DOI: 10.1126/sciadv.1603015. Machine learning of accurate energy-conserving molecular force fields

Machine learning of accurate energy-conserving molecular force fields

10.1126/sciadv.1603015

Crossref journal-article

American Association for the Advancement of Science (AAAS)

Science Advances (221)

Abstract

The law of energy conservation is used to develop an efficient machine learning approach to construct accurate force fields.

Bibliography

Chmiela, S., Tkatchenko, A., Sauceda, H. E., Poltavsky, I., SchÃ¼tt, K. T., & MÃ¼ller, K.-R. (2017). Machine learning of accurate energy-conserving molecular force fields. Science Advances, 3(5).

Authors 6

Stefan Chmiela (first)
Alexandre Tkatchenko (additional)
Huziel E. Sauceda (additional)
Igor Poltavsky (additional)
Kristof T. Schütt (additional)
Klaus-Robert Müller (additional)

References 36 Referenced 898

10.1103/PhysRevLett.98.146401
10.1063/1.2746232
10.1103/PhysRevLett.104.136403
J. Behler, Atom-centered symmetry functions for constructing high-dimensional neural network potentials. J. Chem. Phys. 134, 074106 (2011). (10.1063/1.3553717) / J. Chem. Phys. / Atom-centered symmetry functions for constructing high-dimensional neural network potentials by Behler J. (2011)
J. Behler, Neural network potential-energy surfaces in chemistry: A tool for large-scale simulations. Phys. Chem. Chem. Phys. 13, 17930–17955 (2011). (10.1039/c1cp21668f) / Phys. Chem. Chem. Phys. / Neural network potential-energy surfaces in chemistry: A tool for large-scale simulations by Behler J. (2011)
K. V. J. Jose, N. Artrith, J. Behler, Construction of high-dimensional neural network potentials using environment-dependent atom pairs. J. Chem. Phys. 136, 194111 (2011). (10.1063/1.4712397) / J. Chem. Phys. / Construction of high-dimensional neural network potentials using environment-dependent atom pairs by Jose K. V. J. (2011)
10.1103/PhysRevB.87.184115
A. P. Bartók, G. Csányi, Gaussian approximation potentials: A brief tutorial introduction. Int. J. Quantum Chem. 115, 1051–1057 (2015). (10.1002/qua.24927) / Int. J. Quantum Chem. / Gaussian approximation potentials: A brief tutorial introduction by Bartók A. P. (2015)
S. De, A. P. Bartók, G. Csányi, M. Ceriotti, Comparing molecules and solids across structural and alchemical space. Phys. Chem. Chem. Phys. 18, 13754–13769 (2016). (10.1039/C6CP00415F) / Phys. Chem. Chem. Phys. / Comparing molecules and solids across structural and alchemical space by De S. (2016)
10.1103/PhysRevLett.108.058301
G. Montavon, M. Rupp, V. Gobre, A. Vazquez-Mayagoitia, K. Hansen, A. Tkatchenko, K.-R. Müller, O. A. von Lilienfeld, Machine learning of molecular electronic properties in chemical compound space. New J. Phys. 15, 095003 (2013). (10.1088/1367-2630/15/9/095003) / New J. Phys. / Machine learning of molecular electronic properties in chemical compound space by Montavon G. (2013)
K. Hansen, G. Montavon, F. Biegler, S. Fazli, M. Rupp, M. Scheffler, O. A. von Lilienfeld, A. Tkatchenko, K.-R. Müller, Assessment and validation of machine learning methods for predicting molecular atomization energies. J. Chem. Theory Comput. 9, 3404–3419 (2013). (10.1021/ct400195d) / J. Chem. Theory Comput. / Assessment and validation of machine learning methods for predicting molecular atomization energies by Hansen K. (2013)
K. Hansen, F. Biegler, R. Ramakrishnan, W. Pronobis, O. A. von Lilienfeld, K.-R. Müller, A. Tkatchenko, Machine learning predictions of molecular properties: Accurate many-body potentials and nonlocality in chemical space. J. Phys. Chem. Lett. 6, 2326–2331 (2015). (10.1021/acs.jpclett.5b00831) / J. Phys. Chem. Lett. / Machine learning predictions of molecular properties: Accurate many-body potentials and nonlocality in chemical space by Hansen K. (2015)
M. Rupp, R. Ramakrishnan, O. A. von Lilienfeld, Machine learning for quantum mechanical properties of atoms in molecules. J. Phys. Chem. Lett. 6, 3309–3313 (2015). (10.1021/acs.jpclett.5b01456) / J. Phys. Chem. Lett. / Machine learning for quantum mechanical properties of atoms in molecules by Rupp M. (2015)
V. Botu, R. Ramprasad, Learning scheme to predict atomic forces and accelerate materials simulations. Phys. Rev. B 92, 094306 (2015). (10.1103/PhysRevB.92.094306) / Phys. Rev. B / Learning scheme to predict atomic forces and accelerate materials simulations by Botu V. (2015)
M. Hirn, N. Poilvert, S. Mallat, Quantum energy regression using scattering transforms. CoRR arXiv:1502.02077 (2015). / CoRR / Quantum energy regression using scattering transforms by Hirn M. (2015)
10.1063/1.4966192
Z. Li, J. R. Kermode, A. De Vita, Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces. Phys. Rev. Lett. 114, 096405 (2015). (10.1103/PhysRevLett.114.096405) / Phys. Rev. Lett. / Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces by Li Z. (2015)
C. A. Micchelli, M. A. Pontil, On learning vector-valued functions. Neural Comput. 17, 177–204 (2005). (10.1162/0899766052530802) / Neural Comput. / On learning vector-valued functions by Micchelli C. A. (2005)
A. Caponnetto, C. A. Micchelli, M. Pontil, Y. Ying, Universal multi-task kernels. J. Mach. Learn. Res. 9, 1615–1646 (2008). / J. Mach. Learn. Res. / Universal multi-task kernels by Caponnetto A. (2008)
V. Sindhwani H. Q. Minh A. C. Lozano Scalable matrix-valued kernel learning for high-dimensional nonlinear multivariate regression and granger causality in Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence (UAI’13) 12 to 14 July 2013.
B. Matérn Spatial Variation Lecture Notes in Statistics (Springer-Verlag 1986). (10.1007/978-1-4615-7892-5)
I. S. Gradshteyn I. M. Ryzhik Table of Integrals Series and Products A. Jeffrey D. Zwillinger Eds. (Academic Press ed. 7 2007).
T. Gneiting, W. Kleiber, M. Schlather, Matérn cross-covariance functions for multivariate random fields. J. Am. Stat. Assoc. 105, 1167–1177 (2010). (10.1198/jasa.2010.tm09420) / J. Am. Stat. Assoc. / Matérn cross-covariance functions for multivariate random fields by Gneiting T. (2010)
H. Helmholtz, Über Integrale der hydrodynamischen Gleichungen, welche den Wirbelbewegungen entsprechen. Angew. Math. 1858, 25–55 (2009). / Angew. Math. / Über Integrale der hydrodynamischen Gleichungen, welche den Wirbelbewegungen entsprechen by Helmholtz H. (2009)
W. H. Press S. A. Teukolsky W. T. Vetterling B. P. Flannery Numerical Recipes: The Art of Scientific Computing (Cambridge Univ. Press ed. 3 2007).
10.1103/PhysRevLett.77.3865
10.1103/PhysRevLett.102.073005
M. Ceriotti, J. More, D. E. Manolopoulos, i-PI: A Python interface for ab initio path integral molecular dynamics simulations. Comput. Phys. Commun. 185, 1019–1026 (2014). (10.1016/j.cpc.2013.10.027) / Comput. Phys. Commun. / i-PI: A Python interface for ab initio path integral molecular dynamics simulations by Ceriotti M. (2014)
I. Poltavsky, A. Tkatchenko, Modeling quantum nuclei with perturbed path integral molecular dynamics. Chem. Sci. 7, 1368–1372 (2016). (10.1039/C5SC03443D) / Chem. Sci. / Modeling quantum nuclei with perturbed path integral molecular dynamics by Poltavsky I. (2016)
A. J. Smola B. Schölkopf Learning with Kernels: Support Vector Machines Regularization Optimization and Beyond (MIT Press 2001).
10.1103/PhysRevLett.108.253002
J. C. Snyder, M. Rupp, K.-R. Müller, K. Burke, Nonlinear gradient denoising: Finding accurate extrema from inaccurate functional derivatives. Int. J. Quantum Chem. 115, 1102–1114 (2015). (10.1002/qua.24937) / Int. J. Quantum Chem. / Nonlinear gradient denoising: Finding accurate extrema from inaccurate functional derivatives by Snyder J. C. (2015)
10.1162/089976698300017467
B. Schölkopf, S. Mika, C. J. C. Burges, P. Knirsch, K.-R. Müller, G. Ratsch, A. J. Smola, Input space versus feature space in kernel-based methods. IEEE Trans. Neural Netw. Learn. Syst. 10, 1000–1017 (1999). (10.1109/72.788641) / IEEE Trans. Neural Netw. Learn. Syst. / Input space versus feature space in kernel-based methods by Schölkopf B. (1999)
K.-R. Müller, S. Mika, G. Rätsch, K. Tsuda, B. Schölkopf, An introduction to kernel-based learning algorithms. IEEE Trans. Neural Netw. Learn. Syst. 12, 181–201 (2001). (10.1109/72.914517) / IEEE Trans. Neural Netw. Learn. Syst. / An introduction to kernel-based learning algorithms by Müller K.-R. (2001)

Dates

Type	When
Created	8 years, 3 months ago (May 5, 2017, 8:40 p.m.)
Deposited	1 year, 7 months ago (Jan. 9, 2024, 11:30 a.m.)
Indexed	22 minutes ago (Aug. 21, 2025, 6:32 a.m.)
Issued	8 years, 3 months ago (May 5, 2017)
Published	8 years, 3 months ago (May 5, 2017)
Published Print	8 years, 3 months ago (May 5, 2017)

Funders 2

Deutsche Forschungsgemeinschaft 10.13039/501100001659
Region: Europe
gov (National government)
Labels3
1. German Research Association
2. German Research Foundation
3. DFG
Awards2
1. ID0EVBAI16416
2. MU 987/20-1
Ministry of Education, Science and Technology 10.13039/501100004085
Region: Asia
gov (National government)
Labels2
1. Korean Ministry of Education, Science and Technology
2. MEST
Awards2
1. ID0EQGAI16417
2. 2012-005741

BibTeX

@article{Chmiela_2017, title={Machine learning of accurate energy-conserving molecular force fields}, volume={3}, ISSN={2375-2548}, url={http://dx.doi.org/10.1126/sciadv.1603015}, DOI={10.1126/sciadv.1603015}, number={5}, journal={Science Advances}, publisher={American Association for the Advancement of Science (AAAS)}, author={Chmiela, Stefan and Tkatchenko, Alexandre and Sauceda, Huziel E. and Poltavsky, Igor and Schütt, Kristof T. and Müller, Klaus-Robert}, year={2017}, month=may }

JSON

{
  "indexed": {
    "date-parts": [
      [
        2025,
        8,
        21
      ]
    ],
    "date-time": "2025-08-21T10:32:03Z",
    "timestamp": 1755772323820,
    "version": "3.41.2"
  },
  "reference-count": 36,
  "publisher": "American Association for the Advancement of Science (AAAS)",
  "issue": "5",
  "funder": [
    {
      "DOI": "10.13039/501100001659",
      "name": "Deutsche Forschungsgemeinschaft",
      "doi-asserted-by": "publisher",
      "award": [
        "ID0EVBAI16416",
        "MU 987/20-1"
      ],
      "id": [
        {
          "id": "10.13039/501100001659",
          "id-type": "DOI",
          "asserted-by": "publisher"
        }
      ]
    },
    {
      "DOI": "10.13039/501100004085",
      "name": "Ministry of Education, Science and Technology",
      "doi-asserted-by": "publisher",
      "award": [
        "ID0EQGAI16417",
        "2012-005741"
      ],
      "id": [
        {
          "id": "10.13039/501100004085",
          "id-type": "DOI",
          "asserted-by": "publisher"
        }
      ]
    }
  ],
  "content-domain": {
    "domain": [],
    "crossmark-restriction": false
  },
  "published-print": {
    "date-parts": [
      [
        2017,
        5,
        5
      ]
    ]
  },
  "abstract": "<jats:p>The law of energy conservation is used to develop an efficient machine learning approach to construct accurate force fields.</jats:p>",
  "DOI": "10.1126/sciadv.1603015",
  "type": "journal-article",
  "created": {
    "date-parts": [
      [
        2017,
        5,
        6
      ]
    ],
    "date-time": "2017-05-06T00:40:24Z",
    "timestamp": 1494031224000
  },
  "source": "Crossref",
  "is-referenced-by-count": 898,
  "title": "Machine learning of accurate energy-conserving molecular force fields",
  "prefix": "10.1126",
  "volume": "3",
  "author": [
    {
      "given": "Stefan",
      "family": "Chmiela",
      "sequence": "first",
      "affiliation": [
        {
          "name": "Machine Learning Group, Technische Universit\u00e4t Berlin, 10587 Berlin, Germany."
        }
      ]
    },
    {
      "ORCID": "https://orcid.org/0000-0002-1012-4854",
      "authenticated-orcid": false,
      "given": "Alexandre",
      "family": "Tkatchenko",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Physics and Materials Science Research Unit, University of Luxembourg, L-1511 Luxembourg, Luxembourg."
        },
        {
          "name": "Fritz-Haber-Institut der Max-Planck-Gesellschaft, 14195 Berlin, Germany."
        }
      ]
    },
    {
      "ORCID": "https://orcid.org/0000-0001-6091-3408",
      "authenticated-orcid": false,
      "given": "Huziel E.",
      "family": "Sauceda",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Fritz-Haber-Institut der Max-Planck-Gesellschaft, 14195 Berlin, Germany."
        }
      ]
    },
    {
      "given": "Igor",
      "family": "Poltavsky",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Physics and Materials Science Research Unit, University of Luxembourg, L-1511 Luxembourg, Luxembourg."
        }
      ]
    },
    {
      "ORCID": "https://orcid.org/0000-0001-8342-0964",
      "authenticated-orcid": false,
      "given": "Kristof T.",
      "family": "Sch\u00fctt",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Machine Learning Group, Technische Universit\u00e4t Berlin, 10587 Berlin, Germany."
        }
      ]
    },
    {
      "given": "Klaus-Robert",
      "family": "M\u00fcller",
      "sequence": "additional",
      "affiliation": [
        {
          "name": "Machine Learning Group, Technische Universit\u00e4t Berlin, 10587 Berlin, Germany."
        },
        {
          "name": "Department of Brain and Cognitive Engineering, Korea University, Anam-dong, Seongbuk-gu, Seoul 136-713, Korea."
        },
        {
          "name": "Max Planck Institute for Informatics, Stuhlsatzenhausweg, 66123 Saarbr\u00fccken, Germany."
        }
      ]
    }
  ],
  "member": "221",
  "reference": [
    {
      "doi-asserted-by": "publisher",
      "key": "e_1_3_2_2_2",
      "DOI": "10.1103/PhysRevLett.98.146401"
    },
    {
      "doi-asserted-by": "publisher",
      "key": "e_1_3_2_3_2",
      "DOI": "10.1063/1.2746232"
    },
    {
      "doi-asserted-by": "publisher",
      "key": "e_1_3_2_4_2",
      "DOI": "10.1103/PhysRevLett.104.136403"
    },
    {
      "key": "e_1_3_2_5_2",
      "doi-asserted-by": "crossref",
      "first-page": "074106",
      "DOI": "10.1063/1.3553717",
      "article-title": "Atom-centered symmetry functions for constructing high-dimensional neural network potentials",
      "volume": "134",
      "author": "Behler J.",
      "year": "2011",
      "unstructured": "J. Behler, Atom-centered symmetry functions for constructing high-dimensional neural network potentials. J. Chem. Phys. 134, 074106 (2011).",
      "journal-title": "J. Chem. Phys."
    },
    {
      "key": "e_1_3_2_6_2",
      "doi-asserted-by": "crossref",
      "first-page": "17930",
      "DOI": "10.1039/c1cp21668f",
      "article-title": "Neural network potential-energy surfaces in chemistry: A tool for large-scale simulations",
      "volume": "13",
      "author": "Behler J.",
      "year": "2011",
      "unstructured": "J. Behler, Neural network potential-energy surfaces in chemistry: A tool for large-scale simulations. Phys. Chem. Chem. Phys. 13, 17930\u201317955 (2011).",
      "journal-title": "Phys. Chem. Chem. Phys."
    },
    {
      "key": "e_1_3_2_7_2",
      "doi-asserted-by": "crossref",
      "first-page": "194111",
      "DOI": "10.1063/1.4712397",
      "article-title": "Construction of high-dimensional neural network potentials using environment-dependent atom pairs",
      "volume": "136",
      "author": "Jose K. V. J.",
      "year": "2011",
      "unstructured": "K. V. J. Jose, N. Artrith, J. Behler, Construction of high-dimensional neural network potentials using environment-dependent atom pairs. J. Chem. Phys. 136, 194111 (2011).",
      "journal-title": "J. Chem. Phys."
    },
    {
      "doi-asserted-by": "publisher",
      "key": "e_1_3_2_8_2",
      "DOI": "10.1103/PhysRevB.87.184115"
    },
    {
      "key": "e_1_3_2_9_2",
      "doi-asserted-by": "crossref",
      "first-page": "1051",
      "DOI": "10.1002/qua.24927",
      "article-title": "Gaussian approximation potentials: A brief tutorial introduction",
      "volume": "115",
      "author": "Bart\u00f3k A. P.",
      "year": "2015",
      "unstructured": "A. P. Bart\u00f3k, G. Cs\u00e1nyi, Gaussian approximation potentials: A brief tutorial introduction. Int. J. Quantum Chem. 115, 1051\u20131057 (2015).",
      "journal-title": "Int. J. Quantum Chem."
    },
    {
      "key": "e_1_3_2_10_2",
      "doi-asserted-by": "crossref",
      "first-page": "13754",
      "DOI": "10.1039/C6CP00415F",
      "article-title": "Comparing molecules and solids across structural and alchemical space",
      "volume": "18",
      "author": "De S.",
      "year": "2016",
      "unstructured": "S. De, A. P. Bart\u00f3k, G. Cs\u00e1nyi, M. Ceriotti, Comparing molecules and solids across structural and alchemical space. Phys. Chem. Chem. Phys. 18, 13754\u201313769 (2016).",
      "journal-title": "Phys. Chem. Chem. Phys."
    },
    {
      "doi-asserted-by": "publisher",
      "key": "e_1_3_2_11_2",
      "DOI": "10.1103/PhysRevLett.108.058301"
    },
    {
      "key": "e_1_3_2_12_2",
      "doi-asserted-by": "crossref",
      "first-page": "095003",
      "DOI": "10.1088/1367-2630/15/9/095003",
      "article-title": "Machine learning of molecular electronic properties in chemical compound space",
      "volume": "15",
      "author": "Montavon G.",
      "year": "2013",
      "unstructured": "G. Montavon, M. Rupp, V. Gobre, A. Vazquez-Mayagoitia, K. Hansen, A. Tkatchenko, K.-R. M\u00fcller, O. A. von Lilienfeld, Machine learning of molecular electronic properties in chemical compound space. New J. Phys. 15, 095003 (2013).",
      "journal-title": "New J. Phys."
    },
    {
      "key": "e_1_3_2_13_2",
      "doi-asserted-by": "crossref",
      "first-page": "3404",
      "DOI": "10.1021/ct400195d",
      "article-title": "Assessment and validation of machine learning methods for predicting molecular atomization energies",
      "volume": "9",
      "author": "Hansen K.",
      "year": "2013",
      "unstructured": "K. Hansen, G. Montavon, F. Biegler, S. Fazli, M. Rupp, M. Scheffler, O. A. von Lilienfeld, A. Tkatchenko, K.-R. M\u00fcller, Assessment and validation of machine learning methods for predicting molecular atomization energies. J. Chem. Theory Comput. 9, 3404\u20133419 (2013).",
      "journal-title": "J. Chem. Theory Comput."
    },
    {
      "key": "e_1_3_2_14_2",
      "doi-asserted-by": "crossref",
      "first-page": "2326",
      "DOI": "10.1021/acs.jpclett.5b00831",
      "article-title": "Machine learning predictions of molecular properties: Accurate many-body potentials and nonlocality in chemical space",
      "volume": "6",
      "author": "Hansen K.",
      "year": "2015",
      "unstructured": "K. Hansen, F. Biegler, R. Ramakrishnan, W. Pronobis, O. A. von Lilienfeld, K.-R. M\u00fcller, A. Tkatchenko, Machine learning predictions of molecular properties: Accurate many-body potentials and nonlocality in chemical space. J. Phys. Chem. Lett. 6, 2326\u20132331 (2015).",
      "journal-title": "J. Phys. Chem. Lett."
    },
    {
      "key": "e_1_3_2_15_2",
      "doi-asserted-by": "crossref",
      "first-page": "3309",
      "DOI": "10.1021/acs.jpclett.5b01456",
      "article-title": "Machine learning for quantum mechanical properties of atoms in molecules",
      "volume": "6",
      "author": "Rupp M.",
      "year": "2015",
      "unstructured": "M. Rupp, R. Ramakrishnan, O. A. von Lilienfeld, Machine learning for quantum mechanical properties of atoms in molecules. J. Phys. Chem. Lett. 6, 3309\u20133313 (2015).",
      "journal-title": "J. Phys. Chem. Lett."
    },
    {
      "key": "e_1_3_2_16_2",
      "doi-asserted-by": "crossref",
      "first-page": "094306",
      "DOI": "10.1103/PhysRevB.92.094306",
      "article-title": "Learning scheme to predict atomic forces and accelerate materials simulations",
      "volume": "92",
      "author": "Botu V.",
      "year": "2015",
      "unstructured": "V. Botu, R. Ramprasad, Learning scheme to predict atomic forces and accelerate materials simulations. Phys. Rev. B 92, 094306 (2015).",
      "journal-title": "Phys. Rev. B"
    },
    {
      "key": "e_1_3_2_17_2",
      "article-title": "Quantum energy regression using scattering transforms",
      "author": "Hirn M.",
      "year": "2015",
      "unstructured": "M. Hirn, N. Poilvert, S. Mallat, Quantum energy regression using scattering transforms. CoRR arXiv:1502.02077 (2015).",
      "journal-title": "CoRR"
    },
    {
      "doi-asserted-by": "publisher",
      "key": "e_1_3_2_18_2",
      "DOI": "10.1063/1.4966192"
    },
    {
      "key": "e_1_3_2_19_2",
      "doi-asserted-by": "crossref",
      "first-page": "096405",
      "DOI": "10.1103/PhysRevLett.114.096405",
      "article-title": "Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces",
      "volume": "114",
      "author": "Li Z.",
      "year": "2015",
      "unstructured": "Z. Li, J. R. Kermode, A. De Vita, Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces. Phys. Rev. Lett. 114, 096405 (2015).",
      "journal-title": "Phys. Rev. Lett."
    },
    {
      "key": "e_1_3_2_20_2",
      "doi-asserted-by": "crossref",
      "first-page": "177",
      "DOI": "10.1162/0899766052530802",
      "article-title": "On learning vector-valued functions",
      "volume": "17",
      "author": "Micchelli C. A.",
      "year": "2005",
      "unstructured": "C. A. Micchelli, M. A. Pontil, On learning vector-valued functions. Neural Comput. 17, 177\u2013204 (2005).",
      "journal-title": "Neural Comput."
    },
    {
      "key": "e_1_3_2_21_2",
      "first-page": "1615",
      "article-title": "Universal multi-task kernels",
      "volume": "9",
      "author": "Caponnetto A.",
      "year": "2008",
      "unstructured": "A. Caponnetto, C. A. Micchelli, M. Pontil, Y. Ying, Universal multi-task kernels. J. Mach. Learn. Res. 9, 1615\u20131646 (2008).",
      "journal-title": "J. Mach. Learn. Res."
    },
    {
      "unstructured": "V. Sindhwani H. Q. Minh A. C. Lozano Scalable matrix-valued kernel learning for high-dimensional nonlinear multivariate regression and granger causality in Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence (UAI\u201913) 12 to 14 July 2013.",
      "key": "e_1_3_2_22_2"
    },
    {
      "doi-asserted-by": "crossref",
      "unstructured": "B. Mat\u00e9rn Spatial Variation Lecture Notes in Statistics (Springer-Verlag 1986).",
      "key": "e_1_3_2_23_2",
      "DOI": "10.1007/978-1-4615-7892-5"
    },
    {
      "unstructured": "I. S. Gradshteyn I. M. Ryzhik Table of Integrals Series and Products A. Jeffrey D. Zwillinger Eds. (Academic Press ed. 7 2007).",
      "key": "e_1_3_2_24_2"
    },
    {
      "key": "e_1_3_2_25_2",
      "doi-asserted-by": "crossref",
      "first-page": "1167",
      "DOI": "10.1198/jasa.2010.tm09420",
      "article-title": "Mat\u00e9rn cross-covariance functions for multivariate random fields",
      "volume": "105",
      "author": "Gneiting T.",
      "year": "2010",
      "unstructured": "T. Gneiting, W. Kleiber, M. Schlather, Mat\u00e9rn cross-covariance functions for multivariate random fields. J. Am. Stat. Assoc. 105, 1167\u20131177 (2010).",
      "journal-title": "J. Am. Stat. Assoc."
    },
    {
      "key": "e_1_3_2_26_2",
      "first-page": "25",
      "article-title": "\u00dcber Integrale der hydrodynamischen Gleichungen, welche den Wirbelbewegungen entsprechen",
      "volume": "1858",
      "author": "Helmholtz H.",
      "year": "2009",
      "unstructured": "H. Helmholtz, \u00dcber Integrale der hydrodynamischen Gleichungen, welche den Wirbelbewegungen entsprechen. Angew. Math. 1858, 25\u201355 (2009).",
      "journal-title": "Angew. Math."
    },
    {
      "unstructured": "W. H. Press S. A. Teukolsky W. T. Vetterling B. P. Flannery Numerical Recipes: The Art of Scientific Computing (Cambridge Univ. Press ed. 3 2007).",
      "key": "e_1_3_2_27_2"
    },
    {
      "doi-asserted-by": "publisher",
      "key": "e_1_3_2_28_2",
      "DOI": "10.1103/PhysRevLett.77.3865"
    },
    {
      "doi-asserted-by": "publisher",
      "key": "e_1_3_2_29_2",
      "DOI": "10.1103/PhysRevLett.102.073005"
    },
    {
      "key": "e_1_3_2_30_2",
      "doi-asserted-by": "crossref",
      "first-page": "1019",
      "DOI": "10.1016/j.cpc.2013.10.027",
      "article-title": "i-PI: A Python interface for ab initio path integral molecular dynamics simulations",
      "volume": "185",
      "author": "Ceriotti M.",
      "year": "2014",
      "unstructured": "M. Ceriotti, J. More, D. E. Manolopoulos, i-PI: A Python interface for ab initio path integral molecular dynamics simulations. Comput. Phys. Commun. 185, 1019\u20131026 (2014).",
      "journal-title": "Comput. Phys. Commun."
    },
    {
      "key": "e_1_3_2_31_2",
      "doi-asserted-by": "crossref",
      "first-page": "1368",
      "DOI": "10.1039/C5SC03443D",
      "article-title": "Modeling quantum nuclei with perturbed path integral molecular dynamics",
      "volume": "7",
      "author": "Poltavsky I.",
      "year": "2016",
      "unstructured": "I. Poltavsky, A. Tkatchenko, Modeling quantum nuclei with perturbed path integral molecular dynamics. Chem. Sci. 7, 1368\u20131372 (2016).",
      "journal-title": "Chem. Sci."
    },
    {
      "unstructured": "A. J. Smola B. Sch\u00f6lkopf Learning with Kernels: Support Vector Machines Regularization Optimization and Beyond (MIT Press 2001).",
      "key": "e_1_3_2_32_2"
    },
    {
      "doi-asserted-by": "publisher",
      "key": "e_1_3_2_33_2",
      "DOI": "10.1103/PhysRevLett.108.253002"
    },
    {
      "key": "e_1_3_2_34_2",
      "doi-asserted-by": "crossref",
      "first-page": "1102",
      "DOI": "10.1002/qua.24937",
      "article-title": "Nonlinear gradient denoising: Finding accurate extrema from inaccurate functional derivatives",
      "volume": "115",
      "author": "Snyder J. C.",
      "year": "2015",
      "unstructured": "J. C. Snyder, M. Rupp, K.-R. M\u00fcller, K. Burke, Nonlinear gradient denoising: Finding accurate extrema from inaccurate functional derivatives. Int. J. Quantum Chem. 115, 1102\u20131114 (2015).",
      "journal-title": "Int. J. Quantum Chem."
    },
    {
      "doi-asserted-by": "publisher",
      "key": "e_1_3_2_35_2",
      "DOI": "10.1162/089976698300017467"
    },
    {
      "key": "e_1_3_2_36_2",
      "doi-asserted-by": "crossref",
      "first-page": "1000",
      "DOI": "10.1109/72.788641",
      "article-title": "Input space versus feature space in kernel-based methods",
      "volume": "10",
      "author": "Sch\u00f6lkopf B.",
      "year": "1999",
      "unstructured": "B. Sch\u00f6lkopf, S. Mika, C. J. C. Burges, P. Knirsch, K.-R. M\u00fcller, G. Ratsch, A. J. Smola, Input space versus feature space in kernel-based methods. IEEE Trans. Neural Netw. Learn. Syst. 10, 1000\u20131017 (1999).",
      "journal-title": "IEEE Trans. Neural Netw. Learn. Syst."
    },
    {
      "key": "e_1_3_2_37_2",
      "doi-asserted-by": "crossref",
      "first-page": "181",
      "DOI": "10.1109/72.914517",
      "article-title": "An introduction to kernel-based learning algorithms",
      "volume": "12",
      "author": "M\u00fcller K.-R.",
      "year": "2001",
      "unstructured": "K.-R. M\u00fcller, S. Mika, G. R\u00e4tsch, K. Tsuda, B. Sch\u00f6lkopf, An introduction to kernel-based learning algorithms. IEEE Trans. Neural Netw. Learn. Syst. 12, 181\u2013201 (2001).",
      "journal-title": "IEEE Trans. Neural Netw. Learn. Syst."
    }
  ],
  "container-title": "Science Advances",
  "original-title": [],
  "language": "en",
  "link": [
    {
      "URL": "https://www.science.org/doi/pdf/10.1126/sciadv.1603015",
      "content-type": "unspecified",
      "content-version": "vor",
      "intended-application": "similarity-checking"
    }
  ],
  "deposited": {
    "date-parts": [
      [
        2024,
        1,
        9
      ]
    ],
    "date-time": "2024-01-09T16:30:40Z",
    "timestamp": 1704817840000
  },
  "score": 1,
  "resource": {
    "primary": {
      "URL": "https://www.science.org/doi/10.1126/sciadv.1603015"
    }
  },
  "subtitle": [],
  "short-title": [],
  "issued": {
    "date-parts": [
      [
        2017,
        5,
        5
      ]
    ]
  },
  "references-count": 36,
  "journal-issue": {
    "issue": "5",
    "published-print": {
      "date-parts": [
        [
          2017,
          5,
          5
        ]
      ]
    }
  },
  "alternative-id": [
    "10.1126/sciadv.1603015"
  ],
  "URL": "http://dx.doi.org/10.1126/sciadv.1603015",
  "relation": {},
  "ISSN": [
    "2375-2548"
  ],
  "subject": [],
  "container-title-short": "Sci. Adv.",
  "published": {
    "date-parts": [
      [
        2017,
        5,
        5
      ]
    ]
  },
  "article-number": "e1603015"
}