Machine learning for predictive design and optimization of high-performance thermoelectric materials: a review

Abstract

Thermoelectric materials enabling direct interconversion between thermal and electrical energy hold transformative potential for sustainable energy technologies, particularly in solid-state power generation and precision refrigeration systems. The pursuit of high-performance thermoelectric materials with exceptional energy conversion efficiency has remained a persistent challenge in materials science, primarily constrained by the resource-intensive nature of traditional experimental approaches and computationally demanding first-principles simulations. The emergence of machine learning (ML) techniques has revolutionized this field by enabling rapid screening of material candidates and establishing quantitative structure-property relationships. This comprehensive review systematically examines cutting-edge methodologies in ML-driven thermoelectric materials research, with particular emphasis on three pivotal aspects: (1) predictive modeling of key performance parameters including electrical conductivity, Seebeck coefficient, and lattice thermal conductivity through advanced feature engineering and algorithm selection; (2) inverse design strategies for optimizing carrier concentration and phonon scattering mechanisms; (3) application-specific material optimization frameworks integrating multi-objective constraints. Furthermore, we critically analyze prevailing challenges in data quality, model interpretability, and cross-scale prediction accuracy, while proposing future research directions encompassing active learning paradigms, generative adversarial networks for virtual material synthesis, and hybrid physics-informed ML architectures.

Keywords

Thermoelectric / machine learning / electrical conductivity / thermal transport properties

References

[1] Cao Y.,Li X.,Yang J..Application of materials genome methods in thermoelectrics.Front. Mater2022;9:861817

[2] Wan X.,Wang Y..Materials discovery and properties prediction in thermal transport via materials informatics: a mini review.Nano Lett2019;19:3387-95

[3] Wang T.,Snoussi H..Machine learning approaches for thermoelectric materials research.Adv. Funct. Mater2020;30:1906041

[4] Zhang Z.,Shu M.,Dong Z..Artificial photosynthesis over metal halide perovskites: achievements, challenges, and prospects.J. Phys. Chem. Lett2021;12:5864-70

[5] Yang J.,Qiu W..On the tuning of electrical and thermal transport in thermoelectrics: an integrated theory–experiment perspective.NPJ Comput. Mater2016;2:15015

[6] Uchida K.,Harii K..Observation of the spin Seebeck effect.Nature2008;455:778-81

[7] Drebushchak V. A..The Peltier effect.J. Therm. Anal. Calorim2008;91:311-5

[8] Geballe T. H..Seebeck effect in germanium.Phys. Rev1954;94:1134

[9] Crane D. T..Optimization of cross flow heat exchangers for thermoelectric waste heat recovery.Energy Convers. Manag2004;45:1565-82

[10] Qin Y.,Wang D.,Zhao L. D..Solid-state cooling: thermoelectrics.Energy Environ. Sci2022;15:4527-41

[11] Chen W. Y.,Zou J..Thermoelectric coolers for on-chip thermal management: materials, design, and optimization.Mater. Sci. Eng. R. Rep2022;151:100700

[12] Yang J. Potential applications of thermoelectric waste heat recovery in the automotive industry. In ICT 2005. 24th International Conference on Thermoelectrics, 2005, Clemson, USA. Jun 19-23, 2005. IEEE; 2005. pp. 170–4.

[13] Xie H.,Gao P..Thermoelectric-powered sensors for Internet of Things.Micromachines2022;14:31

[14] Bonin R.,Chiaberge M..Design and characterization of small thermoelectric generators for environmental monitoring devices.Energy Convers. Manag2013;73:340-9

[15] Date A.,Dixon C..Progress of thermoelectric power generation systems: prospect for small to medium scale power generation.Renew. Sustain. Energy Rev2014;33:371-81

[16] He R.,Nielsch K..Thermoelectric devices: a review of devices, architectures, and contact optimization.Adv. Mater. Technol2018;3:1700256

[17] Zhang Q.,Wilkens L.,Nielsch K..Micro-thermoelectric devices.Nat. Electron2022;5:333-47

[18] Zhang Q. H.,Bai S. Q.,Uher C..Thermoelectric devices for power generation: recent progress and future challenges.Adv. Eng. Mater2016;18:194-213

[19] Sajid M.,Rahman A..An overview of cooling of thermoelectric devices.Renew. Sustain. Energy Rev2017;78:15-22

[20] Belsky A. A..Standalone power system with photovoltaic and thermoelectric installations for power supply of remote monitoring and control stations for oil pipelines.Renew. Energy Focus2023;47:100493

[21] Palaporn D.,Sun Y.,Kurosaki K..Thermoelectric materials for space explorations.Mater. Adv2024;5:5351-64

[22] Venkatasubramanian R.,Colpitts T..Thin-film thermoelectric devices with high room-temperature figures of merit.Nature2001;413:597-602

[23] Yang S.,Chen L..Recent developments in flexible thermoelectric devices.Small Sci2021;1:2100005

[24] Snyder G. J..Figure of merit ZT of a thermoelectric device defined from materials properties.Energy Environ. Sci2017;10:2280-3

[25] Kim H. S.,Tang Y.,Snyder G. J..Characterization of Lorenz number with Seebeck coefficient measurement.APL Mater2015;3:041506

[26] Martin J.,Uher C..High temperature Seebeck coefficient metrology.J. Appl. Phys2010;108:121101

[27] de Boor J..Data analysis for Seebeck coefficient measurements.Rev. Sci. Instrum2013;84:065102

[28] Snyder G. J.,Gurunathan R..Effective mass from Seebeck coefficient.Adv. Funct. Mater2022;32:2112772

[29] Iwanaga S.,LaLonde A..A high temperature apparatus for measurement of the Seebeck coefficient.Rev. Sci. Instrum2011;82:063905

[30] Mott N. F..The electrical conductivity of transition metals.Proc. R. Soc. Lond. A1936;153:699-717

[31] Radzuan N. A. M.,Sahari J..A review of electrical conductivity models for conductive polymer composite.Int. J. Hydrogen Energy2017;42:9262-73

[32] Ebbesen T. W.,Hiura H.,Ghaemi H. F..Electrical conductivity of individual carbon nanotubes.Nature1996;382:54-6

[33] Bardeen J..Electrical conductivity of metals.J. Appl. Phys1940;11:88-111

[34] Kerner E. H..The electrical conductivity of composite media.Proc. Phys. Soc, B1956;69:802

[35] Venkatasubramanian R..Lattice thermal conductivity reduction and phonon localizationlike behavior in superlattice structures.Phys. Rev. B2000;61:3091

[36] Zapata-Arteaga O.,Marina S.,Reparaz J. S..Reduction of the lattice thermal conductivity of polymer semiconductors by molecular doping.ACS Energy Lett2020;5:2972-8

[37] Murakami T.,Hori T.,Shiomi J..Importance of local force fields on lattice thermal conductivity reduction in PbTe_1-xSe_x alloys.EPL2013;102:46002

[38] Wan C.,Wang N.,Kusunoki M..Development of novel thermoelectric materials by reduction of lattice thermal conductivity.Sci. Technol. Adv. Mater2010;11:044306

[39] Kim T. Y.,Marzari N..The electronic thermal conductivity of graphene.Nano Lett2016;16:2439-43

[40] Graf M. J.,Sauls J. A..Electronic thermal conductivity and the Wiedemann-Franz law for unconventional superconductors.Phys. Rev. B1996;53:15147

[41] Lee S.,Yang F..Anomalously low electronic thermal conductivity in metallic vanadium dioxide.Science2017;355:371-4

[42] Ambegaokar V..Theory of the electronic thermal conductivity of superconductors with strong electron-phonon coupling.Phys. Rev1964;134:A805

[43] Burger N.,Ferriol M.,Toniazzo V..Review of thermal conductivity in composites: mechanisms, parameters and theory.Prog. Polym. Sci2016;61:1-28

[44] Wang D. Z.,Shi X. L..Se-alloying reducing lattice thermal conductivity of Ge_0.95Bi_0.05Te.J. Mater. Sci. Technol2022;106:249-56

[45] Zhang Q.,Wang X..Deep defect level engineering: a strategy of optimizing the carrier concentration for high thermoelectric performance.Energy Environ. Sci2018;11:933-40

[46] Pei Y.,Snyder G. J..Band engineering of thermoelectric materials.Adv. Mater2012;24:6125-35

[47] He J.,Girard S. N..On the origin of increased phonon scattering in nanostructured PbTe based thermoelectric materials.J. Am. Chem. Soc2010;132:8669-75

[48] Zheng Y.,Hu L..Defect engineering in thermoelectric materials: what have we learned?.Chem. Soc. Rev2021;50:9022-54

[49] Xie H.,Kanatzidis M. G..Lattice dynamics and thermoelectric properties of diamondoid materials.Interdiscip. Mater2024;3:5-28

[50] Qin D.,Lu Y.,Liu Z..Roles of interface engineering in performance optimization of skutterudite-based thermoelectric materials.Carbon Neutraliz2022;1:233-46

[51] Chen J.,Liu C..Enhanced efficiency of thermoelectric generator by optimizing mechanical and electrical structures.Energies2017;10:1329

[52] Lineykin S..Modeling and analysis of thermoelectric modules.IEEE Trans. Ind. Appl2007;43:505-12

[53] Yang Y.,Chen Z..Stretchable nanolayered thermoelectric energy harvester on complex and dynamic surfaces.Nano Lett2020;20:4445-53

[54] Tritt T. M..Thermoelectric phenomena, materials, and applications.Ann. Rev. Mater. Res2011;41:433-48

[55] Freysoldt C.,Hickel T..First-principles calculations for point defects in solids.Rev. Mod. Phys2014;86:253

[56] Li W.,Katcho N. A..ShengBTE: a solver of the Boltzmann transport equation for phonons.Comput. Phys. Commun2014;185:1747-58

[57] Jonson M..Mott's formula for the thermopower and the Wiedemann-Franz law.Phys. Rev. B1980;21:4223

[58] Binder K.,Kob W.,Varnik F..Molecular dynamics simulations.J. Phys. Condens. Matter2004;16:S429

[59] Kroese D. P.,Taimre T..Why the Monte Carlo method is so important today.Wiley Interdiscip. Rev. Comput. Stat2014;6:386-92

[60] Wei J.,Sun X. Y..Machine learning in materials science.InfoMat2019;1:338-58

[61] Ramprasad R.,Pilania G.,Kim C..Machine learning in materials informatics: recent applications and prospects.npj Comput. Mater2017;3:54

[62] Morgan D..Opportunities and challenges for machine learning in materials science.Ann. Rev. Mater. Res2020;50:71-103

[63] Challapalli A.,Li G..Inverse machine learning framework for optimizing lightweight metamaterials.Mater. Design2021;208:109937

[64] Sliwa B,Wietfeld C. LIMITS: lightweight machine learning for IoT systems with resource limitations. In ICC 2020-2020 IEEE International Conference on Communications (ICC), Dublin, Ireland. Jun 07-11, 2020. IEEE; 2020. p. 1–7.

[65] Mahmood A..Machine learning for high performance organic solar cells: current scenario and future prospects.Energy Environ. Sci2021;14:90-105

[66] Zhang L..Unsupervised machine learning for solar cell materials from the literature.J. Appl. Phys2022;131:064902

[67] Tao Q.,Li M..Machine learning for perovskite materials design and discovery.Npj Comput. Mater2021;7:23

[68] Zhang L.,Shao S..Machine learning for halide perovskite materials.Nano Energy2020;78:105380

[69] Al-Sabana O..Optoelectronic devices informatics: optimizing DSSC performance using random-forest machine learning algorithm.Optoelectron. Lett2022;18:148-51

[70] Miller S. A.,Anand S.,Snyder G. J..Empirical modeling of dopability in diamond-like semiconductors.npj Comput. Mater2018;4:71

[71] Saal J. E.,Aykol M.,Wolverton C..Materials design and discovery with high-throughput density functional theory: the open quantum materials database (OQMD).JOM2013;65:1501-9

[72] Kirklin S.,Meredig B..The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies.npj Comput. Mater2015;1:15010

[73] Jain A.,Hautier G..Commentary: The Materials Project: A materials genome approach to accelerating materials innovation.APL Mater2013;1:011002

[74] de Jong M.,Angsten T..The high-throughput highway to computational materials design.Sci. Data2013;2:150009

[75] de Jong M.,Geerlings H.,Persson K. A..A database to enable discovery and design of piezoelectric materials.Sci. Data2015;2:150053

[76] Sun J.,Huang K..Banzhaf random forests: cooperative game theory based random forests with consistency.Neural Netw2018;106:20-9

[77] Schmidt A. F..Linear regression and the normality assumption.J. Clin. Epidemiol2018;98:146-51

[78] Agatonovic-Kustrin S..Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research.J. Pharm. Biomed. Anal2000;22:717-27

[79] Wan Z.,Liu D..Machine learning prediction of the optimal carrier concentration and band gap of quaternary thermoelectric materials via element feature descriptors.Int. J. Quantum Chem2021;121:e26752

[80] Goldsmid H. J..The electrical conductivity and thermoelectric power of bismuth telluride.Proc. Phys. Soc1958;71:633

[81] Ricci F.,Aydemir U..An ab initio electronic transport database for inorganic materials.Sci. Data2017;4:170085

[82] Antunes L. M.,Grau-Crespo R..Predicting thermoelectric transport properties from composition with attention-based deep learning.Mach. Learn. Sci. Technol2023;4:015037

[83] Tiryaki H.,Ballikaya S..Determination of electrical and thermal conductivities of n-and p-type thermoelectric materials by prediction iteration machine learning method.Energy2024;292:130597

[84] Furmanchuk A.,Doak J. W.,Choudhary A..Prediction of seebeck coefficient for compounds without restriction to fixed stoichiometry: a machine learning approach.J. Comput. Chem2018;39:191-202

[85] Yuan H. M.,Hu R..Machine learning for accelerated prediction of the Seebeck coefficient at arbitrary carrier concentration.Mater. Today Phys2022;25:100706

[86] Gaultois M. W.,Borg C. K. H.,Bonificio W. D..Data-driven review of thermoelectric materials: performance and resource considerations.Chem. Mater2013;25:2911-20

[87] Gaultois M. W.,Mar A.,Mulholland G. J..Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties.APL Mater2016;4:053213

[88] Sheng Y.,Yang J.,Villars P..Active learning for the power factor prediction in diamond-like thermoelectric materials.npj Comput. Mater2020;6:171

[89] Graziosi P.,Neophytou N..Bipolar conduction asymmetries lead to ultra-high thermoelectric power factor.Appl. Phys. Lett2022;120:072102

[90] Qin G.,Yu L..Predicting lattice thermal conductivity from fundamental material properties using machine learning techniques.J. Mater. Chem, A2023;11:5801-10

[91] Ren Q.,Rao L.,Tang G..Machine-learning-assisted discovery of 212-Zintl-phase compounds with ultra-low lattice thermal conductivity.J. Mater. Chem. A2024;12:1157-65

[92] Wudil Y. S..Ensemble learning-based investigation of thermal conductivity of Bi₂Te_2.7Se_0.3-based thermoelectric clean energy materials.Results Eng2023;18:101203

[93] Tewari A.,Sahni N..Machine learning approaches to identify and design low thermal conductivity oxides for thermoelectric applications.Data Centric Eng2020;1:e8

[94] Al-Fahdi M.,Shen C.,Hu M..Rapid prediction of phonon density of states by crystal attention graph neural network and high-throughput screening of candidate substrates for wide bandgap electronic cooling.Mater. Today Phys2025;50:101632

[95] Dong L.,Bu X. H..Predicting thermal transport properties in phononic crystals via machine learning.Appl. Phys. Lett2024;124:162201

[96] Guo Z.,Han Z..Fast and accurate machine learning prediction of phonon scattering rates and lattice thermal conductivity.npj Comput. Mater2023;9:95

[97] Zhou Z.,Liu J..High-throughput prediction of the carrier relaxation time via data-driven descriptor.npj Comput. Mater2020;6:149

[98] Al-Fahdi M,Hu J,Hu M. Accelerating Discovery of extreme lattice thermal conductivity by crystal attention graph neural network (CATGNN) using chemical bonding intuitive descriptors. arXiv 2024; arXiv: 2410.16066. http://dx.doi.org/10.48550/arXiv.2410.16066. (accessed 3 Jun 2025)

[99] You HJ,Bansil A. Effects of four-phonon scattering and wave-like phonon tunneling effects on thermoelectric properties of Mg₂GeSe₄ using machine learning. arXiv 2024; arXiv: 2411.10605. https://doi.org/10.48550/arXiv.2411.10605. (accessed 3 Jun 2025)

[100] Yang Y.,Dai S..HH130: a standardized database of machine learning interatomic potentials, datasets, and its applications in the thermal transport of half-Heusler thermoelectrics.Digit. Discov2024;3:2201-10

[101] Li Y.,Zhang K.,Hu K..Large data set-driven machine learning models for accurate prediction of the thermoelectric figure of merit.ACS Appl. Mater. Interfaces2022;14:55517-27

[102] Xu Y.,Wang J..Prediction of thermoelectric-figure-of-merit based on autoencoder and light gradient boosting machine.J. Appl. Phys2024;135:074901

[103] Wang Y.,Zhang J.,Chen J..High-Performance stacking ensemble learning for thermoelectric figure-ofmerit prediction.Mater. Design2025;249:113552

[104] Madavali B.,Dewangan S. K.,Hong S. J..Predicting the thermoelectric figure of merit in p-type BiSbTe-based alloys using artificial neural network modeling.Mater. Today Commun2024;40:109396

[105] Jia X.,Bao X..Unsupervised machine learning for discovery of promising half-Heusler thermoelectric materials.npj Comput. Mater2022;8:34

[106] Vaitesswar U. S.,Huang T..Machine learning based feature engineering for thermoelectric materials by design.Digit. Discov2024;3:210-20

[107] Xu Y.,Qi X..Machine learning in thermoelectric materials identification: feature selection and analysis.Comput. Mater. Sci2021;197:110625

[108] Fan T..Combining machine learning models with first-principles high-throughput calculation to accelerate the search of promising thermoelectric materials.J. Mater. Chem. C2025;13:1439-48

[109] Chen C..A universal graph deep learning interatomic potential for the periodic table.Nat. Comput. Sci2022;2:718-28

[110] Long Y.,Ma X..Inverse design of high-performance thermoelectric materials via a generative model combined with experimental verification.ACS Appl. Mater. Interfaces2025;17:19856-67

[111] Zhong C.,Wang Y..High-performance diffusion model for inverse design of high T_c superconductors with effective doping and accurate stoichiometry.InfoMat2024;6:e12519

[112] Zhong C.,Lu X..Deep generative model for inverse design of high-temperature superconductor compositions with predicted T_c > 77 K.ACS Appl. Mater. Interfaces2023;15:30029-38