{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T20:25:53Z","timestamp":1783628753644,"version":"3.55.0"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000146","name":"National Science Foundation Division of Chemical Bioengineering Environmental and Transport Systems","doi-asserted-by":"publisher","award":["2154446"],"award-info":[{"award-number":["2154446"]}],"id":[{"id":"10.13039\/100000146","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Physics Communications"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.cpc.2026.110276","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T16:14:25Z","timestamp":1781626465000},"page":"110276","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Neural network preconditioning of linear tabulation methods for fast function approximation"],"prefix":"10.1016","volume":"327","author":[{"given":"Pavel P.","family":"Popov","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jay M.","family":"Arcities","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaku E.","family":"Eduku","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cpc.2026.110276_bib0001","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1080\/713665229","article-title":"Computationally efficient implementation of combustion chemistry using in situ adaptive tabulation","volume":"1","author":"Pope","year":"1997","journal-title":"Combust. Theory Model."},{"key":"10.1016\/j.cpc.2026.110276_bib0002","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/S0010-2180(97)00278-2","article-title":"A consistent flamelet formulation of non-premixed combustion considering differential diffusion effects","volume":"114","author":"Pitsch","year":"1998","journal-title":"Combust. Flame"},{"key":"10.1016\/j.cpc.2026.110276_bib0003","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1016\/0010-2180(95)00250-2","article-title":"Artificial neural network implementation of chemistry with PDF simulation of H2\/CO2 flames","volume":"106","author":"Christo","year":"1996","journal-title":"Combust. Flame"},{"key":"10.1016\/j.cpc.2026.110276_bib0004","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1002\/ijch.199900010","article-title":"PRISM: piecewise reusable implementation of solution mapping. an economical strategy for chemical kinetics","volume":"39","author":"Tonse","year":"1999","journal-title":"Isr. J. Chem."},{"issue":"2","key":"10.1016\/j.cpc.2026.110276_bib0005","doi-asserted-by":"crossref","first-page":"621","DOI":"10.2514\/1.J059721","article-title":"Neural network flame closure for a turbulent combustor with unsteady pressure","volume":"59","author":"Shadram","year":"2021","journal-title":"AIAA J."},{"key":"10.1016\/j.cpc.2026.110276_bib0006","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1177\/1468087419837770","article-title":"Application of deep artificial neural networks to multi-dimensional flamelet libraries and spray flames","volume":"21","author":"Owoyele","year":"2020","journal-title":"Int. J. Engine Res."},{"key":"10.1016\/j.cpc.2026.110276_bib0007","doi-asserted-by":"crossref","first-page":"3514","DOI":"10.2514\/1.J058247","article-title":"Improved methods of laminar flamelet model for compressible flow","volume":"58","author":"Yamamoto","year":"2020","journal-title":"AIAA J."},{"key":"10.1016\/j.cpc.2026.110276_bib0008","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.combustflame.2017.07.014","article-title":"Tabulation of combustion chemistry via artificial neural networks (ANNs): methodology and application to LES-PDF simulation of Sydney flame L","volume":"185","author":"Franke","year":"2017","journal-title":"Combust. Flame"},{"issue":"7","key":"10.1016\/j.cpc.2026.110276_bib0009","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1080\/00102202.2019.1686702","article-title":"An efficient machine-learning approach for PDF tabulation in turbulent combustion closure","volume":"193","author":"Ranade","year":"2021","journal-title":"Combust. Sci. Technol."},{"key":"10.1016\/j.cpc.2026.110276_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.combustflame.2021.111493","article-title":"Machine learning tabulation of thermochemistry in turbulent combustion: an approach based on hybrid flamelet\/random data and multiple multilayer perceptrons","volume":"231","author":"Ding","year":"2021","journal-title":"Combust. Flame"},{"key":"10.1016\/j.cpc.2026.110276_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.combustflame.2025.114130","article-title":"An improved machine learning method for thermochemistry tabulation, with application to LES-PDF simulations of piloted diffusion and swirl-bluff-body stabilised flames with NOx formation","volume":"277","author":"Ding","year":"2025","journal-title":"Combust. Flame"},{"issue":"4","key":"10.1016\/j.cpc.2026.110276_bib0012","doi-asserted-by":"crossref","DOI":"10.1063\/5.0143894","article-title":"On the incorporation of conservation laws in machine learning tabulation of kinetics for reacting flow simulation","volume":"35","author":"Readshaw","year":"2023","journal-title":"Phys. Fluids"},{"key":"10.1016\/j.cpc.2026.110276_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.combustflame.2022.112425","article-title":"Criteria to switch from tabulation to neural networks in computational combustion","volume":"246","author":"Nikolaou","year":"2022","journal-title":"Combust. Flame"},{"key":"10.1016\/j.cpc.2026.110276_bib0014","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1017\/S0022112004008213","article-title":"Progress-variable approach for large-eddy simulation of non-premixed turbulent combustion","volume":"504","author":"Pierce","year":"2004","journal-title":"J. Fluid Mech."},{"key":"10.1016\/j.cpc.2026.110276_bib0015","doi-asserted-by":"crossref","first-page":"2113","DOI":"10.1016\/j.combustflame.2011.04.010","article-title":"Combined dimension reduction and tabulation strategy using ISAT-RCCE-GALI for the efficient implementation of combustion chemistry","volume":"158","author":"Hiremath","year":"2011","journal-title":"Combust. Flame"},{"key":"10.1016\/j.cpc.2026.110276_bib0016","doi-asserted-by":"crossref","first-page":"3100","DOI":"10.1016\/j.combustflame.2014.05.018","article-title":"Large eddy simulation\/probability density function simulations of bluff-body stabilized flames","volume":"161","author":"Popov","year":"2014","journal-title":"Combust. Flame"},{"issue":"2","key":"10.1016\/j.cpc.2026.110276_bib0017","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1016\/j.proci.2020.06.207","article-title":"In-situ adaptive manifolds: enabling computationally efficient simulations of complex turbulent reacting flows","volume":"38","author":"Lacey","year":"2021","journal-title":"Proc. Combust. Inst."},{"issue":"2","key":"10.1016\/j.cpc.2026.110276_bib0018","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/j.jcp.2008.09.015","article-title":"An improved algorithm for in situ adaptive tabulation","volume":"228","author":"Lu","year":"2009","journal-title":"J. Comput. Phys."},{"issue":"4","key":"10.1016\/j.cpc.2026.110276_bib0019","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1080\/00102202.2016.1229312","article-title":"Toward efficient chemistry calculations in engine simulations through static adaptive acceleration","volume":"189","author":"Wei","year":"2017","journal-title":"Combust. Sci. Technol."},{"issue":"1-2","key":"10.1016\/j.cpc.2026.110276_bib0020","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/S0010-2180(97)81759-2","article-title":"Treating chemistry in combustion with detailed mechanisms\u2014in situ adaptive tabulation in principal directions\u2014premixed combustion","volume":"112","author":"Yang","year":"1998","journal-title":"Combust. Flame"},{"issue":"1","key":"10.1016\/j.cpc.2026.110276_bib0021","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/S0082-0784(00)80204-0","article-title":"Probability density function calculations of local extinction and NO production in piloted-jet turbulent methane\/air flames","volume":"28","author":"Tang","year":"2000","journal-title":"Proc. Combust. Inst."},{"key":"10.1016\/j.cpc.2026.110276_bib0022","doi-asserted-by":"crossref","first-page":"1021","DOI":"10.1080\/13647830.2019.1606453","article-title":"A combined PPAC-RCCE-ISAT methodology for efficient implementation of combustion chemistry","volume":"23","author":"Newale","year":"2019","journal-title":"Combust. Theory Model."},{"key":"10.1016\/j.cpc.2026.110276_bib0023","series-title":"6th US National Combustion Meeting","first-page":"17","article-title":"Dimension reduction and tabulation of combustion chemistry using ICE-PIC and ISAT","author":"Ren","year":"2009"},{"key":"10.1016\/j.cpc.2026.110276_bib0024","article-title":"Sobolev training for neural networks","volume":"30","author":"Czarnecki","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cpc.2026.110276_bib0025","unstructured":"H. Son, J.W. Jang, W.J. Han, H.J. Hwang, Sobolev training for physics informed neural networks, (2021) arXiv: 2101.08932."},{"issue":"2","key":"10.1016\/j.cpc.2026.110276_bib0026","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/0893-6080(91)90009-T","article-title":"Approximation capabilities of multilayer feedforward networks","volume":"4","author":"Hornik","year":"1991","journal-title":"Neural Netw."},{"issue":"2","key":"10.1016\/j.cpc.2026.110276_bib0027","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least squares quantization in PCM","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE Trans. Inf. Theory"},{"key":"10.1016\/j.cpc.2026.110276_bib0028","unstructured":"Preconditioning for Linear Tabulation, accessed July 7, 2025. https:\/\/github.com\/popovSDSU\/PreconditioningTabulation."},{"key":"10.1016\/j.cpc.2026.110276_bib0029","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","article-title":"Sigmoid-weighted linear units for neural network function approximation in reinforcement learning","volume":"107","author":"Elfwing","year":"2018","journal-title":"Neural Netw."},{"key":"10.1016\/j.cpc.2026.110276_bib0030","unstructured":"D. Hendrycks, K. Gimpel, Gaussian error linear units (GELUs), (2016) arXiv: 1606.08415."},{"key":"10.1016\/j.cpc.2026.110276_bib0031","doi-asserted-by":"crossref","unstructured":"D. Misra, Mish: a self regularized non-monotonic activation function,(2019) arXiv: 1908.08681.","DOI":"10.5244\/C.34.191"},{"key":"10.1016\/j.cpc.2026.110276_bib0032","unstructured":"PyTorch: from research to production, (accessed September 20, 2021). https:\/\/pytorch.org\/."},{"key":"10.1016\/j.cpc.2026.110276_bib0033","unstructured":"D.P. Kingma, J. Ba, Adam: a method for stochastic optimization,(2014) arXiv: 1412.6980."},{"issue":"11","key":"10.1016\/j.cpc.2026.110276_bib0034","doi-asserted-by":"crossref","first-page":"2113","DOI":"10.1016\/j.combustflame.2011.04.010","article-title":"Combined dimension reduction and tabulation strategy using ISAT\u2013RCCE\u2013GALI for the efficient implementation of combustion chemistry","volume":"158","author":"Hiremath","year":"2011","journal-title":"Combust. Flame"},{"issue":"5","key":"10.1016\/j.cpc.2026.110276_bib0035","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1080\/13647830.2010.499964","article-title":"A greedy algorithm for species selection in dimension reduction of combustion chemistry","volume":"14","author":"Hiremath","year":"2010","journal-title":"Combust. Theory Model."},{"key":"10.1016\/j.cpc.2026.110276_bib0036","unstructured":"G.P. Smith, D.M. Golden, M. Frenklach, N.W. Moriarty, B. Eiteneer, M. Goldenberg, C.T. Bowman, R.K. Hanson, S. Song, W.C. Gardiner, V.V. Lissianski, Z. Qin, GRI-3.0 chemical mechanism, 2021 (accessed Sep 20, 2021). http:\/\/combustion.berkeley.edu\/gri-mech\/releases.html."},{"key":"10.1016\/j.cpc.2026.110276_bib0037","unstructured":"Cantera Custom Reactor, 2025 (accessed 06\/07\/2025). https:\/\/cantera.org\/3.1\/examples\/cxx\/custom.html."},{"key":"10.1016\/j.cpc.2026.110276_bib0038","unstructured":"P. Ramachandran, B. Zoph, Q.V. Le, Searching for activation functions, (2017) arXiv: 1710.05941."}],"container-title":["Computer Physics Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010465526002584?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010465526002584?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T20:00:53Z","timestamp":1783627253000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0010465526002584"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":38,"alternative-id":["S0010465526002584"],"URL":"https:\/\/doi.org\/10.1016\/j.cpc.2026.110276","relation":{},"ISSN":["0010-4655"],"issn-type":[{"value":"0010-4655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Neural network preconditioning of linear tabulation methods for fast function approximation","name":"articletitle","label":"Article Title"},{"value":"Computer Physics Communications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cpc.2026.110276","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"110276"}}