{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:46:16Z","timestamp":1753890376047,"version":"3.41.2"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T00:00:00Z","timestamp":1712016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Appl. Math. Stat."],"abstract":"<jats:p>In the last decade, the use of AI in Condensed Matter physics has seen a steep increase in the number of problems tackled and methods employed. A number of distinct Machine Learning approaches have been employed in many different topics; from prediction of material properties to computation of Density Functional Theory potentials and inter-atomic force fields. In many cases, the result is a surrogate model which returns promising predictions but is opaque on the inner mechanisms of its success. On the other hand, the typical practitioner looks for answers that are explainable and provide a clear insight into the mechanisms governing a physical phenomena. In this study, we describe a proposal to use a sophisticated combination of traditional Machine Learning methods to obtain an explainable model that outputs an explicit functional formulation for the material property of interest. We demonstrate the effectiveness of our methodology in deriving a new highly accurate expression for the enthalpy of formation of solid solutions of lanthanide orthophosphates.<\/jats:p>","DOI":"10.3389\/fams.2024.1355726","type":"journal-article","created":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T04:45:44Z","timestamp":1712033144000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Computing formation enthalpies through an explainable machine learning method: the case of lanthanide orthophosphates solid solutions"],"prefix":"10.3389","volume":"10","author":[{"given":"Edoardo","family":"Di Napoli","sequence":"first","affiliation":[]},{"given":"Xinzhe","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Bornhake","sequence":"additional","affiliation":[]},{"given":"Piotr M.","family":"Kowalski","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2024,4,2]]},"reference":[{"volume-title":"Machine Learning for Science: State of the Art and Future Prospects","year":"2001","author":"Mjolsness","key":"B1"},{"volume-title":"Machine Learning in Materials Informatics: Recent Applications and Prospects","year":"2017","author":"Ramprasad","key":"B2"},{"key":"B3","doi-asserted-by":"publisher","first-page":"4428","DOI":"10.1038\/s41467-020-17112-9","article-title":"Identifying domains of applicability of machine learning models for materials science","volume":"11","author":"Sutton","year":"2020","journal-title":"Nat Commun"},{"journal-title":"THE MNIST DATABASE of Handwritten Digits","year":"1998","author":"LeCun","key":"B4"},{"journal-title":"Deepface","year":"2015","author":"Bolme","key":"B5"},{"key":"B6","article-title":"Machine learning that matters","volume-title":"Proceedings of the 29th International Conference on Machine Learning","author":"Wagstaff","year":"2012"},{"key":"B7","doi-asserted-by":"publisher","first-page":"42200","DOI":"10.1109\/ACCESS.2020.2976199","article-title":"Explainable machine learning for scientific insights and discoveries","volume":"8","author":"Roscher","year":"2020","journal-title":"IEEE Access"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2021.3079836","article-title":"informed machine learning - a taxonomy and survey of integrating prior knowledge into learning systems","volume":"35","author":"von Rueden","year":"2021","journal-title":"IEEE Transact Knowl Data Eng"},{"key":"B9","doi-asserted-by":"publisher","first-page":"115104","DOI":"10.1103\/PhysRevB.85.115104","article-title":"Correcting density functional theory for accurate predictions of compound enthalpies of formation: fitted elemental-phase reference energies","volume":"85","author":"Stevanovi\u0107","year":"2012","journal-title":"Phys Rev B"},{"key":"B10","doi-asserted-by":"publisher","first-page":"085142","DOI":"10.1103\/PhysRevB.93.085142","article-title":"Stevanovi\u0107 V. Predicting density functional theory total energies and enthalpies of formation of metal-nonmetal compounds by linear regression","volume":"93","author":"Deml","year":"2016","journal-title":"Phys Rev B"},{"key":"B11","doi-asserted-by":"publisher","first-page":"214102","DOI":"10.1103\/PhysRevB.95.214102","article-title":"Formation enthalpies for transition metal alloys using machine learning","volume":"95","author":"Ubaru","year":"2017","journal-title":"Phys Rev B"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1214\/009053607000000677","article-title":"Kernel methods in machine learning","volume":"36","author":"Hofmann","year":"2008","journal-title":"Ann Stat"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.114.105503","article-title":"Big data of materials science: critical role of the descriptor","author":"Ghiringhelli","year":"2015","journal-title":"Phys Rev Lett"},{"key":"B14","doi-asserted-by":"publisher","first-page":"023017","DOI":"10.1088\/1367-2630\/aa57bf","article-title":"Learning physical descriptors for materials science by compressed sensing","volume":"19","author":"Ghiringhelli","year":"2017","journal-title":"N J Phys"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1137\/0907087","article-title":"Linear inversion of band-limited reflection seismograms","volume":"7","author":"Santosa","year":"1986","journal-title":"SIAM J Sci Stat Comp"},{"key":"B16","doi-asserted-by":"publisher","first-page":"197","DOI":"10.3389\/fchem.2019.00197","article-title":"Rare-earth orthophosphates from atomistic simulations","volume":"7","author":"Ji","year":"2019","journal-title":"Front Chem"},{"key":"B17","doi-asserted-by":"publisher","first-page":"941","DOI":"10.1016\/j.jeurceramsoc.2010.12.019","article-title":"Crystal chemistry of the monazite structure","volume":"31","author":"Clavier","year":"2011","journal-title":"J Eur Ceram Soc"},{"key":"B18","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","author":"Ni","year":"1995","journal-title":"Am Mineral"},{"key":"B19","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1515\/ract-2017-2819","article-title":"New insights into phosphate based materials for the immobilisation of actinides","volume":"105","author":"Neumeier","year":"2017","journal-title":"Radiochim Acta"},{"key":"B20","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1524\/zkri.2013.1597","article-title":"Monazite as a suitable actinide waste form","volume":"228","author":"Schlenz","year":"2013","journal-title":"Z Kristallogr"},{"key":"B21","doi-asserted-by":"publisher","first-page":"673","DOI":"10.2138\/rmg.2002.48.18","article-title":"Phosphates as nuclear waste forms","volume":"48","author":"Ewing","year":"2002","journal-title":"Rev Mineral Geochem"},{"key":"B22","doi-asserted-by":"crossref","DOI":"10.1002\/14356007.a27_001","volume-title":"Thorium and Thorium Compounds","author":"Stoll","year":"2000"},{"volume-title":"Rare Earth Elements","year":"2000","author":"McGill","key":"B23"},{"key":"B24","doi-asserted-by":"publisher","first-page":"481","DOI":"10.2138\/rmg.2000.40.10","article-title":"Solid-solution solubilities and thermodynamics: sulfates, carbonates and halides","volume":"40","author":"Glynn","year":"2000","journal-title":"Rev Mineral Geochem"},{"key":"B25","doi-asserted-by":"publisher","first-page":"47","DOI":"10.2138\/rmg.2009.70.2","article-title":"Thermodynamics of solid solution-aqueous solution systems [review]","volume":"70","author":"Prieto","year":"2009","journal-title":"Rev Mineral Geochem"},{"key":"B26","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/s00269-006-0139-1","article-title":"On the miscibility gap in monazite\u2013xenotime systems","volume":"34","author":"Mogilevsky","year":"2007","journal-title":"Phys Chem Miner"},{"key":"B27","doi-asserted-by":"publisher","first-page":"3498","DOI":"10.1038\/s41467-023-38978-5","article-title":"Low-spin state of Fe in Fe-doped NiOOH electrocatalysts","volume":"14","author":"He","year":"2023","journal-title":"Nat Commun"},{"key":"B28","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.jssc.2014.08.005","article-title":"Ab initio calculation of excess properties of solid solutions","volume":"220","author":"Li","year":"2014","journal-title":"J Solid State Chem"},{"key":"B29","doi-asserted-by":"publisher","first-page":"2623","DOI":"10.1557\/JMR.2001.0361","article-title":"Thermochemistry of rare-earth orthophosphates","volume":"16","author":"Ushakov","year":"2001","journal-title":"J Mater Res"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1002\/jcc.23618","article-title":"Performance of DFT plus U method for prediction of structural and thermodynamic parameters of monazite-type ceramics","volume":"35","author":"Blanca-Romero","year":"2014","journal-title":"J Comput Chem"},{"key":"B31","doi-asserted-by":"publisher","first-page":"791","DOI":"10.2138\/am.2012.3948","article-title":"Density functional calculations of the enthalpies of formation of rare-earth orthophosphates","volume":"97","author":"Rustad","year":"2012","journal-title":"Am Mineral"},{"key":"B32","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.pnucene.2016.07.012","article-title":"DFT + U as a reliable method for efficient ab initio calculations of nuclear materials","volume":"92","author":"Beridze","year":"2016","journal-title":"Prog Nucl Energ"},{"key":"B33","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/j.jct.2006.07.010","article-title":"High-temperature calorimetry of (La(1-x)Ln(x))PO4 solid solutions","volume":"39","author":"Popa","year":"2007","journal-title":"J Chem Thermodyn"},{"key":"B34","doi-asserted-by":"publisher","first-page":"2093","DOI":"10.1016\/j.jeurceramsoc.2016.01.051","article-title":"Relationship between the thermodynamic excess properties of mixing and the elastic moduli in the monazite-type ceramics","volume":"36","author":"Kowalski","year":"2016","journal-title":"J Eur Ceram Soc"},{"key":"B35","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1016\/j.egypro.2017.08.108","article-title":"Large scale simulation of nuclear waste materials","volume":"127","author":"Ji","year":"2017","journal-title":"Energy Proc"},{"volume-title":"The Theory of Transformations in Metals and Alloys: An Advanced Textbook in Physical Metallurgy. 2nd ed.","year":"1975","author":"Christian","key":"B36"},{"key":"B37","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1016\/j.jct.2016.11.003","article-title":"Thermochemistry of La1-xLnxPO4-monazites (Ln=Gd, Eu)","volume":"105","author":"Neumeier","year":"2017","journal-title":"J Chem Thermodyn"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1058","DOI":"10.1002\/qua.24954","article-title":"Machine learning for quantum mechanics in a nutshell","volume":"115","author":"Rupp","year":"2015","journal-title":"Int J Quantum Chem"},{"key":"B39","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1103\/PhysRevLett.65.353","article-title":"Special quasirandom structures","volume":"65","author":"Zunger","year":"1990","journal-title":"Phys Rev Lett"},{"key":"B40","doi-asserted-by":"publisher","first-page":"136406","DOI":"10.1103\/PhysRevLett.100.136406","article-title":"Restoring the density-gradient expansion for exchange in solids and surfaces","volume":"100","author":"Perdew","year":"2008","journal-title":"Phys Rev Lett"},{"key":"B41","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.jnucmat.2017.07.026","article-title":"Heat capacities of xenotime-type ceramics: an accurate ab initio prediction","volume":"494","author":"Ji","year":"2017","journal-title":"J Nucl Mater"},{"key":"B42","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.jnucmat.2015.04.032","article-title":"Heat capacities of lanthanide and actinide monazite-type ceramics","volume":"464","author":"Kowalski","year":"2015","journal-title":"J Nucl Mater"}],"container-title":["Frontiers in Applied Mathematics and Statistics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fams.2024.1355726\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T04:45:50Z","timestamp":1712033150000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fams.2024.1355726\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,2]]},"references-count":42,"alternative-id":["10.3389\/fams.2024.1355726"],"URL":"https:\/\/doi.org\/10.3389\/fams.2024.1355726","relation":{},"ISSN":["2297-4687"],"issn-type":[{"type":"electronic","value":"2297-4687"}],"subject":[],"published":{"date-parts":[[2024,4,2]]},"article-number":"1355726"}}