000165466 001__ 165466 000165466 005__ 20260108143204.0 000165466 0247_ $$2doi$$a10.1007/s10489-023-04824-w 000165466 0248_ $$2sideral$$a147222 000165466 037__ $$aART-2023-147222 000165466 041__ $$aeng 000165466 100__ $$aZenkner, Gabriel 000165466 245__ $$aA flexible and lightweight deep learning weather forecasting model 000165466 260__ $$c2023 000165466 5203_ $$aNumerical weather prediction is an established weather forecasting technique in which equations describing wind, temperature, pressure and humidity are solved using the current atmospheric state as input. This study examines deep learning to forecast weather given historical data from two London-based locations. Two distinct Bi-LSTM recurrent neural network models were developed in the TensorFlow deep learning framework and trained to make predictions in the next 24 and 72 h, given the past 120 h. The first trained neural network predicted temperature at Kew Gardens with a forecast accuracy of 2 C in 73% of instances in a whole unseen year, and a root mean squared errors of 1.45 C. The second network predicted 72-h air temperature and relative humidity at Heathrow with root mean squared errors 2.26 C and 14% respectively and 80% of the temperature predictions were within 3 C while 80% of relative humidity predictions were within 20%. Both networks were trained with five years of historical data, with cloud training times of over a minute (24-h network) and three minutes (72-h). 000165466 540__ $$9info:eu-repo/semantics/closedAccess$$aby$$uhttps://creativecommons.org/licenses/by/4.0/deed.es 000165466 590__ $$a3.4$$b2023 000165466 591__ $$aCOMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE$$b78 / 197 = 0.396$$c2023$$dQ2$$eT2 000165466 592__ $$a1.193$$b2023 000165466 593__ $$aArtificial Intelligence$$c2023$$dQ2 000165466 594__ $$a6.6$$b2023 000165466 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion 000165466 700__ $$0(orcid)0000-0001-8342-6573$$aNavarro-Martinez, Salvador 000165466 773__ $$g53 (2023), 24991-25002$$pAppl. intell.$$tAPPLIED INTELLIGENCE$$x0924-669X 000165466 8564_ $$s2632773$$uhttps://zaguan.unizar.es/record/165466/files/texto_completo.pdf$$yVersión publicada 000165466 8564_ $$s2614642$$uhttps://zaguan.unizar.es/record/165466/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada 000165466 909CO $$ooai:zaguan.unizar.es:165466$$particulos$$pdriver 000165466 951__ $$a2026-01-08-14:11:08 000165466 980__ $$aARTICLE