A Pilot Indoor-Outdoor Study of Organic Particulate Matter and Particulate Mutagenicity

Abstract

Many large metropolitan areas experience elevated concentrations of ground-level ozone pollution during the summertime “smog season”. Local environmental or health agencies often need to make daily air pollution forecasts for public advisories and for input into decisions regarding abatement measures and air quality management. Such forecasts are usually based on statistical relationships between weather conditions and ambient air pollution concentrations. Multivariate linear regression models have been widely used for this purpose, and well-specified regressions can provide reasonable results. However, pollution-weather relationships are typically complex and nonlinear—especially for ozone—properties that might be better captured by neural networks. This study investigates the potential for using neural networks to forecast ozone pollution, as compared to traditional regression models. Multiple regression models and neural networks are examined for a range of cities under different climate and ozone regimes, enabling a comparative study of the two approaches. Model comparison statistics indicate that neural network techniques are somewhat (but not dramatically) better than regression models for daily ozone prediction, and that all types of models are sensitive to different weather-ozone regimes and the role of persistence in aiding predictions.     

Evolution of air quality in the Sao Paulo metropolitan area and its relation with public policies

The Sao Paulo Metropolitan Area (SPMA) is one of the largest urban regions in the world, with more than 17 million inhabitants, about 2000 major industrial facilities, and more than 6 million vehicles based on diesel, gasoline, and ethanol. The area is thus a representative example of large urban region. The accumulated data collected by a network of air quality measuring stations, distributed throughout the SPMA, enables the monitoring of the air quality and is an adequate source of information for checking the effect of air quality control measures in the region. The present work shows that, although the levels of primary air pollutants have decreased over the last 20 years, events with high levels of NO₂, CO, particulate material and ozone still take place. In the last five years, ozone has become the most problematic pollutant, in view of the high frequency of peak events. Increased control of emission sources and adequate planning of the urban area, especially concerning the traffic system, are both necessary in order to keep pollution in the area under established levels.     

A neural network model forecasting for prediction of daily maximum ozone concentration in an industrialized urban area

Prediction of ambient ozone concentrations in urban areas would allow evaluation of such factors as compliance and noncompliance with EPA requirements. Though ozone prediction models exist, there is still a need for more accurate models. Development of these models is difficult because the meteorological variables and photochemical reactions involved in ozone formation are complex. In this study, we developed a neural network model for forecasting daily maximum ozone levels. We then compared the neural network's performance with those of two traditional statistical models, regression, and Box-Jenkins ARIMA. The neural network model for forecasting daily maximum ozone levels is different from the two statistical models because it employs a pattern recognition approach. Such an approach does not require specification of the structural form of the model. The results show that the neural network model is superior to the regression and Box-Jenkins ARIMA models we tested.     

Systematic development of an artificial neural network model for real-time prediction of ground-level ozone in Edmonton, Alberta, Canada

Ground-level ozone is a secondary pollutant that has recently gained notoriety for its detrimental effects on human and vegetation health. In this paper, a systematic approach is applied to develop artificial neural network (ANN) models for ground-level ozone (O3) prediction in Edmonton, Alberta, Canada, using ambient monitoring data for input. The intent of these models is to provide regulatory agencies with a tool for addressing data gaps in ambient monitoring information and predicting O3 events. The models are used to determine the meteorological conditions and precursors that most affect O3 concentrations. O3 time-series effects and the efficacy of the systematic approach are also assessed. The developed models showed good predictive success, with coefficient of multiple determination values ranging from 0.75 to 0.94 for forecasts up to 2 hr in advance. The inputs most important for O3 prediction were temperature and concentrations of nitric oxide, total hydrocarbons, sulfur dioxide, and nitrogen dioxide.     

Relation between ozone levels and NOx and VOC emissions in the Sao Paulo Metropolitan Area for an episode of August, 1998

At present, major efforts in air pollution control for urban areas are oriented to reduce ozone levels to below standards. Models are a useful tool for air quality assessment and they can help to select the best strategy plan to reduce ozone levels in a polluted area. Like other large cities in the world, Sao Paulo Metropolitan Area (SPMA) has registered high levels of ozone and particulate matter for several decades. In order to establish appropriate strategy plans, a photochemical model has been used for an episode that occurred in 1999. Simple emission control strategies have been examined.     

Prediction of hourly O3 concentrations using support vector regression algorithms

In this paper we present an application of the Support Vector Regression algorithm (SVMr) to the prediction of hourly ozone values in Madrid urban area. In order to improve the training capacity of SVMrs, we have used a recently proposed approach, based on reductions of the SVMr hyper-parameters search space. Using the modified SVMr, we study different influences which may modify the ozone prediction, such as previous ozone measurements in a given station, measurements in neighbors stations, and the influence of meteorologic variables. We use statistical tests to verify the significance of incorporating different variables into the SVMr. A comparison with the results obtained using a neural network (multi-layer perceptron) is also carried out. This study has been carried out in 5 different stations of the air pollution monitoring network of Madrid, so the conclusions raised are backed by real data. The final result of the work is a robust and powerful software for tropospheric ozone prediction in Madrid. Also, the prediction tool based on SVMr is flexible enough to incorporate any other prediction variable, such as city models, or traffic patters, which may improve the prediction obtained with the SVMr.     

Extreme value modeling for the analysis and prediction of time series of extreme tropospheric ozone levels: a case study

The occurrence of high concentrations of tropospheric ozone is considered as one of the most important issues of air management programs. The prediction of dangerous ozone levels for the public health and the environment, along with the assessment of air quality control programs aimed at reducing their severity, is of considerable interest to the scientific community and to policy makers. The chemical mechanisms of tropospheric ozone formation are complex, and highly variable meteorological conditions contribute additionally to difficulties in accurate study and prediction of high levels of ozone. Statistical methods offer an effective approach to understand the problem and eventually improve the ability to predict maximum levels of ozone. In this paper an extreme value model is developed to study data sets that consist of periodically collected maxima of tropospheric ozone concentrations and meteorological variables. The methods are applied to daily tropospheric ozone maxima in Guadalajara City, Mexico, for the period January 1997 to December 2006. The model adjusts the daily rate of change in ozone for concurrent impacts of seasonality and present and past meteorological conditions, which include surface temperature, wind speed, wind direction, relative humidity, and ozone. The results indicate that trend, annual effects, and key meteorological variables along with some interactions explain the variation in daily ozone maxima. Prediction performance assessments yield reasonably good results.     

Forecasts using neural network versus Box-Jenkins methodology for ambient air quality monitoring data

This study explores ambient air quality forecasts using the conventional time-series approach and a neural network. Sulfur dioxide and ozone monitoring data collected from two background stations and an industrial station are used. Various learning methods and varied numbers of hidden layer processing units of the neural network model are tested. Results obtained from the time-series and neural network models are discussed and compared on the basis of their performance for 1-step-ahead and 24-step-ahead forecasts. Although both models perform well for 1-step-ahead prediction, some neural network results reveal a slightly better forecast without manually adjusting model parameters, according to the results. For a 24-step-ahead forecast, most neural network results are as good as or superior to those of the time-series model. With the advantages of self-learning, self-adaptation, and parallel processing, the neural network approach is a promising technique for developing an automated short-term ambient air quality forecast system.     

Systematic Development of an Artificial Neural Network Model for Real-Time Prediction of Ground-Level Ozone in Edmonton,Alberta, Canada

Abstract

Ground-level ozone is a secondary pollutant that has recently gained notoriety for its detrimental effects on human and vegetation health. In this paper, a systematic approach is applied to develop artificial neural network (ANN) models for ground-level ozone (O₃) prediction in Edmonton, Alberta, Canada, using ambient monitoring data for input. The intent of these models is to provide regulatory agencies with a tool for addressing data gaps in ambient monitoring information and predicting O₃ events. The models are used to determine the meteorological conditions and precursors that most affect O₃ concentrations. O₃ time-series effects and the efficacy of the systematic approach are also assessed. The developed models showed good predictive success, with coefficient of multiple determination values ranging from 0.75 to 0.94 for forecasts up to 2 hr in advance. The inputs most important for O₃ prediction were temperature and concentrations of nitric oxide, total hydrocarbons, sulfur dioxide, and nitrogen dioxide.     

Ground-level ozone in the Pearl River Delta region: Analysis of data from a recently established regional air quality monitoring network

The ambient air quality monitoring data of 2006 and 2007 from a recently established Pearl River Delta (PRD) regional air quality monitoring network are analyzed to investigate the characteristics of ground-level ozone in the region. Four sites covering urban, suburban, rural and coastal areas are selected as representatives for detailed analysis in this paper. The results show that there are distinct seasonal and diurnal cycles in ground-level ozone across the PRD region. Low ozone concentrations are generally observed in summer, while high O₃ levels are typically found in autumn. The O₃ diurnal variations in the urban areas are larger than those at the rural sites. The O₃ concentrations showed no statistically significant difference between weekend and weekdays in contrast to the findings in many other urban areas in the world. The average ozone concentrations are lower in urban areas compared to the sites outside urban centers. Back trajectories are used to show the major air-mass transport patterns and to examine the changes in ozone from the respective upwind sites to a site in the center of the PRD (Wanqingsha). The results show higher average ozone concentrations at the upwind sites in the continental and coastal air masses, but higher 1 h-max O₃ concentrations (by 8–16 ppbv) at the center PRD site under each of air-mass category, suggesting that the ozone pollution in the PRD region exhibits both regional and super-regional characteristics.     

Prediction of ozone concentrations in Oporto city with statistical approaches

The performance of three statistical methods: time-series, multiple linear regression and feedforward artificial neural networks models were compared to predict the daily mean ozone concentrations. The study here reported was based on data from one urban site with traffic influences and one rural background site. The studies were performed for the year 2002 and the respective four trimesters separately. In the multiple linear regression and feedforward artificial neural network models, the concentrations of ozone, the concentrations of its precursors (nitrogen oxides) and some meteorological variables for one and two days before the prediction day were used as predictors. For the application of these models in the validation step, the inputs of ozone concentration for one and two days before were replaced by the ozone concentrations predicted by the models. The results showed that time-series modelling was not profitable. In the development step, similar performances were obtained with multiple linear regression and feedforward artificial neural network. Better performance indexes were achieved with feedforward artificial neural network models in validation step. Concluding, feedforward artificial neural network models were more efficient to predict ozone concentrations.     

Interval estimation of urban ozone level and selection of influential factors by employing automatic relevance determination model

In this work, we focus on simulating the ground-level ozone (O3) time series and its daily maximum concentration in Hong Kong urban air by employing the multilayer perceptron (MLP) model combined with the automatic relevance determination (ARD) method (for simplicity, we name it as MLP-ARD model). Two air quality monitoring sites in Hong Kong, i.e., Tsuen Wan and Tung Chung, are selected for the numerical experiments. The MLP-ARD model based on Bayesian evidence framework can provide reliable interval estimation of real observation as well as offering efficient strategy to avoid over-fitting. The performance comparisons between MLP-ARD model and traditional artificial neural network (ANN) model based on maximum likelihood indicate that MLP-ARD model is more powerful to capture the wild fluctuation of O3 level especially during O3 episodes than the traditional model. Furthermore, it can assess and rank the input variables for the prediction according to their relative importance to the output variable, i.e., the daily maximum O3 concentration in this study. The preliminary experimental results indicate that nitric oxide (NO) and solar radiation are the most important input variables for O3 prediction at both selected sites. In addition, the previous daily maximum O3 level is also important for Tung Chung site. In this regard, MLP-ARD model is a feasible tool to interpret the real physical and chemical process of urban O3 variation.     

Forecasting summertime surface-level ozone concentrations in the Lower Fraser Valley of British Columbia: an ensemble neural network approach

Empirical models for predicting daily maximum hourly average ozone concentrations were developed for 10 monitoring stations in the Lower Fraser Valley (LFV) of British Columbia. According to data from 1991 to 1996, ensemble neural network models increased explained variance an average of 7% over multiple linear regression models using the same input variables. Without modification, all models performed poorly on days when the observed peak ozone concentration exceeded 82 parts per billion, the National Ambient Air Quality Objective. When numbers of extreme events in training data were increased using a histogram equalization process, models were able to forecast exceedances with improved accuracy. Modified generalized additive model (GAM) plots and associated measures of input variable importance and interaction were generated for a subset of the trained models and used to investigate relationships between input variables and ozone levels. The neural network models displayed a high degree of interaction among inputs, and it is likely the ability of these model types to account for interactions, rather than the nonlinearity of individual input variables, that explains their improved forecast skill. Inspection of GAM-style plots indicated that the relative importance of input variables in the ensemble neural network models varied with geographic location within the LFV. Four distinct groups of stations were identified, and rankings of inputs within the groups were generally consistent with physical intuition and results of prior studies.     

Stochastic model to forecast ground-level ozone concentration at urban and rural areas

Stochastic models that estimate the ground-level ozone concentrations in air at an urban and rural sampling points in South-eastern Spain have been developed. Studies of temporal series of data, spectral analyses of temporal series and ARIMA models have been used. The ARIMA model (1,0,0) x (1,0,1)24 satisfactorily predicts hourly ozone concentrations in the urban area. The ARIMA (2,1,1) x (0,1,1)24 has been developed for the rural area. In both sampling points, predictions of hourly ozone concentrations agree reasonably well with measured values. However, the prediction of hourly ozone concentrations in the rural point appears to be better than that of the urban point. The performance of ARIMA models suggests that this kind of modelling can be suitable for ozone concentrations forecasting.     

Predictive mapping of air pollution involving sparse spatial observations

A limited number of sample points greatly reduces the availability of appropriate spatial interpolation methods. This is a common problem when one attempts to accurately predict air pollution levels across a metropolitan area. Using ground-level ozone concentrations in the Tucson, Arizona, region as an example, this paper discusses the above problem and its solution, which involves the use of linear regression. A large range of temporal variability is used to compensate for sparse spatial observations (i.e. few ozone monitors). Gridded estimates of emissions of ozone precursor chemicals, which are developed, stored, and manipulated within a geographic information system, are the core predictor variables in multiple linear regression models. Cross-validation of the pooled models reveals an overall R2 of 0.90 and approximately 7% error. Composite ozone maps predict that the highest ozone concentrations occur in a monitor-less area on the eastern edge of Tucson. The maps also reveal the need for ozone monitors in industrialized areas and in rural, forested areas.     

Predicting hourly air pollutant levels using artificial neural networks coupled with uncertainty analysis by Monte Carlo simulations

Recent progress in developing artificial neural network (ANN) metamodels has paved the way for reliable use of these models in the prediction of air pollutant concentrations in urban atmosphere. However, improvement of prediction performance, proper selection of input parameters and model architecture, and quantification of model uncertainties remain key challenges to their practical use. This study has three main objectives: to select an ensemble of input parameters for ANN metamodels consisting of meteorological variables that are predictable by conventional weather forecast models and variables that properly describe the complex nature of pollutant source conditions in a major city, to optimize the ANN models to achieve the most accurate hourly prediction for a case study (city of Tehran), and to examine a methodology to analyze uncertainties based on ANN and Monte Carlo simulations (MCS). In the current study, the ANNs were constructed to predict criteria pollutants of nitrogen oxides (NO_x), nitrogen dioxide (NO₂), nitrogen monoxide (NO), ozone (O₃), carbon monoxide (CO), and particulate matter with aerodynamic diameter of less than 10 μm (PM₁₀) in Tehran based on the data collected at a monitoring station in the densely populated central area of the city. The best combination of input variables was comprehensively investigated taking into account the predictability of meteorological input variables and the study of model performance, correlation coefficients, and spectral analysis. Among numerous meteorological variables, wind speed, air temperature, relative humidity and wind direction were chosen as input variables for the ANN models. The complex nature of pollutant source conditions was reflected through the use of hour of the day and month of the year as input variables and the development of different models for each day of the week. After that, ANN models were constructed and validated, and a methodology of computing prediction intervals (PI) and probability of exceeding air quality thresholds was developed by combining ANNs and MCSs based on Latin Hypercube Sampling (LHS). The results showed that proper ANN models can be used as reliable metamodels for the prediction of hourly air pollutants in urban environments. High correlations were obtained with R ² of more than 0.82 between modeled and observed hourly pollutant levels for CO, NO_x, NO₂, NO, and PM₁₀. However, predicted O₃ levels were less accurate. The combined use of ANNs and MCSs seems very promising in analyzing air pollution prediction uncertainties. Replacing deterministic predictions with probabilistic PIs can enhance the reliability of ANN models and provide a means of quantifying prediction uncertainties.     

Study of atmospheric ozone formation by means of a neural network-based model

The occurrence of high ozone levels in the atmosphere of urban areas has become a serious pollution problem in a number of large cities in the world. Although mathematical models have been proposed for predicting ozone concentrations as a function of a number of gas components, sometimes there are uncertainties due to lack of the combined effects of meteorological factors and the complex chemical reaction system involved. The application of neural network models, based on measured values of air pollutants and meteorological factors at different locations within the S?o Paulo Metropolitan Area, combine chemical and meteorological information. This has shown to be a promising tool for predicting ozone concentration. Simulations carried out with the model indicate the sensitivity of ozone in relation to different air pollution and weather conditions. Predictions using this model have shown good agreement with measured values of ozone concentrations.     

Modeling and direct sensitivity analysis of biogenic emissions impacts on regional ozone formation in the Mexico-U.S. border area

A spatially and temporally resolved biogenic hydrocarbon and nitrogen oxides (NOx) emissions inventory has been developed for a region along the Mexico-U.S. border area. Average daily biogenic non-methane organic gases (NMOG) emissions for the 1700 x 1000 km2 domain were estimated at 23,800 metric tons/day (62% from Mexico and 38% from the United States), and biogenic NOx was estimated at 1230 metric tons/day (54% from Mexico and 46% from the United States) for the July 18-20, 1993, ozone episode. The biogenic NMOG represented 74% of the total NMOG emissions, and biogenic NOx was 14% of the total NOx. The CIT photochemical airshed model was used to assess how biogenic emissions impact air quality. Predicted ground-level ozone increased by 5-10 ppb in most rural areas, 10-20 ppb near urban centers, and 20-30 ppb immediately downwind of the urban centers compared to simulations in which only anthropogenic emissions were used. A sensitivity analysis of predicted ozone concentration to emissions was performed using the decoupled direct method for three dimensional air quality models (DDM-3D). The highest positive sensitivity of ground-level ozone concentration to biogenic volatile organic compound (VOC) emissions (i.e., increasing biogenic VOC emissions results in increasing ozone concentrations) was predicted to be in locations with high NOx levels, (i.e., the urban areas). One urban center--Houston--was predicted to have a slight negative sensitivity to biogenic NO emissions (i.e., increasing biogenic NO emissions results in decreasing local ozone concentrations). The highest sensitivities of ozone concentrations to on-road mobile source VOC emissions, all positive, were mainly in the urban areas. The highest sensitivities of ozone concentrations to on-road mobile source NOx emissions were predicted in both urban (either positive or negative sensitivities) and rural (positive sensitivities) locations.     

Application of the Urban Airshed Model to forecasting next-day peak ozone concentrations in Atlanta, Georgia

Twenty-four to forty-eight-hour ozone air quality forecasts are increasingly being used in metropolitan areas to inform the public about potentially harmful air quality conditions. The forecasts are also behind "ozone action day" programs in which the public and private sectors are encouraged or mandated to alter activities that contribute to the formation of ground-level ozone. Presented here is a low-cost application of the Urban Airshed Model (UAM), an Eulerian 3-dimensional photochemical-transport grid model for generating next-day peak ozone concentration forecasts. During the summer of 1997, next-day peak ozone concentrations in Atlanta, GA, were predicted both by a team of eight forecasters and by the Urban Airshed Model in Forecast Mode (UAM-FM). Results are presented that compare the accuracy of the team and the UAM-FM. The results for the summer of 1997 indicate that the UAM-FM may be a better predictor of peak ozone concentrations when concentrations are high (> 0.095 ppmv), and the team may be a better predictor of ozone concentrations when concentrations are low (< or = 0.095 ppmv). The UAM-FM is also discussed in the context of other forecasting tools, primarily linear regression models and a no-skill, persistence-based technique.