Forecasting the PM10 Concentration by Using the Artificial Neural Network and the Autoregressive Form
Abstract
This research aims to study a development of the forecasting model to predict the daily average PM10 concentration in the North area of Thailand with 3 datasets. Each of datasets is the univariate time series that is a daily data, since 1st Jan - 31th May 2016. To generate the forecasting model, we present a forecasting model by the artificial neural network technique combine with the autoregressive of ARIMA model, called AR-ANN model. We evaluated our experiment by measurement error between our AR-ANN model and the ARIMA model. The error measurement of each model is measured by the Root Mean Square Error (RMSE) and the Mean Absolute Percentage Error (MAPE). From the result, we found that RMSE and MAPE of the AR-ANN model has lower than ARIMA model for whole datasets. Therefore, we concluded that our AR-ANN model can use to forecast the daily average PM10 concentration appropriately. Keywords : forecasting, PM10, Artificial Neural Networks, autoregressiveReferences
Antanasijevic, D.Z., Pocajt, V.V., Povrenovic, D.S., Ristic, M.D., and Peric-Grujic, A.A. (2013). PM10 emission
forecasting using artificial neural networks and genetic algorithm input variable optimization.
Science of the Total Environment, 443, 511–519.
Box, G.E.P., and Jenkins, G. (1990). Time Series Analysis, Forecasting and Control. San Francissco: Holden-Day.
Cadenas, E., and Rivera, W. (2010). Wind speed forecasting in three different regions of Mexico, using a hybrid ARIMA-ANN model. Renewable Energy, 35, 2732-2738.
Department of Health. (2015). The surveillance areas at risk from air pollution in case of PM10. Retrieved October
4, 2016, from http://hia.anamai.moph.go.th/more_news.php?cid=317&filename=hia_book_2. (in Thai)
Grivas, G., and Chaloulakou, A. (2006). Artificial neural network models for prediction of PM10 hourly
concentrations, in the Greater Area of Athens, Greece. Atmospheric Environment, 40, 1216–1229.
He, H.D., Lu, W.Z., and Xue, Y. (2014). Prediction of particulate matter at street level using artificial neural networks
coupling with chaotic particle swarm optimization algorithm. Building and Environment, 78, 111-117.
Hooyberghs, J., Mensink, C., Dumont, G., Fierens, F., and Brasseur, O. (2005). A neural network forecast for
daily average PM10 concentrations in Belgium. Atmospheric Environment, 39, 3279–3289.
Khanthongkham, W., Charoensiri, T., and Soponpimol, C. (2016). Forecasting of Broiler Price.
Burapha Science Journal, 21(1), 100-109.
Kumar, S. (2004). Neural Networks: A Classroom Approach. New Delhi: Tata McGraw-Hill Education.
Lee, Y.S., and Tong, L.I. (2011). Forecasting time series using a methodology based on autoregressive integrated
moving average and genetic programming. Knowledge-Based Systems, 24,66-72.
Hyndman, R.J. (2015). Forecasting Functions for Time Series and Linear Models. Retrieved November 22, 2015,
from http://github.com/robjhyndman/forecast.
Perez, P. (2012). Combined model for PM10 forecasting in a large city. Atmospheric Environment, 60, 271-276.
Pollution Control Department. (2016). Air Quality Index. Retrieved October 4, 2016,
from http://aqmthai.com/aqi_info.php. (in Thai)
Pollution Control Department. (2016). Data Archives for Air and Noise Pollution. Retrieved October 4, 2016,
from http://aqnis.pcd.go.th/. (in Thai)
Thanapala, D., Charoensiri, T., and Soponpimol, C. (2016). Forecasting of Factory Pineapple Prices with Box-Jenkins
Method. Burapha Science Journal, 21(1), 110-118.
Wang, X., and Meng, M. (2012). A Hybrid Neural Network and ARIMA Model for Energy Consumption Forecasting.
JOURNAL OF COMPUTERS, 7(5), 1184-1190.
Wang, Y., Wang, J., Zhao, G., and Dong, Y. (2012). Application of residual modification approach in seasonal
ARIMA for electricity demand forecasting: A case study of China. Energy Policy, 48, 284-294.
Wongsathan, R., and Seedadan, I. (2016). A hybrid ARIMA and Neural Networks model for PM-10 pollution
estimation: The case of Chiang Mai city moat area. Procedia Computer Science, 86, 273 – 276.
forecasting using artificial neural networks and genetic algorithm input variable optimization.
Science of the Total Environment, 443, 511–519.
Box, G.E.P., and Jenkins, G. (1990). Time Series Analysis, Forecasting and Control. San Francissco: Holden-Day.
Cadenas, E., and Rivera, W. (2010). Wind speed forecasting in three different regions of Mexico, using a hybrid ARIMA-ANN model. Renewable Energy, 35, 2732-2738.
Department of Health. (2015). The surveillance areas at risk from air pollution in case of PM10. Retrieved October
4, 2016, from http://hia.anamai.moph.go.th/more_news.php?cid=317&filename=hia_book_2. (in Thai)
Grivas, G., and Chaloulakou, A. (2006). Artificial neural network models for prediction of PM10 hourly
concentrations, in the Greater Area of Athens, Greece. Atmospheric Environment, 40, 1216–1229.
He, H.D., Lu, W.Z., and Xue, Y. (2014). Prediction of particulate matter at street level using artificial neural networks
coupling with chaotic particle swarm optimization algorithm. Building and Environment, 78, 111-117.
Hooyberghs, J., Mensink, C., Dumont, G., Fierens, F., and Brasseur, O. (2005). A neural network forecast for
daily average PM10 concentrations in Belgium. Atmospheric Environment, 39, 3279–3289.
Khanthongkham, W., Charoensiri, T., and Soponpimol, C. (2016). Forecasting of Broiler Price.
Burapha Science Journal, 21(1), 100-109.
Kumar, S. (2004). Neural Networks: A Classroom Approach. New Delhi: Tata McGraw-Hill Education.
Lee, Y.S., and Tong, L.I. (2011). Forecasting time series using a methodology based on autoregressive integrated
moving average and genetic programming. Knowledge-Based Systems, 24,66-72.
Hyndman, R.J. (2015). Forecasting Functions for Time Series and Linear Models. Retrieved November 22, 2015,
from http://github.com/robjhyndman/forecast.
Perez, P. (2012). Combined model for PM10 forecasting in a large city. Atmospheric Environment, 60, 271-276.
Pollution Control Department. (2016). Air Quality Index. Retrieved October 4, 2016,
from http://aqmthai.com/aqi_info.php. (in Thai)
Pollution Control Department. (2016). Data Archives for Air and Noise Pollution. Retrieved October 4, 2016,
from http://aqnis.pcd.go.th/. (in Thai)
Thanapala, D., Charoensiri, T., and Soponpimol, C. (2016). Forecasting of Factory Pineapple Prices with Box-Jenkins
Method. Burapha Science Journal, 21(1), 110-118.
Wang, X., and Meng, M. (2012). A Hybrid Neural Network and ARIMA Model for Energy Consumption Forecasting.
JOURNAL OF COMPUTERS, 7(5), 1184-1190.
Wang, Y., Wang, J., Zhao, G., and Dong, Y. (2012). Application of residual modification approach in seasonal
ARIMA for electricity demand forecasting: A case study of China. Energy Policy, 48, 284-294.
Wongsathan, R., and Seedadan, I. (2016). A hybrid ARIMA and Neural Networks model for PM-10 pollution
estimation: The case of Chiang Mai city moat area. Procedia Computer Science, 86, 273 – 276.
Downloads
Published
2017-11-20
Issue
Section
Research Article
