Neural network and multiple regression models for PM10 prediction in Athens: a comparative assessment

Particulate atmospheric pollution in urban areas is considered to have significant impact on human health. Therefore, the ability to make accurate predictions of particulate ambient concentrations is important to improve public awareness and air quality management. This study examines the possibility of using neural network methods as tools for daily average particulate matter with aerodynamic diameter <10 microm (PM10) concentration forecasting, providing an alternative to statistical models widely used up to this day. Based on a data inventory, in a fixed central site in Athens, Greece, ranging over a two-year period, and using mainly meteorological variables as inputs, neural network models and multiple linear regression models were developed and evaluated. Comparison statistics used indicate that the neural network approach has an edge over regression models, expressed both in terms of prediction error (root mean square error values lower by 8.2-9.4%) and of episodic prediction ability (false alarm rate values lower by 7-13%). The results demonstrate that artificial neural networks (ANNs), if properly trained and formed, can provide adequate solutions to particulate pollution prognostic demands.     

Impacts of Meteorological Factors on PM10: Artificial Neural Networks (ANN) and Multiple Linear Regression (MLR) Approaches

In this study, prediction capacities of multi-linear regression (MLR) and artificial neural networks (ANN) onto coarse particulate matter (PM₁₀) concentrations were investigated. Different meteorological factors on particulate pollution were chosen for operating variables in the model analyses. Two different regions (urban and industrial) were identified in the region of Kocaeli, Turkey. All data sets were obtained from air quality monitoring network of the Ministry of Environment and Urban Planning, and 120 data sets were used in the MLR and ANN models. Regression equations explained the effects of the meteorological factors in MLR analyses. In the ANN model, backpropagation network with two hidden layers has achieved the best prediction efficiency. Determination coefficients and error values were examined for each model. ANN models displayed more accurate results compared to MLR.     

Two-days ahead prediction of daily maximum concentrations of SO2, O3, PM10, NO2, CO in the urban area of Palermo,Italy

Artificial neural networks are functional alternative techniques in modelling the intricate vehicular exhaust emission dispersion phenomenon. Pollutant predictions are notoriously complex when using either deterministic or stochastic models, which explains why this model was developed using a neural network. Neural networks have the ability to learn about non-linear relationships between the used variables. In this paper a recurrent neural network (Elman model) based forecaster for the prediction of daily maximum concentrations of SO₂, O₃, PM10, NO₂, CO in the city of Palermo is proposed. The effectiveness of the presented forecaster was tested using a time series recorded between 1 January 2003 to 31 December 2004 in eight monitoring stations in urban area of Palermo (Italy). Experimental trials show that the developed and tuned model is appropriate, giving small values of root mean square error (RMSE) , mean absolute error (MAE) and mean square error (MSE). In addition, the related correlation coefficient ranges from 0.72 to 0.97 for each forecasted pollutant, underlying a small difference between the forecasted and the measured values. The above results make the proposed forecaster a powerful tool for pollution management systems.     

Evaluation of PM10 forecasting based on the artificial neural network model and intake fraction in an urban area: A case study in Taiyuan City,China

Primary fine particulate matters with a diameter of less than 10 µm (PM₁₀) are important air emissions causing human health damage. PM₁₀ concentration forecast is important and necessary to perform in order to assess the impact of air on the health of living beings. To better understand the PM₁₀ pollution health risk in Taiyuan City, China, this paper forecasted the temporal and spatial distribution of PM₁₀ yearly average concentration, using Back Propagation Artificial Neural Network (BPANN) model with various air quality parameters. The predicted results of the models were consistent with the observations with a correlation coefficient of 0.72. The PM₁₀ yearly average concentrations combined with the population data from 2002 to 2008 were given into the Intake Fraction (IF) model to calculate the IFs, which are defined as the integrated incremental intake of a pollutant released from a source category or a region over all exposed individuals. The results in this study are only for main stationary sources of the research area, and the traffic sources have not been included. The computed IFs results are therefore under-estimations. The IFs of PM₁₀ from Taiyuan with a mean of 8.5 per million were relatively high compared with other IFs of the United States, Northern Europe and other cities in China. The results of this study indicate that the artificial neural network is an effective method for PM₁₀ pollution modeling, and the Intake Fraction model provides a rapid population risk estimate for pollutant emission reduction strategies and policies.

Implications The PM₁₀ (particulate matter with an aerodynamic diameter ≤10 μm) yearly average concentration of Taiyuan, with a mean of 0.176 mg/m³, was higher than the 65 μg/m³ recommended by the U.S. Environmental Protection Agency (EPA). The spatial distribution of PM₁₀ yearly average concentrations showed that wind direction and wind speed played an important role, whereas temperature and humidity had a lower effect than expected. Intake fraction estimates of Taiyuan were relatively high compared with those observed in other cities. Population density was the major factor influencing PM₁₀ spatial distribution. The results indicated that the artificial neural network was an effective method for PM₁₀ pollution modeling.     

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.     

Model for forecasting expressway fine particulate matter and carbon monoxide concentration: application of regression and neural network models

The Borman Expressway is a heavily traveled 16-mi segment of the Interstate 80/94 freeway through Northwestern Indiana. The Lake and Porter counties through which this expressway passes are designated as particulate matter < 2.5 microm (PM2.5) and ozone 8-hr standard nonattainment areas. The Purdue University air quality group has been collecting PM2.5, carbon monoxide (CO), wind speed, wind direction, pressure, and temperature data since September 1999. In this work, regression and neural network models were developed for forecasting hourly PM2.5 and CO concentrations. Time series of PM2.5 and CO concentrations, traffic data, and meteorological parameters were used for developing the neural network and regression models. The models were compared using a number of statistical quality indicators. Both models had reasonable accuracy in predicting hourly PM2.5 concentration with coefficient of determination -0.80, root mean square error (RMSE) <4 microg/m3, and index of agreement (IA) > 0.90. For CO prediction, both models showed moderate forecasting performance with a coefficient of determination -0.55, RMSE < 0.50 ppm, and IA -0.85. These models are computationally less cumbersome and require less number of predictors as compared with the deterministic models. The availability of real time PM2.5 and CO forecasts will help highway managers to identify air pollution episodic events beforehand and to determine mitigation strategies.     

Evaluation of artificial neural networks for fine particulate pollution (PM10 and PM2.5) forecasting

Multi-layer perceptron (MLP) artificial neural network (ANN) models are compared with traditional multiple regression (MLR) models for daily maximum and average O3 and particulate matter (PM10 and PM2.5) forecasting. MLP particulate forecasting models show little if any improvement over MLR models and exhibit less skill than do O3 forecasting models. Meteorological variables (precipitation, wind, and temperature), persistence, and co-pollutant data are shown to be useful PM predictors. If MLP approaches are adopted for PM forecasting, training methods that improve extreme value prediction are recommended.     

Prediction of dissolved oxygen concentration in hypoxic river systems using support vector machine: a case study of Wen-Rui Tang River,China

Accurate quantification of dissolved oxygen (DO) is critically important for managing water resources and controlling pollution. Artificial intelligence (AI) models have been successfully applied for modeling DO content in aquatic ecosystems with limited data. However, the efficacy of these AI models in predicting DO levels in the hypoxic river systems having multiple pollution sources and complicated pollutants behaviors is unclear. Given this dilemma, we developed a promising AI model, known as support vector machine (SVM), to predict the DO concentration in a hypoxic river in southeastern China. Four different calibration models, specifically, multiple linear regression, back propagation neural network, general regression neural network, and SVM, were established, and their prediction accuracy was systemically investigated and compared. A total of 11 hydro-chemical variables were used as model inputs. These variables were measured bimonthly at eight sampling sites along the rural-suburban-urban portion of Wen-Rui Tang River from 2004 to 2008. The performances of the established models were assessed through the mean square error (MSE), determination coefficient (R ²), and Nash-Sutcliffe (NS) model efficiency. The results indicated that the SVM model was superior to other models in predicting DO concentration in Wen-Rui Tang River. For SVM, the MSE, R ², and NS values for the testing subset were 0.9416 mg/L, 0.8646, and 0.8763, respectively. Sensitivity analysis showed that ammonium-nitrogen was the most significant input variable of the proposal SVM model. Overall, these results demonstrated that the proposed SVM model can efficiently predict water quality, especially for highly impaired and hypoxic river systems.     

Particulate Air Pollution and Health Effects for Cardiovascular and Respiratory Causes in Temuco,Chile: A Wood-Smoke-Polluted Urban Area

Abstract

Temuco is one of the most highly wood-smoke-polluted cities in the world. Its population in 2004 was 340,000 inhabitants with 1587 annual deaths, of which 24% were due to cardiovascular and 11% to respiratory causes. For hospital admissions, cardiovascular diseases represented 6% and respiratory diseases 13%. Emergency room visits for acute respiratory infections represented 28%. The objective of the study presented here was to determine the relationship between air pollution from particulate matter less than or equal to 10 µm in aerodynamic diameter (PM₁₀; mostly PM_2.5, or particulate matter <2.5 µm in aerodynamic diameter) and health effects measured as the daily number of deaths, hospital admissions, and emergency room visits for cardiovascular, respiratory, and acute respiratory infection (ARI) diseases. The Air Pollution Health Effects European Approach (APHEA2) protocol was followed, and a multivariate Poisson regression model was fitted, controlling for trend, seasonality, and confounders for Temuco during 1998–2006. The results show that PM₁₀ had a significant association with daily mortality and morbidity, with the elderly (population >65 yr of age) being the group that presented the greatest risk. The relative risk for respiratory causes, with an increase of 100 µg/m³ of PM_10, was 1.163 with a 95% confidence interval (CI) of 1.057–1.279 for mortality, 1.137 (CI 1.096–1.178) for hospital admissions, and 1.162 for ARI (CI 1.144–1.181). There is evidence in Temuco of positive relationships between ambient particulate levels and mortality, hospital admissions, and ARI for cardiovascular and respiratory diseases. These results are consistent with those of comparable studies in other similar cities where wood smoke is the most important air pollution problem.     

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.     

Application and Evaluation of Two Air Quality Models for Particulate Matter for a Southeastern U.S. Episode

Abstract

The Models-3 Community Multiscale Air Quality (CMAQ) Modeling System and the Particulate Matter Comprehensive Air Quality Model with extensions (PMCAMx) were applied to simulate the period June 29–July 10, 1999, of the Southern Oxidants Study episode with two nested horizontal grid sizes: a coarse resolution of 32 km and a fine resolution of 8 km. The predicted spatial variations of ozone (O₃), particulate matter with an aerodynamic diameter less than or equal to 2.5 μm (PM_2.5), and particulate matter with an aerodynamic diameter less than or equal to 10 μm (PM₁₀) by both models are similar in rural areas but differ from one another significantly over some urban/suburban areas in the eastern and southern United States, where PMCAMx tends to predict higher values of O₃ and PM than CMAQ. Both models tend to predict O₃ values that are higher than those observed. For observed O₃ values above 60 ppb, O₃ performance meets the U.S. Environmental Protection Agency's criteria for CMAQ with both grids and for PMCAMx with the fine grid only. It becomes unsatisfactory for PMCAMx and marginally satisfactory for CMAQ for observed O₃ values above 40 ppb.

Both models predict similar amounts of sulfate (SO₄ ^2?) and organic matter, and both predict SO₄ ^2? to be the largest contributor to PM_2.5. PMCAMx generally predicts higher amounts of ammonium (NH₄ ⁺), nitrate (NO₃ ^?), and black carbon (BC) than does CMAQ. PM performance for CMAQ is generally consistent with that of other PM models, whereas PMCAMx predicts higher concentrations of NO₃ ^?,NH₄ ⁺, and BC than observed, which degrades its performance. For PM₁₀ and PM_2.5 predictions over the southeastern U.S. domain, the ranges of mean normalized gross errors (MNGEs) and mean normalized bias are 37–43% and –33–4% for CMAQ and 50–59% and 7–30% for PMCAMx. Both models predict the largest MNGEs for NO₃ ^? (98–104% for CMAQ, 138–338% for PMCAMx). The inaccurate NO₃ ^? predictions by both models may be caused by the inaccuracies in the ammonia emission inventory and the uncertainties in the gas/particle partitioning under some conditions. In addition to these uncertainties, the significant PM overpredictions by PMCAMx may be attributed to the lack of wet removal for PM and a likely underprediction in the vertical mixing during the daytime.     

The Southeastern Aerosol Research and Characterization Study: Part II. Filter-Based Measurements of Fine and Coarse Particulate Matter Mass and Composition

Abstract

The Southeastern Aerosol Research and Characterization Study (SEARCH) was implemented in 1998–1999 to provide data and analyses for the investigation of the sources, chemical speciation, and long-term trends of fine particulate matter (PM_2.5) and coarse particulate matter (PM_10–2.5) in the Southeastern United States. This work is an initial analysis of 5 years (1999–2003) of filter-based PM_2.5 and PM_10–2.5 data from SEARCH. We find that annual PM_2.5 design values were consistently above the National Ambient Air Quality Standards (NAAQS) 15 µg/m³ annual standard only at monitoring sites in the two largest urban areas (Atlanta, GA, and North Birmingham, AL). Other sites in the network had annual design values below the standard, and no site had daily design values above the NAAQS 65 µg/m³ daily standard. Using a particle composition monitor designed specifically for SEARCH, we found that volatilization losses of nitrate, ammonium, and organic carbon must be accounted for to accurately characterize atmospheric particulate matter. In particular, the federal reference method for PM_2.5 underestimates mass by 3–7% as a result of these volatilization losses. Organic matter (OM) and sulfate account for ≥60% of PM_2.5 mass at SEARCH sites, whereas major metal oxides (MMO) and unidentified components (“other”) account for ≥80% of PM_10–2.5 mass. Limited data suggest that much of the unidentified mass in PM_10–2.5 may be OM. For paired comparisons of urban-rural sites, differences in PM_2.5 mass are explained, in large part, by higher OM and black carbon at the urban site. For PM₁₀, higher urban concentrations are explained by higher MMO and “other.” Annual means for PM_2.5 and PM_10–2.5 mass and major components demonstrate substantial declines at all of the SEARCH sites over the 1999–2003 period (10–20% in the case of PM_2.5, dominated by 14–20% declines in sulfate and 11–26% declines in OM, and 14–25% in the case of PM_10–2.5, dominated by 17–30% declines in MMO and 14–31% declines in “ other”). Although declining national emissions of sulfur dioxide and anthropogenic carbon may account for a portion of the observed declines, additional investigation will be necessary to establish a quantitative assessment, especially regarding trends in local and regional emissions, primary carbon emissions, and meteorology.     

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.     

PM10 Levels in the Lower Fraser Valley,British Columbia,Canada: An Overview of Spatiotemporal Variations and Meteorological Controls

ABSTRACT

Three years of hourly averaged PM₁₀ (particulate matter less than 10 Lrm in diameter) tapered element oscillating microbalance (TEOM) data from 10 sites in the large coastal valley incorporating Greater Vancouver were used to investigate the spatiotemporal dimensions and air pollution meteorology of particulate pollution. During the period studied, the provincial “acceptable” objective daily concentration of 50 μg m^-3 was exceeded at 7 of the 10 sites. The highest annual, seasonal, and maximum hourly concentrations were recorded at Abbotsford in the central valley. Mean seasonal PM₁₀ concentrations were highest in the wintertime in the western Lower Fraser Valley (LFV) and in the summertime at the central and eastern valley locations. Within the network, interstation correlations of daily average concentrations exceed 0.8 at interstation distances less than 20 km and decrease thereafter. For daily maximum concentrations (hourly), interstation correlations decrease sharply with distance. Meteorological conditions responsible for elevated par-ticulate concentrations in the LFV are associated with (1) short periods (1- to 3-hr duration) of reduced dispersion during summer nights at sites close to primary sources, (2) summer anticyclonic conditions when photochemical pollutant concentrations build up across the entire valley, and (3) occasional wintertime “gap wind” events in the eastern valley.     

Characterizing the spatiotemporal variability of PM2.5 in Cusco,Peru using kriging with external drift

Advancing the understanding of spatiotemporal aspects of air pollution in the urban environment is an area where improved methods can be of great benefit to exposure assessment and policy support. This paper explores the potential of a technique known as kriging with external drift (KED) to provide high resolution maps of fine particulate matter for a downtown region of Cusco, Peru. There were three stages in this research. The first was to conduct a pilot level monitoring campaign to investigate ambient, regional, and street-level air pollutant concentrations for particulate matter (PM_2.5, PM₁₀) and carbon monoxide (CO) in the Province of Cusco. The second was to compile observations within a geographic information system (GIS) in order to characterize the proximal effect of the local transportation network, elevation, and land use classifications on PM_2.5. Third, regression, ordinary kriging and kriging with external drift were used to model PM_2.5 for three select time periods during a 24-h day. Statistical evaluations indicate kriging with external drift resulted in the strongest models explaining 64% of variability seen with morning particle concentrations, 25% for afternoon particles, and 53% in evening particles. These models capture spatial and temporal variability for air pollution in Cusco. These variations seem to be influenced, to varying degrees, by elevation, meteorological conditions, spatial location, and transportation characteristics. In conclusion, combining GIS, meteorological data and geostatistics proved to be a complementary suite of tools for incorporating spatiotemporal analysis into the air quality assessment.     

A Comparison of Nonlinear Regression and Neural Network Models for Ground-Level Ozone Forecasting

ABSTRACT

A hybrid nonlinear regression (NLR) model and a neural network (NN) model, each designed to forecast next-day maximum 1-hr average ground-level O₃ concentrations in Louisville, KY, were compared for two O₃ seasons—1998 and 1999. The model predictions were compared for the forecast mode, using forecasted meteorological data as input, and for the hindcast mode, using observed meteorological data as input. The two models performed nearly the same in the forecast mode. For the two seasons combined, the mean absolute forecast error was 12.5 ppb for the NLR model and 12.3 ppb for the NN model. The detection rate of 120 ppb threshold exceedances was 42% for each model in the forecast mode. In the hindcast mode, the NLR model performed marginally better than the NN     

The Impact of Particulate Matter on Daily Mortality in Bangkok,Thailand

ABSTRACT

Several studies conducted in U.S. cities report an association between acute exposures to particulate matter (PM), usually measured as PM_10, and mortality. Evidence of high concentrations of PM₁₀ in Eastern Europe and in large metropolitan areas outside of the United States, such as Mexico City and Bangkok, underscores the need to determine whether these same associations occur outside of the United States. In addition, conducting studies of mortality and air pollution in regions that have distinctly different seasonal patterns than those of the United States provides an effective opportunity to assess the potentially confounding aspects of seasonality. Over the last few years, daily measures of ambient PM₁₀ have been collected in Bangkok, a tropical city of over 6 million people. In this metropolitan area, PM₁₀ consists largely of fine particles generated from diesel- and gasoline-powered automobiles, and from two-stroke motorcycle engines. Our analysis involved the examination of the relationship between PM₁₀ and daily mortality for 1992 through 1995. In addition to counts of daily natural mortality (total mortality net of accidents, homicides, and suicides), the data were compiled to assess both cardiovascular and respiratory mortality, and natural mortality by age group. A multivariate Poisson regression model was used to explain daily mortality while controlling for several covariates including temperature, humidity, day of the week, season, and time. The analysis indicated a statistically significant association between PM10 and all of the alternative measures of mortality. The results suggest a 10-µg/m³ change in daily PM₁₀ is associated with a 1–2% increase in natural mortality, a 1–2% increase in cardiovascular mortality, and a 3–6% increase in respiratory mortality. These relative risks are generally consistent with or greater than those reported in most studies undertaken in the United States.     

Air Pollution Control and Waste Management in a New World

Abstract

A research site for atmospheric chemistry and air pollution measurements was established at Pinnacle State Park in Addison, NY, in 1995. This paper presents an overview of the site characteristics and measurement program, as well as monthly average concentrations for many of the trace gas and aerosol pollutants over the full measurement period. Monthly averaged ozone concentrations range from values as low as 15 parts per billion (ppb) during cold-season months, to values approaching 50 ppb during some spring and summer months. Sulfur dioxide (SO₂), oxides of nitrogen (NO_x), and reactive odd nitrogen (NO_y) all show distinct seasonal variation, with summertime monthly averages as low as 1–3 ppb, and wintertime monthly averages from 6–12 ppb. The variation in carbon monoxide (CO) is much smaller, with minimums of approximately 150 ppb and maximums only rarely exceeding 250 ppb. Data for three hydrocarbon species propane, benzene, and isoprene—are presented. Propane and benzene show higher monthly averaged concentrations in the winter and lower values in the summer, with values ranging over a factor of 4–5. Isoprene, on the other hand has much higher values during the summer season, sometimes a factor of 10 or more greater than concentrations measured in the winter. Monthly averaged plots for fine particulate matter (PM_2.5) beginning in 1999 show a robust summer maximum and winter minimum, and roughly a factor of two difference between the two. An empirical measure of ozone production using the correlation of hour-averaged ozone and NO_y data illustrates relatively robust ozone production during some, but not all, summertime months over the time period. Also, an analysis of the frequency distribution of the hours of maximum ozone concentration shows a strong mid-afternoon peak, as expected, but also a prominent secondary maximum centered around midnight. The secondary peak is interpreted as ozone transported from ozone-producing areas to the west, including Buffalo, Cleveland, Pittsburgh, and the Ohio Valley. Finally, SO₂ concentrations as a function of wind direction clearly indicate maximum impacts when the winds are out of the south (Pittsburgh and Philadelphia), with a secondary peak when the winds are from the north-northeast, consistent with the locations of major SO₂ emission sources in the region.     

An hourly PM10 diagnosis model for the Bilbao metropolitan area using a linear regression methodology

There is extensive evidence of the negative impacts on health linked to the rise of the regional background of particulate matter (PM) 10 levels. These levels are often increased over urban areas becoming one of the main air pollution concerns. This is the case on the Bilbao metropolitan area, Spain. This study describes a data-driven model to diagnose PM10 levels in Bilbao at hourly intervals. The model is built with a training period of 7-year historical data covering different urban environments (inland, city centre and coastal sites). The explanatory variables are quantitative—log [NO₂], temperature, short-wave incoming radiation, wind speed and direction, specific humidity, hour and vehicle intensity—and qualitative—working days/weekends, season (winter/summer), the hour (from 00 to 23 UTC) and precipitation/no precipitation. Three different linear regression models are compared: simple linear regression; linear regression with interaction terms (INT); and linear regression with interaction terms following the Sawa’s Bayesian Information Criteria (INT-BIC). Each type of model is calculated selecting two different periods: the training (it consists of 6 years) and the testing dataset (it consists of 1 year). The results of each type of model show that the INT-BIC-based model (R ²?=?0.42) is the best. Results were R of 0.65, 0.63 and 0.60 for the city centre, inland and coastal sites, respectively, a level of confidence similar to the state-of-the art methodology. The related error calculated for longer time intervals (monthly or seasonal means) diminished significantly (R of 0.75–0.80 for monthly means and R of 0.80 to 0.98 at seasonally means) with respect to shorter periods.