Reservoir inflow forecasting with a modified coactive neuro-fuzzy inference system: a case study for a semi-arid region
- 56 Downloads
Existing forecast models applied for reservoir inflow forecasting encounter several drawbacks, due to the difficulty of the underlying mathematical procedures being to cope with and to mimic the naturalization and stochasticity of the inflow data patterns. In this study, appropriate adjustments to the conventional coactive neuro-fuzzy inference system (CANFIS) method are proposed to improve the mathematical procedure, thus enabling a better detection of the high nonlinearity patterns found in the reservoir inflow training data. This modification includes the updating of the back propagation algorithm, leading to a consequent update of the membership rules and the induction of the centre-weighted set rather than the global weighted set used in feature extraction. The modification also aids in constructing an integrated model that is able to not only detect the nonlinearity in the training data but also the wide range of features within the training data records used to simulate the forecasting model. To demonstrate the model’s efficacy, the proposed CANFIS method has been applied to forecast monthly inflow data at Aswan High Dam (AHD), located in southern Egypt. Comparative analyses of the forecasting skill of the modified CANFIS and the conventional ANFIS model are carried out with statistical score indicators to assess the reliability of the developed method. The statistical metrics support the better performance of the developed CANFIS model, which significantly outperforms the ANFIS model to attain a low relative error value (23%), mean absolute error (1.4 BCM month−1), root mean square error (1.14 BCM month−1), and a relative large coefficient of determination (0.94). The present study ascertains the better utility of the modified CANFIS model in respect to the traditional ANFIS model applied in reservoir inflow forecasting for a semi-arid region.
This work was supported by a research grant from the Ministry of Higher Education, FRGS/1/2016/STG06/UKM/02/1, and a grant from the University of Malaya’s BKP Grant BK023-2015. The authors thank the Nile Water Authority (NWA) and Aswan High Dam Authority (AHDA), Ministry of Water Resources and Irrigation, Egypt for providing the natural inflow data sets used in this study. Dr. R C Deo also acknowledges the University of Southern Queensland s-ADOSP research grant (Sept – Nov 2017). The authors would like to thank the research facilities support received from DIP-2015-012 project funded by University Kebangsaan Malaysia for the sixth author.The authors thank all reviewers and the Editor-In-Chief for their insightful comments that has improved the quality of the final manuscript.
Compliance with ethical standards
Conflicts of interest
The authors declare that they have no conflict of interest.
- Bai Y, Wang P, Xie J et al (2015) Additive model for monthly reservoir inflow forecast. J Hydrol Eng 20:4014079. https://doi.org/10.1061/(ASCE)HE.1943-5584.0001101 CrossRefGoogle Scholar
- Box GEP, Jenkins GM (1970) Time series analysis: forecasting and control, Rev. ed. Holden-Day, San FranciscoGoogle Scholar
- Ghorbani MA, Deo RC, Yaseen ZM, et al (2017) Pan evaporation prediction using a hybrid multilayer perceptron-firefly algorithm (MLP-FFA) model: case study in North Iran. Theor Appl Climatol 1–13. https://doi.org/10.1007/s00704-017-2244-0
- Gillberg C, Wahlström J (2008) Chromosome abnormalities in infantile autism and other childhood psychoses: a population study of 66 cases. Dev Med Child Neurol 27:293–304. https://doi.org/10.1111/j.1469-8749.1985.tb04539.x CrossRefGoogle Scholar
- Jang J-SR, Sun C-T, Mizutani E (1997) Neuro-fuzzy and soft computing, a computational approach to learning and machine intelligence. Prentice Hall, New JerseyGoogle Scholar
- Kurup PU, Dudani NK (2002) Neural networks for profiling stress history of clays from PCPT data. J Geotech Geoenviron Eng 128:569–579. https://doi.org/10.1061/(ASCE)1090-0241(2002)128:7(569) CrossRefGoogle Scholar
- Raheli B, Aalami MT, El-Shafie A et al (2017) Uncertainty assessment of the multilayer perceptron (MLP) neural network model with implementation of the novel hybrid MLP-FFA method for prediction of biochemical oxygen demand and dissolved oxygen: a case study of Langat River. Environ Earth Sci 76:503. https://doi.org/10.1007/s12665-017-6842-z CrossRefGoogle Scholar
- Shoaib M, Shamseldin AY, Melville BW, Khan MM (2016) Hybrid wavelet neuro-fuzzy approach for rainfall-runoff modeling. J Comput Civ Eng 30:4014125. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000457 CrossRefGoogle Scholar
- Smith J, Eli RN (1995) Neural-network models of rainfall-runoff process. J Water Resour Plan Manag 121:499–508. https://doi.org/10.1061/(ASCE)0733-9496(1995)121:6(499) CrossRefGoogle Scholar