{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T12:27:49Z","timestamp":1787056069501,"version":"build-2736575974"},"reference-count":77,"publisher":"American Chemical Society (ACS)","issue":"42","license":[{"start":{"date-parts":[[2020,9,24]],"date-time":"2020-09-24T00:00:00Z","timestamp":1600905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,24]],"date-time":"2020-09-24T00:00:00Z","timestamp":1600905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2020,9,24]],"date-time":"2020-09-24T00:00:00Z","timestamp":1600905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F?rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["200020-188724"],"award-info":[{"award-number":["200020-188724"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F?rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["200021 175747"],"award-info":[{"award-number":["200021 175747"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F?rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["200021-117810"],"award-info":[{"award-number":["200021-117810"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008375","name":"Universit?t Basel","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008375","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Machine learning (ML) has become a promising tool for improving the quality of atomistic simulations. Using formaldehyde as a benchmark system for intramolecular interactions, a comparative assessment of ML models based on state-of-the-art variants of deep neural networks (NNs), reproducing kernel Hilbert space (RKHS+F), and kernel ridge regression (KRR) is presented. Learning curves for energies and atomic forces indicate rapid convergence toward excellent predictions for B3LYP, MP2, and CCSD\u00ad(T)-F12 reference results for modestly sized (in the hundreds) training sets. Typically, learning curve offsets decay as one goes from NN (PhysNet) to RKHS+F to KRR (FCHL). Conversely, the predictive power for extrapolation of energies toward new geometries increases in the same order with RKHS+F and FCHL performing almost equally. For harmonic vibrational frequencies, the picture is less clear, with PhysNet and FCHL yielding accuracies of \u223c1 and \u223c0.2 cm\u20131, respectively, no matter which reference method, while RKHS+F models level off for B3LYP and exhibit continued improvements for MP2 and CCSD\u00ad(T)-F12. Finite-temperature molecular dynamics (MD) simulations using the PESs from the three ML methods with identical initial conditions yield indistinguishable infrared spectra with good performance compared with experiment except for the high-frequency modes involving hydrogen stretch motion which is a known limitation of MD for vibrational spectroscopy. For sufficiently large training set sizes, all three models can detect insufficient convergence (\u201cnoise\u201d) of the reference electronic structure calculations in that the learning curves level off. Transfer learning (TL) from B3LYP to CCSD\u00ad(T)-F12 with PhysNet indicates that additional improvements in data efficiency can be achieved.<\/jats:p>","DOI":"10.1021\/acs.jpca.0c05979","type":"journal-article","created":{"date-parts":[[2020,9,24]],"date-time":"2020-09-24T15:05:03Z","timestamp":1600959903000},"page":"8853-8865","source":"Crossref","is-referenced-by-count":34,"title":["Machine Learning Models of Vibrating H2CO: Comparing Reproducing\nKernels, FCHL, and PhysNet"],"prefix":"10.1021","volume":"124","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3641-8519","authenticated-orcid":true,"given":"Silvan","family":"Ka\u0308ser","sequence":"first","affiliation":[{"name":"University of Basel , , Klingelbergstrasse 80 , ,","place":["Basel, Switzerland, CH-4056"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5116-4908","authenticated-orcid":true,"given":"Debasish","family":"Koner","sequence":"additional","affiliation":[{"name":"University of Basel , , Klingelbergstrasse 80 , ,","place":["Basel, Switzerland, CH-4056"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anders S.","family":"Christensen","sequence":"additional","affiliation":[{"name":"University of Basel , , Klingelbergstrasse 80 , ,","place":["Basel, Switzerland, CH-4056"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7419-0466","authenticated-orcid":true,"given":"O. Anatole","family":"von Lilienfeld","sequence":"additional","affiliation":[{"name":"University of Basel , , Klingelbergstrasse 80 , ,","place":["Basel, Switzerland, CH-4056"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7930-8806","authenticated-orcid":true,"given":"Markus","family":"Meuwly","sequence":"additional","affiliation":[{"name":"University of Basel , , Klingelbergstrasse 80 , ,","place":["Basel, Switzerland, CH-4056"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2020,9,24]]},"reference":[{"key":"2026081807111708400_cit1","doi-asserted-by":"publisher","first-page":"170901","DOI":"10.1063\/1.4966192","article-title":"Perspective:\nMachine learning potentials for atomistic simulations","volume":"145","author":"Behler","year":"2016","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit2","doi-asserted-by":"publisher","first-page":"4164","DOI":"10.1002\/anie.201709686","article-title":"Quantum machine learning in chemical compound space","volume":"57","author":"Von\nLilienfeld","year":"2018","journal-title":"Angew. Chem., Int. Ed."},{"key":"2026081807111708400_cit3","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","article-title":"Machine learning\nfor molecular and materials science","volume":"559","author":"Butler","year":"2018","journal-title":"Nature"},{"key":"2026081807111708400_cit4","doi-asserted-by":"publisher","DOI":"10.1063\/5.0009628","article-title":"Non-conventional force\nfields for applications in spectroscopy and chemical reaction dynamics","volume":"153","author":"Koner","year":"2020","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit5","doi-asserted-by":"publisher","first-page":"8980","DOI":"10.1021\/jp048339l","article-title":"A global ab initio potential energy\nsurface for formaldehyde","volume":"108","author":"Zhang","year":"2004","journal-title":"J. Phys. Chem. A"},{"key":"2026081807111708400_cit6","doi-asserted-by":"publisher","first-page":"20160194","DOI":"10.1098\/rsta.2016.0194","article-title":"A new (multi-reference\nconfiguration\ninteraction) potential energy surface for H2CO and preliminary\nstudies of roaming","volume":"375","author":"Wang","year":"2017","journal-title":"Philos. Trans. R. Soc.,\nA"},{"key":"2026081807111708400_cit7","doi-asserted-by":"publisher","first-page":"144108","DOI":"10.1063\/1.2348881","article-title":"W4 theory for computational\nthermochemistry: In pursuit of confident sub-kJ\/mol predictions","volume":"125","author":"Karton","year":"2006","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit8","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.jqsrt.2004.03.021","article-title":"Determination\nof line strengths for selected transitions in the \u03bd2 band relative to the \u03bd1 and \u03bd5 bands of H2CO","volume":"90","author":"Herndon","year":"2005","journal-title":"J. Quant. Spectrosc.\nRadiat. Transfer"},{"key":"2026081807111708400_cit9","first-page":"1","volume-title":"Ullmann\u2019s Encyclopedia of Industrial\nChemistry","author":"Franz","year":"2016"},{"key":"2026081807111708400_cit10","doi-asserted-by":"publisher","first-page":"3550","DOI":"10.2903\/j.efsa.2014.3550","article-title":"Endogenous\nformaldehyde turnover in humans compared with exogenous contribution\nfrom food sources","volume":"12","author":"European\nFood Safety Authority.","year":"2014","journal-title":"EFSA J."},{"key":"2026081807111708400_cit11","doi-asserted-by":"publisher","first-page":"11934","DOI":"10.1002\/2017JD027266","article-title":"Sources\nand potential photochemical roles of formaldehyde in an urban atmosphere\nin South China","volume":"122","author":"Wang","year":"2017","journal-title":"J. Geophys. Res. Atmos."},{"key":"2026081807111708400_cit12","volume-title":"Formaldehyde: Exposure,\nToxicity and Health Effects","author":"Zhang","year":"2018"},{"key":"2026081807111708400_cit13","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1103\/PhysRevLett.22.679","article-title":"Microwave detection\nof interstellar formaldehyde","volume":"22","author":"Snyder","year":"1969","journal-title":"Phys. Rev. Lett."},{"key":"2026081807111708400_cit14","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1126\/science.1104386","article-title":"The roaming atom: straying from the\nreaction path in formaldehyde decomposition","volume":"306","author":"Townsend","year":"2004","journal-title":"Science"},{"key":"2026081807111708400_cit15","doi-asserted-by":"publisher","first-page":"5648","DOI":"10.1063\/1.464913","article-title":"Beckes\nthree parameter hybrid method using the LYP correlation functional","volume":"98","author":"Becke","year":"1993","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit16","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1103\/PhysRevB.37.785","article-title":"Development of the Colle-Salvetti\ncorrelation-energy formula into a functional of the electron density","volume":"37","author":"Lee","year":"1988","journal-title":"Phys. Rev. B: Condens. Matter Mater. Phys."},{"key":"2026081807111708400_cit17","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1103\/PhysRev.46.618","article-title":"Note on an approximation\ntreatment for many-electron\nsystems","volume":"46","author":"M\u00f8ller","year":"1934","journal-title":"Phys. Rev."},{"key":"2026081807111708400_cit18","doi-asserted-by":"publisher","first-page":"221106","DOI":"10.1063\/1.2817618","article-title":"A simple\nand efficient CCSD (T)-F12\napproximation","volume":"127","author":"Adler","year":"2007","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit19","doi-asserted-by":"publisher","first-page":"2584","DOI":"10.1063\/1.470984","article-title":"A general method for\nconstructing multidimensional\nmolecular potential energy surfaces from ab initio calculations","volume":"104","author":"Ho","year":"1996","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit20","doi-asserted-by":"publisher","first-page":"1923","DOI":"10.1021\/acs.jcim.7b00090","article-title":"Toolkit for the construction of reproducing kernel-based\nrepresentations of data: application to multidimensional potential\nenergy surfaces","volume":"57","author":"Unke","year":"2017","journal-title":"J. Chem. Inf. Model."},{"key":"2026081807111708400_cit21","doi-asserted-by":"publisher","first-page":"5474","DOI":"10.1021\/acs.jctc.0c00535","article-title":"Permutationally invariant,\nreproducing kernel-based\npotential energy surfaces for polyatomic molecules: from formaldehyde\nto acetone","volume":"16","author":"Koner","year":"2020","journal-title":"J. Chem. Theory Comput."},{"key":"2026081807111708400_cit22","doi-asserted-by":"publisher","first-page":"3678","DOI":"10.1021\/acs.jctc.9b00181","article-title":"PhysNet: A neural network\nfor predicting energies,\nforces, dipole moments, and partial charges","volume":"15","author":"Unke","year":"2019","journal-title":"J. Chem. Theory Comput."},{"key":"2026081807111708400_cit23","doi-asserted-by":"publisher","first-page":"241717","DOI":"10.1063\/1.5020710","article-title":"Alchemical\nand structural distribution based representation for universal quantum\nmachine learning","volume":"148","author":"Faber","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit24","doi-asserted-by":"publisher","first-page":"3381","DOI":"10.1021\/acs.jctc.8b00298","article-title":"Assessing\nGaussian process regression and permutationally invariant polynomial\napproaches to represent high-dimensional potential energy surfaces","volume":"14","author":"Qu","year":"2018","journal-title":"J. Chem. Theory Comput."},{"key":"2026081807111708400_cit25","doi-asserted-by":"publisher","first-page":"9672","DOI":"10.1039\/C8CP06919K","article-title":"A critical comparison of neural network\npotentials for molecular reaction dynamics with exact permutation\nsymmetry","volume":"21","author":"Li","year":"2019","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2026081807111708400_cit26","doi-asserted-by":"publisher","first-page":"241725","DOI":"10.1063\/1.5024577","article-title":"Comparison of permutationally\ninvariant polynomials, neural networks, and Gaussian approximation\npotentials in representing water interactions through many-body expansions","volume":"148","author":"Nguyen","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit27","doi-asserted-by":"publisher","first-page":"241702","DOI":"10.1063\/1.5003074","article-title":"Neural networks\nvs Gaussian process\nregression for representing potential energy surfaces: A comparative\nstudy of fit quality and vibrational spectrum accuracy","volume":"148","author":"Kamath","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit28","doi-asserted-by":"publisher","first-page":"5120","DOI":"10.1021\/acs.jpclett.0c00989","article-title":"High-Fidelity\nPotential Energy Surfaces for Gas-Phase\nand GasSurface Scattering Processes from Machine Learning","volume":"11","author":"Jiang","year":"2020","journal-title":"J. Phys. Chem. Lett."},{"key":"2026081807111708400_cit29","unstructured":"Gilmer, J.; Schoenholz, S. S.; Riley, P. F.; Vinyals, O.; Dahl, G.\nE.\n          Neural message\npassing for quantum chemistry. Proc. of the 34th Int.\nConf. on Machine Learning, Volume 70; 2017; pp 1263\u20131272."},{"key":"2026081807111708400_cit30","first-page":"5595","article-title":"Automatic differentiation\nin machine learning: a survey","volume":"18","author":"Baydin","year":"2017","journal-title":"J. Mach. Learn.\nRes."},{"key":"2026081807111708400_cit31","unstructured":"Kingma, D. P.; Ba, J.\n          Adam: A method for stochastic\noptimization. 2014, arXiv:1412.6980.\narXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1412.6980."},{"key":"2026081807111708400_cit32","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1090\/S0002-9947-1950-0051437-7","article-title":"Theory of\nreproducing kernels","volume":"68","author":"Aronszajn","year":"1950","journal-title":"Trans. Am. Math. Soc."},{"key":"2026081807111708400_cit33","doi-asserted-by":"publisher","DOI":"10.1063\/1.5126701","article-title":"FCHL revisited:\nFaster and more accurate quantum machine learning","volume":"152","author":"Christensen","year":"2020","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit34","doi-asserted-by":"crossref","unstructured":"Scho\u0308lkopf, B.; Herbrich, R.; Smola, A. J.\n          A Generalized\nRepresenter Theorem. International Conference on Computational\nLearning Theory; 2001; pp 416\u2013426.","DOI":"10.1007\/3-540-44581-1_27"},{"key":"2026081807111708400_cit35","doi-asserted-by":"crossref","DOI":"10.56021\/9781421407944","volume-title":"Matrix Computations","author":"Golub","year":"2012"},{"key":"2026081807111708400_cit36","doi-asserted-by":"publisher","first-page":"4415","DOI":"10.1063\/1.480988","article-title":"On the long-range and short-range\nbehavior of potentials\nfrom reproducing kernel Hilbert space interpolation","volume":"112","author":"Soldan","year":"2000","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit37","doi-asserted-by":"publisher","first-page":"5255","DOI":"10.1021\/acs.jctc.7b00577","article-title":"Prediction errors of molecular machine learning models\nlower than hybrid DFT error","volume":"13","author":"Faber","year":"2017","journal-title":"J. Chem. Theory\nComput."},{"key":"2026081807111708400_cit38","doi-asserted-by":"publisher","first-page":"136403","DOI":"10.1103\/PhysRevLett.104.136403","article-title":"Gaussian Approximation\nPotentials: The Accuracy of Quantum Mechanics, without the Electrons","volume":"104","author":"Barto\u0301k","year":"2010","journal-title":"Phys. Rev. Lett."},{"key":"2026081807111708400_cit39","doi-asserted-by":"crossref","first-page":"2326","DOI":"10.1021\/acs.jpclett.5b00831","article-title":"Interaction potentials in molecules and non-local information\nin chemical space","volume":"6","author":"Hansen","year":"2015","journal-title":"J. Phys. Chem. Lett."},{"key":"2026081807111708400_cit40","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1002\/qua.24927","article-title":"Gaussian approximation\npotentials: A brief tutorial\nintroduction","volume":"115","author":"Barto\u0301k","year":"2015","journal-title":"Int. J. Quantum Chem."},{"key":"2026081807111708400_cit41","volume-title":"Gaussian Processes\nfor Machine Learning","author":"Rasmussen","year":"2006"},{"key":"2026081807111708400_cit42","unstructured":"Mathias, S.\n          \n          A kernel-based\nlearning method for an efficient approximation of the high-dimensional\nBorn-Oppenheimer potential energy surface. M.Sc. Thesis,\nMathematisch-Naturwissenschaftliche Fakulta\u0308t der Rheinischen\nFriedrich-Wilhelms-Universita\u0308t Bonn, Germany, 2015; http:\/\/wissrech.ins.uni-bonn.de\/teaching\/master\/masterthesis_mathias_revised.pdf; accessed February 2020."},{"key":"2026081807111708400_cit43","doi-asserted-by":"publisher","DOI":"10.1063\/1.5053562","article-title":"Operators in quantum machine learning:\nResponse properties in chemical space","volume":"150","author":"Christensen","year":"2019","journal-title":"J. Chem.\nPhys."},{"key":"2026081807111708400_cit44","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1002\/qua.24912","article-title":"Fourier series\nof atomic radial distribution functions: A molecular fingerprint for\nmachine learning models of quantum chemical properties","volume":"115","author":"von\nLilienfeld","year":"2015","journal-title":"Int. J. Quantum Chem."},{"key":"2026081807111708400_cit45","doi-asserted-by":"publisher","first-page":"3219","DOI":"10.1016\/0040-4020(80)80168-2","article-title":"Iterative partial equalization of orbital electronegativity\n\u2013 a rapid access to atomic charges","volume":"36","author":"Gasteiger","year":"1980","journal-title":"Tetrahedron"},{"key":"2026081807111708400_cit46","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/1758-2946-3-33","article-title":"Open Babel:\nAn open chemical toolbox","volume":"3","author":"O\u2019Boyle","year":"2011","journal-title":"J. Cheminf."},{"key":"2026081807111708400_cit47","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1063\/1.456153","article-title":"Gaussian basis\nsets for use in correlated molecular\ncalculations. I. The atoms boron through neon and hydrogen","volume":"90","author":"Dunning","year":"1989","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit48","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1002\/wcms.81","article-title":"The ORCA program\nsystem","volume":"2","author":"Neese","year":"2012","journal-title":"Wiley Interdiscip. Rev.: Comput. Mol.\nSci."},{"key":"2026081807111708400_cit49","doi-asserted-by":"publisher","first-page":"6796","DOI":"10.1063\/1.462569","article-title":"Electron affinities\nof the first-row atoms revisited. Systematic basis sets and wave functions","volume":"96","author":"Kendall","year":"1992","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit50","doi-asserted-by":"publisher","DOI":"10.1063\/1.2831537","article-title":"Systematically convergent basis sets\nfor explicitly correlated wavefunctions: The atoms H, He, B\u2013Ne,\nand Al\u2013Ar","volume":"128","author":"Peterson","year":"2008","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit51","unstructured":"Werner, H.-J.; Knowles, P. J.; Knizia, G.; Manby, F.\nR.; Schu\u0308tz, M.; Celani, P.; Gyo\u0308rffy, W.; Kats, D.; Korona, T.; Lindh, R.\n               ; et al.\n          MOLPRO, version 2019.2, a\npackage of ab initio programs; 2019."},{"key":"2026081807111708400_cit52","doi-asserted-by":"publisher","first-page":"170193","DOI":"10.1038\/sdata.2017.193","article-title":"ANI-1, A data set\nof 20 million calculated\noff-equilibrium conformations for organic molecules","volume":"4","author":"Smith","year":"2017","journal-title":"Sci. Data"},{"key":"2026081807111708400_cit53","doi-asserted-by":"publisher","first-page":"273002","DOI":"10.1088\/1361-648X\/aa680e","article-title":"The atomic simulation environment \u2013 a Python\nlibrary for working with atoms","volume":"29","author":"Hjorth\nLarsen","year":"2017","journal-title":"J. Phys.: Condens.\nMatter"},{"key":"2026081807111708400_cit54","volume-title":"A guide to NumPy","author":"Oliphant","year":"2006"},{"key":"2026081807111708400_cit55","doi-asserted-by":"publisher","first-page":"214304","DOI":"10.1063\/5.0008223","article-title":"Isomerization and decomposition\nreactions\nof acetaldehyde relevant to atmospheric processes from dynamics simulations\non neural network-based potential energy surfaces","volume":"152","author":"Ka\u0308ser","year":"2020","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit56","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/aba184","article-title":"Impact of\nnon-normal error distributions\non the benchmarking and ranking of quantum machine learning models","volume":"1","author":"Pernot","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"2026081807111708400_cit57","doi-asserted-by":"publisher","first-page":"114104","DOI":"10.1063\/1.5020436","article-title":"Analytical energy gradients for explicitly\ncorrelated\nwave functions. II. Explicitly correlated coupled cluster singles\nand doubles with perturbative triples corrections: CCSD\u00ad(T)-F12","volume":"148","author":"Gyorffy","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit58","doi-asserted-by":"publisher","first-page":"1584","DOI":"10.1002\/jcc.20082","article-title":"Empirical\nforce fields for biological macromolecules: Overview and issues","volume":"25","author":"Mackerell","year":"2004","journal-title":"J. Comput. Chem."},{"key":"2026081807111708400_cit59","doi-asserted-by":"publisher","first-page":"1673","DOI":"10.1002\/jcc.22996","article-title":"Atomic multipoles: Electrostatic\npotential fit, local reference axis systems, and conformational dependence","volume":"33","author":"Kramer","year":"2012","journal-title":"J. Comput. Chem."},{"key":"2026081807111708400_cit60","doi-asserted-by":"publisher","first-page":"5450","DOI":"10.1021\/ct400803f","article-title":"Leveraging Symmetries of Static Atomic\nMultipole Electrostatics in Molecular Dynamics Simulations","volume":"9","author":"Bereau","year":"2013","journal-title":"J. Chem. Theory Comput."},{"key":"2026081807111708400_cit61","doi-asserted-by":"publisher","first-page":"24976","DOI":"10.1039\/C9CP05259C","article-title":"Near dissociation states\nfor H2+-He on MRCI and FCI potential energy\nsurfaces","volume":"21","author":"Koner","year":"2019","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2026081807111708400_cit62","doi-asserted-by":"publisher","first-page":"2604","DOI":"10.1021\/acs.jpclett.8b00447","article-title":"IR Spectra of (HCOOH)2 and (DCOOH)2: Experiment, VSCF\/VCI, and ab initio\nmolecular dynamics calculations\nusing full-dimensional potential and dipole moment surfaces","volume":"9","author":"Qu","year":"2018","journal-title":"J. Phys. Chem. Lett."},{"key":"2026081807111708400_cit63","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1039\/C8FD00077H","article-title":"Quantum and classical IR spectra of (HCOOH)2,(DCOOH)2 and (DCOOD)2 using ab initio potential\nenergy and dipole moment surfaces","volume":"212","author":"Qu","year":"2018","journal-title":"Faraday Discuss."},{"key":"2026081807111708400_cit64","doi-asserted-by":"publisher","first-page":"5389","DOI":"10.1021\/acs.jpca.7b02234","article-title":"Vibrational spectroscopy\nand proton transfer dynamics\nin protonated oxalate","volume":"121","author":"Xu","year":"2017","journal-title":"J. Phys. Chem. A"},{"key":"2026081807111708400_cit65","unstructured":"Cortes, C.; Jackel, L. D.; Solla, S. A.; Vapnik, V.; Denker, J. S.\n          Learning curves:\nAsymptotic values and rate of convergence. Advances in Neural Information Processing Systems; 1994; pp 327\u2013334."},{"key":"2026081807111708400_cit66","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1162\/neco.1996.8.5.1085","article-title":"A numerical\nstudy on learning curves in stochastic multilayer feedforward networks","volume":"8","author":"Mu\u0308ller","year":"1996","journal-title":"Neural Comput."},{"key":"2026081807111708400_cit67","unstructured":"Christensen, A. S.; Anatole von Lilienfeld, O.\n          On the role of gradients for machine learning of\nmolecular energies and forces. 2020,\narXiv:2007.09593. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2007.09593"},{"key":"2026081807111708400_cit68","first-page":"1633","article-title":"Transfer learning for\nreinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J.\nMach. Learn. Res."},{"key":"2026081807111708400_cit69","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on\ntransfer learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans.\nKnowl. Data Eng."},{"key":"2026081807111708400_cit70","doi-asserted-by":"publisher","first-page":"2087","DOI":"10.1021\/acs.jctc.5b00099","article-title":"Big Data\nmeets quantum chemistry approximations: The \u0394-machine learning\napproach","volume":"11","author":"Ramakrishnan","year":"2015","journal-title":"J. Chem. Theory Comput."},{"key":"2026081807111708400_cit71","doi-asserted-by":"publisher","first-page":"24906","DOI":"10.1021\/acsami.9b02174","article-title":"Multifidelity\ninformation fusion with machine learning: A case study of dopant formation\nenergies in hafnia","volume":"11","author":"Batra","year":"2019","journal-title":"ACS Appl. Mater. Interfaces"},{"key":"2026081807111708400_cit72","doi-asserted-by":"publisher","first-page":"1546","DOI":"10.1021\/acs.jctc.8b00832","article-title":"Boosting\nquantum machine learning models with a multilevel combination technique:\nPople diagrams revisited","volume":"15","author":"Zaspel","year":"2019","journal-title":"J. Chem. Theory Comput."},{"key":"2026081807111708400_cit73","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/ab81b5","article-title":"Reactive dynamics\nand spectroscopy\nof hydrogen transfer from neural network-based reactive potential\nenergy surfaces","volume":"22","author":"Ka\u0308ser","year":"2020","journal-title":"New J. Phys."},{"key":"2026081807111708400_cit74","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1063\/1.470844","article-title":"Pure vibrational\nspectroscopy of S0 formaldehyde\nby dispersed fluorescence","volume":"104","author":"Bouwens","year":"1996","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit75","doi-asserted-by":"publisher","DOI":"10.1063\/1.5046906","article-title":"The C\u00ad(3P) + NO\u00ad(X2\u03a0) \u2192 O\u00ad(3P) +\nCN\u00ad(X2\u03a3+), N\u00ad(2D)\/N\u00ad(4S) + CO\u00ad(X1\u03a3+) reaction: Rates, branching\nratios, and final states from\n15 to 20000 K","volume":"149","author":"Koner","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2026081807111708400_cit76","doi-asserted-by":"publisher","first-page":"3927","DOI":"10.1039\/C9CP06085E","article-title":"The N\u00ad(4S) + O2(X3\u03a3)\n\u2194 O\u00ad(3P) + NO\u00ad(X2\u03a0) reaction: thermal\nand vibrational relaxation rates for the 2A\u2019, 4A\u2019 and 2A\u201d states","volume":"22","author":"San\nVicente Veliz","year":"2020","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2026081807111708400_cit77","unstructured":"Koner, D.; Veliz, J. C. S. V.; Bemish, R. J.; Meuwly, M.\n          Accurate\nreproducing kernel-based potential energy surfaces for the triplet\nground states of N2O and dynamics for the N+NO\u2194O+N2 and N2+O\u21922N+O reactions. 2020, arXiv:2002.02310. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2002.02310"}],"container-title":["The Journal of Physical Chemistry A"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jpca.0c05979","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jpcafh\/article-pdf\/124\/42\/8853\/13288755\/jp0c05979.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jpcafh\/article-pdf\/124\/42\/8853\/13288755\/jp0c05979.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T11:38:14Z","timestamp":1787053094000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jpcafh\/article\/124\/42\/8853\/1333907\/Machine-Learning-Models-of-Vibrating-H2CO"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,24]]},"references-count":77,"journal-issue":{"issue":"42","published-online":{"date-parts":[[2020,9,24]]},"published-print":{"date-parts":[[2020,10,22]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jpca.0c05979","relation":{},"ISSN":["1089-5639","1520-5215"],"issn-type":[{"value":"1089-5639","type":"print"},{"value":"1520-5215","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,24]]}}}