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.     

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.     

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.     

Uncertainty analysis of developed ANN and ANFIS models in prediction of carbon monoxide daily concentration

This study aims to predict daily carbon monoxide (CO) concentration in the atmosphere of Tehran by means of developed artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) models. Forward selection (FS) and Gamma test (GT) methods are used for selecting input variables and developing hybrid models with ANN and ANFIS. From 12 input candidates, 7 and 9 variables are selected using FS and GT, respectively. Evaluation of developed hybrid models and its comparison with ANN and ANFIS models fed with all input variables shows that both FS and GT techniques reduce not only the output error, but also computational cost due to less inputs. FS–ANN and FS–ANFIS models are selected as the best models considering R², mean absolute error and also developed discrepancy ratio statistics. It is also shown that these two models are superior in predicting pollution episodes. Finally, uncertainty analysis based on Monte-Carlo simulation is carried out for FS–ANN and FS–ANFIS models which shows that FS–ANN model has less uncertainty; i.e. it is the best model which forecasts satisfactorily the trends in daily CO concentration levels.     

A Simple Methodology for the Determination of Back Trajectories

Abstract

This study comprehensively characterizes hourly fine particulate matter (PM_2.5) concentrations measured via a tapered element oscillating microbalance (TEOM), β-gauge, and nephelometer from four different monitoring sites in U.S. Environment Protection Agency (EPA) Region 5 (in U.S. states Illinois, Michigan, and Wisconsin) and compares them to the Federal Reference Method (FRM). Hourly characterization uses time series and autocorrelation. Hourly data are compared with FRM by averaging across 24-hr sampling periods and modeling against respective daily FRM concentrations. Modeling uses traditional two-variable linear least-squares regression as well as innovative nonlinear regression involving additional meteorological variables such as temperature and humidity. The TEOM shows a relationship with season and temperature, linear correlation as low as 0.7924 and nonlinear model correlation as high as 0.9370 when modeled with temperature. The β-gauge shows no relationship with season or meteorological variables. It exhibits a linear correlation as low as 0.8505 with the FRM and a nonlinear model correlation as high as 0.9339 when modeled with humidity. The nephelometer shows no relationship with season or temperature but a strong relationship with humidity is observed. A linear correlation as low as 0.3050 and a nonlinear model correlation as high as 0.9508 is observed when modeled with humidity. Nonlinear models have higher correlation than linear models applied to the same dataset. This correlation difference is not always substantial, which may introduce a tradeoff between simplicity of model and degree of statistical association. This project shows that continuous monitor technology produces valid PM_2.5 characterization, with at least partial accounting for variations in concentration from gravimetric reference monitors once appropriate nonlinear adjustments are applied. Although only one regression technically meets new EPA National Ambient Air Quality Standards (NAAQS) Federal Equivalent Method (FEM) correlation coefficient criteria, several others are extremely close, showing optimistic potential for use of this nonlinear adjustment model in garnering EPA NAAQS FEM approval for continuous PM_2.5 sampling methods.     

A design of two simple models to predict PCDD/F concentrations in vegetation and soils

The vegetation and soil levels of the 17 polychlorinated dibenzo-p-dioxin and dibenzofuran (PCDD/F) toxic congeners were calculated by means of a vegetation and a soil model, respectively. Both models predicted the levels of the 17 PCDD/F congeners in quite good agreement with the observed results although the soil model was more accurate than the vegetation model. Four different pathways of contribution to the vegetation concentrations were taken into account: vapour-phase absorption, dry particle deposition, wet particle deposition and uptake by root. The most important pathway was the vapour-phase absorption and the less was the uptake by root. In the soils model four pathways were considered: background soil concentration, dry particle deposition, wet particle deposition and uptake by root. After the background concentration, the most important pathway was the wet deposition.     

Measurement of odor intensity by an electronic nose

The possibility of using electronic noses (ENs) to measure odor intensity was investigated in this study. Two commercially available ENs, an Aromascan A32S with conducting polymer sensors and an Alpha M.O.S. Fox 3000 with metal oxide sensors, as well as an experimental EN made of Taguchi-type tin oxide sensors, were used in the experiments. Odor intensity measurement by sensory analysis and EN sensor response were obtained for samples of odorous compounds (n-butanol, CH3COCH3, and C2H5SH) and for binary mixtures of odorous compounds (n-butanol and CH3COCH3). Linear regression analysis and artificial neural networks (ANN) were used to establish a relationship between odor intensity and EN sensor responses. The results, suggest that large differences in sensor response to samples of equivalent odor intensity exist and that sensitivity to odorous compounds varies according to the type of sensors. A linear relationship between odor intensity and averaged sensor response was found to be appropriate for the EN based on conducting polymer sensors with a correlation coefficient (r) of 0.94 between calculated and measured odor intensity. However, the linear regression approach was shown to be inadequate for both ENs, which included metal oxide-type sensors. Very strong correlation (r = 0.99) between measured odor intensity and calculated odor intensity using the ANN developed were obtained for both commercial ENs. A weaker correlation (r = 0.84) was found for the experimental instrument, suggesting an insufficient number of sensors and/or not enough diversity in sensor responses. The results demonstrated the ability of ENs to measure odor intensity associated with simple mixtures of odorous compounds and suggest that ANN are appropriate to model the relationship between odor intensity measurement and EN sensor response.     

Nonlinear regression adjustments of multiple continuous monitoring methods produce effective characterization of short-term fine particulate matter

This study comprehensively characterizes hourly fine particulate matter (PM(2.5)) concentrations measured via a tapered element oscillating microbalance (TEOM), beta-gauge, and nephelometer from four different monitoring sites in U.S. Environment Protection Agency (EPA) Region 5 (in U.S. states Illinois, Michigan, and Wisconsin) and compares them to the Federal Reference Method (FRM). Hourly characterization uses time series and autocorrelation. Hourly data are compared with FRM by averaging across 24-hr sampling periods and modeling against respective daily FRM concentrations. Modeling uses traditional two-variable linear least-squares regression as well as innovative nonlinear regression involving additional meteorological variables such as temperature and humidity. The TEOM shows a relationship with season and temperature, linear correlation as low as 0.7924 and nonlinear model correlation as high as 0.9370 when modeled with temperature. The beta-gauge shows no relationship with season or meteorological variables. It exhibits a linear correlation as low as 0.8505 with the FRM and a nonlinear model correlation as high as 0.9339 when modeled with humidity. The nephelometer shows no relationship with season or temperature but a strong relationship with humidity is observed. A linear correlation as low as 0.3050 and a nonlinear model correlation as high as 0.9508 is observed when modeled with humidity. Nonlinear models have higher correlation than linear models applied to the same dataset. This correlation difference is not always substantial, which may introduce a tradeoff between simplicity of model and degree of statistical association. This project shows that continuous monitor technology produces valid PM(2.5) characterization, with at least partial accounting for variations in concentration from gravimetric reference monitors once appropriate nonlinear adjustments are applied. Although only one regression technically meets new EPA National Ambient Air Quality Standards (NAAQS) Federal Equivalent Method (FEM) correlation coefficient criteria, several others are extremely close, showing optimistic potential for use of this nonlinear adjustment model in garnering EPA NAAQS FEM approval for continuous PM(2.5) sampling methods.     

Nonlinear analysis and prediction of coarse particulate matter concentration in ambient air

This study attempts to characterize and predict coarse particulate matter (PM10) concentration in ambient air using the concepts of nonlinear dynamical theory. PM10 data observed daily from 1999 to 2002 at a site in Mumbai, India, was used to study the applicability of the chaos theory. First, the autocorrelation function and Fourier power spectrum were used to analyze the behavior of the time-series. The dynamics of the time-series was additionally studied through correlation integral analysis and phase space reconstruction. The nonlinear predictions were then obtained using local polynomial approximation based on the reconstructed phase space. The results were then compared with the autoregressive model. The results of nonlinear analysis indicated the presence of chaotic character in the PM10 time-series. It was also observed that the nonlinear local approximation outperforms the autoregressive model, because the observed relative error of prediction for the autoregressive model was greater than the local approximation model. The invariant measures of nonlinear dynamics computed for the predicted time-series using the two models also supported the same findings.     

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.     

A neural network-based approach for the prediction of urban SO2 concentrations in the Istanbul metropolitan area

A three-layer Artificial Neural Network (ANN) model was developed to forecast air pollution levels. The subsequent SO₂ concentration (24-hour averaged) being the output parameter of this study was estimated by seven input parameters such as preceding SO₂ concentrations (24-hour averaged), average daily temperature, sea-level pressure, relative humidity, cloudiness, average daily wind speed and daily dominant wind direction. After Backpropagation training combined with Principal Component Analysis (PCA), the proposed model predicted subsequent SO₂ values based on measured data. ANN testing outputs were proven to be satisfactory with correlation coefficients of about 0.770, 0.744 and 0.751 for the winter, summer and overall data, respectively.     

A Simple Neural Network for Estimating Emission Rates of Hydrogen Sulfide and Ammonia from Single Point Sources

Abstract

Neural networks have shown tremendous promise in modeling complex problems. This work describes the development and validation of a neural network for the purpose of estimating point source emission rates of hazardous gases. This neural network approach has been developed and tested using experimental data obtained for two specific air pollutants of concern in West Texas, hydrogen sulfide and ammonia. The prediction of the network is within 20% of the measured emission rates for these two gases at distances of less than 50 m. The emission rate estimations for ground level releases were derived as a function of seven variables: downwind distance, crosswind distance, wind speed, downwind concentration, atmospheric stability, ambient temperature, and relative humidity. A backpropagation algorithm was used to develop the neural network and is also discussed here. The experimental data were collected at the Wind Engineering Research Field Site located at Texas Tech University in Lubbock, Texas. Based on the results of this study, the use of neural networks provides an attractive and highly effective tool to model atmospheric dispersion, in which a large number of variables interact in a nonlinear manner.     

An analytical solution to contaminant diffusion in semi-infinite clayey soils with piecewise linear adsorption

The adsorption of contaminants onto soil particles typically is nonlinear if the contaminant concentration is sufficiently high. A simplified piecewise linear adsorption isotherm consistent with experimental results is proposed as an approximation for nonlinear adsorption behavior. This approximation allows for the use of analytical solution to model solute diffusion of contaminants that exhibit nonlinear adsorption. A moving boundary is introduced to represent significant changes in the retardation factor of clay with an increase in solute concentration. The proposed analytical solutions were validated using experimental data presented in the literature. There is negligible difference between the results obtained by the proposed analytical solution and those obtained by the linear model when C_m/C₀ reached 0.5. The results also show that the model based on linear adsorption using the initial secant of the Freundlich isotherm leads to significantly lower estimated breakthrough time for the contaminant of interest than that obtained using the proposed model. The earlier breakthrough is due to an under-estimation of the amount of adsorption. The proposed method is relatively simple to apply and can be used for evaluating experimental results and verifying more complex numerical models.     

Artificial neural network (ANN) modeling of adsorption of methylene blue by NaOH-modified rice husk in a fixed-bed column system

In this study, rice husk was modified with NaOH and used as adsorbent for dynamic adsorption of methylene blue (MB) from aqueous solutions. Continuous removal of MB from aqueous solutions was studied in a laboratory scale fixed-bed column packed with NaOH-modified rice husk (NMRH). Effect of different flow rates and bed heights on the column breakthrough performance was investigated. In order to determine the most suitable model for describing the adsorption kinetics of MB in the fixed-bed column system, the bed depth service time (BDST) model as well as the Thomas model was fitted to the experimental data. An artificial neural network (ANN)-based model was also developed for describing the dynamic dye adsorption process. An extensive error analysis was carried out between experimental data and data predicted by the models by using the following error functions: correlation coefficient (R ²), average relative error, sum of the absolute error and Chi-square statistic test (χ ²). Results show that with increasing bed height and decreasing flow rate, the breakthrough time was delayed. All the error functions yielded minimum values for the ANN model than the traditional models (BDST and Thomas), suggesting that the ANN model is the most suitable model to describe the fixed-bed adsorption of MB by NMRH. It is also more rational and reliable to interpret dynamic dye adsorption data through a process of ANN architecture.     

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.     

Comparison of nonideal sorption formulations in modeling the transport of phthalate esters through packed soil columns

Sorption of dimethyl phthalate (DMP), diethyl phthalate (DEP) and dipropyl phthalate (DPP) to two soil materials that vary in organic matter content was investigated using miscible displacement experiments under saturated flow conditions. Generated breakthrough curves (BTCs) were inversely simulated using linear, equilibrium sorption (LE), nonlinear, equilibrium sorption (NL), linear, first-order nonequilibrium sorption (LFO), linear, radial diffusion (LRD), and nonlinear, first-order nonequilibrium sorption (NFO) models. The Akaike information criterion was utilized to determine the preferred model. The LE model could not adequately describe phthalate ester (PE) BTCs in higher organic matter soil or for more hydrophobic PEs. The LFO and LRD models adequately described the BTCs but a slight improvement in curve-fitting was gained in some cases when the NFO model was used. However, none of the models could properly describe the desorptive tail of DPP for the high organic matter soil. Transport of DPP through this soil was adequately predicted when degradation or sorption hysteresis was considered. Using the optimized parameter values along with values reported by others it was shown that the organic carbon distribution coefficient (K(oc)) of PEs correlates well with the octanol/water partition coefficient (K(ow)). Also, a strong relationship was found between the first-order sorption rate coefficient normalized to injection pulse size and compound residence time. A similar trend of timescale dependence was found for the rate parameter in the radial diffusion model. Results also revealed that the fraction of instantaneous sorption sites is dependent on K(ow) and appears to decrease with the increase in the sorption rate parameter.     

Forecasting Daily Source Air Quality Using Multivariate Statistical Analysis and Radial Basis Function Networks

Abstract

It is vital to forecast gas and particle matter concentrations and emission rates (GPCER) from livestock production facilities to assess the impact of airborne pollutants on human health, ecological environment, and global warming. Modeling source air quality is a complex process because of abundant nonlinear interactions between GPCER and other factors. The objective of this study was to introduce statistical methods and radial basis function (RBF) neural network to predict daily source air quality in Iowa swine deep-pit finishing buildings. The results show that four variables (outdoor and indoor temperature, animal units, and ventilation rates) were identified as relative important model inputs using statistical methods. It can be further demonstrated that only two factors, the environment factor and the animal factor, were capable of explaining more than 94% of the total variability after performing principal component analysis. The introduction of fewer uncorrelated variables to the neural network would result in the reduction of the model structure complexity, minimize computation cost, and eliminate model overfitting problems. The obtained results of RBF network prediction were in good agreement with the actual measurements, with values of the correlation coefficient between 0.741 and 0.995 and very low values of systemic performance indexes for all the models. The good results indicated the RBF network could be trained to model these highly nonlinear relationships. Thus, the RBF neural network technology combined with multivariate statistical methods is a promising tool for air pollutant emissions modeling.     

Simulation of the evolution of particle size distributions containing coarse particulate in the atmospheric surface layer with a simple convection-diffusion-sedimentation model

The Fugitive Dust Model (FDM) and Industrial Source Complex (ISC), widely used coarse particulate dispersion models, have been shown inaccurate due to the neglect of vertical variations in atmospheric wind speed and turbulent diffusivity (Vesovic et al., 2001), omission of the gravitational advection velocity, and an underestimation of the ground deposition velocity (Kim and Larson, 2001). A simple, transient two-dimensional convection-diffusion-sedimentation model is proposed to simulate the evolution in particle size distribution of an aerosol ‘puff’ containing coarse particulate in the atmospheric surface layer. Monin-Okhubov similarity theory, accompanied by empirical observations made by Businger et al. (1971), is adopted to characterize the surface layer wind speed and turbulent diffusivity profiles over a wide range of atmospheric conditions. A first order analysis of the crossing trajectories effect suggests simulation data presented here are not significantly affected by particle inertia. The model is validated against Suffield experimental data in which coarse particulate deposition was measured out to a distance of 800 m from the source (Walker, 1965). Good agreement is found for the decay in ground deposits with distance from the source for stable atmospheres. Deposition data was also simulated for unstable atmospheric stratification and the current model was determined to modestly underestimate the peak concentration with increasing accuracy further downwind of the release. The current model's effective deposition velocity was compared to that suggested by Kim et al. (2000) and shows improvement with respect to FDM. Lastly, the model was used to simulate the dispersion of nine lognormal aerosol puffs in the lowest 50 m of the atmospheric surface layer for four classes of atmospheric stability. The simulated mass median aerodynamic diameters (MMAD) at multiple downwind sampling locations were calculated and plotted with distance from the source. The first 50 m from the source was found to have a substantial impact on the evolution of MMAD for stable atmospheric conditions. Away from the source, it was observed that particle size distributions were truncated by removal of all particles larger than about 60 μm. A particle Peclet number was also defined to quantify the relative importance of turbulent dispersion and sedimentation on particle motion in the vertical direction.     

Sensitivity of the terrestrial biosphere to climatic changes: impact on the carbon cycle

The biosphere is a major pool in the global carbon cycle; its response to climatic change is therefore of great importance. We developed a 5 degrees x 5 degrees longitude-latitude resolution model of the biosphere in which the global distributions of the major biospheric variables, i.e. the vegetation types and the main carbon pools and fluxes, are determined from climatic variables. We defined nine major broad vegetation types: perennial ice, desert and semi-desert, tundra, coniferous forest, temperate deciduous forest, grassland and shrubland, savannah, seasonal tropical forest and evergreen tropical forest. Their geographical repartition is parameterized using correlations between observed vegetation type, precipitation and biotemperature distributions. The model computes as a function of climate and vegetation type, the variables related to the continental biospheric carbon cycle, i.e. the carbon pools such as the phytomass, the litter and the soil organic carbon; and carbon fluxes such as net primary production, litter production and heterotrophic respiration. The modeled present-day biosphere is in good agreement with observation. The model is used to investigate the response of the terrestrial biosphere to climatic changes as predicted by different General Circulation Models (GCM). In particular, the impact on the biosphere of climatic conditions corresponding to the last glacial climate (LGM), 18 000 years ago, is investigated. Comparison with results from present-day climate simulations shows the high sensitivity of the geographical distribution of vegetation types and carbon content as well as biospheric trace gases emissions to climatic changes. The general trend for LGM compared to the present is an increase in low density vegetation types (tundra, desert, grassland) to the detriment of forested areas, in tropical as well as in other regions. Consequently, the biospheric activity (carbon fluxes and trace gases emissions) was reduced.