20.500.12556/RUL-136369 Forecasting the daily maximal and minimal temperatures from radiosonde measurements using neural networks This study investigates the potential of direct prediction of daily extremes of temperature at 2 m from a vertical profile measurement using neural networks (NNs). The analysis is based on 3800 daily profiles measured in the period 2004–2019. Various setups of dense sequential NNs are trained to predict the daily extremes at different lead times ranging from 0 to 500 days into the future. The short- to medium-range forecasts rely mainly on the profile data from the lowest layer—mostly on the temperature in the lowest 1 km. For the long-range forecasts (e.g., 100 days), the NN relies on the data from the whole troposphere. The error increases with forecast lead time, but at the same time, it exhibits periodic behavior for long lead times. The NN forecast beats the persistence forecast but becomes worse than the climatological forecast on day two or three. The forecast slightly improves when the previous-day measurements of temperature extremes are added as a predictor. The best forecast is obtained when the climatological value is added as well, with the biggest improvement in the long-term range where the error is constrained to the climatological forecast error. machine learning neural networks weather forecasting air temperature climatology radiosonde measurements prediction maximum temperature minimum temperature explainable AI strojno učenje nevronske mreže napovedovanje vremena temperatura zraka klimatologija meritve z radiosondo true false true Angleški jezik Slovenski jezik Članek v reviji 2022-04-26 14:58:26 2022-04-26 14:58:27 2022-09-15 04:13:48 0000-00-00 00:00:00 2021 0 0 17 str. iss. 22, art. 10852 Vol. 11 Nov. 2021 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 551.509 2076-3417 10.3390/app112210852 85351683 applsci-11-10852.pdf applsci-11-10852.pdf 1 3A48F95390EB6915CB13DC6CADFAB04B 43a715ef8e08539390c7a27b4092e8fa019bccb40394690be057a13279dd62e8 cb2c7528-c560-11ec-8aca-00155dcfd717 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=155986 https://www.mdpi.com/2076-3417/11/22/10852 0 9804718e-c560-11ec-8aca-00155dcfd717 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=155985 Fakulteta za matematiko in fiziko 0 0 0