Neural network-based study for predicting ground-level ozone concentration in large urban areas, applied to the Sao Paulo metropolitan area

Events of high concentration of ground-level ozone constitute a matter of major concern in large urban areas in terms of air quality, and public health. In the Sao Paulo Metropolitan Area (SPMA), air quality data generated by a network of air quality measuring stations have been used in a number of studies correlating ozone formation with different variables. A study was carried out on the application of neural network models in the identification of typical sceneries leading to high ground-level ozone concentrations in the SPMA. The results were then applied in the selection of variables, and in the definition of neural network-based models for estimating ozone levels from meteorological variables. When combined with existing weather prediction tools, the models can be applied in the prediction of ozone levels in the SPMA     

Characteristics of urban ground-level ozone in Korea

This study considers the characteristics of ground-level ozone (O3) in five Korean cities over a time period of 6-8 years. The focus of this study is daily maximum 1-hr and 8-hr concentrations. For all the study cities in the period examined, the mean and most of the percentiles (5, 10, 25, 50, 75, 90, and 95) for the daily maximum 1-hr and 8-hr concentrations showed increasing trends, although not all trends were statistically significant. The daily maximum 1-hr and 8-hr concentrations slowly increased during late winter, and peaks were attained during the summer season (from May to September). All the selected cities exhibited a high degree of correlation between their daily maximum 8-hr and 1-hr concentrations. The daily maximum 8-hr concentrations, which were climatologically equivalent to the Korean 1 hr/100 parts per billion (ppb) standard, were higher than the current 8 hr/60 ppb by a difference of 8-16 ppb. Compared with other cities in Korea, Seoul recorded a substantially higher frequency of days and hours with concentrations above 1 hr/100 ppb, and a higher frequency of days with concentrations above 8 hr/60 ppb and 8 hr/80 ppb. Seoul also recorded a substantially higher frequency of hours with concentrations above 1 hr/100 ppb than days with concentrations above 1 hr/100 ppb, implying that on some days severe exceedances persisted for more than one hour per day. During multiple-day episodes a North Pacific High dominated Korea, which is quite typical in Korea during the summer season.     

A novel bagging ensemble approach for predicting summertime ground-level ozone concentration

Ozone pollution appears as a major air quality issue, e.g. for the protection of human health and vegetation. Formation of ground level ozone is a complex photochemical phenomenon and involves numerous intricate factors most of which are interrelated with each other. Machine learning techniques can be adopted to predict the ground level ozone. The main objective of the present study is to develop the state-of-the-art ensemble bagging approach to model the summer time ground level ozone in an industrial area comprising a hazardous waste management facility. In this study, the feasibility of using ensemble model with seven meteorological parameters as input variables to predict the surface level O3 concentration. Multilayer perceptron, RTree, REPTree, and Random forest were employed as the base learners. The error measures used for checking the performance of each model includes IoAd, R2, and PEP. The model results were validated against an independent test data set. Bagged random forest predicted the ground level ozone better with higher Nash-Sutcliffe coefficient 0.93. This study scaffolded the current research gap in big data analysis identified with air pollutant prediction.

Implications: The main focus of this paper is to model the summer time ground level O₃ concentration in an Industrial area comprising of hazardous waste management facility. Comparison study was made between the base classifiers and the ensemble classifiers. Most of the conventional models can well predict the average concentrations. In this case the peak concentrations are of importance as it has serious effect on human health and environment. The models developed should also be homoscedastic.     

Comparison of ozone temporal scales for large urban, small urban, and rural areas in Georgia

Ground-level ozone (O3) time series are characterized by the sum of several distinct temporal scales: long-term, seasonal, synoptic, diurnal (daily), and intraday variation. In this study, the authors use a Kolmorogov-Zurbenko filter to separate the 1981-2001 O3 time-series from many sites in and around Georgia into these various components. The authors compare the temporal components to examine differences between small and large metropolitan areas and between urban and rural areas. They then focus on the synoptic component to define a predominant transport region or airshed for each site.     

Sources and sinks of ozone in rural areas

Based on data collected at rural sites in South Dakota, Louisiana and Virginia during the summers of 1978–1980, the factors controlling the diurnal behavior of O₃ near the surface were determined. At all three sites, the diurnal O₃ profile consisted of a period of O₃ increase from sunrise until mid-afternoon, and a period of O₃ decrease from late afternoon until sunrise. The daily O₃ increase was comprised of two approximately equal portions: one due to downmixing of O₃ from aloft (0600–1000 h), and the other due to photochemistry and possibly some further downmixing (1000–1400 h). Even assuming that all of the O₃ increase during the 1000–1400 h period was due to local photochemistry, only very small amounts of O₃ were formed i.e. about 6 ppb of O₃ per ppb of nitrogen oxides (NO_x). Both bag irradiation and photochemical modeling studies suggested similar, but slightly higher O₃ formation. Comparing the ambient data with the bag irradiation and modeling results, it was concluded that rural photochemistry was not controlled exclusively by NO_x, but depended on hydrocarbons as well.The O₃ decrease (1800 to 0600 h) generally occurred while nocturnal inversions isolated the lower 50 m of the atmosphere from the air aloft. Since the O₃ loss-rate could be parameterized equally well by either zero- or first-order rate laws, we could not distinguish between the two mechanisms. However, concentrations of gaseous species such as terpenes and NO_x that might lead to pseudo zero-order O₃ loss were generally of minor significance. Consequently, it is concluded that O₃ loss was controlled by surface deposition with deposition velocities ranging from 0.06 to 0.34cms⁻¹ at the three sites.     

Establishment of a Box-Jenkins multivariate time-series model to simulate ground-level peak daily one-hour ozone concentrations at Ta-Liao in Taiwan

Box-Jenkins univariate autoregressive integrated moving average (ARIMA) and regression with time-series error (RTSE) models were established to simulate historical peak daily 1-hr ozone concentrations at Ta-Liao, Taiwan, 1997-2001. During 1995-2003, the 600 days of Pollution Standard Index (PSI) more than 100 (peak daily 1-hr ozone concentrations detected by greater than 120 ppm) at Tao-Liao showed the highest ozone exceedances among the six monitoring stations in Kaohsiung County. To improve the predictability of extremely high ozone, two different principal components, PC1 and PC(1 + 2), were introduced in the RTSE model. Four typical predictors (particular matter with an aerodynamic diameter less than or equal to 10 microm, temperature, wind speed, and wind direction) plus a PC trigger remained significant in the RTSE model. The model performance statistics concluded that the RTSE model with PC1 was optimal, compared with the univariate ARIMA, the RTSE model without PC, and RTSE model with PC(1 + 2). The contingency table shows that the successful predictions of the univariate model were only 12.9% of that of the RTSE model with PC1. Also, the POD value was improved approximately 5-fold when the univariate model was replaced by the RTSE model, and almost 8-fold when it was replaced by the RTSE model with PC1. Moreover, introducing the PC trigger indeed enhanced the ozone predictability. After the PC trigger was introduced in the RTSE model, the POD was increased 69.9%, and the FAR was reduced 8.3%. The overall correlation between the observed and simulated ozone was improved 9.6%. Also, the first principal component was more useful than the first two components in playing the "trigger" role, though it counted only for 58.62% of the environmental variance during the high ozone days.     

Trends in concentration of ground-level ozone and meteorological conditions during high ozone episodes in the Kao-Ping Airshed, Taiwan

This work analyzes the variations in daily maximum 1-hr ozone (O3) concentrations and the long-term trends in annual means of hourly ambient concentrations of O3, nitrogen oxides (nitrous oxide + nitrogen dioxide), and nonmethane hydrocarbons in the three administrative regions of Kao-Ping airshed in southern Taiwan over a recent 8-yr period. The annual or monthly means of all maxima, most 95th percentiles, and some 90th percentiles of the daily maximum 1-hr O3 concentrations exceed the daily limit of 120 parts per billion by volume in all three regions, namely, Kao-hsiung City, Kso-hsiung County, and P'ing-tung County. The monthly means of daily maximum 1-hr O3 concentrations exhibit distinct seasonal variations, with a bimodal form with the maxima in autumn and late winter to the middle of spring and a minimum in summer. The long-term variations in the annual means of hourly O3 concentrations in the three regions exhibit increasing trends. These increases in O3 are associated with the decline in ambient concentrations of nitrogen oxides and nonmethane hydrocarbons. High O3 episodes occur most often in autumn and most rarely in summer. The seasonal mean mixing heights in descending order follow the order of spring, summer, autumn, and winter. Meteorological parameters in autumn and winter indicate that the ground-level O3 tends to accumulate and trigger a high O3 episode on a warm day with sufficient sunlight and low wind in a high-pressure system, consistent with the low mixing heights in these two seasons.     

Estimating long-term population exposure to ozone in urban areas of Europe

Tropospheric ozone concentrations regarded as harmful for human health are frequently encountered in Central Europe in summertime. Although ozone formation generally results from precursors transported over long distances, in urban areas local effects, such as reactions due to nearby emission sources, play a major role in determining ozone concentrations. Europe-wide mapping and modeling of population exposure to high ozone concentrations is subject to many uncertainties, because small-scale phenomena in urban areas can significantly change ozone levels from those of the surroundings. Currently the integrated assessment modeling of European ozone control strategies is done utilizing the results of large-scale models intended for estimating the rural background ozone levels. This paper presents an initial study on how much local nitrogen oxide (NOx) concentrations can explain variations between large-scale ozone model results and urban ozone measurements, on one hand, and between urban and nearby rural measurements, on the other. The impact of urban NOx concentrations on ozone levels was derived from chemical equations describing the ozone balance. The study investigated the applicability of the method for improving the accuracy of modeled population exposure, which is needed for efficient control strategy development. The method was tested with NOx and ozone measurements from both urban and rural areas in Switzerland and with the ozone predictions of the large-scale photochemical model currently used in designing Europe-wide control strategies for ground-level ozone. The results suggest that urban NOx levels are a significant explanatory factor in differences between urban and nearby rural ozone concentrations and that the phenomenon could be satisfactorily represented with this kind of method. Further research efforts should comprise testing of the method in more locations and analyzing the performance of more widely applicable ways of deriving the initial parameters.     

A Lagrangian stochastic model for predicting concentration fluctuations in urban areas

A combined Lagrangian stochastic model with a micromixing sub-model is used to estimate the fluctuating concentrations observed in two wind tunnel experiments. The Lagrangian stochastic model allows fluid trajectories to be simulated in the inhomogeneous flow, while the mixing model accounts for the dissipation of fluctuations using the interaction by exchange with the mean (IEM) mechanism. The model is first tested against the open terrain, wind tunnel data of Fackrell, J.E. and Robins, A.E. [1982. Concentration fluctuations and fluxes in plumes from point sources in a turbulent boundary layer. Journal of Fluid Mechanics 117, 1–26] and shows good agreement with the observed mean concentrations and fluctuation intensities. The model is then compared with the wind tunnel simulation of a two-dimensional street canyon by Pavageau, M. and Schatzmann, M. [1999. Wind tunnel measurements of concentration fluctuations in an urban street canyon. Atmospheric Environment 33, 3961–3971]. Despite the limitations of the k–ε turbulence scheme and the IEM mixing mechanism, the model reproduces the fluctuation intensity pattern within the canyon well. Overall, the comparison with both sets of wind tunnel experiments are encouraging, and the simplicity of the model means that predictions in a complex, three-dimensional geometry can be produced in a practicable amount of time.     

A hierarchical Bayesian model to estimate and forecast ozone through space and time

A Bayesian hierarchical regime switching model describing the spatial–temporal behavior of ozone (O₃) within a domain covering Lake Michigan during spring–summer 1999 is developed. The model incorporates linkages between ozone and meteorology. It is specifically formulated to identify meteorological regimes conducive of high ozone levels and allow ozone behavior during these periods to be different from typical ozone behavior. The model is used to estimate or forecast spatial fields of O₃ conditional on observed (or forecasted) meteorology including temperature, humidity, pressure, and wind speed and direction. The model is successful at forecasting the onset of periods of high ozone levels, but more work is needed to also accurately identify departures from these periods.     

Precursor reductions and ground-level ozone in the Continental United States

Numerous papers analyze ground-level ozone (O₃) trends since the 1980s, but few have linked O₃ trends with observed changes in nitrogen oxide (NO_x) and volatile organic compound (VOC) emissions and ambient concentrations. This analysis of emissions and ambient measurements examines this linkage across the United States on multiple spatial scales from continental to urban. O₃ concentrations follow the general decreases in both NO_x and VOC emissions and ambient concentrations of precursors (nitrogen dioxide, NO₂; nonmethane organic compounds, NMOCs). Annual fourth-highest daily peak 8-hr average ozone and annual average or 98th percentile daily maximum hourly NO₂ concentrations show a statistically significant (p < 0.05) linear fit whose slope is less than 1:1 and intercept is in the 30 to >50 ppbv range. This empirical relationship is consistent with current understanding of O₃ photochemistry. The linear O₃–NO₂ relationships found from our multispatial scale analysis can be used to extrapolate the rate of change of O₃ with projected NO_x emission reductions, which suggests that future declines in annual fourth-highest daily average 8-hr maximum O₃ concentrations are unlikely to reach 65 ppbv or lower everywhere in the next decade. Measurements do not indicate increased annual reduction rates in (high) O₃ concentrations beyond the multidecadal precursor proportionality, since aggressive measures for NO_x and VOC reduction are in place and have not produced an accelerated O₃ reduction rate beyond that prior to the mid-2000s. Empirically estimated changes in O₃ with emissions suggest that O₃ is less sensitive to precursor reductions than is found by the CAMx (v. 6.1) photochemical model. Options for increasing the rate of O₃ change are limited by photochemical factors, including the increase in NO_x sensitivity with time (NMOC/NO_x ratio increase), increase in O₃ production efficiency at lower NO_x concentrations (higher O₃/NO_y ratio), and the presence of natural NO_x and NMOC precursors and background O₃.

Implications:?This analysis demonstrates empirical relations between O₃ and precursors based on long term trends in U.S. locations. The results indicate that ground-level O₃ concentrations have responded predictably to reductions in VOC and NO_x since the 1980s. The analysis reveals linear relations between the highest O₃ and NO₂ concentrations. Extrapolation of the historic trends to the future with expected continued precursor reductions suggest that achieving the 2014 proposed reduction in the U.S. National Ambient Air Quality Standard to a level between 65 and 70 ppbv is unlikely within the next decade. Comparison of measurements with national results from a regulatory photochemical model, CAMx, v. 6.1, suggests that model predictions are more sensitive to emissions changes than the observations would support.     

Mediterranean rural ozone characteristics around the urban area of Athens

A systematic analysis of surface ozone observations in rural areas surrounding Athens is presented. The analysis is based on ozone data for the rural station Aliartos about 80 km NW of Athens center and for two stations on the northern periphery of the Athens basin: Demokritos, located 10 km NE of Athens center and Liossia, 12 km to the north. The data for these two stations are screened for cases of strong air flow from rural areas. Average hourly summer afternoon ozone mixing ratios are similar for all three stations about 60 ppb and thus exceed for the hours 12:00–20:00 LST the 55 ppb WHO guideline for human health for 8 h ozone exposure. The corresponding winter afternoon mixing ratios are at 35 ppb. However, due to the large diurnal variation, mean monthly ozone mixing ratios at Aliartos, for the months April–September vary from 32 to 40 ppb, which is comparable to the higher average ozone levels at rural stations in south-central Europe. In cases of southerly air flow in the summer in the Athens basin, afternoon ozone levels at Demokritos and Liossia are generally the highest of any in the monitoring network. Hourly average concentrations, however, are only 40% greater than rural values. A background ozone level of such magnitude will have a significant impact on estimates for the effectiveness of pollution control measures for Athens.     

The effects of meteorology on ozone in urban areas and their use in assessing ozone trends

The United States Environmental Protection Agency issues periodic reports that describe air quality trends in the US. For some pollutants, such as ozone, both observed and meteorologically adjusted trends are displayed. This paper describes an improved statistical methodology for meteorologically adjusting ozone trends as well as characterizes the relationships between individual meteorological parameters and ozone. A generalized linear model that accommodates the nonlinear effects of the meteorological variables was fit to data collected for 39 major eastern US urban areas. Overall, the model performs very well, yielding R² statistics as high as 0.80. The analysis confirms that ozone is generally increasing with increasing temperature and decreasing with increasing relative humidity. Examination of the spatial gradients of these responses show that the effect of temperature on ozone is most pronounced in the north while the opposite is true of relative humidity. By including HYSPLIT-derived transport wind direction and distance in the model, it is shown that the largest incremental impact of wind direction on ozone occurs along the periphery of the study domain, which encompasses major NO_x emission sources.     

Prediction of the vertical profile of ozone based on ground-level ozone observations and cloud cover

A number of statistical techniques have been used to develop models to predict high-elevation ozone (O3) concentrations for each discrete hour of day as a function of elevation based on ground-level O3 observations. The analyses evaluated the effect of exclusion/inclusion of cloud cover as a variable. It was found that a simple model, using the current maximum ground-level O3 concentration and no effect of cloud cover provided a reasonable prediction of the vertical profile of O3, based on data analyzed from O3 sites located in North Carolina and Tennessee. The simple model provided an approach that estimates the concentration of O3 as a function of elevation (up to 1800 m) based on the statistical results with a +/- 13.5 ppb prediction error, an R2 of 0.56, and an index of agreement, d1, of 0.66. The inclusion of cloud cover resulted in a slight improvement in the model over the simple regression model. The developed models, which consist of two matrices of 24 equations (one for each hour of day for clear to partly cloudy conditions and one for cloudy conditions), can be used to estimate the vertical O3 profile based on the inputs of the current day's 1-hr maximum ground-level O3 concentration and the level of cloud cover.     

Storm water runoff concentration matrix for urban areas

The infrastructure (roads, sidewalk, commercial and residential structures) added during the land development and urbanisation process is designed to collect precipitation and convey it out of the watershed, typically in existing surface water channels, such as streams and rivers. The quality of surface water, seepage water and ground water is influenced by pollutants that collect on impervious surfaces and that are carried by urban storm water runoff. Heavy metals, e.g. lead (Pb), zinc (Zn), copper (Cu), cadmium (Cd), polycyclic aromatic hydrocarbons (PAH), mineral oil hydrocarbons (MOH) and readily soluble salts in runoff, contribute to the degradation of water. An intensive literature search on the distribution and concentration of the surface-dependent runoff water has been compiled. Concentration variations of several pollutants derived from different surfaces have been averaged. More than 300 references providing about 1300 data for different pollutants culminate in a representative concentration matrix consisting of medians and extreme values. This matrix can be applied to long-term valuations and numerical modelling of storm water treatment facilities.     

Surface ozone comparison conducted in two rural areas in central-southern Spain

Purpose  

The purpose of this work is to contribute to the understanding of the photochemical air pollution analysing the levels and temporal variations of surface ozone in two rural areas situated in central-southern Spain.     

Nitrogen oxides and ozone in Portugal: trends and ozone estimation in an urban and a rural site

Environmental Science and Pollution Research - This study provides an analysis of the spatial distribution and trends of NO, NO2 and O3 concentrations in Portugal between 1995 and 2010....     

Simplified model for the prediction of ozone generation in polluted urban areas with continuous precursor species emissions

In this paper we study the transient ozone generation process in polluted urban areas, using a simplified set of chemical reactions for the NO_x and hydrocarbon photolysis. We obtained a reduced kinetic mechanism and it is solved using the boundary layer theory due to the appearance of two time scales in the problem associated with the photo-chemical reactions of the NO₂ and unburned fuel, respectively. Assuming a temporal addition of ozone precursor species, we obtained in closed form, the temporal evolution of the ozone concentration as a function of the physico-chemical parameters.