Abstract
We develop multiple step ahead prediction models of river flow for locations in Tasmania (Australia) for decision support in aquaculture. In predicting river flows for multiple days ahead, we first statistically determine the maximum input lags of rainfall and river flow. We then use machine learning techniques in building models. In multiple step ahead prediction, we consider both static and dynamic approaches. In dynamic approach, one day prediction is served as input to two days ahead prediction. The experimental results demonstrate that, in general, a dynamic approach provides better accuracy in multiple day’s ahead prediction. For Duck Bay location using dynamic approach, support vector regression performs best over linear regression, M5P and multilayer perceptron. However, at Montagu Bay location, we find that M5P performs best over methods. We find that multiple step ahead prediction of river flow for each location requires modelling of lags with associated machine learning techniques.
Similar content being viewed by others
References
Badrzadeh H, Sarukkalige R, Jayawardena A (2013) Impact of multi resolution analysis of artificial intelligence models inputs on multi-step ahead river flow forecasting. J Hydrol 507:75–85
Chang LC, Chang FJ, Chiang YM (2004) A two-step-ahead recurrent neural network for stream-flow forecasting. Hydrol Process 18:81–92
Chernodub A (2013) Direct method for training feed-forward neural networks using batch extended kalman filter for multi-step-ahead predictions. Artif Neural Netw Mach Learn ICANN 8131:138–145
Kamruzzaman M, Metcalfe A, Beecham S (2014) Wavelet-based rainfall stream flow models for the southeast murray darling basin. J Hydrol Eng 19:1283–1293
Liu S, Tai H, Ding Q, Li D, Xu L, Wei Y (2011) A hybrid approach of support vector regression with genetic algorithm optimization for aquaculture water quality prediction. Math Comput Model 58:458–465
Liu S, Xu L, Jiang Y, Li D, Chen Y, Li Z (2014) A hybrid wa-cpso-lssvr model for dissolved oxygen content prediction in crab culture. Eng Appl Artif Intell 29:114–124
Nagesh Kumar D, Srinivasa Raju K, Sathish T (2004) River flow forecasting using recurrent neural networks. Water Resour Manag 18:143–161
Quinlan RJ (1992) Learning with continuous classes, 5th Australian Joint Conference on Artificial Intelligence, World Scientific, 343–348
Smola AJ, Scholkopf B (2004) A tutorial on support vector regression. Stat Comput 14:199–222
Solomatine D, See L, Abrahart R (2008) Data-driven modelling: Concepts, approaches and experiences. Pract Hydroinf 68:17– 30
Taieb SB, Hyndman RJ (2014) Boosting multi-step autoregressive forecasts, International Conference on Machine Learning
Wang Y, Witten IH (1997) Induction of model trees for predicting continuous classes, Poster papers of the 9th European Conference on Machine Learning, Springer
Wu C, Chau K (2011) Rainfall-runoff modeling using artificial neural network coupled with singular spectrum analysis. J Hydrol 399:394–409
Wu C, Chau K (2013) Prediction of rainfall time series using modular soft computing methods. Eng Appl Artif Intell 26:997–1007
Wu C, Chau K, Fan C (2010) Prediction of rainfall time series using modular artificial neural networks coupled with data-preprocessing techniques. J Hydrol 389:146–167
Estrada Gutirrez JC, de Pedro Sanz E, Lpez Luque R, Pulido Calvo I (2004) Comparison between traditional methods and artificial neural networks for ammonia concentration forecasting in an ell (Anguilla anguilla L.) intensive rearing system. Aquac Eng 31(3-4):183–203
Gutirrez-Estrada JC, Pulido-Calvo I, De la Rosa I, Marchini B (2012) Modeling inflow rates for the water exchange management in semi-intensive aquaculture ponds. Aquac Eng 48:19–30
Pulido-Calvo I, Gutirrez-Estrada JC, Daz-Rubio E, de la Rosa I (2014) Assisted management of water exchange in traditional semi-intensive aquaculture ponds. Comput Electron Agric 101:128–134
Chang F-J., Chiang Y-M., Chang L-C. (2007) Multi-step-ahead neural networks for flood forecasting. Hydrol Sci J 52(1):114–130
Xiong T, Bao Y, Hu Z (2013) Beyond one-step-ahead forecasting: Evaluation of alternative multi-step-ahead forecasting models for crude oil prices. Energy Econ 40:405–415
Dibike YB, Solomatine DP (2001) River flow forecasting using artificial neural networks. Phys Chem Earth Part B 26(1):1–7
Acknowledgments
The Intelligent Sensing and Systems Laboratory and the Tasmanian node of the Australian Centre for Broadband Innovation were assisted by a grant from the Tasmanian Government which was administered by the Tasmanian Department of Economic Development, Tourism and the Arts. This research was also supported with Aquaculture Decision Support (AquaDS) project under the CSIRO Food Futures Flagship. We acknowledge Doug Palmer, Daniel Hugo, Chris Sharman, Ashfaqur Rahman, Daniel Smith, Claire D’Este and Greg Smith for their insightful comments and helpful feedback.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by: H. A. Babaie
Rights and permissions
About this article
Cite this article
Shahriar, M.S., Kamruzzaman, M., McCulloch, J. et al. Multiple step ahead river flow modelling for south east tasmanian aquaculture. Earth Sci Inform 9, 271–279 (2016). https://doi.org/10.1007/s12145-015-0247-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-015-0247-x