Comparison of the BOD Forecasting Ability of the ARIMA model and the Artificial Neural Network Model

ARIMA 모형과 인공신경망모형의 BOD예측력 비교

  • 정효준 (서울대학교 환경보건학과) ;
  • 이홍근 (서울대학교 환경보건학과)
  • Published : 2002.09.01


In this paper, the water quality forecast was performed on the BOD of the Chungju Dam using the ARIMA model, which is a nonlinear statistics model, and the artificial neural network model. The monthly data of water quality were collected from 1991 to 2000. The most appropriate ARIMA model for Chungju dam was found to be the multiplicative seasonal ARIMA(1,0,1)(1,0,1)$_{12}$, model. While the artificial neural network model, which is used relatively often in recent days, forecasts new data by the strength of a learned matrix like human neurons. The BOD values were forecasted using the back-propagation algorithm of multi-layer perceptrons in this paper. Artificial neural network model was com- posed of two hidden layers and the node number of each hidden layer was designed fifteen. It was demonstrated that the ARIMA model was more appropriate in terms of changes around the overall average, but the artificial neural net-work model was more appropriate in terms of reflecting the minimum and the maximum values.s.


ARIMA;Artificial neural networks;Back-propagation;Forecasting


  1. Kolehmainen, M., Martikainen, H. and Ruuskanen, J. : Neural networks and periodic components used in air quality forecasting, Atmospheric Environment, 35, 815-825, 2001
  2. Maier, H. R., Dandy, G. C., and Burch, M. D. : Use of artificial neural networks for modelling cyanobac-teria Anabaena spp. in the River Murray, South Aus-tralia. Ecological Modelling, 105, 257-272, 1998
  3. Hwarng, H. B. and Ang, H. T. : A simple neural net-work for ARMA(p, q) time series. The International Journal of Management Science, 29, 319-333, 2001
  4. 환경부, 환경연감, 1990-2000
  6. Kung, S. Y. : Digital Neural Networks, Prentice Hall International Inc. 30-33, 1993
  7. See, L. and Abrahart, R. J. : Multi-model data fusion for hydrological forecasting. Computer & Geosciences, 27, 987-994, 2001
  8. Ahmad, S., Khan, I. H. and Parida, B. P.: Performance of stochastic approaches for forecasting river water quality. Wat. Res., 35, 4261-4266, 2001
  9. Hameed, T. Marino, M. A. and Cheema, M. N. : Time series modeling of channel transmission losses. Agricultural Water Management, 29, 283-298, 1996
  10. Law, R. : Back-propagation learning in improving the accuracy of neural network-based tourism demand forecasting. Tourism Management, 21, 331-340, 2000
  11. Montanari, A. and Rosso, R. : Fractionally differ-enced ARIMA models applied to hydrologic time series(Identification, estimation, and simulation). Water Resources Research, 33, 1035-1044, 1997
  12. Luk, K. C., Ball, J. E. and Sharma, A. : A study of optimal model lag and spatial input to artificial neural network for rainfall forecasting. Journal of Hydrology, 227, 56-65, 2000
  13. Balkin, S. D. and Ord, J. K. : Automatic neural network modelling for univariate time series. International Journal of Forecasting, 16, 509-515, 2000