Evaluating the Performance of Machine Learning Models for Predicting Suspended Sediment Load (case study: Taleghan watershed, Iran)

Mohammadi-Raigani, Zeinab; Gholami, Hamid; Mohamadi, Mojtaba

doi:10.61186/jeer.15.1.83

year 15, Issue 1 (Spring 2025) E.E.R. 2025, 15(1): 83-104 | Back to browse issues page

‎ 10.61186/jeer.15.1.83

Mendeley

Zotero

RefWorks

Mohammadi-Raigani Z, Gholami H, Mohamadi M. Evaluating the Performance of Machine Learning Models for Predicting Suspended Sediment Load (case study: Taleghan watershed, Iran). E.E.R. 2025; 15 (1) :83-104
URL: http://magazine.hormozgan.ac.ir/article-1-867-en.html

Evaluating the Performance of Machine Learning Models for Predicting Suspended Sediment Load (case study: Taleghan watershed, Iran)

Zeinab Mohammadi-Raigani

, Hamid Gholami ^*

, Mojtaba Mohamadi

Department of Natural Resources Engineering, Faculty of Natural Resources and Agriculture, University of Hormozgan, Bandar Abbas, Hormozgan, Iran. , hadesert64@gmail.com

Abstract: (886 Views)

1- Introduction
Accurate prediction of suspended sediment load (SSL) in rivers is crucial for sustainable water resources management. Sediment, as a significant factor in degrading aquatic ecosystems, reducing the lifespan of hydraulic structures, and deteriorating water quality, has been a major concern. Given the complexity of hydrological processes and the interplay of various factors affecting sediment production and transport, accurate modeling of this phenomenon has always been challenging. In recent years, advancements in machine learning techniques have enabled the development of highly accurate predictive models. This study aims to enhance the understanding of sediment dynamics in watersheds and provide more precise tools for SSL prediction by applying machine learning models to daily SSL forecasting in the Taleghan watershed. The Taleghan watershed, characterized by its mountainous topography and specific hydrological conditions, was selected for this study due to its significance in supplying water to the Tehran region. Accurate SSL prediction in this watershed is of paramount importance.
2- Material and Methods
For this study, hydrological data including discharge, precipitation, snow index, and suspended sediment load were collected from the Gelink Taleghan hydrometric station over the period 2000 to 2018. The collected data, after undergoing quality checks and outlier removal, were prepared for training and testing machine learning models. Data preprocessing involved standardization, normalization, and outlier removal to enhance model accuracy. Principal Component Analysis (PCA) was employed to reduce data dimensionality and select the most significant input variables for the model. This method aids in identifying new linear combinations of original variables that explain the maximum variance in the data. By using PCA, the number of input variables in the model can be reduced, thereby decreasing model training time and complexity. Six machine learning models, including xgbTree, Cubist, qrnn, Ctree, Cforest, and LASSO, were utilized in this study. These models were chosen due to their ability to model nonlinear and complex relationships between variables. To evaluate model performance, various statistical metrics such as Root Mean Squared Error (RMSE), Nash-Sutcliffe Efficiency (NSE), and Mean Absolute Error (MAE) were employed. Additionally, time series plots, scatter plots, and Taylor diagrams were used for visual assessment of model performance.
3- Results
Results indicated that xgbTree, Cubist, and qrnn models outperformed other models in predicting SSL. These models effectively simulated daily variations in SSL. Overall, the xgbTree model demonstrated the best performance in SSL prediction. A comparison of the models' predictive accuracy revealed that ML algorithms can successfully predict daily SSL, particularly xgbTree (RMSE = 63.301, NSE = 0.97), Cubist (RMSE = 46.330, NSE = 0.96), and qrnn (RMSE = 85.349, NSE = 0.96), which exhibited the lowest prediction errors and highest efficiency metrics. Taylor diagrams further confirmed that xgbTree, Cubist, and qrnn models demonstrated a better fit to the observed data.
Sensitivity analysis revealed that discharge and precipitation had the most significant influence on SSL variations. Additionally, employing PCA to reduce data dimensionality and select key variables played a crucial role in enhancing model performance. The findings of this study demonstrate that machine learning models can serve as powerful tools for predicting SSL in watersheds. Furthermore, the results indicated that machine learning models are capable of identifying complex and nonlinear patterns in hydrological data that cannot be detected using traditional modeling techniques. This is particularly significant in scenarios where climate change and human activities impact hydrological processes.
4- Discussion & Conclusions
This study employed machine learning models to forecast daily suspended sediment load (SSL) in the Taleghan watershed. Results indicated that xgbTree, Cubist, and qrnn models exhibited superior performance in predicting SSL. These models can serve as powerful management tools for assessing the impacts of climate change and human activities on sedimentation processes, and for planning and managing water resources sustainably. The findings of this study demonstrate that machine learning models can be effective alternatives to traditional modeling methods for SSL prediction. These models can capture complex nonlinear relationships between input and output variables, leading to more accurate forecasts. However, to enhance predictive accuracy, further research is needed using higher spatial and temporal resolution data, as well as considering additional factors influencing sedimentation processes. For future research, it is recommended to explore hybrid models combining machine learning and physical models. Additionally, deep learning techniques can be employed to extract more complex features from data. Furthermore, investigating the impacts of climate change on sedimentation processes and developing predictive models under various climate scenarios is a crucial topic for future research.

Keywords: Suspended sediment load, Machine learning models, Principal Component Analysis, Taleghan watershed.

Full-Text [PDF 1942 kb] (99 Downloads)

Received: 2024/11/17 | Published: 2025/03/23

References

1. Abrahart, R.J., White, S.M., 2001. Modeling sediment transfer in Malawi: comparing backpropagation neural network solutions against a multiple linear regression benchmark using small data sets. Physics and Chemistry of the Earth B 26 (1), 19-24. [DOI:10.1016/S1464-1909(01)85008-5]

2. Alp, M., Cigizoglu, H.K., 2007. Suspended sediment estimation by feed forward back propagation method using hydro meteorological data. Environmental Modelling & Software 22 (1), 2-13. [DOI:10.1016/j.envsoft.2005.09.009]

3. Bou-Fakhreddine, B., Mougharbel, I., Faye, A., Abou Chakra, S., Pollet, Y., 2018. Daily river flow prediction based on Two-Phase Constructive Fuzzy Systems Modeling: A case of hydrological - meteorological measurements asymmetry. J. Hydrol. 558, 255-265. https://doi.org/10.1016/j.jhydrol.2018.01.035 [DOI:10.1016/j.jhydrol.2018.01.035.]

4. Chiang, J.-L., Tsai, Y.-S., )2011(. Suspended sediment load estimate using support vector machines in Kaoping river basin, in: Consumer Electronics, Communications and Networks (CECNet), 2011 International Conference On. pp. 1750-1753. [DOI:10.1109/CECNET.2011.5769267]

5. Choubin, Bahram, Darabi, Hamid, Rahmati, Omid, Sajedi-Hosseini, Farzaneh, & Kløve, Bjørn. (2018). River suspended sediment modelling using the CART model: A comparative study of machine learning techniques. Science of The Total Environment, 615, 272-281. doi: https://doi.org/10.1016/j.scitotenv.2017.09.293 [DOI:10.1016/j.scitotenv.2017.09.293.]

6. Çimen, M., 2016. Estimation of daily suspended sediments using support vector machines. Hydrol. Sci. J. 6667.

7. Cobaner, M., Unal, B., Kisi, O., )2009(. Suspended sediment concentration estimation by an adaptive neuro-fuzzy and neural network approaches using hydrometeorological data. J. Hydrol. 367, 52-61. [DOI:10.1016/j.jhydrol.2008.12.024]

8. Darabi, H., Mohamadi, S., Karimidastenaei, S., Kisi, S., Ehteram, M., ELShafie, A., Torabi Haghighi, A., 2021. Prediction of daily suspended sediment load (SSL) using new optimization algorithms and soft computing models. Soft Computing (2021) 25:7609-7626, https://doi.org/10.1007/s00500-021-05721-5 [DOI:10.1007/s00500-021-05721-5.]

9. Dawson, Christian W, Abrahart, Robert J, & See, Linda M. (2007). HydroTest: a web-based toolbox of evaluation metrics for the standardised assessment of hydrological forecasts. Environmental Modelling & Software, 22(7), 1034-1052. [DOI:10.1016/j.envsoft.2006.06.008]

10. Diop, L., Bodian, A., Djaman, K., Yaseen, Z.M., Deo, R.C., El-shafie, A., Brown, L.C., )2018(. The influence of climatic inputs on stream-flow pattern forecasting: case study of Upper Senegal River. Environ. Earth Sci. 77, 182. https://doi.org/10.1007/s12665-018-7376-8 [DOI:10.1007/s12665-018-7376-8.]

11. Gholami, Hamid, Mohammadifar, Aliakbar, Golzari, Shahram, Kaskaoutis, Dimitris G, & Collins, Adrian L. (2021 b). Using the Boruta algorithm and deep learning models for mapping land susceptibility to atmospheric dust emissions in Iran. Aeolian Research, 50, 100682. [DOI:10.1016/j.aeolia.2021.100682]

12. Ghorbani, M.A., Deo, R.C., Yaseen, Z.M., H. Kashani, M., Mohammadi, B., 2017. Pan evaporation prediction using a hybrid multilayer perceptron-firefly algorithm (MLP-FFA) model: case study in North Iran. Theor. Appl. Climatol. [DOI:10.1007/s00704- 017-2244-0]

13. Haghighi AT, Darabi H, Shahedi K, Solaimani K, Kløve B (2019) A scenario-based approach for assessing the hydrological impacts of land use and climate change in the Marboreh Watershed. Iran. Environ Model Assess 25:1-17. [DOI:10.1007/s10666-019-09665-x]

14. Hassanpour, F., et al., 2019. Development of the FCM-SVR hybrid model for estimating the suspended sediment load. KSCE Journal of Civil Engineering, 23 (6), 2514-2523. doi:10.1007/s12205-019-1693-7. [DOI:10.1007/s12205-019-1693-7]

15. Hosseini, Majid, Ghafouri, A., Amin, M., Tabatabaei, Mohsen, Goodarzi, Massoud, & Abdeh Kolahchi, Abdolnabi. (2012). Effects of Land Use Changes on Water Balance in Taleghan Catchment, Iran. Journal of Agricultural Science and Technology, 14, 1159-1172.

16. Hothorn, T., Hornik, K., & Zeileis, A. (2015). ctree: Conditional inference trees. The comprehensive R archive network, 8, 1-34.‏

17. Houborg, R., & McCabe, M. F. (2018). A hybrid training approach for leaf area index estimation via Cubist and random forests machine-learning. ISPRS Journal of Photogrammetry and Remote Sensing, 135, 173-188.‏ [DOI:10.1016/j.isprsjprs.2017.10.004]

18. Idrees, M. B., Jehanzaib, M., Kim, D., Kim, T.D., 2021. Comprehensive evaluation of machine learning models for suspended sediment load inflow prediction in a reservoir. Stochastic Environmental Research and Risk Assessment https://doi.org/10.1007/s00477-021-01982-6 [DOI:10.1007/s00477-021-01982-6(0123456789().,-volV)(0123456789,-().volV).]

19. Khan, A.I., Topping, B.H.V., Bahreininejad, A., 1993. Parallel training of neural networks for finite element mesh generation. In: Topping, B.H.V., Khan, A.I. (Eds.), Neural Networks and Combinatorial Optimization in Civil&Structural Engineering. Civil-Comp Press, Edinburgh, pp. 81-94. [DOI:10.4203/ccp.16.5.1]

20. Khosravi, Khabat, Mao, Luca, Kisi, Ozgur, Yaseen, Zaher Mundher, & Shahid, Shamsuddin. (2018). Quantifying hourly suspended sediment load using data mining models: Case study of a glacierized Andean catchment in Chile. Journal of Hydrology, 567, 165-179. doi: https://doi.org/10.1016/j.jhydrol.2018.10.015 [DOI:10.1016/j.jhydrol.2018.10.015.]

21. Kisi, Ozgur, Dailr, Ali Hosseinzadeh, Cimen, Mesut, & Shiri, Jalal. (2012). Suspended sediment modeling using genetic programming and soft computing techniques. Journal of Hydrology, 450-451, 48-58. doi: https://doi.org/10.1016/j.jhydrol.2012.05.031 [DOI:10.1016/j.jhydrol.2012.05.031.]

22. Lafdani, E Kakaei, Nia, A Moghaddam, & Ahmadi, A. (2013). Daily suspended sediment load prediction using artificial neural networks and support vector machines. Journal of Hydrology, 478, 50-62. [DOI:10.1016/j.jhydrol.2012.11.048]

23. Li, Y., Wang, Z., Han, R., Shi, S., Li, J., Shang, R., ... & Gu, Y. (2023). Quantum recurrent neural networks for sequential learning. Neural Networks, 166, 148-161.‏ [DOI:10.1016/j.neunet.2023.07.003]

24. Liu, Qian-Jin, Shi, Zhi-Hua, Fang, Nu-Fang, Zhu, Hua-De, & Ai, Lei. (2013). Modeling the daily suspended sediment concentration in a hyperconcentrated river on the Loess Plateau, China, using the Wavelet-ANN approach. Geomorphology, 186, 181-190. doi: https://doi.org/10.1016/j.geomorph.2013.01.012 [DOI:10.1016/j.geomorph.2013.01.012.]

25. Lu H, Meng Y, Yan K, Gao Z (2019) Kernel principal component analysis combining rotation forest method for linearly inseparable data. Cogn Syst Res 53:111-122 [DOI:10.1016/j.cogsys.2018.01.006]

26. Luo, Y., Xue, Y., Liu, W., Song, H., Huang, Y., Tang, G., ... & Sun, Z. (2022). Development of diagnostic algorithm using machine learning for distinguishing between active tuberculosis and latent tuberculosis infection. BMC Infectious Diseases, 22(1), 965.‏ [DOI:10.1186/s12879-022-07954-7]

27. Ma, J., Yu, Z., Qu, Y., Xu, J., & Cao, Y. (2020). Application of the XGBoost machine learning method in PM2. 5 prediction: a case study of Shanghai. Aerosol and Air Quality Research, 20(1), 128-138.‏ [DOI:10.4209/aaqr.2019.08.0408]

28. Masters, Timothy. (1993). Practical neural network recipes in C++: Morgan Kaufmann. [DOI:10.1016/B978-0-08-051433-8.50017-3]

29. Mehri, Y., Nasrabadi, M., Omid, M.H., (2021). Prediction of suspended sediment distributions using data mining algorithms. Ain Shams Engineering Journal, https://doi.org/10.1016/j.asej.2021.02.034 [DOI:10.1016/j.asej.2021.02.034.]

30. Melesse, A. M., Ahmad, S., McClain, M. E., Wang, X., & Lim, Y. H. (2011). Suspended sediment load prediction of river systems: An artificial neural network approach. Agricultural Water Management, 98(5), 855-866. doi: https://doi.org/10.1016/j.agwat.2010.12.012 [DOI:10.1016/j.agwat.2010.12.012.]

31. Melesse, A., Jayachandran, K., Zhang, K., 2008. Modeling coastal eutrophication at Florida Bay using neural networks. Journal of Coastal Research 24, 190-196. [DOI:10.2112/06-0646.1]

32. MixSIR model. CATENA 164, 32-43.

33. Muthukrishnan, R., & Rohini, R. (2016, October). LASSO: A feature selection technique in predictive modeling for machine learning. In 2016 IEEE international conference on advances in computer applications (ICACA) (pp. 18-20). Ieee.‏ [DOI:10.1109/ICACA.2016.7887916]

34. Nadiri, A.A., Gharekhani, M., Khatibi, R., Sadeghfam, S., Moghaddam, A.A., )2017(. Groundwater vulnerability indices conditioned by Supervised Intelligence Committee Machine (SICM). Sci. Total Environ. 574, 691-706. https://doi.org/10.1016/j.scitotenv.2016.09.093 [DOI:10.1016/j.scitotenv.2016.09.093.]

35. Nagy, H.M., Watanabe, K., Hirano, M., 2002. Prediction of sediment load concentration in rivers using artificial neural network model. Journal of Hydraulic Engineering 128 (6), 588-595. [DOI:10.1061/(ASCE)0733-9429(2002)128:6(588)]

36. Noori, R., Sabahi, M.S., Karbassi, A.R., Baghvand, A., Taati Zadeh, H., 2010d. Multivariate statistical analysis of surface water quality based on correlations and variations in the data set. Desalination 260, 129-136. [DOI:10.1016/j.desal.2010.04.053]

37. Nosrati, K., Collins, A.L., Madankan, M., 2018a. Fingerprinting sub-basin spatial sediment sources using different multivariate statistical techniques and the Modified [DOI:10.1016/j.catena.2018.01.003]

38. Nosrati, Kazem, Mohammadi-Raigani, Zeinab, Haddadchi, Arman, & Collins, Adrian L. (2021). Elucidating intra-storm variations in suspended sediment sources using a Bayesian fingerprinting approach. Journal of Hydrology, 596, 126115. doi: https://doi.org/10.1016/j.jhydrol.2021.126115 [DOI:10.1016/j.jhydrol.2021.126115.]

39. Pourghasemi, H.R., Yousefi, S., Kornejady, A., Cerda, A., (2017). Performance assessment of individual and ensemble data-mining techniques for gully erosion modeling. Sci. Total Environ. 609, 764-775. [DOI:10.1016/j.scitotenv.2017.07.198]

40. Rahul, Atul Kumar, Shivhare, Nikita, Kumar, Shashi, Dwivedi, Sumita, & Dikshit, P. K. S. (2021). Modelling of Daily Suspended Sediment Concentration Using FFBPNN and SVM Algorithms.

41. Raigani, Zeinab Mohammadi, Nosrati, Kazem, & Collins, Adrian L. (2019). Fingerprinting sub-basin spatial sediment sources in a large Iranian catchment under dry-land cultivation and rangeland farming: Combining geochemical tracers and weathering indices. Journal of Hydrology: Regional Studies, 24, 100613. doi: https://doi.org/10.1016/j.ejrh.2019.100613 [DOI:10.1016/j.ejrh.2019.100613.]

42. Rajaee, T., Nourani, V., Zounemat-Kermani, M., Kisi, O., (2011). River suspended sediment load prediction: application of ANN and wavelet conjunction model. J. Hydrol. Eng. 16 (8), 613-627. [DOI:10.1061/(ASCE)HE.1943-5584.0000347]

43. Ren J, Zhao M, Zhang W, Xu Q, Yuan J, Dong B (2020) Impact of the construction of cascade reservoirs on suspended sediment peak transport variation during flood events in the Three Gorges Reservoir. CATENA 188:104409. [DOI:10.1016/j.catena.2019.104409]

44. Shojaeezadeh SA, Nikoo MR, McNamara JP, AghaKouchak A, Sadegh M (2018). Stochastic modeling of suspended sediment load in alluvial rivers. Adv Water Resour 119:188-196. [DOI:10.1016/j.advwatres.2018.06.006]

45. Solomatine, D.P., Torres, L.A., 1996. Neural network approximation of a hydrodynamicmodel. In: Optimizing Reservoir Operation, Proceedings of the Second International Conference on Hydroinformatics , Zurich, pp. 201-206.

46. Tao, H., Diop, L., Bodian, A., Djaman, K., Ndiaye, P.M., Yaseen, Z.M., 2018. Reference evapotranspiration prediction using hybridized fuzzy model with firefly algorithm: Regional case study in Burkina Faso. Agric. Water Manag. [DOI:10.1016/j.agwat.2018.06.018]

47. Taylor, Karl E. (2001). Summarizing multiple aspects of model performance in a single diagram. Journal of Geophysical Research: Atmospheres, 106(D7), 7183-7192. doi: [DOI:10.1029/2000JD900719]

48. Tokar, A. Sezin, & Johnson, Peggy A. (1999). Rainfall-Runoff Modeling Using Artificial Neural Networks. Journal of Hydrologic Engineering, 4(3), 232-239. doi: doi:10.1061/(ASCE)1084-0699(1999)4:3(232) [DOI:10.1061/(ASCE)1084-0699(1999)4:3(232)]

49. Wen, C.G., Lee, C.S., )1998(. A neural network approach to multi-objective optimization for water quality management in a river basin. Water Resources Research 34 (3), 427-436. [DOI:10.1029/97WR02943]

50. Yang CT, Marsooli R, Aalami MT (2009). Evaluation of total load sediment transport formulas using ANN. Int J Sedim Res 24(3):274-286. [DOI:10.1016/S1001-6279(10)60003-0]

51. Yang, C.C., Prasher, S.O., Tan, C.S., 1998. An artificial neural network model for water table management systems. In: Drainage in the 21st Century: Food Production and the Environment. Proceedings of the Seventh International Drainage Symposium, Orlando, Florida, USA, 8-10 March 1998, ASAE, St. Joseph, MI.

52. Yu, H., Wen, X., Feng, Q., Deo, R.C., Si, J., Wu, M., 2018. Comparative Study of Hybrid- Wavelet Artificial Intelligence Models for Monthly Groundwater Depth Forecasting in Extreme Arid Regions, Northwest China. Water Resour. Manag. https://doi.org/10.1007/s11269-017-1811-6 [DOI:10.1007/s11269-017-1811-6.]