Comparative analysis of ANFIS models in Prediction of Streamflow: the case of Seyhan Basin

Year 2023, Volume: 11 Issue: 2, 72 - 78, 30.06.2023

Furkan Özkan , Bülent Haznedar

https://doi.org/10.18100/ijamec.1308666

Cited By: 1

Abstract

In order to sustain human life without problems, a rational planning is required for the conservation and use of existing water resources. The potential of future water sources should be determined as the first step in such planning. Therefore, river flow forecasting is necessary to provide basic information about a variety of problems related to the operation of river systems. In this study, the long-term daily flow values of the Zamantı River-Değirmenocağı, Zamantı River-Ergenuşağı, and Eğlence River-Eğribük stations in the Seyhan Basin in Turkey were examined. In order to predict the forward flow rate from past flow measurement values, the Adaptative Neuro-Fuzzy Inference System (ANFIS) model was trained using Backpropagation (BP), Hybrid Learning (HB), and Simulated Annealing (SA) algorithms, and the results were compared. The performance of ANFIS models created with different input parameters using Grid Partitioning (GP) and Fuzzy C-Means Clustering (FCM) methods was also examined. The evaluation criteria used for comparison were Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Determination Coefficient (R2), and Mean Absolute Percentage Error (MAPE). The best results for R2 values of 0.6854, 0.9242, and 0.9373 were obtained for FMSs using the BP model. As a result of the analysis, it was concluded that the BP algorithm could be used more successfully and effectively than other algorithms for training ANFIS parameters in nonlinear problems.

Keywords

Anfis, Forecasting, Hydrology, Neuro-fuzzy, Streamflow

References

• [1] Gleick, Peter H. "Basic water requirements for human activities: meeting basic needs." Water international 21.2 (1996): 83-92.
• [2] Storck, Pascal, et al. "Application of a GIS‐based distributed hydrology model for prediction of forest harvest effects on peak stream flow in the Pacific Northwest." Hydrological Processes 12.6 (1998): 889-904.
• [3] Dibike, Y. B., and Solomatine D. P. (2001). River flow forecasting using artificial neural networks. Physics and Chemistry of the Earth, Part B: Hydrology, Oceans and Atmosphere 26.1 1-7.
• [4] Firat, M., and Turan M. E. (2010). Monthly river flow forecasting by an adaptive neuro-fuzzy inference system. Water and environment journal 24.2 116-125.
• [5] Liu, Yuqiong, et al. (2008). Linking science with environmental decision making: Experiences from an integrated modeling approach to supporting sustainable water resources management. Environmental Modelling & Software 23.7: 846-858.
• [6] Tezcan, Levent, et al. (2007). Assessment of climate change impacts on water resources of Seyhan River Basin. The final report of impact of the climate changes on the agricultural production system in the arid areas, Turkey.
• [7] Behzad, M., et al. (2009). Generalization performance of support vector machines and neural networks in runoff modelling. Expert Systems with applications 36.4 7624-7629.
• [8] ALTUNKAYNAK, A., and BASAKIN, E. A. (2018). River flow estimation using time series and comparison with different methods. Journal of Erzincan University Institute of Science and Technology 11.1 92-101.
• [9] Dawood, Thikra, et al. "Artificial intelligence for the modeling of water pipes deterioration mechanisms." Automation in
• [10] Firat, M. A. H. M. U. T. "Comparison of artificial intelligence techniques for river flow forecasting." Hydrology and Earth System Sciences 12.1 (2008): 123-139.
• [11] Agarwal, Anil, et al. Integrated water resources management. Stockholm: Global water partnership, 2000.
• [12] Sarma, A. K., et al., eds. (2016). Urban hydrology, watershed management and socio-economic aspects. Basel, Switzerland: Springer International Publishing.
• [13] Bisht, D. CS. and Ashok J. (2011). Discharge modelling using adaptive neuro-fuzzy inference system. International Journal of Advanced Science and Technology 31.1 99-114.
• [14] Mahabir, C., F. E. Hicks, and A. Robinson Fayek. (2003). Application of fuzzy logic to forecast seasonal runoff. Hydrological processes 17.18 3749-3762.
• [15] Bizimana, H., Demir F., and Sonmez O. (2016). Modeling of Yuvacık Dam Water Level Changes with Fuzzy Logic. 4th International Symposium on Innovative Technologies in Engineering and Science (ISITES2016) 3-5 Nov 2016 Alanya/Antalya-Turkey.
• [16] Altunkaynak, Abdusselam, Mehmet Ozger, and Mehmet Cakmakci. "Water consumption prediction of Istanbul city by using fuzzy logic approach." Water Resources Management 19.5 (2005): 641-654.
• [17] Gunathilake, M. B., et al. (2021). Hydrological models and Artificial Neural Networks (ANNs) to simulate streamflow in a tropical catchment of Sri Lanka. Applied Computational Intelligence and Soft Computing 2021
• [18] Riad, S., et al. (2004). Rainfall-runoff model using an artificial neural network approach." Mathematical and Computer Modelling 40.7-8 839-846.
• [19] Samanataray, S., and A.Sahoo. (2021). A Comparative Study on Prediction of Monthly Streamflow Using Hybrid ANFIS-PSO Approaches. KSCE Journal of Civil Engineering 25.10 4032-4043.
• [20] Niu, W., and Feng, Z. (2021). Evaluating the performances of several artificial intelligence methods in forecasting daily streamflow time series for sustainable water resources management. Sustainable Cities and Society 64 102562.
• [21] Ozcalık, H., Uygur, A., (2003). Effective modeling of dynamic systems based on coherent neural-fuzzy network structure. KSU Journal of Science and Engineering, 6 (1): 36-46.
• [22] Avcı, E., Akpolat, Z. H. (2002). Speed control of DC motors with an adaptive network-based fuzzy inference system. ELECO’2002 Electrical-Electronics-Computer Engineering Symposium, Bursa. 193-196.
• [23] Guney, K., Sarıkaya, N., (2008). Calculation of patch radius of circular microstrip antennas with adaptive networks based on fuzzy logic system optimized by various algorithms. ELECO'2008 Electrical-Electronics-Computer Engineering Symposium and Fair, Bursa.
• [24] Cihan, P., Ozel, H., and Ozcan H. K. (2021). Modelling of atmospheric particulate matters via artificial intelligence methods. Environmental Monitoring and Assessment 193.5 1-15.
• [25] Atik, I. (2022). A New CNN-Based Method for Short-Term Forecasting of Electrical Energy Consumption in the Covid-19 Period: The Case of Turkey. IEEE Access 10 22586-22598.
• [26] Wang, Weijie, and Yanmin Lu. "Analysis of the mean absolute error (MAE) and the root mean square error (RMSE) in assessing rounding model." IOP conference series: materials science and engineering. Vol. 324. No. 1. IOP Publishing, 2018.
• [27] Fujihara, Yoichi, et al. "Assessing the impacts of climate change on the water resources of the Seyhan River Basin in Turkey: Use of dynamically downscaled data for hydrologic simulations." Journal of Hydrology 353.1-2 (2008): 33-48.
• [28] Tulun, S., et al. (2021). Adaptive neuro-fuzzy interference system modelling for chlorpyrifos removal with walnut shell biochar. Arabian Journal of Chemistry 14.12 103443.
• [29] Olatunji, O. M., et al. (2022). Application of hybrid ANFIS-based non-linear regression modelling to predict the% oil yield from grape peels: Effect of process parameters and FIS generation techniques. Cleaner Engineering and Technology 6 100371.