The performance evaluation of machine learning models and optimization algorithms for predicting the River Discharge of Kashkan River | ||
| پژوهش های آبخیزداری | ||
| Article 2, Volume 38, Issue 1 - Serial Number 146, March 2025, Pages 1-18 PDF (1.76 M) | ||
| Document Type: Research | ||
| DOI: 10.22092/wmrj.2024.365128.1579 | ||
| Authors | ||
| Fatemeh Avazpour1; Mohammad Reza Hadian* 2; Ali Talebi3 | ||
| 1Ph.D. Candidate, Department of Civil Engineering, Yazd University, Yazd, Iran | ||
| 2Assistant Professor, Department of Civil Engineering, Yazd University, Yazd, Iran | ||
| 3Professor, Department of Natural Resources and Desert Studies, Yazd University, Yazd, Iran | ||
| Abstract | ||
| Introduction and Goal The simulation of river discharge at hydrometric stations to predict future flow discharge over specific time periods is an important issue typically addressed using hydrological time series associated with the respective station. To predict river discharge with the hights accuracy, three major groups of methods are commonly utilized: empirical and statistical methods, conceptual methods, and process-based approaches. Among data-driven methods, those based on artificial intelligence-based are prominent. The aim of this study was evaluating the performance of machine learning models, including SVM, ANFIS, and ANN, and assessing the performance of a neural network model trained with Whale Optimization Algorithm (WOA) and Particle Swarm Optimization (PSO) to predict flow discharge. In addition to evaluating the intelligent models, the impact of using optimization algorithms on the accuracy of river discharge predictions was also examined. Since input data have a significant impact on the performance of data-driven models, the criteria influencing the river discharge were identified, and the best combination of input variables for each model was determined. Materials and Methods In this study, to predict the daily discharge at the Poldokhtar hydrometric station located on the Kashkan River, discharge and precipitation data from 1971 to 2018 were collected, and Intelligent models, including Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Machine (SVM), Artificial Neural Network (ANN), and the hybrid model of Artificial Neural Network with Particle Swarm Optimization (ANN-PSO) and the hybrid model of Artificial Neural Network with Whale Optimization Algorithm (ANN-WOA) were employed. In the two hybrid models, efforts were made to adjust the criterias of the artificial neural network using metaheuristic algorithms, and their impact on the performance of the ANN model was examined. Additionally, this study investigated the impact of river discharge and precipitation data, along with their time lags (data from previous days), and combinations of these metrics as input variables for the models. To determine the best combination of input variables, statistical methods such as the Autocorrelation Function (ACF), Partial Autocorrelation Function (PACF), and Pearson Correlation Coefficient (PCC) were employed. After applying the effective inputs and training the mentioned intelligent models, their performance in predicting river discharge was evaluated by comparing RMSE, R², and NE metrics. Results and Discussion The evaluation of all models in this study showed that the river discharge of one day (Q-1), two days (Q-2), and three days (Q-3) ago, along with the precipitation of one day ago (P-1), exhibited the highest correlation with the river’s daily discharge. Overall, all models demonstrated acceptable accuracy in modeling the river discharge in the Kashkan watershed. According to the results, the highest accuracy in predicting daily discharge was achieved by the ANN-WOA model, with the highest coefficient of determination (R² = 0.896), Nash-Sutcliffe efficiency (NE = 0.803), and the lowest error (RMSE = 0.0186). Subsequently, the SVM model, using a radial basis kernel function with parameters C=4, γ=1, and ϵ=0.001 demonstrated superior performance, with a coefficient of determination (R² = 0.895), Nash-Sutcliffe efficiency (NE = 0.801), and an error (RMSE = 0.0187). Then, the ANN-PSO and ANN models ranked third and fourth, respectively. The results indicated that using metaheuristic optimization algorithms significantly improved the accuracy of the ANN model, making it a suitable tool for neural network training. The evaluation of different ANFIS structures revealed that triangular and Gaussian functions performed better for modeling river discharge in the study area. On the other hand, the error of this model, with values of RMSE=0.023 and NE=0.76 was higher compared to the other models. Conclusion and Suggestions This study demonstrated that machine learning models, such as SVM, ANFIS, and ANN, exhibited acceptable accuracy in predicting river discharge. Adjusting neural network parameters using optimization algorithms like WOA and PSO significantly enhanced the performance of the ANN model. Finally, it can be concluded that these models can serve as suitable alternatives to conceptual and hydrological models for addressing hydrological and discharge-related issues. It is recommended to train the SVM and ANFIS models using the PSO and WOA algorithms and then compare the results with the findings of this study. | ||
| Keywords | ||
| Kashkan Watershed; Rainfall-Runoff; Particle Swarm Optimization; Whale Optimization Algorithm; Artificial Intelligence | ||
| References | ||
|
Abdollah Pour Azad MR, Sattari MT. 2015. Forecasting daily river flow of Ahar Chay River using artificial neural networks (ANN) and comparison with Adaptive neuro fuzzy inference system (ANFIS). Journal of Water and Soil Conservation. 22(1):287-298. (In Persian). https://doi : 20.1001.1.23222069.1394.22.1.15.7 Asadabadi AS, Dinpazhuh Y, Mirabasi Najafabadi R. 2014. Forecasting the average daily discharge of the Beheshtabad River using wavelet analysis. Journal of Water and Soil Science. 28(3): 534–45. (In Persian). https://doi: 20.1001.1.23222069.1394.22.1.15.7 Buyukyildiz M, Kumcu SY. 2017. An estimation of the suspended sediment load using adaptive network based fuzzy inference system, support vector machine and artificial neural network models. Journal of Water Resources Management. 31(5): 1343–1359. https://doi.org/10.1007/s11269-017-1581-1 Choubin B, Moradi E, Golshan M, Adamowski J, Sajedi Hosseini F, Mousavi A. 2019. An ensemble prediction of flood susceptibility using multivariate discriminant analysis, classification and regression trees, and support vector machines. Journal of Science of the Total Environment. 651(2/15): 2087-2096. https://doi.org/10.1016/j.scitotenv.2018.10.064 Ditthakit P, Sirimon P, Nureehan S, Jakkarin W, Thai Th, and Quoc BP. 2023. Comparative study of machine learning methods and GR2M model for monthly runoff prediction. Journal of Ain Shams Engineering. 14(4) 101941. https://doi.org/10.1016/j.asej.2022.101941 Emami H, Emami S, Heidari Tashe Kabud SH. 2019. Prediction suspended sediment load of river using meta-heuristic algorithms. Journal of Irrigation and Drainage. 13(5): 1426-1438. (In Persian). https://doi: 20.1001.1.20087942.1398.13.5.21.5 Eskandari A, Nouri R, Vesali Naseh MR, Saeedi F. 2019. Uncertainty evaluation of ANN and ANFIS models in estimating the inflow to Rais Ali Delwari dam. Journal of Environmental Science and Technology. 21(7):34-47 .(In Persian). https://doi: 10.22034/jest.2020.20068.2909 Falamaki A, Eskandari M, Baghlani A, Ahmadi SA. 2012. Modeling total sediment load in rivers using artificial neural networks. Journal of Water and Soil Resources Conservation. 2(3):13-25 . (In Persian). https://sid.ir/paper/403921/fa Ghafari GH, Vafakhah M. 2013. Simulation of rainfall-runoff process using artificial neural network and fuzzy-adaptive neural system (case study: Hajighoshan watershed). Journal of Watershed Management Research. 4(8):120-136. (In Persian). https://jwmr.sanru.ac.ir/article-1-321-fa.html Hakimi Khansar H, Parsa J, Momeni Keleshteri O, Karami N, Khoshdel Sangdeh M. 2024. Extended estimation of daily inflow of Sefidroud dam using meta-heuristic algorithms combined with fuzzy neural inference system. Journal of Civil Engineering, Amirkabir. 56(1): 03-22. (In Persian). https://doi: 10.22060/ceej.2024.21634.7784 Jang, J-SR. 1993. ANFIS: Adaptive-Network-Based Fuzzy Inference System. IEEE Transactions on systems, man, and cybernetics. 23(3): 665–85. Joudi HA, Kadkhoda Hosseini M, Akhavan S, Nozari H. 2015. Evaluation of AWAT and SVM models in the simulation of Ligvanchai river runoff. Journal of Water and Soil Science. 26(4/1): 137-150. (In Persian). https://civilica.com/doc/1587524 Katipoğlu OM. 2023. Modeling the effect of meteorological variables on streamflow estimation: application of data mining techniques in mixed rainfall–snowmelt regime Munzur River. Türkiye. Journal of Environmental Science and Pollution Research. 30(4): 96312–96328.https://doi.org/10.1007/s11356-023-29220-2 Latif SD, Chong KL, Ahmed AN, Huang YF, Sherif M, Shafie A EL. 2023. Sediment load prediction in Johor River: deep learning versus machine learning models. Journal of Applied Water Science. 13(3): 79-93. https://doi.org/10.1007/s13201-023-01874-w Malik A, Tikhamarine Y, Souag-Gamane D, Rai P, Sammen SS, Kisi O. 2021. Support vector regression integrated with novel meta-heuristic algorithms for meteorological drought prediction. Journal of Meteorology and Atmospheric Physics. 133(2): 891–909. https://doi.org/10.1007/s00703-021-00787-0 Marcé R, Comerma M, García JC. Armengol J. 2004. A neuro‐fuzzy modeling tool to estimate fluvial nutrient loads in watersheds under time‐varying human impact. Limnology and Oceanography Methods, 2(11): 342-355. https://doi.org/10.4319/lom.2004.2.342 Memari M, Harifi M, Khalili A. 2020. Improving the classification performance of polynomial neural network using whale algorithm. Journal of Electrical and Computer Engineering. 20(2):145-154. (In Persian). https://sid.ir/paper/959517/fa Mirjalili S, Lewis A. 2016. The whale optimization algorithm. Journal of Advances in Engineering Software. 95(6):51-67 https://doi.org/10.1016/j.advengsoft. 2016.01.008 Mohammadi B, Moazenzadeh R. 2019. Prediction of stream flow using intelligent hybrid models in monthly scale (case study: Zarrin roud River). Journal of Environmental Science and Technology. 21(9):71-81. (In Persian). https://doi: 10.22034/jest.2020.24315.3331. Moriasi DN, Jeffrey GA, Michael WVL, Ronald LB, Daren H, Tamie LV. 2007. Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the American Society of Agricultural and Biological Engineers (ASABE). 50(3): 885–900. https://doi: 10.13031/2013.23153 Nazeri Tahroudi M, Hashemi SR, Ahmadi F, Nazeri Tahroudi Z. 2016. Examining the accuracy of ANFIS, SVM and GP models in modeling the river flow discharge. Journal of Echohydrology. 3(3):347-361. (In Persian). https://doi: 10.22059/ije.2016.60024 Nie Y, Sun J, Jiehua M. 2023. Seasonal prediction of summer extreme precipitation frequencies over southwest China based on machine learning. Journal of Atmospheric Research. 294 (5): 106947. https://doi.org/10.1016/j.atmosres.2023.106947 Nourani V, Alizadeh F, Roushangar K. 2015. Evaluation of a two-Stage SVM and spatial statistics methods for modeling monthly river suspended sediment load. Journal of Water Resour Management. 30(9):393-407. https://doi: 10.1007/s11269-015-1168-7 Parisouj P, Mohebzadeh H, Lee T. 2020. Employing machine learning algorithms for streamflow prediction: A case study of four River basins with different climatic zones in the United States. Journal of Water Resource Management. 34(3): 4113-4131. https://doi.org/10.1007/s11269-020-02659-5 Samadi M, Fath Abadi A. 2018. Application of Time Series, ANN, and SVM Models in forecasting the Gorgan Dam inflow rate. Journal of Environment and Water Engineering. 4(4): 299-309. (In Persian). https://doi.org/10.22034/jewe.2018.128256.1256 Samantaray S, Sahoo A. 2022. Prediction of suspended sediment concentration using hybrid SVM-WOA approaches. Journal of Geocarto Internationa. 37(19): 5609-5635. https://doi.org/10.1080/10106049.2021.1920638 Shahhoseini Sh, Moosavi M, Mollajafari M. 2011. Evolutionary algorithms- fundamentals, applications, implementation. Tehran Press Center, Iran University of Science and Technology, Tehran, 590 p. (In Persian). Shahi Nejad B, Dehghani R. 2017. Evaluation and performance of support vector machine model in estimation of suspended sediment. Journal of Irrigation and Water Engineering. 8(29):25-34.(In Persian). https://www.waterjournal.ir/article_74207.html Studies on the modernization of the country's water comprehensive plan in the border watersheds of the West, Karkheh, Karun and Jarahi-Zahre. 2006. Ministry of Energy and Water Research Institute. pp. 52-58 (In Persian). Yu X, Liong SY. Babovic V. 2004. EC-SVM approach for real-time hydrologic forecasting. Journal of Hydroinformatics, 6 (3): 209–223. https://doi.org/10.2166/hydro.2004.0016 | ||
|
Statistics Article View: 987 PDF Download: 388 |
||
Journal management system. designed by sinaweb