Neural network model for predicting peak photochemical pollutant levels

In this paper, an attempt is made for the 24-hr prediction of photochemical pollutant levels using a neural network model. For this purpose, a model is developed that relates peak pollutant concentrations to meteorological and emission variables and indexes. The analysis is based on measurements of O3 and NO2 from the city of Athens. The meteorological variables are selected to cover atmospheric processes that determine the fate of the airborne pollutants while special care is taken to ensure the availability of the required input data from routine observations or forecasts. The comparison between model predictions and actual observations shows a good agreement. In addition, a series of sensitivity tests is performed in order to evaluate the sensitivity of the model to the uncertainty in meteorological variables. Model forecasts are generally rather insensitive to small perturbations in most of the input meteorological data, while they are relatively more sensitive in changes in wind speed and direction.     

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.     

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.     

A Review of Recent Reports Dealing with the Greenhouse Effect of Atmospheric Carbon Dioxide

Abstract

A statistical study on the behavior of ground-level O₃ concentration in different regions of a large urban area was carried out, with emphasis on pollutant gas concentrations and meteorological variables. The study was based on data generated by a network of measuring stations distributed throughout the São Paulo Metropolitan Area, in regions with different characteristics of traffic and economic activities. The combined application of principal component analysis and clustering techniques to data collected from 1997 until 2000 has led to the identification of implicit relationships between variables that have been associated with dominant processes related to O₃ formation in different locations. Similarities between different regions of the city have also been detected and associated with local characteristics. The results indicate that the application of such statistical techniques to data collected in large urban areas enables the grouping of different regions according to their behavior in terms of O₃ levels, as well as the identification of dominant processes in each group. These techniques are thus important in the planning of air pollution policies, especially in the case of O₃ , a pollutant that is not directly related to pollution levels alone.     

Emission Reductions Needed to Meet the Standard for Ozone in Southern California: Effect of Boundary Conditions

Abstract

Combinations of total reactive organic gas (ROG) and nitrogen oxide (NO_x) emissions that do not exceed the National Ambient Air Quality Standard (NAAQS) for ozone for the meteorological conditions of the August 26-28, 1987 SCAQS episode, have been determined using the California Institute of Technology (CIT) photochemical air quality model. The sensitivity of these combinations to pollutant boundary conditions is examined.     

Near-road air pollutant concentrations of CO and PM2.5: A comparison of MOBILE6.2/CALINE4 and generalized additive models

The contribution of vehicular traffic to air pollutant concentrations is often difficult to establish. This paper utilizes both time-series and simulation models to estimate vehicle contributions to pollutant levels near roadways. The time-series model used generalized additive models (GAMs) and fitted pollutant observations to traffic counts and meteorological variables. A one year period (2004) was analyzed on a seasonal basis using hourly measurements of carbon monoxide (CO) and particulate matter less than 2.5 μm in diameter (PM_2.5) monitored near a major highway in Detroit, Michigan, along with hourly traffic counts and local meteorological data. Traffic counts showed statistically significant and approximately linear relationships with CO concentrations in fall, and piecewise linear relationships in spring, summer and winter. The same period was simulated using emission and dispersion models (Motor Vehicle Emissions Factor Model/MOBILE6.2; California Line Source Dispersion Model/CALINE4). CO emissions derived from the GAM were similar, on average, to those estimated by MOBILE6.2. The same analyses for PM_2.5 showed that GAM emission estimates were much higher (by 4–5 times) than the dispersion model results, and that the traffic-PM_2.5 relationship varied seasonally. This analysis suggests that the simulation model performed reasonably well for CO, but it significantly underestimated PM_2.5 concentrations, a likely result of underestimating PM_2.5 emission factors. Comparisons between statistical and simulation models can help identify model deficiencies and improve estimates of vehicle emissions and near-road air quality.     

Prediction of Ambient PM10 and Toxic Metals Using Artificial Neural Networks

Abstract

In this study, an artificial neural network is employed to predict the concentration of ambient respirable particu-late matter (PM₁₀) and toxic metals observed in the city of Jaipur, India. A feed-forward network with a back-propagation learning algorithm is used to train the neural network the behavior of the data patterns. The meteorological variables of wind speed, wind direction, relative humidity, temperature, and time are taken as input to the network. The results indicate that the network is able to predict concentrations of PM₁₀ and toxic metals quite accurately.     

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     

Air Quality Modeling in the South Coast Air Basin of California: What Do the Numbers Really Mean?

Abstract

This study evaluates air quality model sensitivity to input and to model components. Simulations are performed using the California Institute of Technology (CIT) airshed model. Results show the impacts on ozone (O₃) concentration in the South Coast Air Basin (SCAB) of California because of changes in: (1) input data, including meteorological conditions (temperature, UV radiation, mixing height, and wind speed), boundary conditions, and initial conditions (ICs); and (2) model components, including advection solver and chemical mechanism. O₃ concentrations are strongly affected by meteorological conditions and, in particular, by temperature. ICs also affect O₃ concentrations, especially in the first 2 days of simulation. On the other hand, boundary conditions do not significantly affect the absolute peak O₃ concentration, although they do affect concentrations near the inflow boundaries. Moreover, predicted O₃ concentrations are impacted considerably by the chemical mechanism. In addition, dispersion of pollutants is affected by the advection routine used to calculate its transport. Comparison among CIT, California Photochemical Grid Model (CALGRID), and Urban Airshed Model air quality models suggests that differences in O₃ predictions are mainly caused by the different chemical mechanisms used. Additionally, advection solvers contribute to the differences observed among model predictions. Uncertainty in predicted peak O₃ concentration suggests that air quality evaluation should not be based solely on this single value but also on trends predicted by air quality models using a number of chemical mechanisms and with an advection solver that is mass conservative.     

Artificial neural network for the identification of unknown air pollution sources

Artificial neural networks (ANN), whose performances to deal with pattern recognition problems is well known, are proposed to identify air pollution sources. The problem that is addressed is the apportionment of a small number of sources from a data set of ambient concentrations of a given pollutant. Three layers feed-forward ANN trained with a back-propagation algorithm are selected. A test case is built, based on a Gaussian dispersion model. A subset of hourly meteorological conditions and measured concentrations constitute the input patterns to the network that is wired to recover relevant emission parameters of unknown sources as outputs. The rest of the model data are corrupted adding noise to some meteorological parameters and we test the effectiveness of the method to recover the correct answer. The ANN is applied to a realistic case where 24 h SO₂ concentrations were previously measured. Some of the limitations of the ANN approach, together with its capabilities, are discussed in this paper.     

Process analysis of a regional air pollution episode over Pearl River Delta Region,China, using the MM5-CMAQ model

This study focuses on the influences of a warm high-pressure meteorological system on aerosol pollutants, employing the simulations by the Models-3/CMAQ system and the observations collected during October 10–12, 2004, over the Pearl River Delta (PRD) region. The results show that the spatial distributions of air pollutants are generally circular near Guangzhou and Foshan, which are cities with high emissions rates. The primary pollutant is particulate matter (PM) over the PRD. MM5 shows reasonable performance for major meteorological variables (i.e., temperature, relative humidity, wind direction) with normalized mean biases (NMB) of 4.5–38.8% and for their time series. CMAQ can capture one peak of all air pollutant concentrations on October 11, but misses other peaks. The CMAQ model systematically underpredicts the mass concentrations of all air pollutants. Compared with chemical observations, SO₂ and O₃ are predicted well with a correlation coefficient of 0.70 and 0.65. PM_2.5 and NO are significantly underpredicted with an NMB of 43% and 90%, respectively. The process analysis results show that the emission, dry deposition, horizontal transport, and vertical transport are four main processes affecting air pollutants. The contributions of each physical process are different for the various pollutants. The most important process for PM₁₀ is dry deposition, and for NO_x it is transport. The contributions of horizontal and vertical transport processes vary during the period, but these two processes mostly contribute to the removal of air pollutants at Guangzhou city, whose emissions are high. For this high-pressure case, the contributions of the various processes show high correlations in cities with the similar geographical attributes. According to the statistical results, cities in the PRD region are divided into four groups with different features. The contributions from local and nonlocal emission sources are discussed in different groups.

Implications: The characteristics of aerosol pollution episodes are intensively studied in this work using the high-resolution modeling system MM5/SMOKE/CMAQ, with special efforts on examining the contributions of different physical and chemical processes to air concentrations for each city over the PRD region by a process analysis method, so as to provide a scientific basis for understanding the formation mechanism of regional aerosol pollution under the high-pressure system over PRD.     

Progress in developing an ANN model for air pollution index forecast

An air pollution index (API) reporting system is introduced to selected cities of China for public communication on air quality data. Shanghai is the first city in China providing daily average API reports and forecasts. This paper describes the development of an artificial neural network (ANN) model for the API forecasting in Shanghai. It is a multiple layer perceptron (MLP) network, with meteorological forecasting data as the main input, to output the next day average API values. However, the initial version of the MLP model did not work well. To improve the model, a series of tests were conducted with respect to the training method and structure optimization. Based on the test results, the training algorithm was modified and a new model was built. The new model is now being used in Shanghai for API forecasting. Its performance is shown reasonably well in comparison with observation. The application of the old model was only weakly correlated with observation. In 1-year application, the correlation coefficients were 0.2314, 0.1022 and 0.1710 for TSP, SO₂ and NO_x, respectively. But for the new model, for over 8 months application, the correlation coefficients are raised to 0.6056, 0.6993 and 0.6300 for PM₁₀, SO₂, and NO₂. Further, the new algorithm does not rely on manpower intervention so that it is now being applied in several other Chinese cities with quite different meteorological conditions. The structure of the model and the application results are presented in this paper and also the problems to be further studied.     

An enhanced ozone forecasting model using air mass trajectory analysis

An enhanced ozone forecasting model using nonlinear regression and an air mass trajectory parameter has been developed and field tested. The model performed significantly better in predicting daily maximum 1-h ozone concentrations during a five-year model calibration period (1993–1997) than did a previously reported regression model. This was particularly true on the 28 “high ozone” days ([O₃]>120 ppb) during the period, for which the mean absolute error (MAE) improved from 21.7 to 12.1 ppb. On the 77 days meteorologically conducive to high ozone, the MAE improved from 12.2 to 9.1 ppb, and for all 580 calibration days the MAE improved from 9.5 to 8.35 ppb. The model was field-tested during the 1998 ozone season, and performed about as expected. Using actual meteorological data as input for the ozone predictions, the MAE for the season was 11.0 ppb. For the daily ozone forecasts, which used meteorological forecast data as input, the MAE was 13.4 ppb. The high ozone days were all anticipated by the ozone forecasters when the model was used for next day forecasts.     

Meteorological Factors of Ozone Predictability at Houston,Texas

ABSTRACT

Several ozone modeling approaches were investigated to determine if uncertainties in the meteorological data would be sufficiently large to limit the application of physically realistic ozone (O₃) forecast models. Three diagnostic schemes were evaluated for the period of May through September 1997 for Houston, TX. Correlations between measured daily maximum and model calculated O₃ air concentrations were found to be 0.70 using a linear regression model, 0.65 using a non-advective box model, and 0.49 using a three-dimensional (3-D) transport and dispersion model. Although the regression model had the highest correlation, it showed substantial underestimates of the highest concentrations. The box model results were the most similar to the regression model and did not show as much underestimation. The more complex 3-D modeling approach yielded the worst results, likely resulting from O₃ maxima that were driven by local factors rather than by the transport of pollutants from outside of the Houston domain. The highest O₃ concentrations at Houston were associated with light winds and meandering trajectories. A comparison of the gridded meteorological data used by the 3-D model to the observations showed that the wind direction and speed values at Houston differed most on those days on which the O₃ underestima-tions were the greatest. These periods also tended to correspond with poor precipitation and temperature estimates. It is concluded that better results are not just obtained through additional modeling complexity, but there needs to be a comparable increase in the accuracy of the meteorological data.     

Neural network forecasting of air pollutants hourly concentrations using optimised temporal averages of meteorological variables and pollutant concentrations

The new method for the forecasting hourly concentrations of air pollutants is presented in the paper. The method was developed for a site in urban residential area in city of Zagreb, Croatia, for four air pollutants (NO₂, O₃, CO and PM₁₀). Meteorological variables and concentrations of the respective pollutant were taken as predictors. A novel approach, based on families of univariate regression models, was employed in selecting the averaging intervals for input variables. For each variable and each averaging period between 1 and 97 h, a separate model was built. By inspecting values of the coefficient of correlation between measured and modelled concentrations, optimal averaging periods for each variable were selected. A new dataset for building the forecasting model was then calculated as temporal moving averages (running means) of former variables. A multi-layer perceptron type of neural networks is used as the forecasting model. Index of agreement, calculated for the entire dataset including the data for model building, ranged from 0.91 to 0.97 for the respective pollutants. As suggested by the analysis of the relative importance of the input variables, different agreements for different pollutants are likely due to different sources and production mechanisms of investigated pollutants. A comparison of the new method with more traditional method, which takes hourly averages of the forecast hour as input variables, showed similar or better performance. The model was developed for the purpose of public-health-oriented air quality forecasting, aiming to use a numerical weather forecast model for the prediction of the part of input data yet unknown at the forecasting time. It is to expect that longer term averages used as inputs in the proposed method will contribute to smaller input errors and the greater accuracy of the model.     

A Study of the Association between Daily Mortality and Ambient Air Pollutant Concentrations in Pittsburgh,Pennsylvania

ABSTRACT

We have studied the possible association of daily mortality with ambient pollutant concentrations (PM₁₀, CO, O₃, SO₂, NO₂, and fine [PM_{2 5}] and coarse PM) and weather variables (temperature and dew point) in the Pittsburgh, PA, area for two age groups—less than 75, and 75 and over—for the 3-year period of 1989-1991. Correlation functions among pollutant concentrations show important seasonal dependence, and this fact necessitates the use of seasonal models to better identify the link between ambient pollutant concentrations and daily mortality. An analysis of the seasonal model results for the younger-age group reveals significant multicollinearity problems among the highly correlated concentrations of PM₁₀, CO, and NO₂ (and O₃ in spring and summer), and calls into question the rather consistent results of the single- and multi-pollutant non-seasonal models that show a significant positive association between PM₁₀ and daily mortality. For the older-age group, dew point consistently shows a significant association with daily mortality in all models. Collinearity problems appear in the multi-pollutant seasonal and non-seasonal models such that a significant, positive PM₁₀ coefficient is accompanied by a significant, negative coefficient of another ambient pollutant, and the identity of this other pollutant changes with season. The PM₂₅ data set is half that of PM₁₀. Identical-model runs for both data sets reveal instability in the pollutant coefficients, especially for the younger age group. The concern for the instability of the pollutant coefficients due to a small signal-to-noise ratio makes it impossible to ascertain credibly the relative associations of the fine- and coarse-particle modes with daily mortality. In this connection, we call for caution in the interpretation of model results for causal inference when the models use fully or partially estimated PM values to fill large data gaps.     

developing a practical dispersion model for an air quality region

A series of computer models have been developed to predict air quality in the New York/New Jersey/Connecticut Air Quality Region. Efforts have been directed at models which have a shorter time scale than climatological models, and which are capable of providing better recommendations for effective abatement and planning, but use input data presently available.

The basic dispersion model for these investigations is a steady-state,nondivergent Gaussian-type model. A modified inventory of SO₂ sources,based on published data for the New York/New Jersey/Connecticut Air Quality Region, was prepared for use with the model. The basic model has been subjected to various internal sensitivity analyses, in which was isolated the variation produced in the pollutant concentration by a given change in each of the factors that contribute, e.g., wind speed, wind direction,mixing depth, stability conditions, source strengths, and grid size for the area sources.

To date, validation tests of the model have been made against the July and August 1969 data for the ten telemetering stations of the New York City Aerometric Network. Hourly as well as averaged concentrations were considered. Various sets of meteorological data from the network stations and the three area airports, were compared and tested. Additional tests, particularly for the winter season, are needed to substantiate the preliminary conclusions suggested by the results to date.

Considerable insight into the relative importance of model components has been acquired from the sensitivity studies. Furthermore the validation results lend support to the belief that a reasonably simple, practical dispersion model can be developed for the region.     

Assessment of the Nested Grid Model Estimates for Driving Regional Visibility Models in the Southwestern United States

ABSTRACT

The Nested Grid Model (NGM) is a primitive-equation meteorological model that is routinely exercised over North America for forecasting purposes by the National Meteorological Center. While prognostic meteorological models are being increasingly used to drive air quality models, their use in conducting annual simulations requires significant resources. NGM estimates of wind fields and other meteorological variables provide an attractive alternative since they are typically archived and readily available for an entire year. Preliminary evaluation of NGM winds during the summer of 1992 for application to the region surrounding the Grand Canyon National Park showed serious shortcomings. The NGM winds along the borders between California, Arizona and Mexico tend to be northwesterly with a speed of about 6 m/sec, while the observed flow is predominantly southerly at about 2-5 m/sec. The mesoscale effect of a thermal low pressure area over the highly heated Southern California and western Arizona deserts does not appear to be represented by the NGM because of its coarse resolution and the use of sparse observations in that region. Tracer simulations and statistical evaluation against special high resolution observations of winds in the southwest United States clearly demonstrate the northwest bias in NGM winds and its adverse effect on predictions of an air quality model. The “enhanced” NGM winds, in which selected wind observations are incorporated in the NGM winds using a diagnostic meteorological model provide additional confirmation on the primary cause of the northwest bias. This study has demonstrated that in situations where limited resources prevent the use of prognostic meteorological models, previously archived coarse resolution wind fields in which additional observations are incorporated to correct known biases provide an attractive option.     

The Limitations of Air Quality Standards

This paper describes a diffusion model designed to permit calculation of seasonal average concentrations of an air pollutant, in particular, sulfur dioxide. The calculations can encompass multiple sources and multiple receptors. For each receptor location the model sums the effect of all sources over a wide range of meteorological conditions. Input data include source pollutant emissions, source configuration and location, receptor location, and meteorological data expressed as a joint frequency distribution of wind direction, wind speed, stability. To determine the model’s accuracy, concentration estimates for St. Louis, Mo., are compared with measured SO₂ concentrations. The overall correlation with observed data is satisfactory. A computer program to handle the numerous calculations was written in Fortran IV language for use on an IBM 1130 computer.     

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.