Analysis of Romanian Air Quality using Machine Learning Techniques

Andreea-Mihaela Niculae ()
Additional contact information
Andreea-Mihaela Niculae: The Bucharest University of Economic Studies, Romania

Database Systems Journal, 2022, vol. 13, issue 1, 1-10

Abstract: Air quality monitoring has become an increasingly important subject and is one of the most important concerns of governments worldwide. Monitoring is especially important in industrial and urban areas. Due to the many forms of pollution generated mainly by fuel consumption, means of transport, coal-fired electricity generation, etc., air quality is negatively affected. As the current trend is an increase in air pollution, it is necessary to install equipment to measure air quality both in areas with a high risk of pollution and in areas where pollution is low. These types of equipment must communicate in real-time their measured values, which then can be accessed to be able to make analyzes and predictions regarding air quality in a certain geographical area, areas with a high industrialization level, or in areas with a growing population. This paper aims to investigate the application of big data and machine learning techniques to make predictions on air quality using, as a source of data, data recorded in the period 2018-2021 from measurement probes throughout Romania for PM10, NO2, O3, and SO2. The results of this paper's analysis show that time-series models outperform traditional models. Moreover, ANN models are successful only in classifying pollutants' AQI levels and not their actual values.

Keywords: Big Data; Machine Learning; Romania; Air quality; MLR; SARIMA; C5.0; Random Forest; ANN (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://dbjournal.ro/archive/33/33_1.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:aes:dbjour:v:13:y:2022:i:1:p:1-10

Access Statistics for this article

Database Systems Journal is currently edited by Ion Lungu

More articles in Database Systems Journal from Academy of Economic Studies - Bucharest, Romania Contact information at EDIRC.
Bibliographic data for series maintained by Adela Bara ().