DOI: 10.1063/1.4952607. Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties

Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties

10.1063/1.4952607

Crossref journal-article

AIP Publishing

APL Materials (317)

Abstract

The experimental search for new thermoelectric materials remains largely confined to a limited set of successful chemical and structural families, such as chalcogenides, skutterudites, and Zintl phases. In principle, computational tools such as density functional theory (DFT) offer the possibility of rationally guiding experimental synthesis efforts toward very different chemistries. However, in practice, predicting thermoelectric properties from first principles remains a challenging endeavor [J. Carrete et al., Phys. Rev. X 4, 011019 (2014)], and experimental researchers generally do not directly use computation to drive their own synthesis efforts. To bridge this practical gap between experimental needs and computational tools, we report an open machine learning-based recommendation engine (http://thermoelectrics.citrination.com) for materials researchers that suggests promising new thermoelectric compositions based on pre-screening about 25 000 known materials and also evaluates the feasibility of user-designed compounds. We show this engine can identify interesting chemistries very different from known thermoelectrics. Specifically, we describe the experimental characterization of one example set of compounds derived from our engine, RE12Co5Bi (RE = Gd, Er), which exhibits surprising thermoelectric performance given its unprecedentedly high loading with metallic d and f block elements and warrants further investigation as a new thermoelectric material platform. We show that our engine predicts this family of materials to have low thermal and high electrical conductivities, but modest Seebeck coefficient, all of which are confirmed experimentally. We note that the engine also predicts materials that may simultaneously optimize all three properties entering into zT; we selected RE12Co5Bi for this study due to its interesting chemical composition and known facile synthesis.

Bibliography

Gaultois, M. W., Oliynyk, A. O., Mar, A., Sparks, T. D., Mulholland, G. J., & Meredig, B. (2016). Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties. APL Materials, 4(5).

Authors 6

Michael W. Gaultois (first)
Anton O. Oliynyk (additional)
Arthur Mar (additional)
Taylor D. Sparks (additional)
Gregory J. Mulholland (additional)
Bryce Meredig (additional)

References 49 Referenced 175

10.1557/mrs2006.45 / MRS Bull. / Recent developments in bulk thermoelectric materials (2006)
10.1103/PhysRevX.4.011019 / Phys. Rev. X / Finding unprecedentedly low-thermal-conductivity half-Heusler semiconductors via high-throughput materials modeling (2014)
10.1063/1.4812323 / APL Mater. / Commentary: The Materials Project: A materials genome approach to accelerating materials innovation (2013)
10.1103/PhysRevB.56.R12685 / Phys. Rev. B / Large thermoelectric power in NaCo2O4 single crystals (1997)
10.1021/ja800073m / J. Am. Chem. Soc. / Iron-based layered superconductor La[O1 − xFx]FeAs (x = 0.05–0.12) with Tc = 26 K (2008)
10.1021/cm400893e / Chem. Mater. / Data-driven review of thermoelectric materials: Performance and resource considerations (2013)
10.1103/PhysRevB.89.094104 / Phys. Rev. B / Combinatorial screening for new materials in unconstrained composition space with machine learning (2014)
10.1021/cm403727z / Chem. Mater. / Dissolving the periodic table in cubic zirconia: Data mining to discover chemical trends (2014)
10.1038/natrevmats.2015.4 / Nat. Rev. Mater. / Computational predictions of energy materials using density functional theory (2016)
10.1007/s10853-012-6424-0 / J. Mater. Sci. / From the computer to the laboratory: Materials discovery and design using first-principles calculations (2012)
10.1002/adfm.201401201 / Adv. Funct. Mater. / Nanograined half-Heusler semiconductors as advanced thermoelectrics: An ab initio high-throughput statistical study (2014)
10.1103/PhysRevB.92.085205 / Phys. Rev. B / High-throughput exploration of alloying as design strategy for thermoelectrics (2015)
10.1021/acs.chemmater.5b01179 / Chem. Mater. / Computational exploration of the binary A1B1 chemical space for thermoelectric performance (2015)
10.1039/c5tc01440a / J. Mater. Chem. C / Computational and experimental investigation of TmAgTe2 and XYZ2 compounds, a new group of thermoelectric materials identified by first-principles high-throughput screening (2015)
10.1039/c5tc04339e / J. Mater. Chem. C / Understanding thermoelectric properties from high-throughput calculations: Trends, insights, and comparisons with experiment (2016)
10.1016/j.cpc.2006.03.007 / Comput. Phys. Commun. / Boltztrap. a code for calculating band-structure dependent quantities (2006)
10.1039/c5ra07678a / RSC Adv. / Correlation between the electronic structure, effective mass and thermoelectric properties of rare earth tellurides Ba2MY Te5 (M = Ga, In) (2015)
10.1146/annurev-matsci-070214-021132 / Annu. Rev. Mater. Res. / Materials informatics: The materials ‘gene’ and big data (2015)
10.1038/srep13285 / Sci. Rep. / Materials prediction via classification learning (2015)
10.1007/s11837-006-0226-2 / JOM / Linking length scales via materials informatics (2006)
10.1016/S1369-7021(05)71123-8 / Mater. Today / Materials informatics (2005)
10.1016/j.commatsci.2012.10.028 / Comput. Mater. Sci. / Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis (2013)
10.1038/nmat3568 / Nat. Mater. / The high-throughput highway to computational materials design (2013)
10.1103/PhysRevLett.114.105503 / Phys. Rev. Lett. / Big data of materials science: Critical role of the descriptor (2015)
10.1021/acs.jpclett.5b00831 / J. Phys. Chem. Lett. / Machine learning predictions of molecular properties: Accurate many-body potentials and non-locality in chemical space (2015)
10.1023/A:1010933404324 / Mach. Learn. / Random forests (2001)
{'key': '2024051414255160900_c27', 'article-title': 'Machine learning for the materials scientist, part 2: Feature engineering & model building (2015)'} / Machine learning for the materials scientist, part 2: Feature engineering & model building (2015)
See supplementary material at http://dx.doi.org/10.1063/1.4952607E-AMPADS-4-015693 for X-ray diffraction patterns and backscatter electron micrographs collected from the prepared materials.
10.1016/j.commatsci.2015.11.006 / Comput. Mater. Sci. / Te design lab: A virtual laboratory for thermoelectric material design (2016)
10.1016/0022-4596(86)90105-2 / J. Solid State Chem. / β-NbPO5 and β-TaPO5: Bronzoïds, second members of the monophosphate tungsten bronze series (PO2)4(WO3)2m (1986)
10.1016/0025-5408(88)90073-6 / Mater. Res. Bull. / TaVO5, a novel derivative of the series of monophosphate tungsten bronzes (PO2)4(WO3)2m (1988)
10.1142/S0217979293003553 / Int. J. Mod. Phys. B / Phosphate tungsten bronzes: A new family of quasi-low-dimensional metallic oxides (1993)
10.1021/ic200003n / Inorg. Chem. / Phase transformation and negative thermal expansion in TaVO5 (2011)
10.1021/cm402593f / Chem. Mater. / Enhanced thermoelectric properties of variants of Tl9SbTe6 and Tl9BiTe6 (2013)
10.1088/1468-6996/14/5/055003 / Sci. Technol. Adv. Mater. / Alkaline earth lead and tin compounds Ae2Pb, Ae2Sn, Ae = Ca, Sr, Ba, as thermoelectric materials (2013)
10.1143/apex.2.091102 / Appl. Phys. Express / Huge thermoelectric power factor: FeSb2 versus FeAs2 and RuSb2 (2009)
10.1006/jssc.1996.7234 / J. Solid State Chem. / Cation sublattice and coordination polyhedra in ABO4 type of structures (1997)
10.1006/jssc.2001.9266 / J. Solid State Chem. / SbSbxM1−xO4 (M = NbV or TaV): Solid solution behavior and second-harmonic generating properties (2001)
10.1103/PhysRevB.84.125114 / Phys. Rev. B / Magnetic order, transport and infrared optical properties in the ACrO3 system (A = Ca, Sr, and Pb) (2011)
10.2138/am-1995-1-203 / Am. Mineral. / Crystal chemistry of the monazite and xenotime structures (1995)
10.1111/j.1551-2916.2006.01410.x / J. Am. Ceram. Soc. / Oxide materials with low thermal conductivity (2007)
10.1021/ic048195p / Inorg. Chem. / Structure and physical properties of ternary rare-earth cobalt bismuth intermetallics RE12Co5Bi (RE = Y, Gd, Tb, Dy, Ho, Er, Tm) (2005)
10.1063/1.361828 / J. Appl. Phys. / The effect of rare-earth filling on the lattice thermal conductivity of skutterudites (1996)
10.1016/j.progsolidstchem.2011.02.001 / Prog. Solid State Chem. / Simple rules for the understanding of Heusler compounds (2011)
10.1063/1.4765358 / Appl. Phys. Lett. / Enhanced thermoelectric properties of bulk TiNiSn via formation of a TiNi2Sn second phase (2012)
10.1038/nature06381 / Nature / Enhanced thermoelectric performance of rough silicon nanowires (2008)
10.1016/B978-044482794-4/50000-0 / Thermophys. Prop. Mater. (1999)
10.1103/PhysRevB.40.9541 / Phys. Rev. B / Thermal conductivity and electrical resistivity of gadolinium as functions of pressure and temperature (1989)
{'article-title': 'Thermal conductivity: Theory, properties, and applications', 'volume-title': 'Physics of Solids and Liquids', 'year': '2004', 'key': '2024051414255160900_c49'} / Physics of Solids and Liquids / Thermal conductivity: Theory, properties, and applications (2004)

Dates

Type	When
Created	9 years, 3 months ago (May 27, 2016, 3:01 p.m.)
Deposited	3 months ago (May 29, 2025, 3:29 p.m.)
Indexed	1 week, 3 days ago (Aug. 21, 2025, 2:22 p.m.)
Issued	9 years, 4 months ago (May 1, 2016)
Published	9 years, 4 months ago (May 1, 2016)
Published Online	9 years, 3 months ago (May 27, 2016)
Published Print	9 years, 4 months ago (May 1, 2016)

Funders 3

Division of Materials Research 10.13039/100000078
Region: Americas
gov (National government)
Labels4
1. NSF Division of Materials Research
2. Materials Research
3. DMR
4. MPS/DMR
Awards1
1. 1121053
U.S. Department of State 10.13039/100000194
Region: Americas
gov (National government)
Labels6
1. United States Department of State
2. Department of State
3. State Department
4. U.S. State Department
5. DOS
6. USDOS
Natural Sciences and Engineering Research Council of Canada 10.13039/501100000038
Region: Americas
gov (National government)
Labels3
1. Conseil de Recherches en Sciences Naturelles et en Génie du Canada
2. NSERC
3. CRSNG

BibTeX

@article{Gaultois_2016, title={Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties}, volume={4}, ISSN={2166-532X}, url={http://dx.doi.org/10.1063/1.4952607}, DOI={10.1063/1.4952607}, number={5}, journal={APL Materials}, publisher={AIP Publishing}, author={Gaultois, Michael W. and Oliynyk, Anton O. and Mar, Arthur and Sparks, Taylor D. and Mulholland, Gregory J. and Meredig, Bryce}, year={2016}, month=may }

JSON

{
  "indexed": {
    "date-parts": [
      [
        2025,
        8,
        21
      ]
    ],
    "date-time": "2025-08-21T18:22:15Z",
    "timestamp": 1755800535981,
    "version": "3.41.2"
  },
  "reference-count": 49,
  "publisher": "AIP Publishing",
  "issue": "5",
  "license": [
    {
      "start": {
        "date-parts": [
          [
            2016,
            5,
            27
          ]
        ],
        "date-time": "2016-05-27T00:00:00Z",
        "timestamp": 1464307200000
      },
      "content-version": "vor",
      "delay-in-days": 26,
      "URL": "https://creativecommons.org/licenses/by/4.0/"
    },
    {
      "start": {
        "date-parts": [
          [
            2016,
            5,
            27
          ]
        ],
        "date-time": "2016-05-27T00:00:00Z",
        "timestamp": 1464307200000
      },
      "content-version": "tdm",
      "delay-in-days": 26,
      "URL": "https://creativecommons.org/licenses/by/4.0/"
    }
  ],
  "funder": [
    {
      "DOI": "10.13039/100000078",
      "name": "Division of Materials Research",
      "doi-asserted-by": "publisher",
      "award": [
        "1121053"
      ],
      "id": [
        {
          "id": "10.13039/100000078",
          "id-type": "DOI",
          "asserted-by": "publisher"
        }
      ]
    },
    {
      "DOI": "10.13039/100000194",
      "name": "U.S. Department of State",
      "doi-asserted-by": "publisher",
      "id": [
        {
          "id": "10.13039/100000194",
          "id-type": "DOI",
          "asserted-by": "publisher"
        }
      ]
    },
    {
      "DOI": "10.13039/501100000038",
      "name": "Natural Sciences and Engineering Research Council of Canada",
      "doi-asserted-by": "publisher",
      "id": [
        {
          "id": "10.13039/501100000038",
          "id-type": "DOI",
          "asserted-by": "publisher"
        }
      ]
    }
  ],
  "content-domain": {
    "domain": [
      "pubs.aip.org"
    ],
    "crossmark-restriction": true
  },
  "published-print": {
    "date-parts": [
      [
        2016,
        5,
        1
      ]
    ]
  },
  "abstract": "<jats:p>The experimental search for new thermoelectric materials remains largely confined to a limited set of successful chemical and structural families, such as chalcogenides, skutterudites, and Zintl phases. In principle, computational tools such as density functional theory (DFT) offer the possibility of rationally guiding experimental synthesis efforts toward very different chemistries. However, in practice, predicting thermoelectric properties from first principles remains a challenging endeavor [J. Carrete et al., Phys. Rev. X 4, 011019 (2014)], and experimental researchers generally do not directly use computation to drive their own synthesis efforts. To bridge this practical gap between experimental needs and computational tools, we report an open machine learning-based recommendation engine (http://thermoelectrics.citrination.com) for materials researchers that suggests promising new thermoelectric compositions based on pre-screening about 25\u2009000 known materials and also evaluates the feasibility of user-designed compounds. We show this engine can identify interesting chemistries very different from known thermoelectrics. Specifically, we describe the experimental characterization of one example set of compounds derived from our engine, RE12Co5Bi (RE = Gd, Er), which exhibits surprising thermoelectric performance given its unprecedentedly high loading with metallic d and f block elements and warrants further investigation as a new thermoelectric material platform. We show that our engine predicts this family of materials to have low thermal and high electrical conductivities, but modest Seebeck coefficient, all of which are confirmed experimentally. We note that the engine also predicts materials that may simultaneously optimize all three properties entering into zT; we selected RE12Co5Bi for this study due to its interesting chemical composition and known facile synthesis.</jats:p>",
  "DOI": "10.1063/1.4952607",
  "type": "journal-article",
  "created": {
    "date-parts": [
      [
        2016,
        5,
        27
      ]
    ],
    "date-time": "2016-05-27T19:01:00Z",
    "timestamp": 1464375660000
  },
  "update-policy": "https://doi.org/10.1063/aip-crossmark-policy-page",
  "source": "Crossref",
  "is-referenced-by-count": 175,
  "title": "Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties",
  "prefix": "10.1063",
  "volume": "4",
  "author": [
    {
      "ORCID": "https://orcid.org/0000-0003-2172-2507",
      "authenticated-orcid": false,
      "given": "Michael W.",
      "family": "Gaultois",
      "sequence": "first",
      "affiliation": [
        {
          "name": "University of Cambridge 1 Department of Chemistry, , Cambridge CB2 1EW, United Kingdom"
        }
      ]
    },
    {
      "given": "Anton O.",
      "family": "Oliynyk",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "University of Alberta 2 Department of Chemistry, , Edmonton, Alberta T6G 2G2, Canada"
        }
      ]
    },
    {
      "given": "Arthur",
      "family": "Mar",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "University of Alberta 2 Department of Chemistry, , Edmonton, Alberta T6G 2G2, Canada"
        }
      ]
    },
    {
      "given": "Taylor D.",
      "family": "Sparks",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "University of Utah 3 Department of Materials Science and Engineering, , Salt Lake City, Utah 84112, USA"
        }
      ]
    },
    {
      "ORCID": "https://orcid.org/0000-0002-2277-9647",
      "authenticated-orcid": false,
      "given": "Gregory J.",
      "family": "Mulholland",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Citrine Informatics 4 , Redwood City, California 94063, USA"
        }
      ]
    },
    {
      "given": "Bryce",
      "family": "Meredig",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Citrine Informatics 4 , Redwood City, California 94063, USA"
        }
      ]
    }
  ],
  "member": "317",
  "published-online": {
    "date-parts": [
      [
        2016,
        5,
        27
      ]
    ]
  },
  "reference": [
    {
      "key": "2024051414255160900_c1",
      "doi-asserted-by": "publisher",
      "first-page": "199",
      "DOI": "10.1557/mrs2006.45",
      "article-title": "Recent developments in bulk thermoelectric materials",
      "volume": "31",
      "year": "2006",
      "journal-title": "MRS Bull."
    },
    {
      "key": "2024051414255160900_c2",
      "doi-asserted-by": "publisher",
      "first-page": "011019",
      "DOI": "10.1103/PhysRevX.4.011019",
      "article-title": "Finding unprecedentedly low-thermal-conductivity half-Heusler semiconductors via high-throughput materials modeling",
      "volume": "4",
      "year": "2014",
      "journal-title": "Phys. Rev. X"
    },
    {
      "key": "2024051414255160900_c3",
      "doi-asserted-by": "publisher",
      "first-page": "011002",
      "DOI": "10.1063/1.4812323",
      "article-title": "Commentary: The Materials Project: A materials genome approach to accelerating materials innovation",
      "volume": "1",
      "year": "2013",
      "journal-title": "APL Mater."
    },
    {
      "key": "2024051414255160900_c4",
      "doi-asserted-by": "publisher",
      "first-page": "R12685",
      "DOI": "10.1103/PhysRevB.56.R12685",
      "article-title": "Large thermoelectric power in NaCo2O4 single crystals",
      "volume": "56",
      "year": "1997",
      "journal-title": "Phys. Rev. B"
    },
    {
      "key": "2024051414255160900_c5",
      "doi-asserted-by": "publisher",
      "first-page": "3296",
      "DOI": "10.1021/ja800073m",
      "article-title": "Iron-based layered superconductor La[O1 \u2212 xFx]FeAs (x = 0.05\u20130.12) with Tc = 26\u2009K",
      "volume": "130",
      "year": "2008",
      "journal-title": "J. Am. Chem. Soc."
    },
    {
      "key": "2024051414255160900_c6",
      "doi-asserted-by": "publisher",
      "first-page": "2911",
      "DOI": "10.1021/cm400893e",
      "article-title": "Data-driven review of thermoelectric materials: Performance and resource considerations",
      "volume": "25",
      "year": "2013",
      "journal-title": "Chem. Mater."
    },
    {
      "key": "2024051414255160900_c7",
      "doi-asserted-by": "publisher",
      "first-page": "094104",
      "DOI": "10.1103/PhysRevB.89.094104",
      "article-title": "Combinatorial screening for new materials in unconstrained composition space with machine learning",
      "volume": "89",
      "year": "2014",
      "journal-title": "Phys. Rev. B"
    },
    {
      "key": "2024051414255160900_c8",
      "doi-asserted-by": "publisher",
      "first-page": "1985",
      "DOI": "10.1021/cm403727z",
      "article-title": "Dissolving the periodic table in cubic zirconia: Data mining to discover chemical trends",
      "volume": "26",
      "year": "2014",
      "journal-title": "Chem. Mater."
    },
    {
      "key": "2024051414255160900_c9",
      "doi-asserted-by": "publisher",
      "first-page": "15004",
      "DOI": "10.1038/natrevmats.2015.4",
      "article-title": "Computational predictions of energy materials using density functional theory",
      "volume": "1",
      "year": "2016",
      "journal-title": "Nat. Rev. Mater."
    },
    {
      "key": "2024051414255160900_c10",
      "doi-asserted-by": "publisher",
      "first-page": "7317",
      "DOI": "10.1007/s10853-012-6424-0",
      "article-title": "From the computer to the laboratory: Materials discovery and design using first-principles calculations",
      "volume": "47",
      "year": "2012",
      "journal-title": "J. Mater. Sci."
    },
    {
      "key": "2024051414255160900_c11",
      "doi-asserted-by": "publisher",
      "first-page": "7427",
      "DOI": "10.1002/adfm.201401201",
      "article-title": "Nanograined half-Heusler semiconductors as advanced thermoelectrics: An ab initio high-throughput statistical study",
      "volume": "24",
      "year": "2014",
      "journal-title": "Adv. Funct. Mater."
    },
    {
      "key": "2024051414255160900_c12",
      "doi-asserted-by": "publisher",
      "DOI": "10.1103/PhysRevB.92.085205",
      "article-title": "High-throughput exploration of alloying as design strategy for thermoelectrics",
      "volume": "92",
      "year": "2015",
      "journal-title": "Phys. Rev. B"
    },
    {
      "key": "2024051414255160900_c13",
      "doi-asserted-by": "publisher",
      "first-page": "6213",
      "DOI": "10.1021/acs.chemmater.5b01179",
      "article-title": "Computational exploration of the binary A1B1 chemical space for thermoelectric performance",
      "volume": "27",
      "year": "2015",
      "journal-title": "Chem. Mater."
    },
    {
      "key": "2024051414255160900_c14",
      "doi-asserted-by": "publisher",
      "first-page": "10554",
      "DOI": "10.1039/c5tc01440a",
      "article-title": "Computational and experimental investigation of TmAgTe2 and XYZ2 compounds, a new group of thermoelectric materials identified by first-principles high-throughput screening",
      "volume": "3",
      "year": "2015",
      "journal-title": "J. Mater. Chem. C"
    },
    {
      "key": "2024051414255160900_c15",
      "doi-asserted-by": "publisher",
      "first-page": "4414",
      "DOI": "10.1039/c5tc04339e",
      "article-title": "Understanding thermoelectric properties from high-throughput calculations: Trends, insights, and comparisons with experiment",
      "volume": "4",
      "year": "2016",
      "journal-title": "J. Mater. Chem. C"
    },
    {
      "key": "2024051414255160900_c16",
      "doi-asserted-by": "publisher",
      "first-page": "67",
      "DOI": "10.1016/j.cpc.2006.03.007",
      "article-title": "Boltztrap. a code for calculating band-structure dependent quantities",
      "volume": "175",
      "year": "2006",
      "journal-title": "Comput. Phys. Commun."
    },
    {
      "key": "2024051414255160900_c17",
      "doi-asserted-by": "publisher",
      "first-page": "51461",
      "DOI": "10.1039/c5ra07678a",
      "article-title": "Correlation between the electronic structure, effective mass and thermoelectric properties of rare earth tellurides Ba2MY Te5 (M = Ga, In)",
      "volume": "5",
      "year": "2015",
      "journal-title": "RSC Adv."
    },
    {
      "key": "2024051414255160900_c18",
      "doi-asserted-by": "publisher",
      "first-page": "153",
      "DOI": "10.1146/annurev-matsci-070214-021132",
      "article-title": "Materials informatics: The materials \u2018gene\u2019 and big data",
      "volume": "45",
      "year": "2015",
      "journal-title": "Annu. Rev. Mater. Res."
    },
    {
      "key": "2024051414255160900_c19",
      "doi-asserted-by": "publisher",
      "first-page": "13285",
      "DOI": "10.1038/srep13285",
      "article-title": "Materials prediction via classification learning",
      "volume": "5",
      "year": "2015",
      "journal-title": "Sci. Rep."
    },
    {
      "key": "2024051414255160900_c20",
      "doi-asserted-by": "publisher",
      "first-page": "42",
      "DOI": "10.1007/s11837-006-0226-2",
      "article-title": "Linking length scales via materials informatics",
      "volume": "58",
      "year": "2006",
      "journal-title": "JOM"
    },
    {
      "key": "2024051414255160900_c21",
      "doi-asserted-by": "publisher",
      "first-page": "38",
      "DOI": "10.1016/S1369-7021(05)71123-8",
      "article-title": "Materials informatics",
      "volume": "8",
      "year": "2005",
      "journal-title": "Mater. Today"
    },
    {
      "key": "2024051414255160900_c22",
      "doi-asserted-by": "publisher",
      "first-page": "314",
      "DOI": "10.1016/j.commatsci.2012.10.028",
      "article-title": "Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis",
      "volume": "68",
      "year": "2013",
      "journal-title": "Comput. Mater. Sci."
    },
    {
      "key": "2024051414255160900_c23",
      "doi-asserted-by": "publisher",
      "first-page": "191",
      "DOI": "10.1038/nmat3568",
      "article-title": "The high-throughput highway to computational materials design",
      "volume": "12",
      "year": "2013",
      "journal-title": "Nat. Mater."
    },
    {
      "key": "2024051414255160900_c24",
      "doi-asserted-by": "publisher",
      "first-page": "105503",
      "DOI": "10.1103/PhysRevLett.114.105503",
      "article-title": "Big data of materials science: Critical role of the descriptor",
      "volume": "114",
      "year": "2015",
      "journal-title": "Phys. Rev. Lett."
    },
    {
      "key": "2024051414255160900_c25",
      "doi-asserted-by": "publisher",
      "first-page": "2326",
      "DOI": "10.1021/acs.jpclett.5b00831",
      "article-title": "Machine learning predictions of molecular properties: Accurate many-body potentials and non-locality in chemical space",
      "volume": "6",
      "year": "2015",
      "journal-title": "J. Phys. Chem. Lett."
    },
    {
      "key": "2024051414255160900_c26",
      "doi-asserted-by": "publisher",
      "first-page": "5",
      "DOI": "10.1023/A:1010933404324",
      "article-title": "Random forests",
      "volume": "45",
      "year": "2001",
      "journal-title": "Mach. Learn."
    },
    {
      "key": "2024051414255160900_c27",
      "article-title": "Machine learning for the materials scientist, part 2: Feature engineering & model building (2015)"
    },
    {
      "key": "2024051414255160900_c28",
      "unstructured": "See supplementary material at http://dx.doi.org/10.1063/1.4952607E-AMPADS-4-015693 for X-ray diffraction patterns and backscatter electron micrographs collected from the prepared materials."
    },
    {
      "key": "2024051414255160900_c29",
      "doi-asserted-by": "publisher",
      "first-page": "368",
      "DOI": "10.1016/j.commatsci.2015.11.006",
      "article-title": "Te design lab: A virtual laboratory for thermoelectric material design",
      "volume": "112",
      "year": "2016",
      "journal-title": "Comput. Mater. Sci."
    },
    {
      "key": "2024051414255160900_c30",
      "doi-asserted-by": "publisher",
      "first-page": "331",
      "DOI": "10.1016/0022-4596(86)90105-2",
      "article-title": "\u03b2-NbPO5 and \u03b2-TaPO5: Bronzo\u00efds, second members of the monophosphate tungsten bronze series (PO2)4(WO3)2m",
      "volume": "65",
      "year": "1986",
      "journal-title": "J. Solid State Chem."
    },
    {
      "key": "2024051414255160900_c31",
      "doi-asserted-by": "publisher",
      "first-page": "805",
      "DOI": "10.1016/0025-5408(88)90073-6",
      "article-title": "TaVO5, a novel derivative of the series of monophosphate tungsten bronzes (PO2)4(WO3)2m",
      "volume": "23",
      "year": "1988",
      "journal-title": "Mater. Res. Bull."
    },
    {
      "key": "2024051414255160900_c32",
      "doi-asserted-by": "publisher",
      "first-page": "3937",
      "DOI": "10.1142/S0217979293003553",
      "article-title": "Phosphate tungsten bronzes: A new family of quasi-low-dimensional metallic oxides",
      "volume": "07",
      "year": "1993",
      "journal-title": "Int. J. Mod. Phys. B"
    },
    {
      "key": "2024051414255160900_c33",
      "doi-asserted-by": "publisher",
      "first-page": "2685",
      "DOI": "10.1021/ic200003n",
      "article-title": "Phase transformation and negative thermal expansion in TaVO5",
      "volume": "50",
      "year": "2011",
      "journal-title": "Inorg. Chem."
    },
    {
      "key": "2024051414255160900_c34",
      "doi-asserted-by": "publisher",
      "first-page": "4097",
      "DOI": "10.1021/cm402593f",
      "article-title": "Enhanced thermoelectric properties of variants of Tl9SbTe6 and Tl9BiTe6",
      "volume": "25",
      "year": "2013",
      "journal-title": "Chem. Mater."
    },
    {
      "key": "2024051414255160900_c35",
      "doi-asserted-by": "publisher",
      "first-page": "055003",
      "DOI": "10.1088/1468-6996/14/5/055003",
      "article-title": "Alkaline earth lead and tin compounds Ae2Pb, Ae2Sn, Ae = Ca, Sr, Ba, as thermoelectric materials",
      "volume": "14",
      "year": "2013",
      "journal-title": "Sci. Technol. Adv. Mater."
    },
    {
      "key": "2024051414255160900_c36",
      "doi-asserted-by": "publisher",
      "first-page": "091102",
      "DOI": "10.1143/apex.2.091102",
      "article-title": "Huge thermoelectric power factor: FeSb2 versus FeAs2 and RuSb2",
      "volume": "2",
      "year": "2009",
      "journal-title": "Appl. Phys. Express"
    },
    {
      "key": "2024051414255160900_c37",
      "doi-asserted-by": "publisher",
      "first-page": "82",
      "DOI": "10.1006/jssc.1996.7234",
      "article-title": "Cation sublattice and coordination polyhedra in ABO4 type of structures",
      "volume": "129",
      "year": "1997",
      "journal-title": "J. Solid State Chem."
    },
    {
      "key": "2024051414255160900_c38",
      "doi-asserted-by": "publisher",
      "first-page": "57",
      "DOI": "10.1006/jssc.2001.9266",
      "article-title": "SbSbxM1\u2212xO4 (M = NbV or TaV): Solid solution behavior and second-harmonic generating properties",
      "volume": "161",
      "year": "2001",
      "journal-title": "J. Solid State Chem."
    },
    {
      "key": "2024051414255160900_c39",
      "doi-asserted-by": "publisher",
      "first-page": "125114",
      "DOI": "10.1103/PhysRevB.84.125114",
      "article-title": "Magnetic order, transport and infrared optical properties in the ACrO3 system (A = Ca, Sr, and Pb)",
      "volume": "84",
      "year": "2011",
      "journal-title": "Phys. Rev. B"
    },
    {
      "key": "2024051414255160900_c40",
      "doi-asserted-by": "publisher",
      "first-page": "21",
      "DOI": "10.2138/am-1995-1-203",
      "article-title": "Crystal chemistry of the monazite and xenotime structures",
      "volume": "80",
      "year": "1995",
      "journal-title": "Am. Mineral."
    },
    {
      "key": "2024051414255160900_c41",
      "doi-asserted-by": "publisher",
      "first-page": "533",
      "DOI": "10.1111/j.1551-2916.2006.01410.x",
      "article-title": "Oxide materials with low thermal conductivity",
      "volume": "90",
      "year": "2007",
      "journal-title": "J. Am. Ceram. Soc."
    },
    {
      "key": "2024051414255160900_c42",
      "doi-asserted-by": "publisher",
      "first-page": "2272",
      "DOI": "10.1021/ic048195p",
      "article-title": "Structure and physical properties of ternary rare-earth cobalt bismuth intermetallics RE12Co5Bi (RE = Y, Gd, Tb, Dy, Ho, Er, Tm)",
      "volume": "44",
      "year": "2005",
      "journal-title": "Inorg. Chem."
    },
    {
      "key": "2024051414255160900_c43",
      "doi-asserted-by": "publisher",
      "first-page": "4002",
      "DOI": "10.1063/1.361828",
      "article-title": "The effect of rare-earth filling on the lattice thermal conductivity of skutterudites",
      "volume": "79",
      "year": "1996",
      "journal-title": "J. Appl. Phys."
    },
    {
      "key": "2024051414255160900_c44",
      "doi-asserted-by": "publisher",
      "first-page": "1",
      "DOI": "10.1016/j.progsolidstchem.2011.02.001",
      "article-title": "Simple rules for the understanding of Heusler compounds",
      "volume": "39",
      "year": "2011",
      "journal-title": "Prog. Solid State Chem."
    },
    {
      "key": "2024051414255160900_c45",
      "doi-asserted-by": "publisher",
      "first-page": "163514",
      "DOI": "10.1063/1.4765358",
      "article-title": "Enhanced thermoelectric properties of bulk TiNiSn via formation of a TiNi2Sn second phase",
      "volume": "101",
      "year": "2012",
      "journal-title": "Appl. Phys. Lett."
    },
    {
      "key": "2024051414255160900_c46",
      "doi-asserted-by": "publisher",
      "first-page": "163",
      "DOI": "10.1038/nature06381",
      "article-title": "Enhanced thermoelectric performance of rough silicon nanowires",
      "volume": "451",
      "year": "2008",
      "journal-title": "Nature"
    },
    {
      "key": "2024051414255160900_c47",
      "doi-asserted-by": "publisher",
      "first-page": "255",
      "DOI": "10.1016/B978-044482794-4/50000-0",
      "volume-title": "Thermophys. Prop. Mater.",
      "year": "1999"
    },
    {
      "key": "2024051414255160900_c48",
      "doi-asserted-by": "publisher",
      "first-page": "9541",
      "DOI": "10.1103/PhysRevB.40.9541",
      "article-title": "Thermal conductivity and electrical resistivity of gadolinium as functions of pressure and temperature",
      "volume": "40",
      "year": "1989",
      "journal-title": "Phys. Rev. B"
    },
    {
      "article-title": "Thermal conductivity: Theory, properties, and applications",
      "volume-title": "Physics of Solids and Liquids",
      "year": "2004",
      "key": "2024051414255160900_c49"
    }
  ],
  "container-title": "APL Materials",
  "original-title": [],
  "language": "en",
  "link": [
    {
      "URL": "https://pubs.aip.org/aip/apm/article-pdf/doi/10.1063/1.4952607/19949591/053213_1_1.4952607.pdf",
      "content-type": "application/pdf",
      "content-version": "vor",
      "intended-application": "text-mining"
    },
    {
      "URL": "https://pubs.aip.org/aip/apm/article-pdf/doi/10.1063/1.4952607/19949591/053213_1_1.4952607.pdf",
      "content-type": "application/pdf",
      "content-version": "vor",
      "intended-application": "syndication"
    },
    {
      "URL": "https://pubs.aip.org/aip/apm/article-pdf/doi/10.1063/1.4952607/19949591/053213_1_1.4952607.pdf",
      "content-type": "unspecified",
      "content-version": "vor",
      "intended-application": "similarity-checking"
    }
  ],
  "deposited": {
    "date-parts": [
      [
        2025,
        5,
        29
      ]
    ],
    "date-time": "2025-05-29T19:29:37Z",
    "timestamp": 1748546977000
  },
  "score": 1,
  "resource": {
    "primary": {
      "URL": "https://pubs.aip.org/apm/article/4/5/053213/121538/Perspective-Web-based-machine-learning-models-for"
    }
  },
  "subtitle": [],
  "short-title": [],
  "issued": {
    "date-parts": [
      [
        2016,
        5,
        1
      ]
    ]
  },
  "references-count": 49,
  "journal-issue": {
    "issue": "5",
    "published-print": {
      "date-parts": [
        [
          2016,
          5,
          1
        ]
      ]
    }
  },
  "URL": "http://dx.doi.org/10.1063/1.4952607",
  "relation": {},
  "ISSN": [
    "2166-532X"
  ],
  "subject": [],
  "published-other": {
    "date-parts": [
      [
        2016,
        5,
        1
      ]
    ]
  },
  "published": {
    "date-parts": [
      [
        2016,
        5,
        1
      ]
    ]
  },
  "article-number": "053213"
}