Prediction of daily streamflow using adaptive neuro-fuzzy inference systems and group method of data handling approaches: a case study of kone river, binh dinh province
DOI:
https://doi.org/10.5281/zenodo.18476973Keywords:
Adaptive neuro-fuzzy inference systems (ANFIS), Group Method of Data Handling (GMDH), daily streamflow, predictionAbstract
Accurate streamflow forecasting plays a vital role in water resource engineering, management, and planning. This study evaluates the performance of the Group Method of Data Handling (GMDH) and Adaptive Neuro-Fuzzy Inference System (ANFIS) models in predicting daily streamflow. Rainfall and streamflow data, collected from rain gauges and hydrological stations in the upstream area of the Kone River in Binh Dinh Province, were used as inputs for the models and tested across various input scenarios. Model performance was assessed using three statistical metrics: the coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE). The results revealed that the ANFIS model consistently outperformed the GMDH model, achieving the highest R² value of 0.94 and the lowest RMSE (64.6 m³/s) and MAE (14.2 m³/s). Additionally, Scenario 1 demonstrated the best predictive performance across both models. This study successfully developed reliable approaches for daily streamflow forecasting and provided valuable insights into the influence of input variables on prediction accuracy.
Downloads
References
[1] K. Anusree and K. O. Varghese, “Streamflow Prediction of Karuvannur River Basin Using ANFIS, ANN and MNLR Models,” Procedia Technology, vol. 24, pp. 101–108, 2016, doi: https://10.1016/j.protcy.2016.05.015.
[2] A. Al-Anazi and I. D. Gates, “A support vector machine algorithm to classify lithofacies and model permeability in heterogeneous reservoirs,” Eng Geol, vol. 114, no. 3, pp. 267–277, 2010, doi: https://doi.org/10.1016/j.enggeo.2010.05.005.
[3] D. Liu, W. Jiang, L. Mu, and S. Wang, “Streamflow Prediction Using Deep Learning Neural Network: Case Study of Yangtze River,” IEEE Access, vol. 8, pp. 90069–90086, 2020, doi: 10.1109/ACCESS.2020.2993874.
[4] A. Kadirhodjaev, F. Rezaie, M. J. Lee, and S. Lee, “Landslide susceptibility assessment using an optimized group method of data handling model,” ISPRS Int J Geoinf, vol. 9, no. 10, Oct. 2020, doi: https://doi.org/10.3390/ijgi9100566.
[5] G. Teng, J. Xiao, Y. He, T. Zheng, and C. He, “Use of group method of data handling for transport energy demand modeling,” Energy Sci Eng, vol. 5, no. 5, pp. 302–317, Oct. 2017, doi: https://doi.org/10.1002/ese3.176.
[6] W. Wang, Y. Du, K. Chau, H. Chen, C. Liu, and Q. Ma, “A comparison of bpnn, gmdh, and arima for monthly rainfall forecasting based on wavelet packet decomposition,” Water (Switzerland), vol. 13, no. 20, Oct. 2021, doi: https://doi.org/10.3390/w13202871.
[7] R. Walton, A. Binns, H. Bonakdari, I. Ebtehaj, and B. Gharabaghi, “Estimating 2-year flood flows using the generalized structure of the Group Method of Data Handling,” J Hydrol (Amst), vol. 575, pp. 671–689, Aug. 2019, doi: https://10.1016/j.jhydrol.2019.05.068.
[8] C. Shen, S. Asante-Okyere, Y. Y. Ziggah, L. Wang, and X. Zhu, “Group method of data handling (GMDH) lithology identification based on wavelet analysis and dimensionality reduction as well log data pre-processing techniques,” Energies (Basel), vol. 12, no. 8, Apr. 2019, doi: https://doi.org/10.3390/en12081509.
[9] S. F. Stefenon, L. O. Seman, N. F. Sopelsa Neto, L. H. Meyer, V. C. Mariani, and L. dos S. Coelho, “Group Method of Data Handling Using Christiano–Fitzgerald Random Walk Filter for Insulator Fault Prediction,” Sensors, vol. 23, no. 13, Jul. 2023, doi: https://doi.org/10.3390/s23136118.
[10] D. A. Bograchev, Y. M. Volfkovich, V. E. Sosenkin, O. A. Podgornova, and N. V. Kosova, “The influence of porous structure on the electrochemical properties of LiFe0.5Mn0.5PO4 cathode material prepared by mechanochemically assisted solid-state synthesis,” Energies (Basel), vol. 13, no. 3, 2020, doi: https://doi.org/10.3390/en13030551.
[11] S. S. Band, I. Al-Shourbaji, H. Karami, S. Karimi, J. Esfandiari, and A. Mosavi, “Combination of group method of data handling (GMDH) and computational fluid dynamics (CFD) for prediction of velocity in channel intake,” Applied Sciences (Switzerland), vol. 10, no. 21, pp. 1–15, Nov. 2020, doi: https://doi.org/10.3390/app10217521.
[12] R. M. Adnan, Z. Liang, K. S. Parmar, K. Soni, and O. Kisi, “Modeling monthly streamflow in mountainous basin by MARS, GMDH-NN and DENFIS using hydroclimatic data,” Neural Comput Appl, vol. 33, no. 7, pp. 2853–2871, Apr. 2021, doi: https://doi.org/10.1007/s00521-020-05164-3.
[13] M. Amiri and S. Soleimani, “ML-based group method of data handling: an improvement on the conventional GMDH,” Complex and Intelligent Systems, vol. 7, no. 6, pp. 2949–2960, Dec. 2021, doi: https://doi.org/10.1007/s40747-021-00480-0.
[14] J. .-S. R. Jang, “ANFIS: adaptive-network-based fuzzy inference system,” IEEE Trans Syst Man Cybern, vol. 23, no. 3, pp. 665–685, 1993, doi: https://doi.org/10.1109/21.256541.
[15] S. M. Vatanchi, H. Etemadfard, M. F. Maghrebi, and R. Shad, “A Comparative Study on Forecasting of Long-term Daily Streamflow using ANN, ANFIS, BiLSTM and CNN-GRU-LSTM,” Water Resources Management, vol. 37, no. 12, pp. 4769–4785, 2023, doi: https://doi.org/10.1007/s11269-023-03579-w.
[16] S. Samanataray and A. Sahoo, “A Comparative Study on Prediction of Monthly Streamflow Using Hybrid ANFIS-PSO Approaches,” KSCE Journal of Civil Engineering, vol. 25, no. 10, pp. 4032–4043, 2021, doi: https://doi.org/10.1007/s12205-021-2223-y.
[17] Z. M. Yaseen et al., “Novel approach for streamflow forecasting using a hybrid ANFIS-FFA model,” J Hydrol (Amst), vol. 554, pp. 263–276, 2017, doi: https://doi.org/10.1016/j.jhydrol.2017.09.007.
[18] J. T. Jalles and J. Ge, “Emissions and economic development in commodity exporting countries,” Energy Econ, vol. 85, p. 104572, 2020, doi: https://doi.org/10.1016/j.eneco.2019.104572.
[19] M. Dorn, A. L. S. Braga, C. H. Llanos, and L. S. Coelho, “A GMDH polynomial neural network-based method to predict approximate three-dimensional structures of polypeptides,” Expert Syst Appl, vol. 39, no. 15, pp. 12268–12279, 2012, doi: https://doi.org/10.1016/j.eswa.2012.04.046.
[20] G. S. Mudholkar and A. D. and Hutson, “The exponentiated weibull family: some properties and a flood data application,” Commun Stat Theory Methods, vol. 25, no. 12, pp. 3059–3083, Jan. 1996, doi: https://doi.org/10.1080/03610929608831886
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
CC 4.0
