Meteorologically adjusted trends of daily maximum ozone concentrations in Taipei,Taiwan

The meteorological conditions exert large impacts on ozone concentrations, and may mask the long-term trends in ozone concentrations resulting from precursor emissions. Estimation of long-term trends of ozone concentrations due to the changes in precursor emissions is important for corresponding control strategy. Multiple linear regression (method I), multilayer perceptron (MLP) neural network (method II) and Komogorov-Zurbenko (KZ) filter method plus MLP methodology (method III), are used to estimate the meteorologically adjusted long-term trends of daily maximum ozone concentrations by removing the masking effects of meteorological conditions in this study. The daily maximum ozone concentrations and relative meteorological variables were extracted from six air-monitoring stations in Taipei area from 1994 to 2001. The data collected during 1994–2000 period were used as modeling set and utilized to estimate the meteorologically adjusted trends, and the data of 2001 were used as the validation data. The meteorologically adjusted trends of ozone for these three methods were calculated and compared. The results show that both MLP and KZ filter +MLP models are more suitable than multiple linear regression for estimating the long-term trends of ozone in Taipei, Taiwan. The long-term linear trends of meteorologically adjusted ozone concentrations due to the precursor emissions show an increase trend at all stations, and the percent changes per year range from 1.0% to 2.25% during the modeling period in Taipei area.     

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.     

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.     

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.     

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.     

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.     

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.     

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.     

Neural Network and Multiple Regression Models for PM10 Prediction in Athens: A Comparative Assessment

Abstract

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 µm (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.     

Variation of surface ozone in Campo Grande,Brazil: meteorological effect analysis and prediction

The effect of meteorological variables on surface ozone (O₃) concentrations was analysed based on temporal variation of linear correlation and artificial neural network (ANN) models defined by genetic algorithms (GAs). ANN models were also used to predict the daily average concentration of this air pollutant in Campo Grande, Brazil. Three methodologies were applied using GAs, two of them considering threshold models. In these models, the variables selected to define different regimes were daily average O₃ concentration, relative humidity and solar radiation. The threshold model that considers two O₃ regimes was the one that correctly describes the effect of important meteorological variables in O₃ behaviour, presenting also a good predictive performance. Solar radiation, relative humidity and rainfall were considered significant for both O₃ regimes; however, wind speed (dispersion effect) was only significant for high concentrations. According to this model, high O₃ concentrations corresponded to high solar radiation, low relative humidity and wind speed. This model showed to be a powerful tool to interpret the O₃ behaviour, being useful to define policy strategies for human health protection regarding air pollution.     

Comparison of artificial neural network and regression models in the prediction of urban stormwater quality.

Urban stormwater quality is influenced by many interrelated processes. However, the site-specific nature of these complex processes makes stormwater quality difficult to predict using physically based process models. This has resulted in the need for more empirical techniques. In this study, artificial neural networks (ANN) were used to model urban stormwater quality. A total of 5 different constituents were analyzed-chemical oxygen demand, lead, suspended solids, total Kjeldahl nitrogen, and total phosphorus. Input variables were selected using stepwise linear regression models, calibrated on logarithmically transformed data. Artificial neural networks models were then developed and compared with the regression models. The results from the analyses indicate that multiple linear regression models were more applicable for predicting urban stormwater quality than ANN models.     

Forecasting daily pollen concentrations using data-driven modeling methods in Thessaloniki,Greece

Airborne pollen have been associated with allergic symptoms in sensitized individuals, having a direct impact on the overall quality of life of a considerable fraction of the population. Therefore, forecasting elevated airborne pollen concentrations and communicating this piece of information to the public are key issues in prophylaxis and safeguarding the quality of life of the overall population. In this study, we adopt a data-oriented approach in order to develop operational forecasting models (1–7 days ahead) of daily average airborne pollen concentrations of the highly allergenic taxa: Poaceae, Oleaceae and Urticaceae. The models are developed using a representative dataset consisting of pollen and meteorological time-series recorded during the years 1987–2002, in the city of Thessaloniki, Greece. The input variables (features) of the models have been optimized by making use of genetic algorithms, whereas we evaluate the performance of three algorithms: i) multi-Layer Perceptron, ii) support vector regression and iii) regression trees originating from distinct domains of Computational Intelligence (CI), and compare the resulting models with traditional multiple linear regression models. Results show the superiority of CI methods, especially when forecasting several days ahead, compared to traditional multiple linear regression models. Furthermore, the CI models complement each other, resulting to a combined model that performs better than each one separately. The overall performance ranges, in terms of the index of agreement, from 0.85 to 0.93 clearly suggesting the potential operational use of the models. The latter ones can be utilized in provision of personalized and on-time information services, which can improve quality of life of sensitized citizens.     

Artificial neural network-derived trends in daily maximum surface ozone concentrations

Interannual variability in meteorological conditions can confound attempts to identify changes in ozone concentrations driven by reduced precursor emissions. In this paper, a technique is described that attempts to maximize the removal of meteorological variability from a daily maximum ozone time series, thereby revealing longer term changes in ozone concentrations with increased confidence. The technique employs artificial neural network [multilayer perceptron (MLP)] models, and is shown to remove more of the meteorological variability from U.S. ozone data than does a Kolmogorov-Zurbenko (KZ) filter and conventional regression-based technique.     

Artificial Neural Network-Derived Trends in Daily Maximum Surface Ozone Concentrations

ABSTRACT

Interannual variability in meteorological conditions can confound attempts to identify changes in ozone concentrations driven by reduced precursor emissions. In this paper, a technique is described that attempts to maximize the removal of meteorological variability from a daily maximum ozone time series, thereby revealing longer term changes in ozone concentrations with increased confidence. The technique employs artificial neural network [multilayer perceptron (MLP)] models, and is shown to remove more of the meteorological variability from U.S. ozone data than does a Kolmogorov-Zurbenko (KZ) filter and conventional regression-based technique.     

Ozone predictions in Atlanta, Georgia: analysis of the 1999 ozone season

Ozone prediction has become an important activity in many U.S. ozone nonattainment areas. In this study, we describe the ozone prediction program in the Atlanta metropolitan area and analyze the performance of this program during the 1999 ozone-forecasting season. From May to September, a team of 10 air quality regulators, meteorologists, and atmospheric scientists made a daily prediction of the next-day maximum 8-hr average ozone concentration. The daily forecast was made aided by two linear regression models, a 3-dimensional air quality model, and the no-skill ozone persistence model. The team's performance is compared with the numerical models using several numerical indicators. Our analysis indicated that (1) the team correctly predicted next-day peak ozone concentrations 84% of the time, (2) the two linear regression models had a better performance than a 3-dimensional air quality model, (3) persistence was a strong predictor of ozone concentrations with a performance of 78%, and (4) about half of the team's wrong predictions could be prevented with improved meteorological predictions.     

Ozone Predictions in Atlanta,Georgia: Analysis of the 1999 Ozone Season

ABSTRACT

Ozone prediction has become an important activity in many U.S. ozone nonattainment areas. In this study, we describe the ozone prediction program in the Atlanta metropolitan area and analyze the performance of this program during the 1999 ozone-forecasting season. From May to September, a team of 10 air quality regulators, meteorologists, and atmospheric scientists made a daily prediction of the next-day maximum 8-hr average ozone concentration. The daily forecast was made aided by two linear regression models, a 3-dimensional air quality model, and the no-skill ozone persistence model. The team's performance is compared with the numerical models using several numerical indicators. Our analysis indicated that (1) the team correctly predicted next-day peak ozone concentrations 84% of the time, (2) the two linear regression models had a better performance than a 3-dimensional air quality model, (3) persistence was a strong predictor of ozone concentrations with a performance of 78%, and (4) about half of the team's wrong predictions could be prevented with improved meteorological predictions.     

Development of a multi-factor model for predicting the effects of ambient ozone on the biomass of white clover

Results are presented from the UN/ECE ICP Vegetation (International Cooperative Programme on effects of air pollution on natural vegetation and crops) experiments in which ozone(O(3))-resistant (NC-R) and -sensitive (NC-S) clones of white clover (Trifolium repens cv. Regal) were exposed to ambient O(3) episodes at 14 sites in eight European countries in 1996, 1997 and 1998. The plants were grown according to a standard protocol, and the forage was harvested every 28 days for 4-5 months per year by excision 7 cm above the soil surface. Biomass ratio (NC-S/NC-R) was related to the climatic and pollutant conditions at each site using multiple linear regression (MLR) and artificial neural networks (ANNs). Twenty-one input parameters [e.g. AOT40, 7-h mean O(3) concentration, daylight vapour pressure deficit (VPD), daily maximum temperature] were considered individually and in combination with the aim of developing a model with high r(2) and simple structure that could be used to predict biomass change in white clover. MLR models were generally more complex, and performed less well for unseen data than non-linear ANN models. The ANN model with the best performance had five inputs with an r(2) value of 0.84 for the training data, and 0.71 for previously unseen data. Two inputs to the model described the O(3) conditions (AOT40 and 24-h mean for O(3)), two described temperature (daylight mean and 24-h mean temperature), and the fifth input appeared to be differentiating between semi-urban and rural sites (NO concentration at 17:00). Neither VPD nor harvest interval was an important component of the model. The model predicted that a 5% reduction in biomass ratio was associated with AOT40s in the range 0.9-1.7 ppm x h (microl l(-1) h) accumulated over 28 days, with plants being most sensitive in conditions of low NO(x), medium-range temperature, and high 24-h mean O(3) concentration.     

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.     

Prediction of maximum of 24-h average of PM10 concentrations 30 h in advance in Santiago,Chile

We have developed a neural network based model that uses values of PM10 concentrations measured until 6 p.m. on the present day plus measured and forecasted values of meteorological variables as input in order to predict the level reached by the maximum of the 24-h moving average (24MA) of PM10 concentration on the next day. We have adjusted the parameters of the model using 1998 data to predict 1999 conditions and 1999 data to forecast 2000 maximum concentrations. We have found that among the relevant meteorological input variables, the forecasted difference between maximum and minimum temperature is the most important. Due to the fact that local authorities impose restrictions to emissions on days when the maximum of 24MA of PM10 concentration is expected to exceed 240 μg/m³, we have corrected the measured concentrations on these days before evaluating the efficacy of the forecasting model. Percent errors in forecasting the numerical value are of the order of 20%. The performance of the neural network is better than that of a linear model with the same inputs, but the difference being not great is an indication that the right choice of input variables may be more important than the decision to use a linear or a nonlinear model.