Forecasting the daily maximal and minimal temperatures from radiosonde measurements using neural networks

Gregor Skok (Author), Doruntina Hoxha (Author), Žiga Zaplotnik (Author)

Abstract

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.

Keywords

strojno učenje;nevronske mreže;napovedovanje vremena;temperatura zraka;klimatologija;meritve z radiosondo;machine learning;neural networks;weather forecasting;air temperature;climatology;radiosonde measurements;

Data

Language:	English
Year of publishing:	2021
Typology:	1.01 - Original Scientific Article
Organization:	UL FMF - Faculty of Mathematics and Physics
UDC:	551.509
COBISS:	85351683
ISSN:	2076-3417
Views:	121
Downloads:	42
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	Slovenian
Secondary keywords:	strojno učenje;nevronske mreže;napovedovanje vremena;temperatura zraka;klimatologija;meritve z radiosondo;
Type (COBISS):	Article
Pages:	17 str.
Volume:	ǂVol. ǂ11
Issue:	ǂart. no. ǂ10852
Chronology:	Nov. 2021
DOI:	10.3390/app112210852
ID:	15138823