{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T20:46:58Z","timestamp":1760647618655,"version":"build-2065373602"},"reference-count":62,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2022,5,13]],"date-time":"2022-05-13T00:00:00Z","timestamp":1652400000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computation"],"abstract":"<jats:p>Machine learning approaches can drastically decrease the computational time for the predictions of spectroscopic properties in materials, while preserving the quality of the computational approaches. We studied the performance of kernel-ridge regression (KRR) and gradient boosting regressor (GBR) models trained on the isotropic shielding values, computed with density-functional theory (DFT), in a series of different known zeolites containing out-of-frame metal cations or fluorine anion and organic structure-directing cations. The smooth overlap of atomic position descriptors were computed from the DFT-optimised Cartesian coordinates of each atoms in the zeolite crystal cells. The use of these descriptors as inputs in both machine learning regression methods led to the prediction of the DFT isotropic shielding values with mean errors within 0.6 ppm. The results showed that the GBR model scales better than the KRR model.<\/jats:p>","DOI":"10.3390\/computation10050074","type":"journal-article","created":{"date-parts":[[2022,5,13]],"date-time":"2022-05-13T08:37:02Z","timestamp":1652431022000},"page":"74","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Regression Machine Learning Models Used to Predict DFT-Computed NMR Parameters of Zeolites"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3581-3971","authenticated-orcid":false,"given":"Robin","family":"Gaumard","sequence":"first","affiliation":[{"name":"ICGM, CNRS, ENSCM, Universite de Montpellier, 34296 Montpellier, France"}]},{"given":"Dominik","family":"Drag\u00fan","sequence":"additional","affiliation":[{"name":"FIIT STU in Bratislava, Ilkovi\u010dova 2, 84216 Bratislava, Slovakia"}]},{"given":"Jes\u00fas N.","family":"Pedroza-Montero","sequence":"additional","affiliation":[{"name":"ICGM, CNRS, ENSCM, Universite de Montpellier, 34296 Montpellier, France"}]},{"given":"Bruno","family":"Alonso","sequence":"additional","affiliation":[{"name":"ICGM, CNRS, ENSCM, Universite de Montpellier, 34296 Montpellier, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9369-523X","authenticated-orcid":false,"given":"Hazar","family":"Guesmi","sequence":"additional","affiliation":[{"name":"ICGM, CNRS, ENSCM, Universite de Montpellier, 34296 Montpellier, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2338-1216","authenticated-orcid":false,"given":"Irina","family":"Malkin Ond\u00edk","sequence":"additional","affiliation":[{"name":"FIIT STU in Bratislava, Ilkovi\u010dova 2, 84216 Bratislava, Slovakia"},{"name":"MicroStep-MIS, Spol. S.R.O., \u010cavojsk\u00e9ho 1, 84104 Bratislava, Slovakia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9156-2396","authenticated-orcid":false,"given":"Tzonka","family":"Mineva","sequence":"additional","affiliation":[{"name":"ICGM, CNRS, ENSCM, Universite de Montpellier, 34296 Montpellier, France"}]}],"member":"1968","published-online":{"date-parts":[[2022,5,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1021\/acs.jctc.5b01006","article-title":"Ab Initio Quality NMR Parameters in Solid-State Materials Using a High-Dimensional Neural-Network Representation","volume":"12","author":"Cuny","year":"2016","journal-title":"J. Chem. Theory Comput."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"21709","DOI":"10.1039\/C9CP02803J","article-title":"NMR shifts in aluminosilicate glasses via machine learning","volume":"21","author":"Chaker","year":"2019","journal-title":"Phys. Chem. Chem. Phys."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"4558","DOI":"10.1021\/acs.jpclett.9b01570","article-title":"Multiresolution 3D-DenseNet for Chemical Shift Prediction in NMR Crystallography","volume":"10","author":"Liu","year":"2019","journal-title":"J. Phys. Chem. Lett."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"4501","DOI":"10.1038\/s41467-018-06972-x","article-title":"Chemical shifts in molecular solids by machine learning","volume":"9","author":"Paruzzo","year":"2018","journal-title":"Nat. Commun."},{"key":"ref_5","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","year":"2015","journal-title":"J. Phys. Chem. Lett."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1039\/C9SC03854J","article-title":"IMPRESSION\u2014Prediction of NMR parameters for 3-dimensional chemical structures using machine learning with near quantum chemical accuracy","volume":"11","author":"Gerrard","year":"2020","journal-title":"Chem. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1021\/acs.jctc.0c00979","article-title":"Predicting Density Functional Theory-Quality Nuclear Magnetic Resonance Chemical Shifts via \u0394-Machine Learning","volume":"17","author":"Unzueta","year":"2021","journal-title":"J. Chem. Theory Comput."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2964","DOI":"10.1038\/s41467-021-23208-7","article-title":"Structure determination of an amorphous drug through large-scale NMR predictions","volume":"12","author":"Cordova","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"8820","DOI":"10.1039\/D2CP00361A","article-title":"Thermal fluctuations and conformational effects on NMR parameters in \u03b2-O-4 lignin dimer from QM\/MM and machine learning approaches","volume":"24","author":"Gaumard","year":"2022","journal-title":"Phys. Chem. Chem. Phys."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ssnmr.2011.04.006","article-title":"The PAW\/GIPAW approach for computing NMR parameters: A new dimension added to NMR study of solids","volume":"40","author":"Charpentier","year":"2011","journal-title":"Solid State Nucl. Magn. Reson."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/bs.arnmr.2015.08.002","article-title":"Chapter Three\u2014Recent Advances in 14N Solid-State NMR Annu","volume":"87","author":"Dib","year":"2016","journal-title":"Rep. NMR Spectrosc."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Jonas, E., Kuhn, S., and Schl\u00f6rer, N. Prediction of chemical shift in NMR: A review. Magn. Reson. Chem., 2021. in press.","DOI":"10.1002\/mrc.5234"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1142\/9781860947292_0035","article-title":"Structure based chemical shift prediction usgin random forests non-linear regression","volume":"Volume 3","author":"Arun","year":"2005","journal-title":"Proceedings of the 4th Asia-Pacific Bioinformatics Conference"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/s10858-011-9478-4","article-title":"SHIFTX2: Significantly improved protein chemical shift prediction","volume":"50","author":"Han","year":"2011","journal-title":"J. Biomol. NMR"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3746","DOI":"10.1021\/acs.jcim.0c00388","article-title":"General Protocol for the Accurate Prediction of Molecular 13C\/1H NMR Chemical Shifts via Machine Learning Augmented DFT","volume":"60","author":"Gao","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"9812","DOI":"10.1021\/acs.jpclett.0c02654","article-title":"Toward Accurate Predictions of Atomic Properties via Quantum Mechanics Descriptors Augmented Graph Convolutional Neural Network: Application of This Novel Approach in NMR Chemical Shifts Predictions","volume":"11","author":"Gao","year":"2020","journal-title":"J. Phys. Chem. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1016\/j.chempr.2020.05.014","article-title":"Learning to Make Chemical Predictions: The Interplay of Feature Representation, Data, and Machine Learning Methods","volume":"6","author":"Haghighatlari","year":"2020","journal-title":"Chem"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3180","DOI":"10.1039\/C9SC06561J","article-title":"Accurate prediction of chemical shifts for aqueous protein structure on \u201cReal World\u201d data","volume":"11","author":"Li","year":"2020","journal-title":"Chem. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"035010","DOI":"10.1088\/2632-2153\/abe347","article-title":"Revving up 13C NMR shielding predictions across chemical space: Benchmarks for atoms-in-molecules kernel machine learning with new data for 134 kilo molecules","volume":"2","author":"Gupta","year":"2021","journal-title":"Mach. Learn. Sci. Technol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Gerrard, W., Yiu, C., and Butts, C.P. Prediction of 15N chemical shifts by machine learning. Magn. Reson. Chem., 2021. in press.","DOI":"10.1002\/mrc.5208"},{"key":"ref_21","unstructured":"Beygelzimer, A., Hazan, E., Kale, S., and Luo, H. (2015, January 7\u201312). Online gradient boosting. Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, Montreal, QC, Canada."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1007\/s10994-019-05787-1","article-title":"Accelerated gradient boosting","volume":"108","author":"Biau","year":"2019","journal-title":"Mach. Learn."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"12012","DOI":"10.1039\/D1SC03343C","article-title":"Real-time prediction of 1H and 13C chemical shifts with DFT accuracy using a 3D graph neural network","volume":"12","author":"Guan","year":"2021","journal-title":"Chem. Sci."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1186\/s13321-019-0374-3","article-title":"Rapid prediction of NMR spectral properties with quantified uncertainty","volume":"11","author":"Jonas","year":"2019","journal-title":"J. Cheminform."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"6901","DOI":"10.1021\/acs.analchem.1c00756","article-title":"Improved Prediction of Carbonless NMR Spectra by the Machine Learning of Theoretical and Fragment Descriptors for Environmental Mixture Analysis","volume":"93","author":"Ito","year":"2021","journal-title":"Anal. Chem."},{"key":"ref_26","unstructured":"Baerlocher, C., and McCusker, L. (2022, March 28). Database of Zeolite Structures. Available online: http:\/\/www.iza-structure.org\/databases\/."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1002\/anie.198802261","article-title":"Zeolites: Catalysts for Organic Syntheses","volume":"27","author":"Hesse","year":"1988","journal-title":"Angew. Chem. Int. Ed. Engl."},{"key":"ref_28","unstructured":"Cejka, J., van Bekkum, H., Corma, A., and Schueth, F. (2007). Introduction to Zeolite Molecular Sieves. Introduction to Zeolite Molecular Sieves, John Wiley and Sons. [3rd ed.]. John Wiley and Sons: Hoboken, NJ, USA, 2007."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"7833","DOI":"10.1021\/acs.chemmater.7b02532","article-title":"Predicting the Mechanical Properties of Zeolite Frameworks by Machine Learning","volume":"29","author":"Evans","year":"2017","journal-title":"Chem. Mater."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"9314","DOI":"10.1021\/acs.jpcc.0c00130","article-title":"Zeolite Adsorption Isotherms Predicted by Pore Channel and Local Environmental Descriptors: Feature Learning on DFT Binding Strength","volume":"124","author":"Gu","year":"2020","journal-title":"J. Phys. Chem. C"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"154112","DOI":"10.1063\/1.5119751","article-title":"A new kind of atlas of zeolite building blocks","volume":"151","author":"Helfrecht","year":"2019","journal-title":"J. Chem. Phys."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1007\/s11814-021-0796-2","article-title":"Recent progress on Al distribution over zeolite frameworks: Linking theories and experiments","volume":"38","author":"Kwak","year":"2021","journal-title":"Korean J. Chem. Eng."},{"key":"ref_33","unstructured":"Welling, M. (2022, March 28). Kernel ridge Regression. Available online: https:\/\/web2.qatar.cmu.edu\/~gdicaro\/10315-Fall19\/additional\/welling-notes-on-kernel-ridge.pdf."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2154","DOI":"10.1016\/j.patcog.2006.12.015","article-title":"Fast cross-validation algorithms for least squares support vector machine and kernel ridge regression","volume":"40","author":"An","year":"2007","journal-title":"Pattern Recognit."},{"key":"ref_35","unstructured":"(2022, March 24). ML-CSC-tutorial. Available online: https:\/\/github.com\/fullmetalfelix\/ML-CSC-tutorial."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting","volume":"55","author":"Freund","year":"1997","journal-title":"J. Comput. Syst. Sci."},{"key":"ref_37","unstructured":"Freund, Y., and Schapire, R.E. (August, January 31). A Short Introduction to Boosting. Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence (IJCAI \u201999), Stockholm, Sweden."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Natekin, A., and Knoll, A. (2013). Gradient boosting machines, a tutorial. Front. Neurorobot., 7.","DOI":"10.3389\/fnbot.2013.00021"},{"key":"ref_39","unstructured":"He, Z., Lin, D., Lau, T., and Wu, M. (2019). Gradient Boosting Machine: A Survey. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R., and Friedman, J. (2009). Boosting and Additive Trees. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer.","DOI":"10.1007\/b94608_10"},{"key":"ref_41","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"106949","DOI":"10.1016\/j.cpc.2019.106949","article-title":"DScribe: Library of descriptors for machine learning in materials science","volume":"247","author":"Himanen","year":"2020","journal-title":"Comput. Phys. Commun."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"273002","DOI":"10.1088\/1361-648X\/aa680e","article-title":"The atomic simulation environment\u2014A Python library for working with atoms","volume":"29","author":"Larsen","year":"2017","journal-title":"J. Phys. Condens. Matter"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/5992.998641","article-title":"An object-oriented scripting interface to a legacy electronic structure code","volume":"4","author":"Bahn","year":"2002","journal-title":"Comput. Sci. Eng."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"e1360","DOI":"10.1002\/wcms.1360","article-title":"Quantum-mechanical condensed matter simulations with CRYSTAL","volume":"8","author":"Dovesi","year":"2018","journal-title":"WIRES Comput. Mol. Sci."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"10686","DOI":"10.1063\/1.467882","article-title":"Crystal field effects on thetopological properties of the electron density in molecular crystals: The case of urea","volume":"101","author":"Gatti","year":"1994","journal-title":"J. Chem. Phys."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"14179","DOI":"10.1103\/PhysRevB.49.14179","article-title":"Quantum-mechanical calculation of the solid-state equilibrium MgO + \u03b1-Al2O3 \u21c4 MgAl2O4 (spinel) versus pressure","volume":"49","author":"Catti","year":"1994","journal-title":"Phys. Rev. B"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"154104","DOI":"10.1063\/1.3382344","article-title":"A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu","volume":"132","author":"Grimme","year":"2010","journal-title":"J. Chem. Phys."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"15831","DOI":"10.1021\/acs.jpcc.7b04861","article-title":"Probing Disorder in Al-ZSM-5 Zeolites by 14N NMR Spectroscopy","volume":"121","author":"Dib","year":"2017","journal-title":"J. Phys. Chem. C"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1002\/cphc.201900953","article-title":"Zeolite Structure Direction: Identification, Strength and Involvement of Weak CHO Hydrogen Bonds","volume":"21","author":"Mineva","year":"2020","journal-title":"Chem. Phys. Chem."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"9728","DOI":"10.1002\/slct.202102771","article-title":"Ubiquitous Presence of Intermolecular CHO Hydrogen Bonds in As-synthesized Host-Guest Zeolite Materials","volume":"6","author":"Ata","year":"2021","journal-title":"ChemistrySelect"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"395502","DOI":"10.1088\/0953-8984\/21\/39\/395502","article-title":"QUANTUM ESPRESSO: A modular and open-source software project for quantum simulations of materials","volume":"21","author":"Giannozzi","year":"2009","journal-title":"J. Phys. Condens. Matter"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"465901","DOI":"10.1088\/1361-648X\/aa8f79","article-title":"Advanced capabilities for materials modelling with Quantum ESPRESSO","volume":"29","author":"Giannozzi","year":"2017","journal-title":"J. Phys. Condens. Matter"},{"key":"ref_54","unstructured":"(2022, March 28). Quantum Espresso. Available online: https:\/\/www.quantum-espresso.org."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"245101","DOI":"10.1103\/PhysRevB.63.245101","article-title":"All-electron magnetic response with pseudopotentials: NMR chemical shifts","volume":"63","author":"Pickard","year":"2001","journal-title":"Phys. Rev. B"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"024401","DOI":"10.1103\/PhysRevB.76.024401","article-title":"Calculation of NMR chemical shifts for extended systems using ultrasoft pseudopotentials","volume":"76","author":"Yates","year":"2007","journal-title":"Phys. Rev. B"},{"key":"ref_57","unstructured":"(2022, March 28). Quantum Espresso Pseudopotentials. Available online: http:\/\/www.quantum-espresso.org\/pseudopotentials."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"5188","DOI":"10.1103\/PhysRevB.13.5188","article-title":"Special points for Brillouin-zone integrations","volume":"13","author":"Monkhorst","year":"1976","journal-title":"Phys. Rev. B"},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/0144-2449(86)90009-6","article-title":"Single crystal structure refinement of TPA ZSM-5 zeolite","volume":"6","author":"Chao","year":"1986","journal-title":"Zeolites"},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/S1387-1811(98)00311-4","article-title":"The structure of TPA-ZSM-5 with Si\/Al = 23","volume":"28","author":"Yokomori","year":"1999","journal-title":"Microporous Mesoporous Mater."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1021\/acs.jpclett.7b03050","article-title":"ZSM-5 Zeolite: Complete Al Bond Connectivity and Implications on Structure Formation from Solid-State NMR and Quantum Chemistry Calculations","volume":"9","author":"Dib","year":"2018","journal-title":"J. Phys. Chem. Lett."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1021\/acs.chemmater.1c03721","article-title":"Host\u2013Guest Silicalite-1 Zeolites: Correlated Disorder and Phase Transition Inhibition by a Small Guest Modification","volume":"34","author":"Fabbiani","year":"2022","journal-title":"Chem. Mater."}],"container-title":["Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-3197\/10\/5\/74\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:10:21Z","timestamp":1760137821000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-3197\/10\/5\/74"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,13]]},"references-count":62,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022,5]]}},"alternative-id":["computation10050074"],"URL":"https:\/\/doi.org\/10.3390\/computation10050074","relation":{},"ISSN":["2079-3197"],"issn-type":[{"type":"electronic","value":"2079-3197"}],"subject":[],"published":{"date-parts":[[2022,5,13]]}}}