.1038/s41427-020-0214-y
Machine-learning-guided discovery of the gigantic magnetocaloric effect in HoB2 near the hydrogen liquefaction temperature
Pedro Baptista de Castro (2020)
10.1002/aisy.201900143
Artificial Intelligence to Power the Future of Materials Science and Engineering
Wuxin Sha (2020)
10.1109/USBEREIT48449.2020.9117689
Machine Learning Methods for Predicting the Lattice Characteristics of Materials
A. N. Filanovich (2020)
Numerical simulation, clustering and prediction of multi-component polymer precipitation
Pavan Inguva (2020)
10.1039/d0cs00098a
QSAR without borders.
Eugene N. Muratov (2020)
10.1016/J.MSEA.2018.11.106
Bayesian approach in predicting mechanical properties of materials: Application to dual phase steels
Jaimyun Jung (2019)
10.1007/978-3-658-25939-6_22
Active materials for electrical motors – Leverage for reducing costs and increasing performance
Moritz Kilper (2019)
10.1103/PhysRevMaterials.4.064414
Understanding Magnetic Properties of Actinide-Based Compounds from Machine Learning
Ayana Ghosh (2019)
10.1557/jmr.2020.38
Data-driven design of B20 alloys with targeted magnetic properties guided by machine learning and density functional theory
Prasanna V. Balachandran (2020)
10.1016/j.commatsci.2019.109350
Application of fuzzy learning in the research of binary alloys: Revisit and validation
Huiran Zhang (2020)
10.1007/s12613-019-1724-x
A novel approach to predict green density by high-velocity compaction based on the materials informatics method
Kai-qi Zhang (2019)
10.1103/PhysRevMaterials.3.104405
Predicting the Curie temperature of ferromagnets using machine learning
James Nelson (2019)
Semantic Scholar Logo Some data provided by SemanticScholar