{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:55:03Z","timestamp":1773107703907,"version":"3.50.1"},"reference-count":37,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T00:00:00Z","timestamp":1705363200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T00:00:00Z","timestamp":1705363200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100019180","name":"HORIZON EUROPE European Research Council","doi-asserted-by":"crossref","award":["101039481"],"award-info":[{"award-number":["101039481"]}],"id":[{"id":"10.13039\/100019180","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Computational modeling is a key resource to gather insight into physical systems in modern scientific research and engineering. While access to large amount of data has fueled the use of machine learning to recover physical models from experiments and increase the accuracy of physical simulations, purely data-driven models have limited generalization and interpretability. To overcome these limitations, we propose a framework that combines symbolic regression (SR) and discrete exterior calculus (DEC) for the automated discovery of physical models starting from experimental data. Since these models consist of mathematical expressions, they are interpretable and amenable to analysis, and the use of a natural, general-purpose discrete mathematical language for physics favors generalization with limited input data. Importantly, DEC provides building blocks for the discrete analog of field theories, which are beyond the state-of-the-art applications of SR to physical problems. Further, we show that DEC allows to implement a strongly-typed SR procedure that guarantees the mathematical consistency of the recovered models and reduces the search space of symbolic expressions. Finally, we prove the effectiveness of our methodology by re-discovering three models of continuum physics from synthetic experimental data: Poisson equation, the Euler\u2019s elastica and the equations of linear elasticity. Thanks to their general-purpose nature, the methods developed in this paper may be applied to diverse contexts of physical modeling.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad1af2","type":"journal-article","created":{"date-parts":[[2024,1,4]],"date-time":"2024-01-04T22:35:31Z","timestamp":1704407731000},"page":"015005","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Discovering interpretable physical models using symbolic regression and discrete exterior calculus"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4060-0620","authenticated-orcid":true,"given":"Simone","family":"Manti","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9807-5451","authenticated-orcid":true,"given":"Alessandro","family":"Lucantonio","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,1,16]]},"reference":[{"key":"mlstad1af2bib1","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1126\/science.1165893","article-title":"Distilling free-form natural laws from experimental data","volume":"324","author":"Schmidt","year":"2009","journal-title":"Science"},{"key":"mlstad1af2bib2","doi-asserted-by":"publisher","first-page":"9943","DOI":"10.1073\/pnas.0609476104","article-title":"Automated reverse engineering of nonlinear dynamical systems","volume":"104","author":"Bongard","year":"2007","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstad1af2bib3","doi-asserted-by":"publisher","first-page":"3932","DOI":"10.1073\/pnas.1517384113","article-title":"Discovering governing equations from data by sparse identification of nonlinear dynamical systems","volume":"113","author":"Brunton","year":"2016","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstad1af2bib4","doi-asserted-by":"publisher","first-page":"eaay2631","DOI":"10.1126\/sciadv.aay2631","article-title":"AI Feynman: a physics-inspired method for symbolic regression","volume":"6","author":"Udrescu","year":"2020","journal-title":"Sci. Adv."},{"key":"mlstad1af2bib5","first-page":"pp 17429","article-title":"Discovering symbolic models from deep learning with inductive biases","volume":"vol 33","author":"Cranmer","year":"2020"},{"key":"mlstad1af2bib6","article-title":"Deep symbolic regression: recovering mathematical expressions from data via risk-seeking policy gradients","author":"Petersen","year":"2019"},{"key":"mlstad1af2bib7","first-page":"pp 936","article-title":"Neural symbolic regression that scales","author":"Biggio","year":"2021"},{"key":"mlstad1af2bib8","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.1602614","article-title":"Data-driven discovery of partial differential equations","volume":"3","author":"Rudy","year":"2017","journal-title":"Sci. Adv."},{"key":"mlstad1af2bib9","doi-asserted-by":"publisher","first-page":"3994","DOI":"10.21105\/joss.03994","article-title":"PySINDy: A comprehensive Python package for robust sparse system identification","volume":"7","author":"Kaptanoglu","year":"2022","journal-title":"Journal of Open Source Software"},{"key":"mlstad1af2bib10","article-title":"Discrete differential geometry: an applied introduction","volume":"vol 7","author":"Grinspun","year":"2006"},{"key":"mlstad1af2bib11","author":"Hirani","year":"2003"},{"key":"mlstad1af2bib12","volume":"vol 10","author":"Tonti","year":"2013"},{"key":"mlstad1af2bib13","doi-asserted-by":"publisher","first-page":"1260","DOI":"10.1016\/j.jcp.2013.08.016","article-title":"Why starting from differential equations for computational physics?","volume":"257","author":"Tonti","year":"2014","journal-title":"J. Comput. Phys."},{"key":"mlstad1af2bib14","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.aei.2007.08.013","article-title":"A codimension-zero approach to discretizing and solving field problems","volume":"22","author":"Milicchio","year":"2008","journal-title":"Adv. Eng. Inform."},{"key":"mlstad1af2bib15","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1109\/TASE.2009.2021342","article-title":"Chain-based representations for solid and physical modeling","volume":"6","author":"DiCarlo","year":"2009","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"mlstad1af2bib16","first-page":"pp 135","article-title":"Discrete physics using metrized chains","author":"DiCarlo","year":"2009"},{"key":"mlstad1af2bib17","article-title":"AI research associate for early-stage scientific discovery","author":"Behandish","year":"2022"},{"key":"mlstad1af2bib18","first-page":"pp 4442","article-title":"Learning equations for extrapolation and control","author":"Sahoo","year":"2018"},{"key":"mlstad1af2bib19","article-title":"Interpretable machine learning for science with PySR and SymbolicRegression.jl","author":"Cranmer","year":"2023"},{"key":"mlstad1af2bib20","volume":"vol 3","author":"Grady","year":"2010"},{"key":"mlstad1af2bib21","author":"Koza","year":"1994"},{"key":"mlstad1af2bib22","author":"O\u2019Neill","year":"2009"},{"key":"mlstad1af2bib23","author":"De Jong","year":"2006"},{"key":"mlstad1af2bib24","article-title":"Discrete Calculus Toolkit library","author":"Lucantonio","year":"2023","unstructured":"Lucantonio A et al 2023 Discrete Calculus Toolkit library (available at: http:\/\/github.com\/alucantonio\/dctkit\/ )"},{"key":"mlstad1af2bib25","article-title":"Alpine library","author":"Lucantonio","year":"2023","unstructured":"Lucantonio A et al 2023 Alpine library (available at: http:\/\/github.com\/alucantonio\/alpine\/ )"},{"key":"mlstad1af2bib26","article-title":"JAX: composable transformations of Python+NumPy programs","author":"Bradbury","year":"2018","unstructured":"Bradbury J et al 2018 JAX: composable transformations of Python+NumPy programs (available at: http:\/\/github.com\/google\/jax )"},{"key":"mlstad1af2bib27","doi-asserted-by":"publisher","first-page":"2338","DOI":"10.21105\/joss.02338","article-title":"A parallel global multiobjective framework for optimization: pagmo","volume":"5","author":"Biscani","year":"2020","journal-title":"J. Open Source Softw."},{"key":"mlstad1af2bib28","first-page":"2171","article-title":"DEAP: Evolutionary algorithms made easy","volume":"13","author":"Fortin","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"mlstad1af2bib29","first-page":"pp 561","author":"Moritz","year":"2018"},{"key":"mlstad1af2bib30","author":"Podio-Guidugli","year":"2019"},{"key":"mlstad1af2bib31","author":"Audoly","year":"2018"},{"key":"mlstad1af2bib32","volume":"vol 158","author":"Gurtin","year":"1981"},{"key":"mlstad1af2bib33","author":"Evans","year":"2010"},{"key":"mlstad1af2bib34","article-title":"Discrete exterior calculus","author":"Desbrun","year":"2005"},{"key":"mlstad1af2bib35","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1002\/nme.2579","article-title":"Gmsh: A 3-D finite element mesh generator with built-in pre-and post-processing facilities","volume":"79","author":"Geuzaine","year":"2009","journal-title":"Int. J. Numer. Methods Eng."},{"key":"mlstad1af2bib36","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/s00454-019-00159-x","article-title":"Convergence of discrete exterior calculus approximations for Poisson problems","volume":"63","author":"Schulz","year":"2020","journal-title":"Discr. Comput. Geom."},{"key":"mlstad1af2bib37","author":"Frankel","year":"2011"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1af2","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1af2\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1af2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1af2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1af2\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1af2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1af2\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1af2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T09:19:31Z","timestamp":1705396771000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1af2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,16]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1,16]]},"published-print":{"date-parts":[[2024,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad1af2","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,16]]},"assertion":[{"value":"Discovering interpretable physical models using symbolic regression and discrete exterior calculus","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 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-10-10","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-01-03","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-01-16","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}