| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Napovedovanje temperature zraka na mikrolokaciji s pomočjo globokega učenja
Authors:ID Krepek, Amadej (Author)
ID Fister, Iztok (Mentor) More about this mentor... New window
Files:.pdf MAG_Krepek_Amadej_2024.pdf (4,94 MB)
MD5: 0BA306F31108BCA45E1F89738F8E5D50
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Živimo v času nenehnega tehnološkega napredka, ko se umetna inteligenca vztrajno vključuje v naš vsakdan. Zaradi vse pogostejših ekstremnih vremenskih pojavov se je pojavila potreba po ažurnih in kvalitetnih kratkoročnih vremenskih napovedih. Z uporabo umetne inteligence pa vse to poteka veliko hitreje kot z računanjem fizikalnih modelov. S pomočjo globokega učenja je bil ustvarjen model napoveditemperature zraka za naslednjih 12 ur. Najboljši rezultat je pri izbranemu napovednemu modelu za določeno obdobje spomočjo izbrane metrike MAE1 znašal 0,4 stopinje Celzija, medtem ko je imel referenčni model vrednost te metrike kar 2,4 stopinje Celzija.
Keywords:nevronska mreža, temperatura zraka, mikrolokacija, napoved, vreme
Place of publishing:Maribor
Publisher:[A. Krepek]
Year of publishing:2024
PID:20.500.12556/DKUM-91081 New window
UDC:004.85:551.509(043.2)
COBISS.SI-ID:221452547 New window
Publication date in DKUM:23.12.2024
Views:163
Downloads:107
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:19.10.2024

Secondary language

Language:English
Title:Predicting air temperature at a micro-location using deep learning
Abstract:We live in a time of constant technological progress, where artificial intelligence is rapidly being integrated into our daily lives. The increasing frequency of extreme weather events has created a need for up-to-date and high-quality short-term weather forecasts. And with the use of artificial intelligence, all this is done much faster than calculating physical models. Using deep learning, a model has been created to predict the air temperature for the next 12 hours. The best result for the selected forecast model for a given period using the metric mean absolute error was 0.4 degrees Celsius, while the reference model had a value of 2.4 degrees Celsius.
Keywords:neural network, air temperature, microlocation, prediction, weather


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica