000145384 001__ 145384
000145384 005__ 20241024135331.0
000145384 0247_ $$2doi$$a10.1016/j.buildenv.2024.112123
000145384 0248_ $$2sideral$$a140267
000145384 037__ $$aART-2024-140267
000145384 041__ $$aeng
000145384 100__ $$aMilla-Val, Jaime
000145384 245__ $$aAdversarial image-to-image model to obtain highly detailed wind fields from mesoscale simulations in urban environments
000145384 260__ $$c2024
000145384 5060_ $$aAccess copy available to the general public$$fUnrestricted
000145384 5203_ $$aWe propose a conditional Generative Adversarial Network (cGAN) that can produce detailed local wind fields in urban areas, comparable in level of detail to those from Computational Fluid Dynamics (CFD) simulations, that are generated from coarser Numerical Weather Prediction (NWP) data. In our approach, the cGAN is trained using NWP data as input and CFD as targets. Both CFD and NWP data are presented to the network as images, using an image-to-image model based on Pix2Pix to transform coarse meteorological conditions into detailed local wind fields. The methodology is tested in a residential district in a large Spanish city, Zaragoza. The model predictions show significant agreement with the actual CFD results, while reducing the computational time from eight hours to seconds. Feature engineering of image channels effectively reduces the model error, especially in the wind direction, achieving a mean absolute error in the wind speed of 0.35 m∕s and a wind direction error of 27.0◦.
000145384 536__ $$9info:eu-repo/grantAgreement/ES/DGA/T32-23R$$9info:eu-repo/grantAgreement/ES/MICIN/DIN2019-010452$$9info:eu-repo/grantAgreement/ES/MICINN/TED2021-131861B-I00
000145384 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
000145384 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000145384 700__ $$0(orcid)0000-0002-6948-2314$$aMontañés, Carlos$$uUniversidad de Zaragoza
000145384 700__ $$0(orcid)0000-0001-6205-5160$$aFueyo, Norberto$$uUniversidad de Zaragoza
000145384 7102_ $$15001$$2600$$aUniversidad de Zaragoza$$bDpto. Ciencia Tecnol.Mater.Fl.$$cÁrea Mecánica de Fluidos
000145384 773__ $$g266 (2024), 112123 [13 pp.]$$pBuild. environ.$$tBuilding and Environment$$x0360-1323
000145384 8564_ $$s5050602$$uhttps://zaguan.unizar.es/record/145384/files/texto_completo.pdf$$yVersión publicada
000145384 8564_ $$s2683146$$uhttps://zaguan.unizar.es/record/145384/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000145384 909CO $$ooai:zaguan.unizar.es:145384$$particulos$$pdriver
000145384 951__ $$a2024-10-24-12:11:47
000145384 980__ $$aARTICLE