Volume 9, Issue 17 (9-2018)
J Watershed Manage Res 2018, 9(17): 119-131 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Tajbakhsh S M, Memarian H, Mohammadi F. (2018). Performance Comparison of the Neural Networks CANFIS, MLP and Optimized MLP using Genetic Programming for Suspended Sediment Load Simulation (Case study: Zoshk-Abardeh Watershed, Shandiz, Iran)
. J Watershed Manage Res. 9(17), 119-131. doi:10.29252/jwmr.9.17.119
URL: http://jwmr.sanru.ac.ir/article-1-818-en.html
URL: http://jwmr.sanru.ac.ir/article-1-818-en.html
Abstract: (4299 Views)
In this study, the predictive performance of three Artificial Neural Networks (ANNs), i.e. Co-Active NeuroFuzzy Inference System (CANFIS), Multi-Layer Perceptron (MLP) and MLP integrated with Genetic Algorithm (GA) in the Zoshk-Abardeh watershed were compared. In this study, three scenarios were considered and simulated in each model. In order to simulate the scenario S1 water flow were fed into the network as input. Daily water discharge and rainfall depth were considered as the input for the scenario S2. The scenario S3 was simulated based on the water discharge, daily rainfall and temperature as the inputs. In all scenarios daily sediment load was considered as the network output. Results showed that the optimum architecture for the S3_CANFIS (as the best network) was based on the Bell membership function, hyperbolic tangent transfer function and the Levenberg-Marquardt training algorithm. The S3_CANFIS with the lower MSE and NMSE acted better as compared with other scenarios during the testing process. This scenario based on the NSE equal to 0.743 and the AM equal to 0.806 showed better performance, as well. The results also suggest that the S2_MLP with 5 neurons in two hidden layers, sigmoid transfer function and the momentum learning algorithm with NSE and AM equal to 0.604 and 0.626, respectively acted better as compared with other MLP scenarios. Since the MLP network compared with CANFIS showed weaker performance in sediment yield simulation, the GA was integrated with MLP to determine the optimal network architecture parameters for the S2_MLP. Results showed that GA-MLP with NSE and AM equal to 0.658 and 0.655, respectively led to a higher capability for sediment load simulation in comparison with MLP network. Totally, the S3_CANFIS according to the criteria MB equal to -0.043, NSE equal to 0.743 and AM equal to 0.806 showed better performances in predicting sediment yield than the other networks in the studied watershed. However, both networks did not show a satisfactory power in sediment load simulation which could be arisen from the lack of data (especially extreme data) in the training series and also the existence of systematic error in observed records.
Keywords: Neural network, CANFIS, Multi-Layer Perceptron, Genetic Algorithm, Sensitivity analysis, Water discharge, Sediment load
Type of Study: Research |
Subject:
فرسايش خاک و توليد رسوب
Received: 2017/06/23 | Accepted: 2018/01/13
Received: 2017/06/23 | Accepted: 2018/01/13
References
1. Alp, M. and H.K. Cigizoglu. 2007. Suspended sediment load simulation by two artificial neural network methods using hydrometeorological data. Journal of Environmental Modelling and Software, 22(234): 2-13. [DOI:10.1016/j.envsoft.2005.09.009]
2. Araghinejad, S. and M. Karamouz. 2005. Long-Lead Stream Flow Forecasting Using Artificial Neural Networks and Fuzzy Inference System Journal of Iranian Water Resources Research, 1(2): 29-41 (In Persian).
3. American Society of Civil Engineers (ASCE). 2000. Artificial neural networks in hydrology, I: Preliminary concepts. Journal of Hydrologic Engineering, 5(35): 115-123. [DOI:10.1061/(ASCE)1084-0699(2000)5:2(115)]
4. Asselman, N.E.M. 2000. Fitting and interpretation of sediment rating curves. Journal of Hydrology, 234(3): 228-248. [DOI:10.1016/S0022-1694(00)00253-5]
5. Aytek, A. 2009. Co-active neurofuzzy inference system for evapotranspiration modeling. Soft Computing, 13(7): 691-700. [DOI:10.1007/s00500-008-0342-8]
6. Aziz, K., A. Rahman, A.Y. Shamseldin and M. Shoaib. 2013. Co-active neuro fuzzy inference system for regional flood estimation in Australia. Journal Hydrological Environment Result, 1(1): 11-20.
7. Chuan, C.S. 1997. Weather prediction using artificial neural network. Journal of Hydrology, 230(3): 101-119.
8. Coulibaly, P.F., A. Anctil and B. Bobee. 2000. Daily reservoir inflow forecasting using artificial neural networks with stopped training approach. Journal of Hydrology, 230(3): 244-257. [DOI:10.1016/S0022-1694(00)00214-6]
9. Dastorani, M.T. 2007. Evaluation of the Application of Artificial Intelligence Model for Simulation and Real - Time Prediction of Flood Flow. Journal of Science and Technology of Agriculture and Natural Resources, 40(20): 27-37 (In Persian).
10. Dastorani, M.T., H. Sharifi Darani, A. Talebi and A. Moghadam Nia. 2011. Evaluation of the application of artificial neural networks and adaptive neuro-fuzzy inference systems for rainfall-runoff modeling in Zayandeh-rood dam basin. Journal of Water and Wastewater, 80: 114-125 (In Persian).
11. Dastorani, M.T., Kh. Azimi Fafhi, A. Talebi and M.R. Ekhtesasi. 2012. Estimation of Suspended Sediment Using Artificial Neural Network (Case Study: Jamishan Watershed in Kermanshah). Journal of Watershed Management Research, 3(6): 61-74 (In Persian).
12. Dehghani, A., A. Zanganeh, M.E. Mosaedi and N. Kouhestani. 2009. Comparison of suspended sediment estimation by artificial neural network and sediment rating curve methods (Case Study: Doogh river in Golestan province). Journal of Agricultural Sciences and Natural Resources, 16(1-A): 266-276 (In Persian).
13. Dehghani, N. and M. Vafakhah. 2013. Comparison of Daily Suspended Sediment Load Estimations by Sediment Rating Curve and Neural Network Models (Case Study: Ghazaghli Station in Golestan Province). Journal of Soil and Water Conservation Studies, 20(2): 221-230 (In Persian).
14. Ebrahimpour. M., S.K. Balasundram, J. Talib, A.R. Anuar and H. Memarian. 2011. Accuracy of GeoWEPP in estimating sediment load and runoff from a tropical watershed. Malaysian Journal of Soil Science. 15: 25-33.
15. Faghih, H. 2010. Evaluating Artificial Neural Network and its Optimization Using Genetic Algorithm in Estimation of Monthly Precipitation Data (Case Study: Kurdistan Region). Journal of Science and Technology of Agriculture and Natural Resources, 4(51): 27-44 (In Persian).
16. Feiznia, S., H. Asgari and M. Moazzami. 2008. Investigating the applicability of Neural Network method for estimating daily suspended sediment yield (Case study: Zard Drainage Basin, Khozestan Province). Journal of the Iranian Natural Resources, 60(4): 1199-1210 (In Persian).
17. Hagan, M.T. and M.B. Menhaj. 1994. Training feedforward networks with the Marquardt algorithm. IEEE transactions on Neural Networks, 5(6): 989-993. [DOI:10.1109/72.329697]
18. Hemachandra, S. and R.V.S. Satyanarayana. 2013. Co-active neuro-fuzzy inference system for prediction of electric load. International Journal of Electrical and Electronics Engineering Research, 3(2): 217-222.
19. Holland, J.H. 1975. Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence, 228 pp. U Michigan Press.
20. Jang, J.S. 1993. ANFIS: adaptive-network-based fuzzy inference system. IEEE transactions on systems, man, and cybernetics, 23(3): 665-685. [DOI:10.1109/21.256541]
21. Jang, J.S.R., C.T. Sun and E. Mizutani. 1997. Neuro-fuzzy and soft computing; a computational approach to learning and machine intelligence.Prentice Hall Upper Saddle River, NJ. P. 614. [DOI:10.1109/TAC.1997.633847]
22. Kisi, O., A.H. Dailr, M. Cimen and J. Shiri. 2012. Suspended sediment modeling using genetic programming and soft computing techniques. Journal of Hydrology, 450(5): 48-58. [DOI:10.1016/j.jhydrol.2012.05.031]
23. Kisi, O. and A. Guven. 2010. A machine code-based genetic programming for suspended sediment concentration estimation. Advances in Engineering Software, 41(7): 939-945. [DOI:10.1016/j.advengsoft.2010.06.001]
24. Melesse, A.M., S. Ahmad., M.E. McClain, X. Wang and Y.H. Lim. 2011. Suspended sediment load prediction of river systems: An artificial neural network approach. Journal of Agricultural Water Management, 98(5): 855-866. [DOI:10.1016/j.agwat.2010.12.012]
25. Memarian, H. and S.K. Balasundram. 2012. Comparison between multi-layer perceptron and radial basis function networks for sediment load estimation in a tropical watershed. Journal of Water Resource and Protection, 4(10): 870-876. [DOI:10.4236/jwarp.2012.410102]
26. Memarian, H., M.P. Bilondi and M. Rezaei. 2016. Drought prediction using co-active neuro-fuzzy inference system, validation, and uncertainty analysis (case study: Birjand, Iran). Theoretical and applied climatology, 125(3-4): 541-554. [DOI:10.1007/s00704-015-1532-9]
27. Memarian, H., S. Feiznia and K. Zakikhani. 2009. Estimating river suspended sediment yield using MLP neural network in arid and semi-arid basins (Case study: Bar River, Neyshaboor, Iran). Desert, 14(1): 43-52.
28. Memarian, H., S.K. Balasundram and M. Tajbakhsh. 2013. An expert integrative approach for sediment load simulation in a tropical watershed. Journal of Integrative Environmental Sciences, 10(3-4): 161-178. [DOI:10.1080/1943815X.2013.852591]
29. Menhaj, M.B. 2002. The Basics of Neural Networks. Amir Kabir University of Technology. First volume, second edition. 715 pp., Tehran, Iran (In Persian).
30. Mohammadi, Y., P. Fathi, A. Najafi Nejad and N. Nura. 2008. Estimation of the average monthly discharge using Artificial Neural Network (Case stady: the Queshlaq's watershed of Sanandaj). Journal of Agricultural Sciences and Natural Resources, 4: 258-268 (In Persian).
31. Mosaedi, A. and S. Hashemi. 2005. Comparison of Artificial Neural Network Efficiency in Preparation of Sediment Curve. Proceedings of the 3th National Conference on Erosion and Sediment, 5 pp., Tehran, Iran (In Persian).
32. Mosaedi, A., M. Jalali and M. Najafi Hajipour. 2007. Estimation of Suspended Sediment Discharges Applying Artificial Neural Network in Tamar Hydrometric Station (Gorganroud-Iran). Proceedings of the 7th International River Engineering Workshop, 8 pp., Ahwaz, Iran (In Persian).
33. Mustafa, M.R., R.B. Rezaur, S. Saiedi and M.H. Isa. 2012. River suspended sediment prediction using various multilayer perceptron neural network training algorithms a (case study: in Malaysia). Journal of Water resources management, 26(7): 1879-1897. [DOI:10.1007/s11269-012-9992-5]
34. Nash, J.E. and J.V. Sutcliffe. 1970. River flow forecasting through conceptual models part I A discussion of principles. Journal of Hydrology, 10(3): 282-290. [DOI:10.1016/0022-1694(70)90255-6]
35. Nourani, V. and L. Malekani. 2010. Use of comparative neuro-fuzzy system in rainfall-runoff modeling. Proceedings of the 5th Congress on Civil Engineering, 6 pp., Mashhad, Iran (In Persian).
36. Principe, J.C., N.R. Euliano and W.C. Lefebvre. 2000. Neural and adaptive systems: fundamentals through simulations (Vol. 672). New York: Wiley.
37. Principe, J.C., W.C. Lefebvre, G. Lynn, C. Fancourt and D. Wooten. 2007. NeuroSolutions-Documentation, the Manual and On-Line Help. Version 5.05. NeuroDimension, Inc.
38. Rezaei, M. and H. Memarian. 2015. Application of Rainfall Time Series and Climatic Indices for Drought Prediction using Co-Active Neurofuzzy Inference System (Case Study: Birjand, Southern Khorasan). Journal of Arid Biome, 5(2): 51-67 (In Persian).
39. Rumelhart, D.E. and D. Zipser. 1986. Feature discovery by competitive learning, Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations. [DOI:10.7551/mitpress/5236.001.0001]
40. Safari, A.F., D. Smedt and F. Moreda. 2012. WetSpa model application in the distributed model intercomparison project (DMIP2). Journal of Hydrology, 418: 78-89. [DOI:10.1016/j.jhydrol.2009.04.001]
41. Tan, Y. and A.Van Cauwenberghe. 1999. Neural-network-based d-step-ahead predictors for nonlinear systems with time delay. Engineering applications of artificial intelligence, 12(1): 21-35. [DOI:10.1016/S0952-1976(98)00043-8]
42. Tfwala, S.S., Y.M. Wang and Y.C. Lin. 2013. Prediction of missing flow records using multilayer perceptron and coactive neurofuzzy inference system. Journal of Scientific World, 2013, 1-7. [DOI:10.1155/2013/584516]
43. Wilson, D.R. and T.R. Martinez. 2003. The general inefficiency of batch training for gradient descent learning. Journal of Neural Networks, 16(10): 1429-1451. [DOI:10.1016/S0893-6080(03)00138-2]
44. Yosefi, M. and R. Poorshariaty. 2014. Suspended Sediment Estimation using Neural Network and Algorithms Assessment (Case Study: Lorestan Province). Journal of Watershed Management Research, 5(10): 85-97 (In Persian).
45. Zare Abyaneh, H. and M. Bayat Varkeshi. 2011. Evaluation of Artificial Intelligent and Empirical Models in Estimation of Annual Runoff. Journal of Water and Soil, 25(2): 365-379 (In Persian).
46. Zealand, C.M., D.H. Burn and S.P. Simonovic. 1999. Short term streamflow forecasting using artificial neural networks. Journal of Hydrology, 214(1): 32-48. [DOI:10.1016/S0022-1694(98)00242-X]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
