{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:31:59Z","timestamp":1772137919742,"version":"3.50.1"},"reference-count":29,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T00:00:00Z","timestamp":1749772800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T00:00:00Z","timestamp":1749772800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"DOE","award":["DE-AC36-08GO28308"],"award-info":[{"award-number":["DE-AC36-08GO28308"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Scientific machine learning (ML) is becoming increasingly useful in learning closure models for multi-scale physics problems; however, many ML approaches require a vast array of training data and can struggle with generalization and interpretability. Here, rather than learning an entire closure operator, we adopt an existing reduced-dimension model of the microphysics and learn an optimal re-parameterization of the solver. We demonstrate two approaches for training the reduced dimension closure model (1) an\n                    <jats:italic>a priori<\/jats:italic>\n                    method that optimizes the closure parameterization and the neural network parameters separately and (2) an\n                    <jats:italic>a posteriori<\/jats:italic>\n                    method that simultaneously optimizes both. Using the simulation of biomass pyrolysis as a motivating example, we show that the\n                    <jats:italic>a posteriori<\/jats:italic>\n                    method achieves better target losses and is less dependent on training dataset size for generalizability. We then demonstrate the impact that implementing this reparameterization has at the macroscale, showing improved predictive performance with no modification to the underlying macroscale solvers.\n                  <\/jats:p>","DOI":"10.1088\/2632-2153\/add8de","type":"journal-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T18:54:48Z","timestamp":1747248888000},"page":"025062","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning for reparameterization of multi-scale closures"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8784-6724","authenticated-orcid":true,"given":"Hilary","family":"Egan","sequence":"first","affiliation":[]},{"given":"Meagan","family":"Crowley","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5304-1664","authenticated-orcid":true,"given":"Hariswaran","family":"Sitaraman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8258-8683","authenticated-orcid":true,"given":"Lila","family":"Branchaw","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Ciesielski","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2025,6,13]]},"reference":[{"key":"mlstadd8debib1","doi-asserted-by":"publisher","first-page":"4444","DOI":"10.1007\/s11837-020-04399-8","article-title":"Linking machine learning with multiscale numerics: data-driven discovery of homogenized equations","volume":"72","author":"Arbabi","year":"2020","journal-title":"JOM"},{"key":"mlstadd8debib2","article-title":"Achieving conservation of energy in neural network emulators for climate modeling","author":"Beucler","year":"2019"},{"key":"mlstadd8debib3","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1146\/annurev-fluid-010719-060214","article-title":"Machine learning for fluid mechanics","volume":"52","author":"Brunton","year":"2020","journal-title":"Ann. Rev. Fluid Mech."},{"key":"mlstadd8debib4","article-title":"Equation-free patch scheme for efficient computational homogenisation via self-adjoint coupling","author":"Bunder","year":"2020"},{"key":"mlstadd8debib5","doi-asserted-by":"publisher","first-page":"14382","DOI":"10.1021\/acs.energyfuels.1c02163","article-title":"Bridging scales in bioenergy and catalysis: a review of mesoscale modeling applications, methods and future directions","volume":"35","author":"Ciesielski","year":"2021","journal-title":"Energy Fuels"},{"key":"mlstadd8debib6","author":"Weinan","year":"2011"},{"key":"mlstadd8debib7","doi-asserted-by":"publisher","DOI":"10.1063\/5.0149861","article-title":"Machine learning-assisted multi-scale modeling","volume":"64","author":"Weinan","year":"2023","journal-title":"J. Math. Phys."},{"key":"mlstadd8debib8","doi-asserted-by":"publisher","DOI":"10.1063\/5.0095270","article-title":"Physics-informed neural networks for solving Reynolds-averaged Navier-Stokes equations","volume":"34","author":"Eivazi","year":"2022","journal-title":"Phys. Fluids"},{"key":"mlstadd8debib9","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2020.0351","article-title":"Environmental sustainability of biofuels: a review","volume":"476","author":"Jeswani","year":"2020","journal-title":"Proc. R. Soc. A"},{"key":"mlstadd8debib10","article-title":"Enforcing physical constraints in CNNs through differentiable PDE Layer","author":"Jiang","year":"2020"},{"key":"mlstadd8debib11","doi-asserted-by":"publisher","DOI":"10.1063\/5.0090050","article-title":"Physics-informed data based neural networks for two-dimensional turbulence","volume":"34","author":"Kag","year":"2022","journal-title":"Phys. Fluids"},{"key":"mlstadd8debib12","article-title":"On neural differential equations","author":"Kidger","year":"2022"},{"key":"mlstadd8debib13","article-title":"Equinox: neural networks in JAX via callable PyTrees and filtered transformations","author":"Kidger","year":"2021"},{"key":"mlstadd8debib14","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1023\/B:BITN.0000046811.70614.38","article-title":"Singly diagonally implicit Runge\u2013Kutta methods with an explicit first stage","volume":"44","author":"Kvaern\u00f8","year":"2004","journal-title":"BIT Numer. Math."},{"key":"mlstadd8debib15","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1017\/jfm.2016.615","article-title":"Reynolds averaged turbulence modelling using deep neural networks with embedded invariance","volume":"807","author":"Ling","year":"2016","journal-title":"J. Fluid Mech."},{"key":"mlstadd8debib16","doi-asserted-by":"publisher","DOI":"10.1016\/j.actamat.2021.116980","article-title":"Machine-learning interatomic potentials for materials science","volume":"214","author":"Mishin","year":"2021","journal-title":"Acta Mater."},{"key":"mlstadd8debib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2020.113470","article-title":"Data-driven variational multiscale reduced order models","volume":"373","author":"Mou","year":"2021","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"mlstadd8debib18","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1016\/j.jcp.2015.11.012","article-title":"A paradigm for data-driven predictive modeling using field inversion and machine learning","volume":"305","author":"Parish","year":"2016","journal-title":"J. Comput. Phys."},{"key":"mlstadd8debib19","article-title":"FourCastNet: a global data-driven high-resolution weather model using adaptive fourier neural operators","author":"Pathak","year":"2022"},{"key":"mlstadd8debib20","doi-asserted-by":"publisher","first-page":"2868","DOI":"10.1039\/C9GC00585D","article-title":"Progress in understanding the four dominant intra-particle phenomena of lignocellulose pyrolysis: chemical reactions, heat transfer, mass transfer and phase change","volume":"21","author":"Pecha","year":"2019","journal-title":"Green Chem."},{"key":"mlstadd8debib21","doi-asserted-by":"publisher","first-page":"20131","DOI":"10.1021\/acs.energyfuels.1c02679","article-title":"Impacts of anisotropic porosity on heat transfer and off-gassing during biomass pyrolysis","volume":"35","author":"Pecha","year":"2021","journal-title":"Energy Fuels"},{"key":"mlstadd8debib22","article-title":"Scientific machine learning for closure models in multiscale problems: a review","author":"Sanderse","year":"2024"},{"key":"mlstadd8debib23","doi-asserted-by":"publisher","DOI":"10.1002\/2017GL076101","article-title":"Earth system modeling 2.0: a blueprint for models that learn from observations and targeted high-resolution simulations","volume":"44","author":"Schneider","year":"2017","journal-title":"Geophys. Res. Lett."},{"key":"mlstadd8debib24","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2020.140760","article-title":"Biomass pyrolysis with alkaline-earth-metal additive for co-production of bio-oil and biochar-based soil amendment","volume":"743","author":"Shen","year":"2020","journal-title":"Sci. Total Environ."},{"key":"mlstadd8debib25","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.cherd.2023.07.031","article-title":"A reacting multiphase computational flow model for 2,3-butanediol synthesis in industrial-scale bioreactors","volume":"197","author":"Sitaraman","year":"2023","journal-title":"Chem. Eng. Res. Des."},{"key":"mlstadd8debib26","article-title":"Learned coarse models for efficient turbulence simulation","author":"Stachenfeld","year":"2022"},{"key":"mlstadd8debib27","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1002\/bbb.1974","article-title":"Potential synergies of drop-in biofuel production with further co-processing at oil refineries","volume":"13","author":"van Dyk","year":"2019","journal-title":"Biofuels, Bioproducts Biorefining"},{"key":"mlstadd8debib28","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1038\/162329b0","article-title":"Feret\u2019s statistical diameter as a measure of particle size","volume":"162","author":"Walton","year":"1948","journal-title":"Nature"},{"key":"mlstadd8debib29","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1016\/j.ces.2013.06.017","article-title":"Development of a generalized numerical framework for simulating biomass fast pyrolysis in fluidized-bed reactors","volume":"99","author":"Xiong","year":"2013","journal-title":"Chem. Eng. Sci."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8de","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8de\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8de","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8de\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8de\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8de\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8de\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8de\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T09:06:05Z","timestamp":1749805565000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8de"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,13]]},"references-count":29,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,6,13]]},"published-print":{"date-parts":[[2025,6,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/add8de","relation":{"has-review":[{"id-type":"doi","id":"10.1088\/2632-2153\/ADD8DE\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/ADD8DE\/v2\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/ADD8DE\/v2\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/ADD8DE\/v2\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/ADD8DE\/v1\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/ADD8DE\/v1\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/ADD8DE\/v2\/review1","asserted-by":"object"}]},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,13]]},"assertion":[{"value":"Machine learning for reparameterization of multi-scale closures","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-11-15","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-05-14","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-06-13","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}