Korekcija vremenske prognoze korištenjem nedavnih mjerenja

master's thesis

• Title (english): Correction of weather forecast by using recent measurements
• Author: Borna Kovačević
• Mentor: Mario Vašak (mentor)
• Committee member: Mario Vašak (predsjednik povjerenstva)
• Committee member: Vinko Lešić (član povjerenstva)
• Committee member: Anita Banjac (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-02-23, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Temeljem duljeg niza mjerenja meteoroloških uvjeta na neboderskoj zgradi Sveučilišta u Zagrebu Fakulteta elektrotehnike i računarstva (FER-a) i usporedbom s vremenskom prognozom Državnog hidrometeorološkog zavoda (DHMZ-a) nastojalo se poboljšati predikciju vremenske prognoze korištenjem linearnih korektora i neuronskih mreža. Izrađeno je 15 jednostavnijih modela strojnog učenja te 45 modela neuronskih mreža. Opisane su razlike između njih i njihova točnost u razdoblju od 29. kolovoza 2020. do 4. prosinca 2020. godine. Poboljšanje vremenske prognoze DHMZ-a korištenjem strojnog učenja i neuronskih mreža može doprinijeti smanjenju potrošnje energije u zgradi.

Abstract (english)

Based on a long series of data measurements of meteorological conditions on the University of Zagreb Faculty of Electrical Engineering and Computing (FER) building and comparison with Croatian Meteorological and Hydrological Service (DHMZ) weather forecast, an attempt to improve prediction of the weather using linear correctors and neural networks, was made. Fifteen simpler models of machine learning and 45 models of neural networks is developed. The differences between models and their accuracy is described, for the testing period from August 29, 2020 to December 4, 2020. The improvement of weather by using machine learning and neural networks can contribute reducing energy consumption in buildings.

• Keywords: Neuronske mreže; strojno učenje; vremenska prognoza; DHMZ; računalna znanost; umjetna inteligencija
• Keywords (english): Neural networks; machine learning; weather forecast; DHMZ; computer science; artificial intelligence
• Language: croatian
• URN:NBN: urn:nbn:hr:168:037871
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 10:11:55