Air Pollution Modelling by Machine Learning Methods

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F21%3A00548678" target="_blank" >RIV/67985807:_____/21:00548678 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.3390/modelling2040035" target="_blank" >http://dx.doi.org/10.3390/modelling2040035</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/modelling2040035" target="_blank" >10.3390/modelling2040035</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Air Pollution Modelling by Machine Learning Methods

Popis výsledku v původním jazyce

Precise environmental modelling of pollutants distributions represents a key factor for addresing the issue of urban air pollution. Nowadays, urban air pollution monitoring is primarily carried out by employing sparse networks of spatially distributed fixed stations. The work in this paper aims at improving the situation by utilizing machine learning models to process the outputs of multi-sensor devices that are small, cheap, albeit less reliable, thus a massive urban deployment of those devices is possible. The main contribution of the paper is the design of a mathematical model providing sensor fusion to extract the information and transform it into the desired pollutant concentrations. Multi-sensor outputs are used as input information for a particular machine learning model trained to produce the CO, NO2, and NOx concentration estimates. Several state-of-the-art machine learning methods, including original algorithms proposed by the authors, are utilized in this study: kernel methods, regularization networks, regularization networks with composite kernels, and deep neural networks. All methods are augmented with a proper hyper-parameter search to achieve the optimal performance for each model. All the methods considered achieved vital results, deep neural networks exhibited the best generalization ability, and regularization networks with product kernels achieved the best fitting of the training set.

Název v anglickém jazyce

Air Pollution Modelling by Machine Learning Methods

Popis výsledku anglicky

Precise environmental modelling of pollutants distributions represents a key factor for addresing the issue of urban air pollution. Nowadays, urban air pollution monitoring is primarily carried out by employing sparse networks of spatially distributed fixed stations. The work in this paper aims at improving the situation by utilizing machine learning models to process the outputs of multi-sensor devices that are small, cheap, albeit less reliable, thus a massive urban deployment of those devices is possible. The main contribution of the paper is the design of a mathematical model providing sensor fusion to extract the information and transform it into the desired pollutant concentrations. Multi-sensor outputs are used as input information for a particular machine learning model trained to produce the CO, NO2, and NOx concentration estimates. Several state-of-the-art machine learning methods, including original algorithms proposed by the authors, are utilized in this study: kernel methods, regularization networks, regularization networks with composite kernels, and deep neural networks. All methods are augmented with a proper hyper-parameter search to achieve the optimal performance for each model. All the methods considered achieved vital results, deep neural networks exhibited the best generalization ability, and regularization networks with product kernels achieved the best fitting of the training set.

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA18-23827S" target="_blank" >GA18-23827S: Schopnosti a omezení mělkých a hlubokých sítí</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Modelling

ISSN

2673-3951

e-ISSN

2673-3951

Svazek periodika

2

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

16

Strana od-do

659-674

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—