Abstract
Time varying coefficient ARMA and ARMA-transfer function (ARMA-TF) models for improving forecasting of water quality and runoff are presented and applied. Kalman filter algorithms are used for recursively updating the coefficients in the models. In the Kalman filter algorithm, different schemes are used for estimating the noise covariance matrices R and Q. Their performances in tracking the variability of the coefficients are also examined. The methodology is then applied to obtain one-step-ahead water quality and runoff forecasts in Hong Kong. It was found that forecasting improvements can be achieved by using the time varying coefficient ARMA and ARMA-TF modelling approach with a Kalman filter algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Anselmo, V. and Ubertini, L. (1979) Transfer function-noise model applied to flow forecasting, Hydrological Science Bulletin, IAHS ,24(3), 353–360.
Baracos, P.C., Hipel, K.W. and McLeod, A.I. (1981) Modelling hydrologic time series from the Arctic, Water Resources Bulletin, American Water Resources Association ,17(3), 414–422.
Boguslavskij, I.A. (1988) Filtering and control ,Optimization Software, Inc., New York, 133–134.
Box, G.E.P. and Jenkins, G.M. (1976) Time series analysis: Forecasting and control ,Holden-Day, Oakland, Calif.
Capodaglio, A.G., Zheng, S., Novotny, V. and Xin Feng (1990) Stochastic system identification of sewer flow models, J. Env. Eng., ASCE ,116(2), 284–298.
Clarke, R.T. (1974) The representation of a short period of experimental catchment data by a linear stochastic difference equation, Proc. of the Warsaw Symposium on Mathematical models in Hydrology, July 1971, International Association of Hydrological Sciences ,1, 3–16.
Diggle, P.J. (1990) Time series: A Biostatistical Introduction ,Clarendon Press, Oxford.
Hipel, K.W., McLeod, A.I. and Noakes, D.J. (1982) Fitting dynamic models to hydrological time series, In: A. H. El-Shaarawi and S. R. Esterby(eds.), Time Series Methods in Hydrosciences ,Elsevier Scientific Publishing Company, Amsterdam, Netherlands, pp 110–119.
Hong Kong Government Water Supplies Department (1959’1986) Hong Kong Rainfall and Runoff.
Huck, P.M. and Farquhar, G.J. (1974) Water quality models using Box-Jenkins method, J. Env. Eng., ASCE, 100(3), 733–753.
Jayawardena, A.W. and Lai Feizhou (1989) Time selies analysis of water quality data in Pearl River, China, J. Env. Eng., ASCE ,115(3), 590–607.
Jayawardena, A.W. and Lai Feizhou (1991) Water quality forecasting using an adaptive ARMA modelling approach, Proc. International Symposium on Environmental Hydraulics ,Dec. 1991, Hong Kong, 1121–1127.
Kahl, D.R. and Ledolter, J. (1983) A recursive Kalman filter forecasting approach, Management Science, 29(11), 1325–1333.
Kalman, R.E. (1960) A new approach to linear filtering and prediction problem,.J. Basic Eng. ,82, 35–45.
Ledolter, J. (1982) Recursive estimation and adaptive forecasting in ARIMA models with time varying coefficients, In D. Findley (Ed.), Applied Time Series II Academic Press, New York, pp 449–472.
Lohani, B.N. an Wang, M.M. (1987) Water quality data analysis in Chung Kang River, J. Env. Eng., ASCE, 113(1), 186–195.
Meade, N. (1985) Forecasting using growth curves-An adaptive approach, J. Operational Research Society ,36(12), 1103–1115.
Ngan, P. (1985) Kalman Filter and its Application to Flow Forecasting, Thesis present to the University of British Columbia, Vancouver, B.C., Canada, in partial fulfilment of the requirements for the degree of Doctor of Philosophy.
Ngan, P. and Russell, SO. (1986) Example of flow forecasting with Kalman filter, J. Hyd. Eng., ASCE, 112(9), 818–832.
Novotny, V. and Zheng, S. (1989) Rainfall-runoff function by ARMA modelling, J. Hyd. Eng., ASCE, 115(10), 1386–1400.
O’Connell, P.E. (1980) (Ed.) Real-Time Hydrological Forecasting and Control, Proceedings of 1st International Workshop held at the Institute of Hydrology ,Wallingford, Oxon, July, 1977.
O’Connell, P.E. and Clarke, R.T. (1981) Adaptive hydrological forecasting-a review, Hydrological Science Bulletin, IAHS ,26(2), 179–205.
Pierce, D.A. and Haugh, L.D. (1977) Causality in temporal systems, J. Econometrics ,5, 265–293.
Sastri, T. (1986) A recursive algorithm for adaptive estimation and parameter change detection of time series models, J. Operational Research Society ,37(10), 987–999.
Snorrason, A., Newbold, P. and Maxwell, W.H. (1984) Multiple input transfer function-noise modelling of river flow, In: W.H.C. Maxwell and L.R. Beard (Eds.), Frontiers in Hydrology ,Water Resources Publishing, Littleton, Colorado.
Todini, E. and Bouillot, D. (1976) A rainfall-runoff Kalman filter model, inter estimation algorithm for realtime hydrologic forecasting: A case study, paper presented at the Workshop on Recent Developments in Real-Time Forecasting Control of Water Resource Systems, Int. Inst, for Appl. Syst. Anal. ,Luxembourg, Austria, Oct 1976, 18–20.
Winkle, R.L. an Makridakis, S. (1983) The combination of forecasts, J. Roy. Stat. Soc., Ser. A ,146, 150–157.
Wood, E. and Szollosi-Nagy, A. (1978) An adaptive algorithm for analyzing short-term structural and parameter changes in hydrologic prediction models, Water Res. Res,. 14(4), 577–581.
Young, P. (1984) Recursive Estimation and Time Series Analysis ,Springer-Verlag, Berlin, Heidelberge.
Young, P.C., Ng, C.N., Lane, K. and Parker, D. (1991) Recursive forecasting, smoothing and seasonal adjustment of non-stationary environmental data, J. Forecasting ,10(1&2), 57–89.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer Science+Business Media Dordrecht
About this paper
Cite this paper
Jayawardena, A.W. (1996). Adaptivity in Stochastic Modelling and Forecasting. In: Singh, V.P., Kumar, B. (eds) Proceedings of the International Conference on Hydrology and Water Resources, New Delhi, India, December 1993. Water Science and Technology Library, vol 16. Springer, Dordrecht. https://doi.org/10.1007/978-94-011-0389-3_28
Download citation
DOI: https://doi.org/10.1007/978-94-011-0389-3_28
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-4174-4
Online ISBN: 978-94-011-0389-3
eBook Packages: Springer Book Archive