Neural networks and periodic components used in air quality forecasting

Forecasting of air quality parameters is one topic of air quality research today due to the health effects caused by airborne pollutants in urban areas. The work presented here aims at comparing two principally different neural network methods that have been considered as potential tools in that area and assessing them in relation to regression with periodic components. Self-organizing maps (SOM) represent a form of competitive learning in which a neural network learns the structure of the data. Multi-layer perceptrons (MLPs) have been shown to be able to learn complex relationships between input and output variables. In addition, the effect of removing periodic components is evaluated with respect to neural networks. The methods were evaluated using hourly time series of NO₂ and basic meteorological variables collected in the city of Stockholm in 1994–1998. The estimated values for forecasting were calculated in three ways: using the periodic components alone, applying neural network methods to the residual values after removing the periodic components, and applying only neural networks to the original data. The results showed that the best forecast estimates can be achieved by directly applying a MLP network to the original data, and thus, that a combination of the periodic regression method and neural algorithms does not give any advantage over a direct application of neural algorithms.     

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.     

Optimizing the specific surface area of fly ash-based sorbents for flue gas desulfurization

High performance sorbents for flue gas desulfurization can be synthesized by hydration of coal fly ash, calcium sulfate, and calcium oxide. In general, higher desulfurization activity correlates with higher sorbent surface area. Consequently, a major aim in sorbent synthesis is to maximize the sorbent surface area by optimizing the hydration conditions. This work presents an integrated modeling and optimization approach to sorbent synthesis based on statistical experimental design and two artificial intelligence techniques: neural network and genetic algorithm. In the first step of the approach, the main and interactive effects of three hydration variables on sorbent surface area were evaluated using a full factorial design. The hydration variables of interest to this study were hydration time, amount of coal fly ash, and amount of calcium sulfate and the levels investigated were 4-32 h, 5-15 g, and 0-12 g, respectively. In the second step, a neural network was used to model the relationship between the three hydration variables and the sorbent surface area. A genetic algorithm was used in the last step to optimize the input space of the resulting neural network model. According to this integrated modeling and optimization approach, an optimum sorbent surface area of 62.2m(2)g(-1) could be obtained by mixing 13.1g of coal fly ash and 5.5 g of calcium sulfate in a hydration process containing 100ml of water and 5 g of calcium oxide for a fixed hydration time of 10 h.     

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.     

The relationships between air pollutants, meteorological parameters and concentration of airborne fungal spores

Fungal spores are an important component of bioaerosol and also considered to act as indicator of the level of atmospheric bio-pollution. Therefore, better understanding of these phenomena demands a detailed survey of airborne particles.The objective of this study was to examine the dependence of two the most important allergenic taxa of airborne fungi - Alternaria and Cladosporium - on meteorological parameters and air pollutant concentrations during three consecutive years (2006-2008). This study is also an attempt to create artificial neural network (ANN) forecasting models useful in the prediction of aeroallergen abundance.There were statistically significant relationships between spore concentration and environmental parameters as well as pollutants, confirmed by the Spearman’s correlation rank analysis and high performance of the ANN models obtained. The concentrations of Cladosporium and Alternaria spores can be predicted with quite good accuracy from meteorological conditions and air pollution recorded three days earlier.     

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.     

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

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

Prediction of ozone concentrations in Oporto city with statistical approaches

The performance of three statistical methods: time-series, multiple linear regression and feedforward artificial neural networks models were compared to predict the daily mean ozone concentrations. The study here reported was based on data from one urban site with traffic influences and one rural background site. The studies were performed for the year 2002 and the respective four trimesters separately. In the multiple linear regression and feedforward artificial neural network models, the concentrations of ozone, the concentrations of its precursors (nitrogen oxides) and some meteorological variables for one and two days before the prediction day were used as predictors. For the application of these models in the validation step, the inputs of ozone concentration for one and two days before were replaced by the ozone concentrations predicted by the models. The results showed that time-series modelling was not profitable. In the development step, similar performances were obtained with multiple linear regression and feedforward artificial neural network. Better performance indexes were achieved with feedforward artificial neural network models in validation step. Concluding, feedforward artificial neural network models were more efficient to predict ozone concentrations.     

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.     

三效催化转化器智能故障诊断系统知识库设计

在分析三效催化转化器故障诊断知识特点的基础上,采用一些措施构建知识库,如采用神经网络方法对转化器工作状态参数进行处理,采用多层前馈神经网络模型和自组织神经网络模型获取知识,采用产生式规则形式和二元化产生式规则形式表达知识,设计量化模块和知识库模块转化知识,并采用多个神经网络来记忆知识。应用效果表明,三效催化转化器神经网络故障诊断专家系统的预报准确率较高,具有较大的实用性。     

基于人工蜂群算法与BP神经网络的水质评价模型

针对BP网络水质评价模型的不足,引入人工蜂群(ABC)算法,将求解BP神经网络各层权值、阀值的过程转化为蜜蜂寻找最佳蜜源的过程,提出了一种新的结合人工蜂群算法的BP网络水质评价方法(ABC-BP)。并以2000—2006年渭河监测断面的10组实测数据作为测试样本对其水质进行了评价,实验结果表明该方法得到的水质评价结果准确,并具有很强的稳定性和鲁棒性。     

RBF与Elman神经网络在人工湿地复合基质去污效果预测中的应用

人工湿地的去污机理复杂、呈高度非线性,故利用神经网络技术构建模型预测其长期运行效果。通过构建人工湿地复合基质模拟槽系统进行为期4个月的实验,监测得到56组COD去除率数据样本,经Matlab小波去噪后分别利用RBF和Elman网络构建动态神经网络模型,预测该系统对生活污水中COD去除效果。结果表明,RBF和Elman神经网络预测值的均方根误差分别为0.0186和0.0163,精度较高,该系统后期的COD去除率在49.4%～59.0%之间。     

Content of aliphatic hydrocarbons in limpets as a new way for classification of species using artificial neural networks

It is demonstrated that biological species like limpets can be classified according to their level of n-alkanes when artificial neural networks are applied. Marine intertidal and subtidal limpets of the Canary Islands (Spain), Patella piperata, Patella candei crenata and Patella ulyssiponensis aspera were selected as bioindicator organisms. Samples were collected at four stations on the coasts of Fuerteventura. Concentration of n-alkanes in the soft tissues of the limpets has been determined by gas chromatography. Data were treated with artificial neural networks (ANNs) and it was found that using suitable architecture of a supervised artificial neural network, the limpets can be successfully distinguished (classified) up to 98%.     

A cumulative-risk assessment method based on an artificial neural network model for the water environment

Environmental Science and Pollution Research - To analyze the cumulative risks to the water environment, the backpropagation artificial neural network (BP-ANN), a self-adapting algorithm, was...     

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.     

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.     

Application of artificial neural network for prediction of Pb(II) adsorption characteristics

The adsorption of Pb(II) onto the surface of microwave-assisted activated carbon was studied through a two-layer feedforward neural network. The activated carbon was developed by microwave activation of Acacia auriculiformis scrap wood char. The prepared adsorbent was characterized by using Brunauer–Emmett–Teller (BET) surface area analyzer, scanning electron microscope (SEM), and X-ray difractometer. In the present study, the input variables for the proposed network were solution pH, contact time, initial adsorbate concentration, adsorbent dose and temperature, whereas the output variable was the percent Pb(II) removal. The network had been trained by using different algorithms and based on the lowest mean squared error (MSE) value and validation error, resilient backpropagation algorithm with 12 neurons in the hidden layer was selected for the present investigation. The tan sigmoid and purelin transfer function were used in the hidden and the output layers of the proposed network, respectively. The model predicted and experimental values of the percent Pb(II) removal were also compared and both the values were found to be in reasonable agreement with each other. The performance of the developed network was further improved by normalizing the experimental data set and it was found that after normalization, the MSE and validation error were reduced significantly. The sensitivity analysis was also performed to determine the most significant input parameter.     

Pattern recognition of the movement tracks of medaka (Oryzias latipes) in response to sub-lethal treatments of an insecticide by using artificial neural networks

Specimens of medaka (Oryzias latipes) were observed continuously through an automatic image recognition system before and after treatments of an anti-cholinesterase insecticide, diazinon (0.1 mg/l), for 4 days in semi-natural conditions (2 days before treatment and 2 days after treatment). The "smooth" pattern was typically shown as a normal movement behavior, while the "shaking" pattern was frequently observed after treatments of diazinon. These smooth and shaking patterns were selected for training with an artificial neural network. Parameters characterizing the movement tracks, such as speed, degree of backward movements, stop duration, turning rate, meander, and maximum distance movements in the y-axis of 1-min duration, were given as input (six nodes) to a multi-layer perceptron with the back propagation algorithm. Binary information for the smooth and shaking patterns was separately given as the matching output (one node), while eight nodes were assigned to a single hidden layer. As new input data were given to the trained network, it was possible to recognize the smooth and shaking patterns of the new input data. Average recognition rates of the smooth pattern decreased significantly while those for the shaking pattern increased to a higher degree after treatments of diazinon. The trained network was able to reveal the difference in the shaking pattern in different light phases before treatments of diazinon. This study demonstrated that artificial neural networks could be useful for detecting the presence of toxic chemicals in the environment by serving as in-situ behavioral monitoring tools.     

Multilayer perceptron neural network-based approach for modeling phycocyanin pigment concentrations: case study from lower Charles River buoy,USA

Environmental Science and Pollution Research - This paper proposes multilayer perceptron neural network (MLPNN) to predict phycocyanin (PC) pigment using water quality variables as predictor. In...     

Patterns of PCDDs and PCDFs in human milk and food and their characterization by artificial neural networks

Artificial neural network (ANN) has been recently introduced as a tool for data analysis. In this study, Kohonen's self-organizing maps (SOMs), a special type of neural network, were applied to a set of PCDD/PCDF concentrations found in 54 human milk and 83 food samples, which were collected in a number of countries all over the world. Data were obtained from the scientific literature. The purpose of the study was to find a potential relationship between PCDD/PCDF congener profiles in human milk and the dietary habits of the different countries in which samples were collected. The comparison of the SOM component planes for human milk and foodstuffs indicates that those countries with a greater fish consumption show also higher PCDD/PCDF concentrations in human milk. SOMs enable both the visualization of sample units and the visualization of congener distribution.