Ari Karppinen

Extensive evaluation of neural network models for the prediction of NO2 and PM10 concentrations, compared with a deterministic modelling system and measurements in central Helsinki

Five neural network (NN) models, a linear statistical model and a deterministic modelling system (DET) were evaluated for the prediction of urban NO2 and PM10 concentrations. The model evaluation work considered the sequential hourly concentration time series of NO2 and PM10, which were measured at two stations in central Helsinki, from 1996 to 1999. The models utilised selected traffic flow and pre-processed meteorological variables as input data. An imputed concentration dataset was also created, in which the missing values were replaced, in order to obtain a harmonised database that is well suited for the inter-comparison of models. Three statistical criteria were adopted: the index of agreement (IA), the squared correlation coefficient (R2) and the fractional bias. The results obtained with various non-linear NN models show a good agreement with the measured concentration data for NO2; for instance, the annual mean of the IA values and their standard deviations range from 0.86±0.02 to 0.91±0.01. In the case of NO2, the non-linear NN models produce a range of model performance values that are slightly better than those by the DET. NN models generally perform better than the statistical linear model, for predicting both NO2 and PM10 concentrations. In the case of PM10, the model performance statistics of the NN models were not as good as those for NO2 over the entire range of models considered. However, the currently available NN models are neither applicable for predicting spatial concentration distributions in urban areas, nor for evaluating air pollution abatement scenarios for future years.

Evolving the neural network model for forecasting air pollution time series

Abstract The modelling of real-world processes such as air quality is generally a difficult task due to both their chaotic and non-linear phenomenon and high dimensional sample space. Despite neural networks (NN) have been used successfully in this domain, the selection of network architecture is still problematic and time consuming task when developing a model for practical situation. This paper presents a study where a parallel genetic algorithm (GA) is used for selecting the inputs and designing the high-level architecture of a multi-layer perceptron model for forecasting hourly concentrations of nitrogen dioxide at a busy urban traffic station in Helsinki. In addition, the tuning of GAs parameters for the problem is considered in experimental way. The results showed that the GA is a capable tool for tackling the practical problems of neural network design. However, it was observed that the evaluation of NN models is a computationally expensive process, which set limits for the search techniques.

A modelling system for predicting urban air pollution: model description and applications in the Helsinki metropolitan area

Abstract We have developed a modelling system for evaluating the traffic volumes, emissions from stationary and vehicular sources, and atmospheric dispersion of pollution in an urban area. The dispersion modelling is based on combined application of the urban dispersion modelling system (UDM-FMI) and the road network dispersion model (CAR-FMI). The system includes also a meteorological pre-processing model and a statistical and graphical analysis of the computed time series of concentrations. The modelling system contains a method, which allows for the chemical interaction of pollutants, originating from a large number of urban sources. This paper presents an overview of the modelling system and its application for estimating the NOx and NO2 concentrations in the Helsinki metropolitan area in 1993. A companion paper addresses comparison of model predictions with the results of an urban measurement network. This modelling system is an important regulatory assessment tool for the national environmental authorities.

A model for evaluating the population exposure to ambient air pollution in an urban area

A mathematical model is presented for the determination of human exposure to ambient air pollution in an urban area. The main objective was to evaluate the spatial and temporal variation of average exposure of the urban population to ambient air pollution in different microenvironments with reasonable accuracy, instead of analysing in detail personal exposures for specific individuals. We have utilised a previously developed modelling system for predicting the traffic flows and emissions, emissions originating from stationary sources, and atmospheric dispersion of pollution in an urban area. A model was developed for combining the predicted concentrations, information on peoples activities (such as the time spent at home, in the workplace and at other places of activity during the day) and location of the population. Time-microenvironment activity data for the working-age population was obtained from the EXPOLIS study (air pollution distributions within adult urban populations in Europe). Information on the location of homes and workplaces was obtained from local municipalities. The concentrations of NO2 were modelled over the Helsinki Metropolitan Area for 1996 and 1997. The computed results were processed and visualised using the geographical information system (GIS) MapInfo. The utilisation of the modelling system has been illustrated by presenting numerical results for the Helsinki Metropolitan Area. The results show the spatial and temporal (diurnal) variation of the ambient air NO2 concentrations, the population density and the corresponding average exposure. The model developed has been designed to be utilised by municipal authorities in urban planning, e.g., for evaluating the impacts of traffic planning and land use scenarios.

A modelling system for predicting urban air pollution: comparison of model predictions with the data of an urban measurement network in Helsinki

We have developed a modelling system for predicting the tra

Intercomparison of air quality data using principal component analysis, and forecasting of PM10 and PM2.5 concentrations using artificial neural networks, in Thessaloniki and Helsinki

c volumes, emissions from stationary and vehicular sources, and atmospheric dispersion of pollution in an urban area. A companion paper addresses model development and its applications. This paper describes a comparison of the predicted NO x and NO 2 concentrations with the results of an urban air quality monitoring network. We performed a statistical analysis concerning the agreement of the predicted and measured hourly time series of concentrations, at four monitoring stations in the Helsinki metropolitan area in 1993. The predicted and measured NO 2 concentrations agreed well at all the stations considered. The agreement of model predictions and measurements for NO x and NO 2 was better for the two suburban monitoring stations, compared with the two urban stations, located in downtown Helsinki. ( 2000 Elsevier Science Ltd. All rights reserved.

Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki

In this paper we propose a methodology consisting of specific computational intelligence methods, i.e. principal component analysis and artificial neural networks, in order to inter-compare air quality and meteorological data, and to forecast the concentration levels for environmental parameters of interest (air pollutants). We demonstrate these methods to data monitored in the urban areas of Thessaloniki and Helsinki in Greece and Finland, respectively. For this purpose, we applied the principal component analysis method in order to inter-compare the patterns of air pollution in the two selected cities. Then, we proceeded with the development of air quality forecasting models for both studied areas. On this basis, we formulated and employed a novel hybrid scheme in the selection process of input variables for the forecasting models, involving a combination of linear regression and artificial neural networks (multi-layer perceptron) models. The latter ones were used for the forecasting of the daily mean concentrations of PM₁₀ and PM₂.₅ for the next day. Results demonstrated an index of agreement between measured and modelled daily averaged PM₁₀ concentrations, between 0.80 and 0.85, while the kappa index for the forecasting of the daily averaged PM₁₀ concentrations reached 60% for both cities. Compared with previous corresponding studies, these statistical parameters indicate an improved performance of air quality parameters forecasting. It was also found that the performance of the models for the forecasting of the daily mean concentrations of PM₁₀ was not substantially different for both cities, despite the major differences of the two urban environments under consideration.

A measurement campaign in a street canyon in Helsinki and comparison of results with predictions of the OSPM model

Forecasting models based on stepwise multiple linear regression (MLR) have been developed for Athens and Helsinki. The predictor variables were the hourly concentrations of pollutants (NO, NO(2), NO(x), CO, O(3), PM(2.5) and PM(10)) and the meteorological variables (ambient temperature, wind speed/direction, and relative humidity) and in case of Helsinki also Monin-Obukhov length and mixing height of the present day. The variables to be forecasted are the maximum hourly concentrations of PM(10) and NO(x), and the daily average PM(10) concentrations of the next day. The meteorological pre-processing model MPP-FMI was used for computing the Monin-Obukhov length and the mixing height. The limitations of such statistical models include the persistence of both the meteorological and air quality situation; the model cannot account for rapid changes (on a temporal scale of hours or less than a day) that are commonly associated, e.g., with meteorological fronts, or episodes of a long-range transport origin. We have selected the input data for the model from one urban background and one urban traffic station both in Athens and Helsinki, in 2005. We have used various statistical evaluation parameters to analyze the performance of the models, and inter-compared the performance of the predictions for both cities. Forecasts from the MLR model were also compared to those from an Artificial Neural Network model (ANN) to investigate, if there are substantial gains that might justify the additional computational effort. The best predictor variables for both cities were the concentrations of NO(x) and PM(10) during the evening hours as well as wind speed, and the Monin-Obukhov length. In Athens, the index of agreement (IA) for NO(x) ranged from 0.77 to 0.84 and from 0.69 to 0.72, in the warm and cold periods of the year. In Helsinki, the corresponding values of IA ranged from 0.32 to 0.82 and from 0.67 to 0.86 for the warm and cold periods. In case of Helsinki the model accuracy was expectedly better on the average, when Monin-Obukhov length and mixing height were included as predictor variables. The models provide better forecasts of the daily average concentration, compared with the maximum hourly concentration for PM(10). The results derived by the ANN model where only slightly better than the ones derived by the MLR methodology. The results therefore suggest that the MLR methodology is a useful and fairly accurate tool for regulatory purposes.

Evaluation of the OSPM model combined with an urban background model against the data measured in 1997 in Runeberg Street, Helsinki

In 1997, a measuring campaign was conducted in a street canyon (Runeberg St.) in Helsinki. Hourly mean concentrations of CO, NOx, NO2 and O3 were measured at street and roof levels, the latter in order to determine the urban background concentrations. The relevant hourly meteorological parameters were measured at roof level; these included wind speed and direction, temperature and solar radiation. Hourly street level measurements and on-site electronic traffic counts were conducted throughout the whole of 1997; roof level measurements were conducted for approximately two months, from 3 March to 30 April in 1997. CO and NOx emissions from traffic were computed using measured hourly traffic volumes and evaluated emission factors. The Operational Street Pollution Model (OSPM) was used to calculate the street concentrations and the results were compared with the measurements. The overall agreement between measured and predicted concentrations was good for CO and NOx (fractional bias were −4.2 and +4.5%, respectively), but the model overpredicted the measured NO2 concentrations (fractional bias was +22%). The agreement between the measured and predicted values was also analysed in terms of its dependence on wind speed and direction; the latter analysis was performed separately for two categories of wind velocity. The model qualitatively reproduces the observed behaviour very well. The database, which contains all measured and predicted data, is available for further testing of other street canyon dispersion models. The dataset contains a larger proportion of low wind speed cases, compared with other available street canyon measurement datasets.

Investigating the Surface Energy Balance in Urban Areas – Recent Advances and Future Needs

Abstract In 1997, a measuring campaign was conducted in a street canyon (Runeberg Street) in Helsinki. Hourly street level measurements and on-site electronic traffic counts were conducted throughout the whole of 1997; roof level measurements were conducted for approximately two months during the so-called intensive measuring campaign, from 3 March to 30 April 1997. Hourly mean concentrations of NOx, NO2, O3 and CO were measured at street and roof levels; the relevant hourly meteorological parameters were measured at roof level. We present here an evaluation of the Operational Street Pollution Model (OSPM) street canyon dispersion model against the data measured during the whole of 1997. As the roof level concentrations and meteorological measurements were not available for the whole year, we utilised computed or meteorologically pre-processed values. The use of modelled urban background concentrations and meteorological values (instead of on-site roof level measurements) did not lessen the agreement between modelled and measured average concentration values at street level. The agreement between the temporal variations of predictions and measured data was also fairly good; for instance, the corresponding index of agreement values for NOx, NO2 and CO were 0.89, 0.81 and 0.87, respectively. However, as expected, the agreement in the temporal variations was somewhat better using actual measured on-site data during the intensive measuring campaign, than when using modelled urban background concentrations and meteorological values. This study demonstrates that it is possible to utilise the street canyon dispersion model OSPM with reasonable accuracy using modelled urban background and pre-processed meteorological values as model input.