doi:10.1063/1.5008205engBadías, A.González, D.Alfaro, I.Chinesta, F.Cueto, E.Local proper generalized decompositionART-2017-104335Local model order reduction methods provide better results than global ones to problems with intricate manifold solution structure. A posteriori methods (e.g. Proper Orthogonal Decomposition) have been many times applied locally, but a priori methods (e.g. Proper Generalized Decomposition) have the difficulty of determining the manifold structure of the solution in a previous way. We propose three strategies for estimating the appropriate size of the local sub-domains where afterwards local PGD (l-PGD) is applied. It can be seen as a sort of a priori manifold learning or non-linear dimensionality reduction technique. Finally, three examples support the work.2017http://zaguan.unizar.es/record/7537410.1063/1.5008205http://zaguan.unizar.es/record/75374oai:zaguan.unizar.es:75374info:eu-repo/grantAgreement/ES/CICYT/DPI2014-51844-C2-1-Rinfo:eu-repo/grantAgreement/ES/DGA/T88info:eu-repo/grantAgreement/ES/MINECO/DPI2015-72365-EXPAIP Conference Proceedings 1896, 1 (2017), 170007 [6 pp.]by-nc-ndhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/info:eu-repo/semantics/openAccess