scholarly journals A concept of the air quality monitoring system in the city of Lublin with machine learning methods to detect data outliers

2019 ◽  
Vol 252 ◽  
pp. 03009 ◽  
Author(s):  
Tomasz Cieplak ◽  
Tomasz Rymarczyk ◽  
Robert Tomaszewski
Keyword(s):  
Machine Learning ◽  
Air Quality ◽  
Monitoring System ◽  
Low Cost ◽  
Quality Monitoring ◽  
Spatiotemporal Variability ◽  
Air Quality Monitoring ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
The City

This paper presents a concept of the air quality monitoring system design and describes a selection of data quality analysis methods. A high level of industrialisation affects the risk of natural disasters related to environmental pollution such ase.g.air pollution by gases and clouds of dust (carbon monoxide, sulphur oxides, nitrogen oxides). That is why researches related to the monitoring this type of phenomena are extremely important. Low-cost air quality sensors are more commonly used to monitor air parameters in urban areas. These types of sensors are used to obtain an image of the spatiotemporal variability in the concentration of air pollutants. Aside from their low price , which is important from a point of view of the economic accessibility of society, low-cost sensors are prone to produce erroneous results compared to professional air quality monitors. The described study focuses on the analysis of outliers as particularly interesting for further analysis, as well as modelling with machine learning methods for air quality assessment in the city of Lublin.

scholarly journals Developing Relative Humidity and Temperature Corrections for Low-Cost Sensors Using Machine Learning

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3338
Author(s):  
Ivan Vajs ◽  
Dejan Drajic ◽  
Nenad Gligoric ◽  
Ilija Radovanovic ◽  
Ivan Popovic
Keyword(s):  
Machine Learning ◽  
Air Quality ◽  
Relative Humidity ◽  
Low Cost ◽  
Quality Monitoring ◽  
Air Quality Monitoring ◽  
Lower Accuracy ◽  
Wide Range ◽  
The Impact ◽  
Monitoring Stations

Existing government air quality monitoring networks consist of static measurement stations, which are highly reliable and accurately measure a wide range of air pollutants, but they are very large, expensive and require significant amounts of maintenance. As a promising solution, low-cost sensors are being introduced as complementary, air quality monitoring stations. These sensors are, however, not reliable due to the lower accuracy, short life cycle and corresponding calibration issues. Recent studies have shown that low-cost sensors are affected by relative humidity and temperature. In this paper, we explore methods to additionally improve the calibration algorithms with the aim to increase the measurement accuracy considering the impact of temperature and humidity on the readings, by using machine learning. A detailed comparative analysis of linear regression, artificial neural network and random forest algorithms are presented, analyzing their performance on the measurements of CO, NO2 and PM10 particles, with promising results and an achieved R2 of 0.93–0.97, 0.82–0.94 and 0.73–0.89 dependent on the observed period of the year, respectively, for each pollutant. A comprehensive analysis and recommendations on how low-cost sensors could be used as complementary monitoring stations to the reference ones, to increase spatial and temporal measurement resolution, is provided.

Development of Design of a Low-Cost Air Quality Monitoring System in Binh Duong Province

2021 ◽  
pp. 597-607
Author(s):  
Thuyet That Vo Nguyen ◽  
Nguyen Duc Thinh ◽  
Hien Vo ◽  
Tran Quang Nhu ◽  
Nguyen Binh Minh
Keyword(s):  
Air Quality ◽  
Monitoring System ◽  
Low Cost ◽  
Quality Monitoring ◽  
Air Quality Monitoring

scholarly journals Rationale For a Regional Monitoring Program of Atmospheric Air Quality in the Dnepropetrovsk Region

2021 ◽  
Vol 6 (3) ◽  
pp. 220-225
Author(s):  
S. V. Stepanov ◽  
◽  
N. I. Rublevska
Keyword(s):  
Public Health ◽  
Air Quality ◽  
Monitoring System ◽  
Phenol Formaldehyde ◽  
Quality Monitoring ◽  
Air Quality Monitoring ◽  
Regional Monitoring ◽  
Atmospheric Air ◽  
Industrial Cities ◽  
The City

The air quality monitoring system in industrial cities is one of the systems for responding to risk factors in the public health system. The purpose of the study is, on the basis of a hygienic assessment of carcinogenic and non-carcinogenic risks from exposure to specific pollutants in the cities of Dnipro, Kamenskoye, Kryvyi Rih, to substantiate a program for regional monitoring of atmospheric air quality. Materials and methods. To achieve this goal, the results of air quality studies in the largest industrial cities of the Dnipropetrovsk region – Dnipro, Kryvyi Rih and Kamenskoe for the period 2005-2019 were analyzed in terms of phenol, formaldehyde, benzene, xylene and toluene, and carcinogenic and non-carcinogenic risks to public health were calculated in these cities. Results and discussion. According to the results of the study, individual carcinogenic risks in all three cities in terms of formaldehyde are medium, and in terms of benzene are high. The population carcinogenic risk ranges from 200-269 additional cases of cancer from exposure to formaldehyde and 3727-4426 additional cases of cancer from chronic inhalation exposure to benzene. The calculation of non-carcinogenic risks identified the priority specific air pollutants in the cities under study, as well as the main target organs. So the main systems that are influenced by the action of the studied chemicals are the central nervous system, the general development of the body and the blood system. Based on the risk assessment, it was established that it is necessary to include the Kamenskoye metro station for regional monitoring. It is necessary to include all pollutants from List A to the minimum list of investigated chemicals, and for the city of Dnipro and Kamenskoye it is additionally necessary to carry out studies of phenol, formaldehyde and toluene and in the city of Kryvyi Rih – formaldehyde and toluene. The mechanism of data processing and interaction between the subjects of monitoring has been substantiated for the timely identification of risks and the development of necessary preventive measures for risk management. Conclusion. It was found that carcinogenic and non-carcinogenic risks in industrial cities of the Dnipropetrovsk region are not acceptable. The existing monitoring system does not fully comply with the current requirements. The minimum program of the regional air quality monitoring system in the Dnipropetrovsk region has been scientifically substantiated

Sign in / Sign up

Export Citation Format

Share Document