000170983 001__ 170983
000170983 005__ 20260430151736.0
000170983 0247_ $$2doi$$a10.1016/j.jnnfm.2026.105601
000170983 0248_ $$2sideral$$a149029
000170983 037__ $$aART-2026-149029
000170983 041__ $$aeng
000170983 100__ $$0(orcid)0000-0001-6727-563X$$aUrdeitx, Pau$$uUniversidad de Zaragoza
000170983 245__ $$aCan transformers overcome the lack of data in the simulation of history-dependent flows?
000170983 260__ $$c2026
000170983 5060_ $$aAccess copy available to the general public$$fUnrestricted
000170983 5203_ $$aIt is well known that the lack of information about certain variables necessary for the description of a dynamical system leads to the introduction of historical dependence (lack of Markovian character of the model) and noise. Traditionally, scientists have made up for these shortcomings by designing phenomenological variables that take into account this historical dependence (typically, conformational tensors in fluids). Often these phenomenological variables are not easily measurable experimentally. In this work we study to what extent Transformer architectures are able to cope with the lack of experimental data on these variables. The methodology is evaluated on three benchmark problems: a cylinder flow with no history dependence, a viscoelastic Couette flow modeled via the Oldroyd-B formalism, and a non-linear polymeric fluid described by the FENE model. Our results show that the Transformer outperforms a thermodynamically consistent, structurepreserving neural network with metriplectic bias in systems with missing experimental data, providing lower errors even in low-dimensional latent spaces. In contrast, for systems whose state variables can be fully known, the metriplectic model achieves superior performance.
000170983 536__ $$9info:eu-repo/grantAgreement/ES/MICINN/PID2023-147373OB-I00$$9info:eu-repo/grantAgreement/ES/MTFP/TSI-100930-2023-1
000170983 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttps://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
000170983 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000170983 700__ $$0(orcid)0000-0002-9135-866X$$aAlfaro, Icíar$$uUniversidad de Zaragoza
000170983 700__ $$0(orcid)0000-0003-3003-5856$$aGonzález, David$$uUniversidad de Zaragoza
000170983 700__ $$aChinesta, Francisco
000170983 700__ $$0(orcid)0000-0003-1017-4381$$aCueto, Elías$$uUniversidad de Zaragoza
000170983 7102_ $$15004$$2605$$aUniversidad de Zaragoza$$bDpto. Ingeniería Mecánica$$cÁrea Mec.Med.Cont. y Teor.Est.
000170983 773__ $$g349 (2026), 105601 [13 pp.]$$pJ. non-Newton. fluid mech.$$tJOURNAL OF NON-NEWTONIAN FLUID MECHANICS$$x0377-0257
000170983 8564_ $$s3337663$$uhttps://zaguan.unizar.es/record/170983/files/texto_completo.pdf$$yVersión publicada
000170983 8564_ $$s2603358$$uhttps://zaguan.unizar.es/record/170983/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000170983 909CO $$ooai:zaguan.unizar.es:170983$$particulos$$pdriver
000170983 951__ $$a2026-04-30-13:58:25
000170983 980__ $$aARTICLE