A Hybrid ARIMA and Artificial Neural Networks Model to Forecast Air Quality in Urban Areas: Case of Tunisia

Ayari, Samia; Nouira, Kaouther; Trabelsi, Abdelwahed

doi:10.4028/www.scientific.net/amr.518-523.2969

Cited by 27 publications

(24 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mean square error (MSE), mean absolute error (MAE), mean relative deviation (Δ), and correlation coefficient (R) are widely acknowledged as effective indices in accuracy evaluation in air pollution modeling (Samia et al 2012;Chen et al 2013;Zou et al 2014a, b). Thus, these indices were utilized to test the reliability of RBF neural network in estimating PM 2.5 concentrations in this study.…”

Section: Accuracy Evaluationmentioning

confidence: 98%

Spatial modeling of PM2.5 concentrations with a multifactoral radial basis function neural network

Zou

Wang

Wan

et al. 2015

Environ Sci Pollut Res

View full text Add to dashboard Cite

Accurate measurements of PM2.5 concentration over time and space are especially critical for reducing adverse health outcomes. However, sparsely stationary monitoring sites considerably hinder the ability to effectively characterize observed concentrations. Utilizing data on meteorological and land-related factors, this study introduces a radial basis function (RBF) neural network method for estimating PM2.5 concentrations based on sparse observed inputs. The state of Texas in the USA was selected as the study area. Performance of the RBF models was evaluated by statistic indices including mean square error, mean absolute error, mean relative deviation, and the correlation coefficient. Results show that the annual PM2.5 concentrations estimated by the RBF models with meteorological factors and/or land-related factors were markedly closer to the observed concentrations. RBF models with combined meteorological and land-related factors achieved best performance relative to ones with either type of these factors only. It can be concluded that meteorological factors and land-related factors are useful for articulating the variation of PM2.5 concentration in a given study area. With these covariate factors, the RBF neural network can effectively estimate PM2.5 concentrations with acceptable accuracy under the condition of sparse monitoring stations. The improved accuracy of air concentration estimation would greatly benefit epidemiological and environmental studies in characterizing local air pollution and in helping reduce population exposures for areas with limited availability of air quality data.

show abstract

Section: Accuracy Evaluationmentioning

confidence: 98%

Spatial modeling of PM2.5 concentrations with a multifactoral radial basis function neural network

Zou

Wang

Wan

et al. 2015

Environ Sci Pollut Res

View full text Add to dashboard Cite

show abstract

“…Unlike current methods [16]- [18] using neural network model, support vector machines and regression model to predict PM 2.5. There are plenty of models using ARIMA to perform air pollution prediction [19]- [22].…”

Section: Background and Related Workmentioning

confidence: 99%

“…So far, the models combine ANN with ARIMA [20], [22] to perform air quality forecasting. Also, the model integrates ANN with Reinforcement learning to monitor air quality [23].…”

Section: Background and Related Workmentioning

confidence: 99%

Reinforcement Learning for Improving the Accuracy of PM2.5 Pollution Forecast Under the Neural Network Framework

Chang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Air pollution seriously damages human health on a large scale. Although earlier works have improved a variety of predictive models of air pollution, the ability to accurately predict air pollution indices remains elusive. Time series prediction plays an important role in many fields. Some predecessors have experimented with artificial neural networks (NNs), combining linear autoregressive integrated moving average (ARIMA) models with nonlinear NN models. The typical assumption is that time series has a long signal with no white noise. However, a real-time short signal with white noise is common. The methods in the literature also do not guarantee that the prediction error of an NN model is minimized. Therefore, we propose the use of reinforcement learning (RL) to predict future PM2.5 values. First, we use the Q-learning algorithm in RL based on its state characteristics on the NN model. Second, we select the input with different input dimensions and values of time delay, calculate the best strategy, and evaluate the computational complexity of our RL algorithm. Finally, we show that we effectively reduce the prediction error of the NN models. INDEX TERMS Smart city, smart environments, urban computing, autoregressive integrated moving average, time series, neural network, reinforcement learning, Q-learning.

show abstract

“…The combination of Box-Jenkins models with other statistical models has been considered, also, for forecasting and analysis of air pollution where ANN is more popular than others. Díaz-Robles et al [42] applied a hybrid Box-Jenkins and ANN model for forecasting PM 10 and O 3 , and Samia et al [43] used the same approach for PM 10 . A summary of the related researches in the past decade based on the type of model(s) for forecasting, the timespan to develop the forecasting model and the air pollutants considered to be forecasted, is presented in Table 1.…”

Section: Introductionmentioning

confidence: 99%

Forecasting Ambient Air Pollutants by Box-Jenkins Stochastic Models in Tehran

Delaram

Khedmati

2020

Scientia Iranica

View full text Add to dashboard Cite

This paper presents a study over the behavior of six air pollutants including PM 10 , PM 2.5 , O 3 , SO 2 , NO 2 and CO in Tehran during a 6-year timespan. In this paper, an iterative procedure based on the univariate Box-Jenkins stochastic models is applied to develop the most effective forecasting model for each air pollutant. Applying a number of widely used criteria, the best model for each air pollutant is selected and the results show that, the proposed models perform accurately and satisfactorily for both fitting and predicting where, the fitted and predicted values are so close to the true values of the related data. Finally, a factor analysis is conducted to investigate the relationships between the air pollutants where the results show that four factors accounts for 93.2704% of the total variance. In this regard, the factor containing PM 10 and PM 2.5 and the factor containing CO and NO 2 are, respectively, the most and the second most affecting factors with proportion of 43.2594% and 21.6500% of total variability. While both factors originate from high number of automobiles which use fossil fuels, decreasing the number of automobiles or increasing the quality of fossil fuels may result in up to 60% improvement in air quality.

show abstract

A Hybrid ARIMA and Artificial Neural Networks Model to Forecast Air Quality in Urban Areas: Case of Tunisia

Cited by 27 publications

References 33 publications

Spatial modeling of PM2.5 concentrations with a multifactoral radial basis function neural network

Spatial modeling of PM2.5 concentrations with a multifactoral radial basis function neural network

Reinforcement Learning for Improving the Accuracy of PM2.5 Pollution Forecast Under the Neural Network Framework

Forecasting Ambient Air Pollutants by Box-Jenkins Stochastic Models in Tehran

Contact Info

Product

Resources

About