{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T17:38:46Z","timestamp":1777138726115,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T00:00:00Z","timestamp":1750032000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T00:00:00Z","timestamp":1750032000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001405","name":"Tata Institute of Fundamental Research","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001405","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The Gibbs free energy of an inorganic material represents its maximum reversible work potential under constant temperature and pressure. Its calculation is crucial for understanding material stability, phase transitions, and chemical reactions, thus guiding optimization for diverse applications like catalysis and energy storage. In this study, we have developed a Physics-Informed Neural Network model that leverages the Gibbs free energy equation. The overall loss function is adjusted to allow the model to simultaneously predict all three thermodynamic quantities, including Gibbs free energy, total energy, and entropy, thus transforming it into a multi-output model. In recent literature, there is a growing emphasis on evaluating machine learning models under challenging conditions, such as small datasets and out-of-distribution predictions. Reflecting this trend, we have rigorously benchmarked our model across these scenarios, demonstrating its robustness and adaptability. It turns out that our model demonstrates a 43% improvement for normal scenario and even more in out-of-distribution regime compared to the next-best model. <\/jats:p>\n          <jats:p>\n            <jats:bold>Scientific Contribution<\/jats:bold> This study introduces the application of a Physics-Informed Neural Network to simultaneously compute multiple thermodynamic properties, including Gibbs free energy, total energy, and entropy. By integrating the Gibbs free energy equation into the loss function, the model achieves superior accuracy in low data regimes and enhances robustness in the out-of-distribution scenarios.<\/jats:p>","DOI":"10.1186\/s13321-025-01033-0","type":"journal-article","created":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T06:38:54Z","timestamp":1750055934000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Advancements in thermochemical predictions: a multi-output thermodynamics-informed neural network approach"],"prefix":"10.1186","volume":"17","author":[{"given":"Raheel","family":"Hammad","sequence":"first","affiliation":[]},{"given":"Sownyak","family":"Mondal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,16]]},"reference":[{"key":"1033_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccr.2022.214956","volume":"478","author":"K Bhunia","year":"2023","unstructured":"Bhunia K, Chandra M, Sharma SK, Pradhan D, Kim S-J (2023) A critical review on transition metal phosphide based catalyst for electrochemical hydrogen evolution reaction: Gibbs free energy, composition, stability, and true identity of active site. Coord Chem Rev 478:214956","journal-title":"Coord Chem Rev"},{"key":"1033_CR2","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1016\/j.actamat.2020.08.008","volume":"200","author":"Z-K Liu","year":"2020","unstructured":"Liu Z-K (2020) Computational thermodynamics and its applications. Acta Mater 200:745\u2013792","journal-title":"Acta Mater"},{"key":"1033_CR3","first-page":"4","volume":"6","author":"EM Carson","year":"2002","unstructured":"Carson EM, Watson JR (2002) Undergraduate students\u00e2\u20ac\u2122 understandings of entropy and Gibbs free energy. Univ Chem Educ 6:4\u201312","journal-title":"Univ Chem Educ"},{"key":"1033_CR4","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.calphad.2016.05.002","volume":"54","author":"C Bale","year":"2016","unstructured":"Bale C et al (2016) FactSage thermochemical software and databases, 2010\u20132016. Calphad 54:35\u201353","journal-title":"Calphad"},{"key":"1033_CR5","volume":"23","author":"EW Lemmon","year":"2002","unstructured":"Lemmon EW, Huber ML, McLinden MO (2002) NIST reference fluid thermodynamic and transport properties-REFPROP. NIST Standard Ref datab 23:v7","journal-title":"NIST Standard Ref datab"},{"key":"1033_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S0033583511000096","volume":"45","author":"J Wereszczynski","year":"2012","unstructured":"Wereszczynski J, McCammon JA (2012) Statistical mechanics and molecular dynamics in evaluating thermodynamic properties of biomolecular recognition. Q Rev Biophys 45:1\u201325","journal-title":"Q Rev Biophys"},{"key":"1033_CR7","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1021\/ci050268f","volume":"46","author":"M Clark","year":"2006","unstructured":"Clark M, Guarnieri F, Shkurko I, Wiseman J (2006) Grand canonical Monte Carlo simulation of ligand\u2013protein binding. J Chem Inf Model 46:231\u2013242","journal-title":"J Chem Inf Model"},{"key":"1033_CR8","doi-asserted-by":"publisher","first-page":"19062","DOI":"10.1039\/D2NJ03515D","volume":"46","author":"R Singh","year":"2022","unstructured":"Singh R, Kumar P, Devi M, Lal S, Kumar A, Sindhu J, Toropova AP, Toropov AA, Singh D (2022) Monte Carlo based QSGFEAR: prediction of Gibb\u2019s free energy of activation at different temperatures using SMILES based descriptors. New J Chem 46:19062\u201319072","journal-title":"New J Chem"},{"key":"1033_CR9","doi-asserted-by":"publisher","first-page":"5876","DOI":"10.1063\/1.455539","volume":"89","author":"T Straatsma","year":"1988","unstructured":"Straatsma T, Berendsen H (1988) Free energy of ionic hydration: analysis of a thermodynamic integration technique to evaluate free energy differences by molecular dynamics simulations. J Chem Phys 89:5876\u20135886","journal-title":"J Chem Phys"},{"key":"1033_CR10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.97.054102","volume":"97","author":"B Cheng","year":"2018","unstructured":"Cheng B, Ceriotti M (2018) Computing the absolute Gibbs free energy in atomistic simulations: applications to defects in solids. Phys Rev B 97:054102","journal-title":"Phys Rev B"},{"key":"1033_CR11","doi-asserted-by":"publisher","first-page":"2000112","DOI":"10.1002\/adts.202000112","volume":"3","author":"G Sai Gautam","year":"2020","unstructured":"Sai Gautam G, Stechel EB, Carter EA (2020) A first-principles-based sub-lattice formalism for predicting off-stoichiometry in materials for solar thermochemical applications: the example of ceria. Adv Theory Simul 3:2000112","journal-title":"Adv Theory Simul"},{"key":"1033_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.actamat.2024.119995","volume":"274","author":"YL M\u00fcller","year":"2024","unstructured":"M\u00fcller YL, Natarajan AR (2024) First-principles thermodynamics of precipitation in aluminum-containing refractory alloys. Acta Mater 274:119995","journal-title":"Acta Mater"},{"key":"1033_CR13","doi-asserted-by":"publisher","first-page":"2423","DOI":"10.1021\/jp112240d","volume":"115","author":"A Michalkova","year":"2011","unstructured":"Michalkova A, Gorb L, Hill F, Leszczynski J (2011) Can the Gibbs free energy of adsorption be predicted efficiently and accurately: an M05\u20132X DFT study. J Phys Chem A 115:2423\u20132430","journal-title":"J Phys Chem A"},{"key":"1033_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.scriptamat.2015.07.021","volume":"108","author":"A Togo","year":"2015","unstructured":"Togo A, Tanaka I (2015) First principles phonon calculations in materials science. Scr Mater 108:1\u20135","journal-title":"Scr Mater"},{"key":"1033_CR15","doi-asserted-by":"publisher","DOI":"10.7566\/JPSJ.92.012001","volume":"92","author":"A Togo","year":"2023","unstructured":"Togo A (2023) First-principles phonon calculations with phonopy and phono3py. J Phys Soc Jpn 92:012001","journal-title":"J Phys Soc Jpn"},{"key":"1033_CR16","doi-asserted-by":"publisher","first-page":"3432","DOI":"10.1021\/acs.jctc.7b00314","volume":"13","author":"MA Caro","year":"2017","unstructured":"Caro MA, Lopez-Acevedo O, Laurila T (2017) Redox potentials from ab initio molecular dynamics and explicit entropy calculations: application to transition metals in aqueous solution. J Chem Theory Comput 13:3432\u20133441","journal-title":"J Chem Theory Comput"},{"key":"1033_CR17","doi-asserted-by":"publisher","first-page":"2104113","DOI":"10.1002\/adma.202104113","volume":"34","author":"Z Wang","year":"2022","unstructured":"Wang Z, Sun Z, Yin H, Liu X, Wang J, Zhao H, Pang CH, Wu T, Li S, Yin Z (2022) Data-driven materials innovation and applications. Adv Mater 34:2104113","journal-title":"Adv Mater"},{"key":"1033_CR18","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1021\/acsomega.3c08861","volume":"9","author":"R Hammad","year":"2023","unstructured":"Hammad R, Mondal S (2023) Predicting Poisson\u00e2\u20ac\u2122s ratio: a study of semisupervised anomaly detection and supervised approaches. ACS Omega 9:1956\u20131961","journal-title":"ACS Omega"},{"issue":"31","key":"1033_CR19","doi-asserted-by":"publisher","first-page":"41145","DOI":"10.1021\/acsami.4c07328","volume":"16","author":"A Ibrahim","year":"2024","unstructured":"Ibrahim A, Ataca C (2024) Prediction of frequency-dependent optical spectrum for solid materials: a multioutput and multifidelity machine learning approach. ACS Appl Mater Interfaces 16(31):41145\u201356","journal-title":"ACS Appl Mater Interfaces"},{"key":"1033_CR20","doi-asserted-by":"crossref","unstructured":"Yang J, Manganaris P, Mannodi-Kanakkithodi A (2024) Discovering novel halide perovskite alloys using multi-fidelity machine learning and genetic algorithm. J Chem Phys 160","DOI":"10.1063\/5.0182543"},{"key":"1033_CR21","unstructured":"Kov\u00e1cs, DP, Moore JH, Browning NJ, Batatia I, Horton JT, Kapil V, Magd\u0103u I-B, Cole DJ, Cs\u00e1nyi G (2023) MACE-OFF23: Transferable machine learning force fields for organic molecules. arXiv preprint arXiv:2312.15211"},{"key":"1033_CR22","doi-asserted-by":"publisher","first-page":"6220","DOI":"10.1021\/acs.chemmater.7b00789","volume":"29","author":"F Legrain","year":"2017","unstructured":"Legrain F, Carrete J, van Roekeghem A, Curtarolo S, Mingo N (2017) How chemical composition alone can predict vibrational free energies and entropies of solids. Chem Mater 29:6220\u20136227","journal-title":"Chem Mater"},{"key":"1033_CR23","doi-asserted-by":"publisher","first-page":"4168","DOI":"10.1038\/s41467-018-06682-4","volume":"9","author":"CJ Bartel","year":"2018","unstructured":"Bartel CJ, Millican SL, Deml AM, Rumptz JR, Tumas W, Weimer AW, Lany S, Stevanovi\u0107 V, Musgrave CB, Holder AM (2018) Physical descriptor for the Gibbs energy of inorganic crystalline solids and temperature-dependent materials chemistry. Nat Commun 9:4168","journal-title":"Nat Commun"},{"key":"1033_CR24","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1007\/s11669-022-01010-2","volume":"43","author":"P Laiu","year":"2022","unstructured":"Laiu P, Yang Y, Lupo Pasini M, Choi JY, Shin D (2022) A neural network approach to predict Gibbs free energy of ternary solid solutions. J Phase Equilib Diffus 43:916\u2013930","journal-title":"J Phase Equilib Diffus"},{"key":"1033_CR25","doi-asserted-by":"crossref","unstructured":"Xu P, Ji X, Li M, Lu W (2023) Small data machine learning in materials science. npj Comput Mater 9(42)","DOI":"10.1038\/s41524-023-01000-z"},{"key":"1033_CR26","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1038\/s42254-021-00314-5","volume":"3","author":"GE Karniadakis","year":"2021","unstructured":"Karniadakis GE, Kevrekidis IG, Lu L, Perdikaris P, Wang S, Yang L (2021) Physics-informed machine learning. Nat Rev Phys 3:422\u2013440","journal-title":"Nat Rev Phys"},{"key":"1033_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2023.112740","volume":"233","author":"A Ghosh","year":"2024","unstructured":"Ghosh A (2024) Towards physics-informed explainable machine learning and causal models for materials research. Comput Mater Sci 233:112740","journal-title":"Comput Mater Sci"},{"key":"1033_CR28","doi-asserted-by":"crossref","unstructured":"Zhang E, Dao M, Karniadakis GE, Suresh S (2022) Analyses of internal structures and defects in materials using physics-informed neural networks Sci Adv 8(7):eabk0644","DOI":"10.1126\/sciadv.abk0644"},{"issue":"44","key":"1033_CR29","doi-asserted-by":"publisher","first-page":"18504","DOI":"10.1039\/D4SC04554H","volume":"15","author":"JG Rittig","year":"2024","unstructured":"Rittig JG, Mitsos A (2024) Thermodynamics-consistent graph neural networks. Chem Sci 15(44):18504\u201312","journal-title":"Chem Sci"},{"key":"1033_CR30","doi-asserted-by":"publisher","first-page":"1752","DOI":"10.1039\/D3DD00103B","volume":"2","author":"JG Rittig","year":"2023","unstructured":"Rittig JG, Felton KC, Lapkin AA, Mitsos A (2023) Gibbs\u2013Duhem-informed neural networks for binary activity coefficient prediction. Digit Discov 2:1752\u20131767","journal-title":"Digit Discov"},{"key":"1033_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cej.2024.149863","volume":"485","author":"T Kircher","year":"2024","unstructured":"Kircher T, D\u00f6ppel FA, Votsmeier M (2024) Global reaction neural networks with embedded stoichiometry and thermodynamics for learning kinetics from reactor data. Chem Eng J 485:149863","journal-title":"Chem Eng J"},{"key":"1033_CR32","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1021\/acscentsci.2c01123","volume":"9","author":"G Bradford","year":"2023","unstructured":"Bradford G, Lopez J, Ruza J, Stolberg MA, Osterude R, Johnson JA, Gomez-Bombarelli R, Shao-Horn Y (2023) Chemistry-informed machine learning for polymer electrolyte discovery. ACS Cent Sci 9:206\u2013216","journal-title":"ACS Cent Sci"},{"key":"1033_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.scriptamat.2021.114217","volume":"207","author":"P-W Guan","year":"2022","unstructured":"Guan P-W (2022) Differentiable thermodynamic modeling. Scr Mater 207:114217","journal-title":"Scr Mater"},{"key":"1033_CR34","unstructured":"Chase MW (1998) NIST-JANAF Thermochemical Tables. 4th ed. J Phys Chem Ref Data, pp 1529\u20131564"},{"key":"1033_CR35","doi-asserted-by":"crossref","unstructured":"Jain A, Ong SP, Hautier G, Chen W, Richards W, Dacek S, Cholia S, Gunter D, Skinner D, Ceder G (2013) Commentary: The Materials Project: A materials genome approach to accelerating materials innovation. APL Mater 1:011002","DOI":"10.1063\/1.4812323"},{"key":"1033_CR36","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.145301","volume":"120","author":"T Xie","year":"2018","unstructured":"Xie T, Grossman JC (2018) Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys Rev Lett 120:145301","journal-title":"Phys Rev Lett"},{"key":"1033_CR37","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML-10), pp 807\u2013814"},{"key":"1033_CR38","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"key":"1033_CR39","doi-asserted-by":"publisher","first-page":"3564","DOI":"10.1021\/acs.chemmater.9b01294","volume":"31","author":"C Chen","year":"2019","unstructured":"Chen C, Ye W, Zuo Y, Zheng C, Ong SP (2019) Graph networks as a universal machine learning framework for molecules and crystals. Chem Mater 31:3564\u20133572","journal-title":"Chem Mater"},{"issue":"1","key":"1033_CR40","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1038\/s41524-021-00552-2","volume":"7","author":"P-P De Breuck","year":"2021","unstructured":"De Breuck P-P, Hautier G, Rignanese G-M (2021) Materials property prediction for limited datasets enabled by feature selection and joint learning with MODNet. NPJ Comput Mater 7(1):83","journal-title":"NPJ Comput Mater"},{"key":"1033_CR41","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1038\/s41524-021-00545-1","volume":"7","author":"AY-T Wang","year":"2021","unstructured":"Wang AY-T, Kauwe SK, Murdock RJ, Sparks TD (2021) Compositionally restricted attention-based network for materials property predictions. NPJ Comput Mater 7:77","journal-title":"NPJ Comput Mater"}],"updated-by":[{"DOI":"10.1186\/s13321-025-01046-9","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000}}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01033-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-025-01033-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01033-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T19:43:40Z","timestamp":1757187820000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-025-01033-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,16]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1033"],"URL":"https:\/\/doi.org\/10.1186\/s13321-025-01033-0","relation":{"correction":[{"id-type":"doi","id":"10.1186\/s13321-025-01046-9","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,16]]},"assertion":[{"value":"3 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1186\/s13321-025-01046-9","URL":"https:\/\/doi.org\/10.1186\/s13321-025-01046-9","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"95"}}