Abstract
The main aims of this study are (a) evaluating effects of discrete wavelet transforms (DWTs) on the machine learning (ML) models, (b) evaluating ability of two types of ML models (regression and classification models) for estimating daily-suspended sediment load (SSL), and (c) selecting the best ML model or hybrid ML model with DWT by new methods such as the TOPSIS (technique for order of preference by similarity to ideal solution) method. The used DWTs are classical DWT, maximal overlap DWT (MODWT), and MODWT-multiresolution analysis (MODWT-MRA) with two types of mother wavelet functions db4 and sym7. The independent variables used as model inputs are daily flow discharge, stage, and precipitation covering period from 2000 to 2018 and collected in the Navrood Watershed (the north of Iran). The obtained results show that DWT can considerably improve accuracy of the ML models with regression nature such as multivariate adaptive regression splines (MARS). The DWT decreased root mean square error (RMSE) of the MARS model from 10,477 to 2038 kg/day. However, DWT has negligible effect on performance of the ML models with classification nature such as the random tree (RT), random forest (RF), M5 model tree (M5T), and classification and regression tree (CART). The TOPSIS method and Taylor diagram show that the RT-MODWT-db4 is the superior model for estimation of the daily SSL. The R and RMSE of this model are 1 and 122.18 kg/day, respectively. Using this model is recommended in the mountainous and forest watersheds for estimation of daily SSL.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Abbreviations
- am :
-
The response variable
- n :
-
Total number of observed daily SSLs
- N s :
-
The number of data
- Rm :
-
A hierarchical binary tree that divides forecasts into several areas
- SSL Cal :
-
The estimated daily SSL (kg/day)
- SSL Obs :
-
The observed daily SSL (kg/day)
- \(\overline{{SSL }_{Obs}}\) :
-
The mean of observed daily SSL (kg/day)
References
Adib A, Mahmoodi A (2017) Prediction of suspended sediment load using ANN GA conjunction model with Markov chain approach at flood conditions. KSCE J Civ Eng 21(1):447–457
Adib A, Lotfirad M, Haghighi A (2019) Using uncertainty and sensitivity analysis for finding the best rainfall-runoff model in mountainous watersheds (Case study: the Navrood watershed in Iran). J Mt Sci-Engl 16(3):529–541. https://doi.org/10.1007/s11629-018-5010-6
Adib A, Kisi O, Khoramgah S, Gafouri HR, Liaghat A, Lotfirad M, Moayyeri N (2021) A new approach for suspended sediment load calculation based on generated flow discharge considering climate change. Water Supply 21(5):2400–2413. https://doi.org/10.2166/ws.2021.069
Afan HA, El-Shafie A, Yaseen ZM, Hameed MM, Mohtar WHMW, Hussain A (2015) ANN based sediment prediction model utilizing different input scenarios. Water Resour Manag 29(4):1231–1245. https://doi.org/10.1007/s11269-014-0870-1
Alizadeh MJ, Nodoushan EJ, Kalarestaghi N, Chau KW (2017) Toward multi-day-ahead forecasting of suspended sediment concentration using ensemble models. Environ Sci Pollut Res 24(36):28017–28025. https://doi.org/10.1007/s11356-017-0405-4
Almasri A, Locking H, Shukur G (2010) Wavelet Based forecasting approach, with application. Int Conf Financ Theory Eng 104–107. https://doi.org/10.1109/ICFTE.2010.5499417
Alp M, Cigizoglu HK (2007) Suspended sediment load simulation by two artificial neural network methods using hydrometeorological data. Environ Modell Softw 22(1):2–13. https://doi.org/10.1016/j.envsoft.2005.09.009
Azamathulla HM, Ghani AA, Fei SY (2012) ANFIS-based approach for predicting sediment transport in clean sewer. Appl Soft Comput 12(3):1227–1230. https://doi.org/10.1016/j.asoc.2011.12.003
Balioti V, Tzimopoulos C, Evangelides C (2018) Multi-criteria decision making using TOPSIS method under fuzzy environment. Appl Spillway Sel Proc 2(11):637. https://doi.org/10.3390/proceedings2110637
Bezak N, Matjaž M, Šraj M (2014) Trivariate frequency analyses of peak discharge, hydrograph volume and suspended sediment concentration data using copulas. Water Resour Manag 28(8):2195–2212. https://doi.org/10.1007/s11269-014-0606-2
Breiman L, Friedman JH, Olsen RA, Stone CJ (1984) Classification and regression trees. Belmont,Wadsworth, Int. Group, Belmont, California
Çimen M (2008) Estimation of daily suspended sediments using support vector machines. Hydrol Sci J 53(3):656–666. https://doi.org/10.1623/hysj.53.3.656
Farajpanah H, Lotfirad M, Adib A, Esmaeili- Gisavandani H, Kisi Ö, Riyahi MM, Salehpoor J (2020) Ranking of hybrid wavelet-AI models by TOPSIS method for estimation of daily flow discharge. Water Supply 20(8):3156–3171. https://doi.org/10.2166/ws.2020.211
Friedman JH (1991) Multivariate adaptive regression splines. Ann Stat 19(1):1–67. https://doi.org/10.1214/aos/1176347963
Guldal V, Muftuoglu RF (2001) 2D unit sediment graph theory. J Hydrol Eng 6(2):132–140. https://doi.org/10.1061/(ASCE)1084-0699(2001)6:2(132)
Gupta HV, Kling H, Yilmaz KK, Martinez GF (2009) Decomposition of the mean squared error and NSE performance criteria: implications for improving hydrological modelling. J Hydrol 377(1–2):80–91. https://doi.org/10.1016/j.jhydrol.2009.08.003
Gutiérrez ÁG, Schnabel S, Contador JFL (2009) Using and comparing two nonparametric methods (CART and MARS) to model the potential distribution of gullies. Ecol Model 220:3630–3637. https://doi.org/10.1016/j.ecolmodel.2009.06.020
Hamaamin YA, Nejadhashemi AP, Zhang Z, Giri S, Woznicki S (2016) Bayesian regression and neuro-fuzzy methods reliability assessment for estimating streamflow. Water 8(7):287. https://doi.org/10.3390/w8070287
Hamel P, Falinski K, Sharp R, Auerbach DA, Sánchez-Canales M, Dennedy-Frank PJ (2017) Sediment delivery modeling in practice: comparing the effects of watershed characteristics and data resolution across hydroclimatic regions. Sci Total Environ 580:1381–1388. https://doi.org/10.1016/j.scitotenv.2016.12.103
Hazarika BB, Gupta D, Berlin M (2020) Modeling suspended sediment load in a river using extreme learning machine and twin support vector regression with wavelet conjunction. Environ Earth Sci 79(10): Article number 234. https://doi.org/10.1007/s12665-020-08949-w
Heng S, Suetsugi T (2014) Comparison of regionalization approaches in parameterizing sediment rating curve in ungauged catchments for subsequent instantaneous sediment yield prediction. J Hydrol 512:240–253. https://doi.org/10.1016/j.jhydrol.2014.03.003
Himanshu SK, Pandey A, Yadav B (2017) Assessing the applicability of TMPA-3B42V7 precipitation dataset in wavelet-support vector machine approach for suspended sediment load prediction. J Hydrol 550:103–117. https://doi.org/10.1016/j.jhydrol.2017.04.051
Ho TK (1995) Random decision forests. Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, 14–16 August 1995, 278–282
Hwang CL, Yoon K (1981) Multiple attribute decision making: methods and applications. Springer-Verlag, New York, 539p. https://doi.org/10.1007/978-3-642-48318-9
Jha SK, Bombardelli FA (2011) Theoretical/numerical model for the transport of nonuniform suspended sediment in open channels. Adv Water Resour 34(5):577–591. https://doi.org/10.1016/j.advwatres.2011.02.001
Kahani M, Ghazvini M, Mohseni-Gharyehsafa B, Ahmadi MH, Pourfarhang A, Shokrgozar M, Heris SZ (2020) Application of M5 tree regression, MARS, and artificial neural network methods to predict the Nusselt number and output temperature of CuO based nanofluid flows in a car radiator. Int Commun Heat Mass 116: Article 104667. https://doi.org/10.1016/j.icheatmasstransfer.2020.104667
Kavianpour M, Seyedabadi M, Moazami S, Yamini OA (2020) Copula based spatial analysis of drought return period in southwest of Iran. Period Polytech-Civ 64(4):1051–1063. https://doi.org/10.3311/PPci.16301
Khan MYA, Tian F, Hasan F, Chakrapani GJ (2019) Artificial neural network simulation for prediction of suspended sediment concentration in the River Ramganga, Ganges Basin, India. Int J Sediment Res 34(2):95–107. https://doi.org/10.1016/j.ijsrc.2018.09.001
Kerich EC (2020) Households drinking water sources and treatment methods options in a regional irrigation scheme. J Hum Earth Future 1(1): 10–19. https://doi.org/10.28991/HEF-2020-01-01-02
Kisi Ö (2008) Constructing neural network sediment estimation models using a datadriven algorithm. Math Comput Simul 79(1):94–103. https://doi.org/10.1016/j.matcom.2007.10.005
Kişi Ö, Yaseen ZM (2019) The potential of hybrid evolutionary fuzzy intelligence model for suspended sediment concentration prediction. CATENA 174:11–23. https://doi.org/10.1016/j.catena.2018.10.047
Kisi O, Dailr AH, Cimen M, Shiri J (2012) Suspended sediment modeling using genetic programming and soft computing techniques. J Hydrol 450–451:48–58. https://doi.org/10.1016/j.jhydrol.2012.05.031
Makarynskyy O, Makarynska D, Rayson M, Langtry S (2015) Combining deterministic modelling with artificial neural networks for suspended sediment estimates. Appl Soft Comput 35:247–256. https://doi.org/10.1016/j.asoc.2015.05.044
Melesse AM, Ahmad S, McClain ME, Wang X, Lim YH (2011) Suspended sediment load prediction of river systems: an artificial neural network approach. Agr Water Manag 98(5):855–866. https://doi.org/10.1016/j.agwat.2010.12.012
Merkhali SP, Ehteshami M, Sadrnejad SA (2015) Assessment quality of a nonuniform suspended sediment transport model under unsteady flow condition (case study: Aras River). Water Environ J 29(4):489–498. https://doi.org/10.1111/wej.12137
Nourani V, Komasi M, Mano A (2009) A multivariate ANN-wavelet approach for rainfall–runoff modeling. Water Resour Manag 23(14):2877–2894. https://doi.org/10.1007/s11269-009-9414-5
Nourani V, Molajou A, Tajbakhsh AD, Najafi H (2019) A wavelet based data mining technique for suspended sediment load modeling. Water Resour Manag 33(5):1769–1784. https://doi.org/10.1007/s11269-019-02216-9
Partal T, Cigizoglu HK (2008) Estimation and forecasting of daily suspended sediment data using wavelet-neural networks. J Hydrol 358(3–4):317–331. https://doi.org/10.1016/j.jhydrol.2008.06.013
Percival DB, Walden AT (2000) Wavelet methods for time series. Cambridge University Press, ISBN: 9780511841040. https://doi.org/10.1017/CBO9780511841040
Prasad R, Deo RC, Li Y, Maraseni T (2017) Input selection and performance optimization of ANN-based streamflow forecasts in a drought-prone Murray Darling Basin using IIS and MODWT algorithm. Atmos Res 197:42–63. https://doi.org/10.1016/j.atmosres.2017.06.014
Rovira A, Ibáñez C, Martín-Vide JP (2015) Suspended sediment load at the lowermost Ebro River (Catalonia, Spain). Quatern Int 388:188–198. https://doi.org/10.1016/j.quaint.2015.05.035
Shadkani S, Abbaspour A, Samadianfard S, Hashemi S, Mosavi A, Band SS (2021) Comparative study of multilayer perceptron-stochastic gradient descent and gradient boosted trees for predicting daily suspended sediment load: the case study of the Mississippi River, U.S. Int J Sediment Res 36(4):512–523. https://doi.org/10.1016/j.ijsrc.2020.10.001
Sharghi E, Nourani V, Najafi H, Gokceku H (2019) Conjunction of a newly proposed emotional ANN (EANN) and wavelet transform for suspended sediment load modeling. Water Supply 19(6):1726–1734. https://doi.org/10.2166/ws.2019.044
Taylor KE (2001) Summarizing multiple aspects of model performance in a single diagram. J Geophys Res Atmos 106(D7):7183–7192. https://doi.org/10.1029/2000JD900719
Wang C, Pan Y, Chen J, Ouyang Y, Rao J, Jiang Q (2020) Indicator element selection and geochemical anomaly mapping using recursive feature elimination and random forest methods in the Jingdezhen region of Jiangxi Province, South China. Appl Geochem 122: Article 104760. https://doi.org/10.1016/j.apgeochem.2020.104760
Yilmaz B, Aras E, Nacar S, Kankal M (2018) Estimating suspended sediment load with multivariate adaptive regression spline, teaching-learning based optimization, and artificial bee colony models. Sci Total Environ 639:826–840. https://doi.org/10.1016/j.scitotenv.2018.05.153
Zounemat-Kermani M, Kişi Ö, Adamowski J, Ramezani-Charmahineh A (2016) Evaluation of data driven models for river suspended sediment concentration modeling. J Hydrol 535:457–472. https://doi.org/10.1016/j.jhydrol.2016.02.012
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no competing interests.
Additional information
Responsible Editor: Broder J. Merkel
Rights and permissions
About this article
Cite this article
Esmaeili-Gisavandani, H., Farajpanah, H., Adib, A. et al. Evaluating ability of three types of discrete wavelet transforms for improving performance of different ML models in estimation of daily-suspended sediment load. Arab J Geosci 15, 29 (2022). https://doi.org/10.1007/s12517-021-09282-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12517-021-09282-7