| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Razvoj razložljivega napovednega modela za določitev prispevkov prometa h koncentracijam trdnih delcev v zunanjem zraku
Authors:ID Lešnik, Uroš (Author)
ID Mongus, Domen (Mentor) More about this mentor... New window
ID Lep, Marjan (Comentor)
Files:.pdf DOK_Lesnik_Uros_2026.pdf (2,98 MB)
MD5: 92B388209767340B3FBBE92917ACA91B
 
Language:Slovenian
Work type:Doctoral dissertation
Typology:2.08 - Doctoral Dissertation
Organization:FGPA - Faculty of Civil Engineering, Transportation Engineering and Architecture
Abstract:V doktorski nalogi smo preučevali vpliv cestnega prometa na kakovost zunanjega zraka z delci PM10, da bi preverili hipotezo, ali je možno z uporabo genetskega algoritma na osnovi strojnega učenja učinkovito napovedati kakovost zunanjega zraka ter sočasno še določiti vpliv prometa na koncentracije trdnih delcev v zunanjem zraku. Razvili smo metodologijo napovedi kakovosti zunanjega zraka na osnovi meteoroloških podatkov in podrobnejših podatkov o količini ter strukturi prometa in jo validirali na preteklih izmerjenih podatkih. Uporabljena metoda se je izkazala za uspešno, saj je natančnejša od primerjanih, hkrati pa sočasno omogoča še določitev vpliva prometa na kakovost zunanjega zraka s pomočjo uteži razlagalnih (pojasnjevalnih) spremenljivk. Izvedli smo analizo obstoječih napovedi Agencije Republike Slovenije za okolje in primerjavo z novo razvito metodologijo iz te naloge. Rezultati so pokazali primerljivo natančnost v napovedi razreda onesnaženosti z delci PM10. S pomočjo pojasnjevalnih spremenljivk smo določili vpliv cestnega prometa na koncentracije delcev PM10. Rezultate smo primerjali s podobnimi raziskavami v Sloveniji in v svetu; primerjava je pokazala, da so rezultati primerljivi. Študija je pokazala, da se v tako dolgem časovnem obdobju raziskovanja (2013–2020) že pojavijo določene razlike pri emisijah skupin virov (zamenjava avtomobilov, sanacije kurilnih naprav, spremenjene vremenske razmere, prerazporeditve prometnih tokov v mestu), kar je treba pri napovedi upoštevati.
Keywords:trdni delci, promet, določitev vpliva, genetski algoritem, strojno učenje
Place of publishing:Maribor
Publisher:U. Lešnik]
Year of publishing:2025
PID:20.500.12556/DKUM-96155 New window
UDC:504.5:621.43.068:519.87:004.8(043.3)
COBISS.SI-ID:280489731 New window
Publication date in DKUM:03.06.2026
Views:216
Downloads:24
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FG
:
Copy citation
  
Average score:(1 vote)
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:04.12.2025

Secondary language

Language:English
Title:Developtment of explanatory forecasting model for determining traffic contributions to the concentrations of solid particles in outdoor air
Abstract:This thesis investigates the influence of road traffic on air quality, specifically focusing on PM10 particulate matter. We aim to assess the effectiveness of a genetic algorithm based on machine learning in predicting air quality while simultaneously determining the impact of traffic on solid particles in outdoor air. We developed a forecasting methodology that integrates meteorological data with detailed traffic data, including traffic volume and composition, and validated this approach against historical measurements. Our method demonstrated superior accuracy compared to existing models and enables the quantification of the impact of traffic on air quality through the analysis of explanatory variable weights. We analysed the forecasts provided by Slovenian environmental agency and compared them with our newly developed methodology. The results indicated comparable accuracy in predicting PM10 pollution levels. By examining the explanatory variables, we quantified the impact of road traffic on PM10 concentrations and benchmarked our findings against similar studies conducted in Slovenia and internationally, revealing comparable results. The study highlighted significant shifts in emission source categories over the research period (2013-2020), including vehicle replacement, upgrades to heating systems, climate change effects, and changes in urban traffic patterns. These factors must be accounted for in future forecasts.
Keywords:particulate matter, traffic, impact determination, genetic algorithm, machine learning


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