000108295 001__ 108295 000108295 005__ 20230519145348.0 000108295 0247_ $$2doi$$a10.1016/j.jcp.2020.109950 000108295 0248_ $$2sideral$$a120910 000108295 037__ $$aART-2021-120910 000108295 041__ $$aeng 000108295 100__ $$aHernández Laín, Quercus$$uUniversidad de Zaragoza 000108295 245__ $$aStructure-preserving neural networks 000108295 260__ $$c2021 000108295 5060_ $$aAccess copy available to the general public$$fUnrestricted 000108295 5203_ $$aWe develop a method to learn physical systems from data that employs feedforward neural networks and whose predictions comply with the first and second principles of thermodynamics. The method employs a minimum amount of data by enforcing the metriplectic structure of dissipative Hamiltonian systems in the form of the so-called General Equation for the Non-Equilibrium Reversible-Irreversible Coupling, GENERIC (Öttinger and Grmela (1997) [36]). The method does not need to enforce any kind of balance equation, and thus no previous knowledge on the nature of the system is needed. Conservation of energy and dissipation of entropy in the prediction of previously unseen situations arise as a natural by-product of the structure of the method. Examples of the performance of the method are shown that comprise conservative as well as dissipative systems, discrete as well as continuous ones. 000108295 536__ $$9info:eu-repo/grantAgreement/ES/DGA-FSE/T24-20R$$9info:eu-repo/grantAgreement/ES/MINECO-CICYT/DPI2017-85139-C2-1-R$$9info:eu-repo/grantAgreement/ES/UZ/ESI-ENSAM-Simulated Reality 000108295 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/ 000108295 590__ $$a4.645$$b2021 000108295 591__ $$aPHYSICS, MATHEMATICAL$$b3 / 56 = 0.054$$c2021$$dQ1$$eT1 000108295 591__ $$aCOMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS$$b40 / 112 = 0.357$$c2021$$dQ2$$eT2 000108295 594__ $$a7.1$$b2021 000108295 592__ $$a2.069$$b2021 000108295 593__ $$aApplied Mathematics$$c2021$$dQ1 000108295 593__ $$aComputational Mathematics$$c2021$$dQ1 000108295 593__ $$aPhysics and Astronomy (miscellaneous)$$c2021$$dQ1 000108295 593__ $$aNumerical Analysis$$c2021$$dQ1 000108295 593__ $$aModeling and Simulation$$c2021$$dQ1 000108295 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion 000108295 700__ $$0(orcid)0000-0001-7639-6767$$aBadías Herbera, Alberto$$uUniversidad de Zaragoza 000108295 700__ $$0(orcid)0000-0003-3003-5856$$aGonzález Ibáñez, David$$uUniversidad de Zaragoza 000108295 700__ $$aChinesta Soria, Francisco 000108295 700__ $$0(orcid)0000-0003-1017-4381$$aCueto Prendes, Elías$$uUniversidad de Zaragoza 000108295 7102_ $$15004$$2605$$aUniversidad de Zaragoza$$bDpto. Ingeniería Mecánica$$cÁrea Mec.Med.Cont. y Teor.Est. 000108295 773__ $$g426, 109950 (2021), [16 pp.]$$pJ. comput. phys.$$tJournal of Computational Physics$$x0021-9991 000108295 8564_ $$s346629$$uhttps://zaguan.unizar.es/record/108295/files/texto_completo.pdf$$yPostprint 000108295 8564_ $$s2498922$$uhttps://zaguan.unizar.es/record/108295/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint 000108295 909CO $$ooai:zaguan.unizar.es:108295$$particulos$$pdriver 000108295 951__ $$a2023-05-18-13:23:10 000108295 980__ $$aARTICLE