TY - GEN

T1 - A Bayesian method to improve the extrapolation ability of anns

AU - Kingston, Greer B.

AU - Maier, Holger R.

AU - Lambert, Martin F.

PY - 2005

Y1 - 2005

N2 - Although artificial neural networks have been shown to be superior prediction models in many hydrology-related areas, their known lack of extrapolation capability has limited the wider use and acceptance of ANNs as forecasting models. This problem lies mainly with the fact that a single "most likely" weight vector, which is determined by calibration with a finite set of data, is used to define the function modelled by the ANN. There are, in fact, many different weight vectors that result in approximately equal model performance; however, standard ANN development approaches do not allow for any weight vectors, other than that which provides the best fit to the calibration data, to impact on the predictions made. In this paper, a Bayesian method is presented that enables the entire range of plausible weight vectors to be accounted for in the model predictions. In doing so, the relationship modelled by the ANN is more general and less dominated by the information contained in the calibration data. The method is applied to a real-world case study known to require extrapolation and the resulting ANN is shown to perform significantly better than an ANN developed using standard approaches.

AB - Although artificial neural networks have been shown to be superior prediction models in many hydrology-related areas, their known lack of extrapolation capability has limited the wider use and acceptance of ANNs as forecasting models. This problem lies mainly with the fact that a single "most likely" weight vector, which is determined by calibration with a finite set of data, is used to define the function modelled by the ANN. There are, in fact, many different weight vectors that result in approximately equal model performance; however, standard ANN development approaches do not allow for any weight vectors, other than that which provides the best fit to the calibration data, to impact on the predictions made. In this paper, a Bayesian method is presented that enables the entire range of plausible weight vectors to be accounted for in the model predictions. In doing so, the relationship modelled by the ANN is more general and less dominated by the information contained in the calibration data. The method is applied to a real-world case study known to require extrapolation and the resulting ANN is shown to perform significantly better than an ANN developed using standard approaches.

KW - Artificial neural networks

KW - Bayesian estimation

KW - Hydrological forecasting

KW - Markov chain Monte Carlo

UR - http://www.scopus.com/inward/record.url?scp=29844450787&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:29844450787

SN - 0889864691

T3 - Proceedings of the 14th IASTED International Conference on Applied Simulation and Modelling

SP - 126

EP - 131

BT - Proceedings of the 14th IASTED International Conference on Applied Simulation and Modelling

A2 - Hamza, M.H.

T2 - Proceedings of the 14th IASTED International Conference on Applied Simulation and Modelling

Y2 - 15 June 2005 through 17 June 2005

ER -