Residuals in the modelling of pollution concentration depending on meteorological conditions and traffic flow, employing decision trees

Kamińska, Joanna

doi:10.1051/itmconf/20182300016

Cited by 5 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[15] with two peaks: in the morning and in the afternoon. Meteorological hourly data are provided by the Institute of Meteorology and Water Management (IMGW) at only one station in Wrocław, located on the outskirts of the city (51.10319 N, 16.89985 E; 9 km from the intersection in a straight line). One can observe clear seasonal variation in temperature, characteristic of transitional climate type subject to both oceanic and continental influences.…”

Section: Data Sourcementioning

confidence: 99%

“…One of the main air pollutants emitted by car combustion engines is nitrogen oxides: NO2 and NOx = NO + NO2. In the literature there exist many different air pollution concentration models, e.g., multidimensional regression models [6][7][8], polynomial functions [9,10], artificial neural networks [11], single random trees [12], random forest (RF) [13][14][15] and boosted regression trees [16,17]. These models take into account, in addition to the current values, the past values of the explanatory variables, which have been used mainly to study the impact of pollution concentration on human health and life.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Lag Variables in Air Pollution Modeling Based on Traffic Flow and Meteorological Factors

Kamińska

Sciavicco

Lucena-Sánchez

et al. 2020

The 9th Innovations-Sustainability-Modernity-Openness Conference (ISMO’20)

Self Cite

View full text Add to dashboard Cite

In order to refine the research on the impact of environmental factors on the concentration of pollutants in the air, in this paper, we present a mathematical model that allows the possibility of taking into account the past values of factors (explanatory variables) when modeling the current concentration of pollution. We conducted numerical analyzes based on hourly data from meteorological, traffic and air quality monitoring stations in Wrocław (Poland, Central Europe) from 2015–2017. In order to determine the optimal delay of each explanatory variable, we used a multi-objective optimization model (MO). It turned out that for the concentration of nitrogen oxides, delayed traffic flow, wind speed and sunshine duration time are more important than current ones. Then we built two random forest models: an actual model of current values of explanatory variables and a lag model with delayed variables determined by the MO method. Taking into account variables with an optimal delay (lag model) results in an increase in model accuracy for NO2 with R2 = 0.51 to 0.56 and for NOx from 0.46 to 0.52. We deduced that in pollutant concentrations modeling, the possibility of greater influence of variables with delay should always be considered because it can significantly increase the accuracy of the model and indicate additional relationships or dependencies.

show abstract

Section: Data Sourcementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Lag Variables in Air Pollution Modeling Based on Traffic Flow and Meteorological Factors

Kamińska

Sciavicco

Lucena-Sánchez

et al. 2020

The 9th Innovations-Sustainability-Modernity-Openness Conference (ISMO’20)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The extension of linear models includes polynomial forms of functions-in which each variable may be raised to some power [10,11] and non-linear behavior can be taken into account. On the other end of this spectrum, there are models that do not require any assumption about a specific analytical function, also called black-box models, such as artificial neural networks [12,13], or those combined with multiple regression [14], single random trees [15], or more complex structures like random forest (RF) [16][17][18][19][20][21] and boosted regression trees (BRT) [22,23]. These models are more computationally advanced and have been successfully used in pollution concentration modeling.…”

Section: Introductionmentioning

confidence: 99%

Lag Variables in Nitrogen Oxide Concentration Modelling: A Case Study in Wrocław, Poland

et al. 2020

Self Cite

View full text Add to dashboard Cite

Due to the unwavering interest of both residents and authorities in the air quality of urban agglomerations, we pose the following question in this paper: What impact do current and past meteorological factors and traffic flow intensity have on air quality? What is the impact of lagged variables on the fit of an explanation model, and how do they affect its ability to predict? We focused on NO2 and NOx concentrations, and conducted this research using hourly data from the city of Wrocław (western Poland) from 2015 to 2017; we used multi-objective optimization to determine the optimal delays. It turned out that for both NO2 and NOx, the past values for traffic flow, wind speed, and sunshine duration are more important than the current ones. We built random forest models on each of the pollutants for both the current and past values and discovered that including a lagged variable increases the resulting R2 from 0.51 to 0.56 for NO2 and from 0.46 to 0.52 for NOx. We also analyzed the feature importance in each model, and found that for NO2, a wind speed delay of more than three hours causes a significant decrease, while the importance of relative humidity increases with a seven-hour delay; likewise, wind speed increases the importance for NOx prediction with a two-hour delay. We concluded that, in pollutant concentration modeling, the possibility of a delayed effect of the independent variables should always be considered, because it can significantly increase the performance of the model and suggest unexpected relationships or dependencies.

show abstract

“…Climate change could have a significant impact on urban socio-environmental systems [1][2][3], which impact over half of the global population [4]. There are many different environmental aspects that influence the urban metabolism which are mainly related with temperature [5][6][7][8], atmospheric precipitation [9][10][11][12][13], or the synergy between climate elements and human activity [14,15]. In order to reduce the urban vulnerability to these phenomena, a new pathway for cities is promoted on the supranational level-one which is based on urban adaptation to climate change [16][17][18].…”

Section: Introductionmentioning

confidence: 99%

The Development of a Novel Decision Support System for the Location of Green Infrastructure for Stormwater Management

Kazak

Chruściński²,

Szewrański

2018

Sustainability

View full text Add to dashboard Cite

In order to maximise the benefits of green infrastructure in a city’s structure for urban adaptation to climate change, there is a need to support decision-makers in the urban design domain with adequate information that would help them to locate such green infrastructure in the most suitable places. Therefore, the aim of this study was to develop a novel decision support system (DSS) for the location of green infrastructure. The goal of the designed solution is to inform users about the location of urban hydrological sinks, which gather stormwater in urban watersheds, and the amount of water which could accumulate in each location depending on the defined precipitation and the soil’s moisture conditions. The designed DSS is based on a multicomponent methodology including both atmospheric and soil conditions. The DSS was tested using a sample that presents the results of stormwater accumulation calculations. The obtained results show which green areas are the most suitable locations for green infrastructure solutions and which facility is optimal because of its retention abilities and amount of accumulated stormwater. The application of the designed DSS allows us to maximise the benefits of the implementation of green infrastructure within the existing urban land use. The fully editable component of hydrological conditions allows for testing projections of the potential amount of accumulated water in different precipitation scenarios. The study provides a DSS for use by local authorities which enables them to concentrate actions in order to better adapt cities to climate change and environmental extremes.

show abstract

Residuals in the modelling of pollution concentration depending on meteorological conditions and traffic flow, employing decision trees

Cited by 5 publications

References 28 publications

Lag Variables in Air Pollution Modeling Based on Traffic Flow and Meteorological Factors

Lag Variables in Air Pollution Modeling Based on Traffic Flow and Meteorological Factors

Lag Variables in Nitrogen Oxide Concentration Modelling: A Case Study in Wrocław, Poland

The Development of a Novel Decision Support System for the Location of Green Infrastructure for Stormwater Management

Contact Info

Product

Resources

About