Neural network model for the prediction of PM10 daily concentrations in two sites in the Western Mediterranean

Gennaro, Gianluigi de; Trizio, Livia; Gilio, Alessia Di; Pey, Jorge; Pérez, Noemí; Cusack, Michael; Alastuey, Andrés; Querol, Xavier

doi:10.1016/j.scitotenv.2013.06.093

Cited by 87 publications

(37 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Gennaro et al (2013) obtained R 2 in the range of 0.73-0.86 for daily predictions, which was better than those of singular models, whereas it was comparable to the results of seasonal models developed in this study. However, it should be noted that the results of performance measures and obtained model structures may change the approach used in modeling and the fluctuations in the data considering extremes.…”

Section: Model Performance Evaluations and Error Statisticssupporting

confidence: 84%

“…ANNs are flexible and nonparametric modeling tools that can perform any complex function mapping with arbitrarily desired accuracy (Gennaro et al, 2013;Saufie et al, 2013). Modeling with ANN covers a learning (training, validation) and a testing process using historical data by determining nonlinear relationships between the variables in input and output data sets.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…It has been shown that the variable selection or determination of proper lags for the inputs of ANN models, as it is addressed in the study by Sfetsos and Vlachogiannis (2010) using an iterative process on hourly data from the days before or in the paper by Gennaro et al (2013) that a lag-based sensitivity analysis has been applied in variable selection, could be alternatively accomplished by applying PCA. Gennaro et al (2013) obtained R 2 in the range of 0.73-0.86 for daily predictions, which was better than those of singular models, whereas it was comparable to the results of seasonal models developed in this study.…”

Section: Model Performance Evaluations and Error Statisticsmentioning

confidence: 99%

See 2 more Smart Citations

Improving artificial neural network model predictions of daily average PM₁₀ concentrations by applying principle component analysis and implementing seasonal models

Taşpınar

2015

Journal of the Air & Waste Management Association

View full text Add to dashboard Cite

This study introduces a seasonal modeling approach in the prediction of daily average PM 10 (particulate matter with an aerodynamic diameter <10 μm) levels 1 day ahead based on multilayer perceptron artificial neural network (MLP-ANN) forecasters. The data set covered all daily based meteorological parameters and PM 10 concentrations in the period of [2007][2008][2009][2010][2011][2012][2013][2014]. Seasonal ANN models for winter and summer periods were separately developed and trained by using a lagged time series data set. The most significant lagged terms of the variables within a 1-week period were determined by principal component analysis (PCA) and assigned as input vectors of ANN models. Cascading training with error back-propagation method was applied in model building. The use of seasonal ANN models with PCA-based inputs showed an increased prediction performance compared with nonseasonal models. For seasonal ANN models, the overall model agreement in training between modeled and observed values varied in the range of 0.78-0.83 and R 2 values ranged in 0.681-0.727, which outperformed nonseasonal models. The best testing R 2 values of seasonal models for winter and summer periods ranged in 0.709-0.727 with lower testing error, and the models did not show a tendency towards overpredicting or underpredicting the PM 10 levels. The approach demonstrated in the study appeared to be promising for predicting short-term levels of pollutants through the data sets with high irregularities and could have significant applicability in the case of large number of considered inputs.Implications: This study provides an alternative approach to predict PM 10 levels 1 day ahead by building seasonal ANN models. Applying PCA on a lagged data set resulted in selection of the most significant lags of variables reducing model complexity. Cascading training with error back-propagation method appropriately determined hidden layer neurons. Separately building ANN models for winter and summer periods over years, even though it required much more effort compared with building regular nonseasonal models, yielded better model agreements and smaller testing errors. This approach can be applied on the data sets with irregularities and a large number of considered inputs.

show abstract

Section: Model Performance Evaluations and Error Statisticssupporting

confidence: 84%

Section: Artificial Neural Networkmentioning

confidence: 99%

Section: Model Performance Evaluations and Error Statisticsmentioning

confidence: 99%

See 1 more Smart Citation

Improving artificial neural network model predictions of daily average PM₁₀ concentrations by applying principle component analysis and implementing seasonal models

Taşpınar

2015

Journal of the Air & Waste Management Association

View full text Add to dashboard Cite

show abstract

“…For example, Russo, Raischel, & Lind optimized an ANN by utilizing random variables to predict air quality [7]. Also according to ANN, Nejadkoorki, & Baroutian and Gennaro et al built models to predict 10 PM pollution levels [8,9]. Voukantsis et al also evaluated air pollution (PM 10 and PM 2.5 ) using an ANN based on PCA [10].…”

Section: State Of the Artmentioning

confidence: 99%

A Deep Belief Network Based Model for Urban Haze Prediction

Song

et al. 2018

Teh. vjesn.

View full text Add to dashboard Cite

Abstract:In order to improve the accuracy of urban haze prediction, a novel deep belief network (DBN)-based model was proposed. Firstly, data pertaining to both air quality and the environment (e.g. meteorology) data was monitored and collected. The primary haze influencing elements were discovered by analyzing the correlations between each of the meteorological factors and haze. Secondly, a DBN combined with multilayer restricted Boltzmann machines and a single-layer back propagation network was applied. Thirdly, the meteorological data predictions were carried out by using a competitive adaptive-reweighed method. A stable model was established by big-data training and its accuracy was verified by experiments. Results demonstrate that the pollution haze occurs in accordance with regular laws, and is greatly affected by wind direction, atmospheric pressure, and seasons. The correlation coefficient (CC) between the actual haze value and the prediction of the proposed model is 0.8, and the mean absolute error (MAE) is 26 μg/m 3 . Compared with the traditional prediction algorithms, the CC is improved by 18 % on average, while the MAE is reduced by 15.7 μg/m 3 . The proposed method has a good prospect to predict haze and investigate the main causes of it. This study provides data support for urban haze prevention and governance.

show abstract

“…Sophisticated statistical methods have been employed by various environmental epidemiologists for analysing effects of air pollution on the human health consequences (Bernard 2001;Elliott 2007;Gasparrini, 2011;Sof ianopoulou 2013;Vanos 2015). A number of linear and nonlinear methods have been applied to time series for forecasting the concentration of air pollutants such as O , PM, NO , CO, and SO while compared to ANNs (Perez & Gramsch, 2000;Solaiman 2008;Moustris 2009;Inal, 2010;de Gennaro, 2013). ANNs are useful tools for forecasting air pollution conditions and providing better results as compared to the other relevant models (Gardner & Dorling, 1998).…”

mentioning

confidence: 99%

Preprocessing and Optimization of Smooth Data-driven Model for Emergency Conditions Against Air Pollution

Ardalan¹,

Mohammadi

A³

et al. 2016

AMBIENT SCIENCE

View full text Add to dashboard Cite

Neural network model for the prediction of PM10 daily concentrations in two sites in the Western Mediterranean

Cited by 87 publications

References 32 publications

Improving artificial neural network model predictions of daily average PM₁₀ concentrations by applying principle component analysis and implementing seasonal models

Improving artificial neural network model predictions of daily average PM₁₀ concentrations by applying principle component analysis and implementing seasonal models

A Deep Belief Network Based Model for Urban Haze Prediction

Preprocessing and Optimization of Smooth Data-driven Model for Emergency Conditions Against Air Pollution

Contact Info

Product

Resources

About

Neural network model for the prediction of PM10 daily concentrations in two sites in the Western Mediterranean

Cited by 87 publications

References 32 publications

Improving artificial neural network model predictions of daily average PM10 concentrations by applying principle component analysis and implementing seasonal models

Improving artificial neural network model predictions of daily average PM10 concentrations by applying principle component analysis and implementing seasonal models

A Deep Belief Network Based Model for Urban Haze Prediction

Preprocessing and Optimization of Smooth Data-driven Model for Emergency Conditions Against Air Pollution

Contact Info

Product

Resources

About

Improving artificial neural network model predictions of daily average PM₁₀ concentrations by applying principle component analysis and implementing seasonal models

Improving artificial neural network model predictions of daily average PM₁₀ concentrations by applying principle component analysis and implementing seasonal models