Prediction of seebeck coefficient for compounds without restriction to fixed stoichiometry: A machine learning approach

The regression model‐based tool is developed for predicting the Seebeck coefficient of crystalline materials in the temperature range from 300 K to 1000 K. The tool accounts for the single crystal versus polycrystalline nature of the compound, the production method, and properties of the constituent elements in the chemical formula. We introduce new descriptive features of crystalline materials relevant for the prediction the Seebeck coefficient. To address off‐stoichiometry in materials, the predictive tool is trained on a mix of stoichiometric and nonstoichiometric materials. The tool is implemented into a web application (http://info.eecs.northwestern.edu/SeebeckCoefficientPredictor) to assist field scientists in the discovery of novel thermoelectric materials. © 2017 Wiley Periodicals, Inc.

[1]  K. Zhao,et al.  Defect engineering for a markedly increased electrical conductivity and power factor in doped ZnO ceramic , 2016 .

[2]  Senén Barro,et al.  Do we need hundreds of classifiers to solve real world classification problems? , 2014, J. Mach. Learn. Res..

[3]  Jeff Sharp,et al.  Overview of Solid-State Thermoelectric Refrigerators and Possible Applications to On-Chip Thermal Management , 2006, Proceedings of the IEEE.

[4]  Remo Guidieri.  Res , 1995, RES: Anthropology and Aesthetics.

[5]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Thermoelectric properties of the unfilled skutterudite FeSb3 from first principles and Seebeck local probes , 2015 .

[7]  Coulomb interaction and spin-orbit coupling calculations of thermoelectric properties of the quaternary chalcogenides Tl2PbXY4 (X = Zr, Hf and Y = S, Se) , 2015 .

[8]  K. Eguchi,et al.  Electrical transport properties and high-temperature thermoelectric performance of (Ca0.9M0.1)MnO3 (M = Y, La, Ce, Sm, In, Sn, Sb, Pb, Bi) , 1995 .

[9]  Enrico Clementi,et al.  Atomic Screening Constants from SCF Functions , 1963 .

[10]  Alok Choudhary,et al.  A predictive machine learning approach for microstructure optimization and materials design , 2015, Scientific Reports.

[11]  Masayuki Nogami,et al.  Multivariate Method-Assisted Ab Initio Study of Olivine-Type LiMXO4 (Main Group M2+–X5+ and M3+–X4+) Compositions as Potential Solid Electrolytes , 2012 .

[12]  D. Morelli,et al.  Improved thermoelectric properties in heavily doped FeGa3 , 2015 .

[13]  Jihui Yang,et al.  Evaluation of Half‐Heusler Compounds as Thermoelectric Materials Based on the Calculated Electrical Transport Properties , 2008 .

[14]  M. Yasukawa,et al.  Thermoelectric properties of the Bi2−xYxRu2O7 (x=0–2) pyrochlores , 2003 .

[15]  Marina Schmid,et al.  Structure And Bonding In Crystals , 2016 .

[16]  W. Xu,et al.  Enhancement of thermoelectric performance in Cd-doped Ca3Co4O9via spin entropy, defect chemistry and phonon scattering , 2014 .

[17]  Bryce Meredig,et al.  A recommendation engine for suggesting unexpected thermoelectric chemistries , 2015, 1502.07635.

[18]  L. Scolfaro,et al.  Electronic and thermoelectric properties of InN studied using ab initio density functional theory and Boltzmann transport calculations , 2014 .

[19]  John C. Slater,et al.  Quantum Theory of Molecules and Solids , 1951 .

[20]  L. Scolfaro,et al.  Ab initio study of thermoelectric properties of doped SnO2 superlattices , 2015 .

[21]  John C. Slater,et al.  Atomic Radii in Crystals , 1964 .

[22]  A. Choudhary,et al.  Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science , 2016 .

[23]  T. Matsui,et al.  Thermoelectric properties of polycrystalline La1−xSrxCoO3 , 2008 .

[24]  Bryce Meredig,et al.  Data mining our way to the next generation of thermoelectrics , 2016 .

[25]  C. Goupil,et al.  Thermoelectric properties of perovskites: Sign change of the Seebeck coefficient and high temperature properties , 2007 .

[26]  James W. Evans,et al.  Printed flexible thermoelectric generators for use on low levels of waste heat , 2015 .

[27]  Sylvain Arlot,et al.  A survey of cross-validation procedures for model selection , 2009, 0907.4728.

[28]  David W. Aha,et al.  Instance-Based Learning Algorithms , 1991, Machine Learning.

[29]  R. D. Shannon,et al.  Effective ionic radii in oxides and fluorides , 1969 .

[30]  Georg K. H. Madsen,et al.  Enhanced Thermoelectric Properties in Zinc Antimonides , 2011 .

[31]  Abhijit Date,et al.  Performance review of a novel combined thermoelectric power generation and water desalination system , 2015 .

[32]  Cormac Toher,et al.  Universal fragment descriptors for predicting properties of inorganic crystals , 2016, Nature Communications.

[33]  Yu-Shen Liu,et al.  Half-metallic properties, single-spin negative differential resistance, and large single-spin Seebeck effects induced by chemical doping in zigzag-edged graphene nanoribbons. , 2015, The Journal of chemical physics.

[34]  C. Randall,et al.  Thermoelectric power factor enhancement of textured ferroelectric Sr_xBa_1-x Nb_2O_6-δ ceramics , 2011 .

[35]  H. Maghraoui-Meherzi,et al.  First-principles study of electronic, thermoelectric and thermal properties of Sb2S3 , 2016 .

[36]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[37]  Taylor D. Sparks,et al.  Data-Driven Review of Thermoelectric Materials: Performance and Resource Considerations , 2013 .

[38]  S. Bux,et al.  Effects of Sc and Y substitution on the structure and thermoelectric properties of Yb14MnSb11 , 2016 .

[39]  P. Villars,et al.  Atomic-environment classification of the chemical elements , 1993 .

[40]  Atsuto Seko,et al.  Machine learning with systematic density-functional theory calculations: Application to melting temperatures of single- and binary-component solids , 2013, 1310.1546.

[41]  Hannu Hänninen,et al.  State-of-the-art of thermoelectric materials processing , 2009 .

[42]  M. Dresselhaus,et al.  Ab initio optimization of phonon drag effect for lower-temperature thermoelectric energy conversion , 2015, Proceedings of the National Academy of Sciences.

[43]  R. D. Shannon.  Revised effective ionic radii and systematic studies of interatomic distances in halides and chalcogenides , 1976 .

[44]  H. J. Mclaughlin,et al.  Learn , 2002 .

[45]  David J. Singh.  Doping-dependent thermopower of PbTe from Boltzmann transport calculations , 2010 .

[46]  Wei Hsin Chen,et al.  Geometric effect on cooling power and performance of an integrated thermoelectric generation-cooling system. , 2014 .

[47]  John G. Cleary,et al.  K*: An Instance-based Learner Using and Entropic Distance Measure , 1995, ICML.

[48]  Ankit Agrawal,et al.  Predictive analytics for crystalline materials: bulk modulus , 2016 .

[49]  S. Turenne,et al.  Production of thermoelectric materials by mechanical alloying - extrusion process , 2001, Proceedings ICT2001. 20 International Conference on Thermoelectrics (Cat. No.01TH8589).

[50]  Corey Oses,et al.  Materials Cartography: Representing and Mining Material Space Using Structural and Electronic Fingerprints , 2014, 1412.4096.

[51]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[52]  Alok Choudhary,et al.  Combinatorial screening for new materials in unconstrained composition space with machine learning , 2014 .

[53]  N. Hamada,et al.  First-principles investigation of structural, electronic, and thermoelectric properties of n- and p-type Mg_2Si , 2015 .

[54]  A. Shakouri.  Recent Developments in Semiconductor Thermoelectric Physics and Materials , 2011 .

[55]  C Wood,et al.  Materials for thermoelectric energy conversion , 1988 .

[56]  Taylor D. Sparks,et al.  Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties , 2016 .

[57]  S. Goumri‐Said,et al.  Optoelectronic structure and related transport properties of BiCuSeO-based oxychalcogenides: First principle calculations , 2016 .