Input-adaptive proxy of air quality parameters: A case study for black carbon in Helsinki, Finland

2020 ◽  
Author(s):  
Pak L Fung ◽  
Martha A Zaidan ◽  
Salla Sillanpää ◽  
Anu Kousa ◽  
Jarkko V Niemi ◽  
...  
Keyword(s):  
Air Quality ◽  
Missing Data ◽  
Black Carbon ◽  
High Reliability ◽  
Pearson Correlation ◽  
Quality Measurement ◽  
Quality Parameters ◽  
Coefficient Of Determination ◽  
Concentration Data ◽  
Input Variables

<p>Urban air pollution has been a global challenge, and continuous air quality measurement is important to understand the nature of the problem. However, missing data has often been an issue in air quality measurement. In this study, we presented a modified method to impute missing data by input-adaptive proxy. We used black carbon (BC) concentration data in Mäkelänkatu traffic site (TR) and Kumpula urban background site (BG) in Helsinki, Finland in 2017–2018 as training sets. The input-adaptive proxy selected input variables of other air quality variables based on their Pearson correlation coefficients with BC. In order to avoid overfitting, this proxy used the algorithm of least squares model with a bisquare weighting function and allowed a maximum of three input variables. The generated models were then evaluated and ranked by adjusted coefficient of determination (adjR<sup>2</sup>), mean absolute error and root mean square error. BC concentration was first estimated by the best model. In case of missing data in the input variables in the best model, the input-adaptive proxy then used the second-best model until all the missing data gaps were filled up.</p><p>The input-adaptive proxy managed to fill up 100% of the missing voids while traditional proxy filled only 20–80% of missing BC data. Furthermore, the overall performance of the input-adaptive proxy is reliable both in TR (adjR<sup>2</sup>=0.86–0.94) and in BG (adjR<sup>2</sup>=0.74–0.91). TR has a generally better regression performance because the level of BC can be mostly explained by traffic count, nitrogen oxides and accumulation mode. On the contrary, the source of BC in BG is more heterogeneous, which includes traffic emission and residential combustion, and the concentration of BC is influenced by meteorological parameters; therefore, the rule of including maximum three input variables might lead to the lower adjR<sup>2</sup>. The proxy works slightly better for workdays scenario than in weekends in both sites. In TR, the proxy works similarly in all seasons, while in BG, the proxy performance is better in winter and autumn than in the other seasons. The simplicity, full coverage and high reliability of the input-adaptive proxy make it sound to further estimate other air quality parameters. Moreover, it can act as an air quality virtual sensor alongside with on-site instruments.</p>

scholarly journals Input-Adaptive Proxy for Black Carbon as a Virtual Sensor

Sensors ◽  
2019 ◽  
Vol 20 (1) ◽  
pp. 182 ◽  
Author(s):  
Pak Lun Fung ◽  
Martha A. Zaidan ◽  
Salla Sillanpää ◽  
Anu Kousa ◽  
Jarkko V. Niemi ◽  
...  
Keyword(s):  
Air Quality ◽  
Missing Data ◽  
Black Carbon ◽  
Street Canyon ◽  
Ordinary Least Squares ◽  
Coefficient Of Determination ◽  
Data Set ◽  
Virtual Sensor ◽  
Urban Background ◽  
Input Variables

Missing data has been a challenge in air quality measurement. In this study, we develop an input-adaptive proxy, which selects input variables of other air quality variables based on their correlation coefficients with the output variable. The proxy uses ordinary least squares regression model with robust optimization and limits the input variables to a maximum of three to avoid overfitting. The adaptive proxy learns from the data set and generates the best model evaluated by adjusted coefficient of determination (adjR2). In case of missing data in the input variables, the proposed adaptive proxy then uses the second-best model until all the missing data gaps are filled up. We estimated black carbon (BC) concentration by using the input-adaptive proxy in two sites in Helsinki, which respectively represent street canyon and urban background scenario, as a case study. Accumulation mode, traffic counts, nitrogen dioxide and lung deposited surface area are found as input variables in models with the top rank. In contrast to traditional proxy, which gives 20–80% of data, the input-adaptive proxy manages to give full continuous BC estimation. The newly developed adaptive proxy also gives generally accurate BC (street canyon: adjR2 = 0.86–0.94; urban background: adjR2 = 0.74–0.91) depending on different seasons and day of the week. Due to its flexibility and reliability, the adaptive proxy can be further extend to estimate other air quality parameters. It can also act as an air quality virtual sensor in support with on-site measurements in the future.

scholarly journals Evaluation of multivariate time series clustering for imputation of air pollution data

2021 ◽  
Vol 10 (2) ◽  
pp. 265-285
Author(s):  
Wedad Alahamade ◽  
Iain Lake ◽  
Claire E. Reeves ◽  
Beatriz De La Iglesia
Keyword(s):  
Air Pollution ◽  
Time Series ◽  
Air Quality ◽  
Missing Data ◽  
Multivariate Time Series ◽  
Real Data ◽  
Economic Benefits ◽  
Air Pollutant ◽  
Monitoring Site ◽  
Concentration Data

Abstract. Air pollution is one of the world's leading risk factors for death, with 6.5 million deaths per year worldwide attributed to air-pollution-related diseases. Understanding the behaviour of certain pollutants through air quality assessment can produce improvements in air quality management that will translate to health and economic benefits. However, problems with missing data and uncertainty hinder that assessment. We are motivated by the need to enhance the air pollution data available. We focus on the problem of missing air pollutant concentration data either because a limited set of pollutants is measured at a monitoring site or because an instrument is not operating, so a particular pollutant is not measured for a period of time. In our previous work, we have proposed models which can impute a whole missing time series to enhance air quality monitoring. Some of these models are based on a multivariate time series (MVTS) clustering method. Here, we apply our method to real data and show how different graphical and statistical model evaluation functions enable us to select the imputation model that produces the most plausible imputations. We then compare the Daily Air Quality Index (DAQI) values obtained after imputation with observed values incorporating missing data. Our results show that using an ensemble model that aggregates the spatial similarity obtained by the geographical correlation between monitoring stations and the fused temporal similarity between pollutant concentrations produces very good imputation results. Furthermore, the analysis enhances understanding of the different pollutant behaviours and of the characteristics of different stations according to their environmental type.

scholarly journals Reconstruction of river water quality missing data using artificial neural networks

2015 ◽  
Vol 50 (4) ◽  
pp. 326-335 ◽  
Author(s):  
Hossein Tabari ◽  
P. Hosseinzadeh Talaee
Keyword(s):  
Water Quality ◽  
Missing Data ◽  
River Water ◽  
Missing Values ◽  
Human Life ◽  
Quality Parameters ◽  
River Water Quality ◽  
Water Quality Parameters ◽  
Rbf Networks ◽  
Input Variables

The monitoring of river water quality is important for human life and the health of the environment. However, water quality studies in many parts of the world, especially in developing countries, are restricted by the existence of missing data. In this study, the efficiency of the multilayer perceptron (MLP) and radial basis function (RBF) networks for recovering the missing values of 13 water quality parameters was examined based on data from five stations located along the Maroon River, Iran. The monthly values of other existing water quality parameters were used as input variables to the MLP and RBF models. According to the achieved results, the hardness missing values were estimated precisely by both the MLP and RBF networks, while the worst performance of the networks was found for the turbidity parameter. It was also found that the MLP models were superior to the RBF models to reconstruct water quality missing data.

scholarly journals Cumulative changes in water quality caused by six cascading hydroelectric dams on the Jauru River, tributary of the Pantanal floodplain

RBRH ◽  
2019 ◽  
Vol 24 ◽  
Author(s):  
Antônio Carlos Coelho da Silva ◽  
Ibraim Fantin-Cruz ◽  
Zoraidy Marques de Lima ◽  
Daniela Maimoni de Figueiredo
Keyword(s):  
Water Quality ◽  
Pearson Correlation ◽  
Statistical Treatment ◽  
Nonparametric Test ◽  
Quality Parameters ◽  
Rate Of Change ◽  
Coefficient Of Determination ◽  
Hydroelectric Dams ◽  
Longitudinal Gradient ◽  
Hydropower Plants

ABSTRACT The present study examines the individual and cumulative environmental effects of the six cascading hydroelectric dams currently in operation on in the Jauru River, a direct tributary of the Paraguay River, the main river in the Pantanal, as well as presenting a general characterization of water quality in the Jauru River. Water quality was evaluated at eight sites along the longitudinal gradient of the Jauru River. A total of 339 water quality samples from between 1990 and 2013 were considered, including 72 samples collected prior to the installation of Hydropower plants, treated as natural, and 267 samples, treated as altered . Statistica 7 software was used for statistical treatment and for the Kruskal-Wallis nonparametric test; squared Pearson correlation (coefficient of determination, R 2) was also applied to evaluated the relationship between the morphological and hydraulic parameters of each reservoir and cumulatively, with the rate of change of water quality parameters in three stretches of the Jauru River. The water quality of the Jauru River in general was characterized by low concentrations of electrolytes and slightly acidic pH, oligotrophy, reduced values of color, turbidity and solids and good oxygenation. While these general conditions were maintained over the two phases studied, we verified the occurrence of change in the pattern of variation of the physical and chemical conditions evaluated, mainly between the second and the fifth hydroelectric reservoir. This change, which implies discontinuity in the longitudinal gradient, was indicated by nine out of the twelve parameters measured in this stretch of the Jauru River, downstream of each individual reservoir and/or cumulatively. The constructive characteristics of the hydropower plants, especially water inlet height, water retention time and flooded area, as well as the proximity between two or more impoundments, are factors that influenced the observed changes, which are important aspects in the processes of environmental licensing for these future plants, or even, in some cases, to avoid them from being built at all as planned. This research also indicated the need for studies that consider the basin in an integrated way, and for the collection of more consistent data before these impoundments are implemented.

scholarly journals Air Quality Characteristics in Junior High School Classroom with Natural Ventilation in Pangkep Regency

2019 ◽  
Vol 2 (2) ◽  
pp. 157-161
Author(s):  
Nur Mutmainnah ◽  
Rosady Mulyadi ◽  
Baharuddin Hamzah
Keyword(s):  
Air Quality ◽  
Junior High School ◽  
Natural Ventilation ◽  
Ventilation System ◽  
Quality Measurement ◽  
Co2 Concentration ◽  
Quality Parameters ◽  
Activity Level ◽  
Total Dust ◽  
Surrounding Environment

The indoor air quality room has turned out to be a major concern due to its adverse effects on human health. This is related to the level of activity of human spend almost 90 percent of their time indoors. This study aims to identify the characteristics of air quality in classrooms with natural ventilation systems in three different schools which vary in topography and the surrounding environment, namely coastal areas, lowlands, and mountains. Air quality measurement focuses on CO, CO2 concentration, total dust content, temperature, humidity, and airflow velocity. The statistical results showed significantly different (p <0.05) in air quality parameters among those three schools. The CO and CO2 concentrations in the three schools are below the recommendations required by DOSH and ASHRAE. This clarifies that a well-used of a natural ventilation system is able to maintain the air quality in the classroom. The measurement of total dust levels was above the threshold required by the Ministry of Health of the Republic of Indonesia No.1405/MENKES/SK/XI/2002. In addition, there was a significant relationship (p <0.05) between air pollutants and meteorological factors such as temperature and air humidity in the classroom. The study found that there was an influence of human activity level and the surrounding environment on the amount of pollutants concentration in the classroom.

scholarly journals Correlation Analysis between Land Use/Cover Change and Air Pollutants—A Case Study in Wuyishan City

Energies ◽  
2019 ◽  
Vol 12 (13) ◽  
pp. 2545 ◽  
Author(s):  
Zhipeng Zhu ◽  
Guangyu Wang ◽  
Jianwen Dong
Keyword(s):  
Land Use ◽  
Air Quality ◽  
Black Carbon ◽  
Urban Areas ◽  
Air Pollutants ◽  
Pearson Correlation ◽  
Water Area ◽  
Air Pollutant ◽  
Cultivated Land ◽  
Bare Land

Land use changes have significantly altered the natural environment in which humans live. In urban areas, diminishing air quality poses a large threat to human health. In order to investigate the relationship between land use/cover change (LUCC) and air pollutants of Wuyishan City between 2014–2017, an integrated approach was used by combining remote sensing techniques with a landscape ecology methods. Annual, seasonal, and weekly mean values of air pollutant (SO2, NO2, CO, PM10, O3, PM2.5, black carbon) concentration and atmospheric visibility were calculated to develop a Pearson correlation between LUCC and air pollutants concentration. Results showed an increase in forested areas (1.79%) and water areas (15.89%), with a simultaneous reduction in cultivated land (6.47%), bare land (72.61%), and built-up land (16.03%) from 2014 to 2017. The transition matrix of land use types revealed that (i) forest expansion took place mainly at the expense of cultivated land (13.94%) and bare land (27.48%); and (ii) water area expansion took place mainly at the expense of cultivated land (1.29%) and forests (0.21%). In 2017, the proportion of days with AQI level I (94.52%) was higher than that in 2014 (88.77%). Additionally, the annual average visibility in 2017 (37.42 km) was higher than 2014 (27.46 km). The concentration of SO2, CO, O3, and black carbon was positively correlated with the cultivated land. The concentration of SO2, CO, and black carbon negatively correlated with the increase of forests. PM10, and PM2.5 is negatively correlated with the water area. Visibility was found to be positively correlated with forested area, and negatively correlated with cultivated land. The findings from this study represent a valuable gain in understanding of policies aimed at improving, safeguarding, and monitoring air quality. These results can be used to inform land-use planning decisions in a comprehensive way and could be a valuable tool for LUCC rational management strategies.

scholarly journals Reliable Low-Cost Air Quality Monitoring Using Off-The-Shelf Sensors and Statistical Calibration

2020 ◽  
Vol 26 (2) ◽  
pp. 32-41
Author(s):  
Dejan D. Drajic ◽  
Nenad R. Gligoric
Keyword(s):  
Air Quality ◽  
High Reliability ◽  
Low Cost ◽  
Quality Parameters ◽  
Air Quality Monitoring ◽  
Short Life ◽  
Short Intervals ◽  
Modern Cities ◽  
Public Monitoring ◽  
Monitoring Stations

Modern cities are densely populated spaces and number of people living in cities is increasing rapidly by years. The air monitoring stations exist in most of the cities to monitor air pollution. However, their number is insufficient having in mind the high cost of stations, as well as annual calibration cost. The potential solution is to use low-cost off-the-shelf sensors to monitor related air quality parameters, but they are not reliable due to the low accuracy, calibration issues, and short life cycle. In this paper, the methodology is proposed for calibration off-the-shelf air quality sensors using statistical algorithms and offset values from the official public measurement stations. The possibilities are analysed to improve the reliability of low-cost sensors by processing the obtained raw data. Special attention is devoted to the detection and elimination of short intervals when the raw results have the extraordinary high value-peaks and to the corresponding interpolation of these data. New algorithm for “peaks” detection and elimination is proposed and evaluated. Common Air Quality Index (CAQI) is calculated and evaluated in comparison with public monitoring station. It is shown that low-cost sensors could be used with high reliability as a complementary network to public monitoring stations.

scholarly journals Analysis of Internally Generated Goodwill Indicators: A Case Study of the Slovak Republic

Organizacija ◽  
2019 ◽  
Vol 52 (4) ◽  
pp. 271-285 ◽  
Author(s):  
Ivana Podhorska ◽  
Lubica Gajanova ◽  
Jana Kliestikova ◽  
Gheorghe H. Popescu
Keyword(s):  
Slovak Republic ◽  
Pearson Correlation ◽  
Financial Economic ◽  
Significance Test ◽  
Coefficient Of Determination ◽  
Future Research ◽  
Inflation Factor ◽  
Input Variables ◽  
Key Indicators

Abstract Background and purpose: Knowing key indicators of goodwill value can contribute to its effective management and growth of the market value of the enterprise. The purpose of this research is to identify individual goodwill indicators. The paper aim is to obtain potential indicators of enterprise goodwill under the conditions of the Slovak Republic. Design/Methodology/Approach: Paper data included 11,483 financial statements of Slovak enterprises in 2017. The value of residual enterprise income represents the value of goodwill. Input data for the identification of goodwill indicators represented 15 financial-economic variables. Outliers in data were searched and removed through an interquartile range. Multicollinearity among input variables, by the coefficient of determination and variance inflation factor, was also analysed. A statistically significant correlation between goodwill and its potential indicator were tested by the significance test of the Pearson correlation coefficient and correlation matrixes. Results: Research results reveal the existence of a statistically significant correlation between goodwill and 8 input variables, which represent its potential vital indicators. Conclusion: Paper findings bring new possibilities for goodwill management, which may create an essential competitive advantage of a company. For the scientific community, the findings represent sources of potential goodwill indicators which can be used for the creation of the new model of goodwill valuation in future research.

scholarly journals Low-Cost Air Quality Measurement System Based on Electrochemical and PM Sensors with Cloud Connection

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6228
Author(s):  
Patricia Arroyo ◽  
Jaime Gómez-Suárez ◽  
José Ignacio Suárez ◽  
Jesús Lozano
Keyword(s):  
Air Quality ◽  
Low Cost ◽  
Pearson Correlation ◽  
Quality Measurement ◽  
Measurement Unit ◽  
Published Data ◽  
Time Data ◽  
Cost System ◽  
Particle Matter ◽  
Pm2.5 And Pm10

This paper presents a portable device for outdoor air quality measurement that provides concentration values for the main pollutants: NO2, NO, CO, O3, PM2.5 and PM10, and other values such as temperature, humidity, location, and date. The device is based on the use of commercial electrochemical gas and optical particle matter sensors with a careful design of the electronics for reducing the electrical noise and increasing the accuracy of the measurements. The result is a low-cost system with IoT technology that connects to the Internet through a GSM module and sends all real-time data to a cloud platform with storage and computational potential. Two identical devices were fabricated and installed on a mobile reference measurement unit and deployed in Badajoz, Spain. The results of a two-month field campaign are presented and published. Data obtained from these measurements were calibrated using linear regression and neural network techniques. Good performance has been achieved for both gaseous pollutants (with a Pearson correlation coefficient of up to 0.97) and PM sensors.

scholarly journals The Association Between Air Quality Parameters and COVID-19 in Turkey

2020 ◽  
Author(s):  
Mehmet Şahin
Keyword(s):  
Air Quality ◽  
Air Pollutants ◽  
Significant Positive Correlation ◽  
Eating Habits ◽  
Statistical Tests ◽  
Pearson Correlation ◽  
Quality Parameters ◽  
Personal Hygiene ◽  
Test Results ◽  
The Relationship

Background: Coronavirus disease 2019 (COVID-19) is an invisible enemy that has made people observe issues such as eating habits, personal hygiene, and environmental factors that may affect their immune systems. Objectives: Because air pollution can affect the immune system, it is necessary to examine the relationship between air quality parameters and COVID-19.  Methods: his study examines the correlation between air quality and COVID-19 considering 7 air pollutants: PM10, SO2, CO, NO2, NOx, NO, and O3. The confirmed COVID-19 cases were considered from 9 provinces, accounting for 78% of the total cases in Turkey. The required data were collected from the websites of the country’s relevant official institutions. Two statistical tests, the Pearson correlation, and Spearman Rho were conducted to determine any potential linear and monotonic relationships.  Results: Based on both test results, a significant positive correlation was observed between air SO2 content and the number of COVID-19 cases in Turkey. Conclusion: The outcomes could help identify provincial actions or measures.

Sign in / Sign up

Export Citation Format

Share Document