Procjena zagađenja zraka u gradu

master's thesis

• Title (english): City air pollution estimation
• Author: Sandra Kuzmić
• Mentor: Mario Kušek (mentor)
• Committee member: Mario Kušek (predsjednik povjerenstva)
• Committee member: Ivana Podnar Žarko (član povjerenstva)
• Committee member: Pavle Skočir (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Zagađenost zraka predstavlja velik problem u mnogim svjetskim gradovima. Na kvalitetu
zraka utječu razni plinovi i čestice te se temeljem njihovih koncentracija računa indeks
kvalitete zraka (AQI). Budući da su mjerni senzori skupi i podložni pogreškama,
koncentracije pojedinih onečišćivača mogu se procijeniti korištenjem dostupnih
meteoroloških mjerenja. Ideja je ovog rada pronaći izvore meteoroloških podataka i
vrijednosti koncentracija pojedinih onečišćivača, obraditi ih te utvrditi postoji li između njih
ovisnost. U tu svrhu koriste se algoritmi strojnog učenja, konkretno regresijski algoritmi i
ansambli. Uz to, istražene su varijable koje najviše utječu na izlazne vrijednosti te su
dobiveni rezultati dani u obliku tablica i grafova.

Abstract (english)

In recent years air pollution has become one of the major issues in many world cities. Air
quality is affected by different gases and particles and their concentration is used to calculate
air quality index (AQI). Sensors used for data collection are often expensive and prone to
errors so it would be better if these values could be estimated using already existing data,
such as meteorological measurements. The main task of his paper is to find datasets that
contain historic meteorological data and pollutants’ concentration, process it, and check if
there is any correlation between them. To do so, different machine learning algorithms are
used, specifically regression and ensembles. Finally, the most important features are selected,
and received results are displayed in the form of tables and graphs.

• Keywords: onečišćenje zraka; AQI; Copernicus; meteorološki podaci; strojno učenje; regresija; ansambl; odabir značajki
• Keywords (english): air pollution; AQI; Copernicus; meteorological data; machine learning; regression analysis; ensemble; feature selection
• Language: croatian
• URN:NBN: urn:nbn:hr:168:234023
• 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 10:16:22