Applying a machine learning-based method for the prediction of suspended sediment concentration in the Red river basin

Son Q. Nguyen1, Linh C. Nguyen2, Thanh Ngo-Duc3, Sylvain Ouillon1,4
1Department of Water – Environment - Oceanography, University of Science and Technology of Hanoi, Vietnam Academy of Science and Technology, Hanoi, Vietnam
2Department of Life Sciences, University of Science and Technology of Hanoi, Vietnam Academy of Science and Technology, Hanoi, Vietnam
3Department of Space and Applications, University of Science and Technology of Hanoi, Vietnam Academy of Science and Technology, Hanoi, Vietnam
4UMR 5566 LEGOS, Université de Toulouse, IRD, CNES, CNRS, UPS, Toulouse, France

Tóm tắt

Knowledge of sediment transport is important to understand the transportation and recycling of elements and matter in the Earth system. Usually, sediment transport in rivers is characterized by suspended sediment concentration (SSC) and river discharge (Q). However, SSC measurements are often inadequate in many river systems, such as the Red River basin in Vietnam. In this study, we performed a Tributary-based Downstream gauge Estimation (TDE) machine learning (ML) approach to estimate SSC at Son Tay hydrological station based on Q and SSC monthly data from three upstream stations, one per tributary of the Red River over a 14-years period (2000–2013). A comparative analysis of four ML algorithms, including Multiple Linear Regression (MLR), Elastic Net (EN), Random Forest (RF), and Support Vector Machines (SVM) was conducted. Results showed that when using both Q and SSC of the three upstream stations, the SVM algorithm with linear kernel exhibited the highest accuracy (r2 = 0.87 and RMSE = 64.7 g m−3). The performance of the TDE-ML was seasonally dependent, with higher accuracy in the high-flow period. This approach also revealed that SSC measured at Yen Bai station (Thao River) had the highest contribution to the prediction of SSC at Son Tay station meanwhile Vu Quang station (Lo River) contributed the least to downstream SSC. Furthermore, new dams have been impounded during the 14-years period. Although the global performance of the RF method was slightly less than SVM with linear kernel, it was the only one able to fairly estimate SSC in the most recent 6-years period affected by new forcing.

Tài liệu tham khảo

Achite M, Ouillon S (2007) Suspended sediment transport in a semiarid watershed, Wadi Abd, Algeria (1973–1995). J Hydrol 343:187–202. https://doi.org/10.1016/j.jhydrol.2007.06.026 Achite M, Ouillon S (2016) Recent changes in climate, hydrology and sediment load in the Wadi Abd, Algeria (1970–2010). Hydrol Earth Syst Sci 20:1355–1372. https://doi.org/10.5194/hess-20-1355-2016 Alp M, Cigizoglu HK (2007) Suspended sediment load simulation by two artificial neural network methods using hydrometeorological data. Environ Model Softw 22:2–13. https://doi.org/10.1016/j.envsoft.2005.09.009 Asselman NEM (2000) Fitting and interpretation of sediment rating curves. J Hydrol 234:228–248. https://doi.org/10.1016/S0022-1694(00)00253-5 Bagnold RA (1966) An approach to the sediment transport problem from general physics. USGS Professional Paper 422-I. https://doi.org/10.3133/pp422I Bhattacharya B, Price RK, Solomatine DP (2007) Machine learning approach to modeling sediment transport. J Hydraul Eng 133:440–450. https://doi.org/10.1061/(ASCE)0733-9429(2007)133:4(440) Boussadia-Omari L, Ouillon S, Hirche A et al (2021) Contribution of phytoecological data to spatialize soil erosion: application of the RUSLE model in the Algerian atlas. Int Soil Water Conserv Res 9:502–519. https://doi.org/10.1016/j.iswcr.2021.05.004 Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324 Castelletti A, Pianosi F, Quach X, Soncini-Sessa R (2012) Assessing water reservoirs management and development in Northern Vietnam. Hydrol Earth Syst Sci 16:189–199. https://doi.org/10.5194/hess-16-189-2012 Cawley GC, Talbot NLC (2010) On over-fitting in model selection and subsequent selection bias in performance evaluation. J Mach Learn Res 11:2079–2107. Available at:. http://jmlr.org/papers/v11/cawley10a.pdf Cigizoglu HK, Alp M (2004) Rainfall-runoff modelling using three neural network methods. In: Rutkowski L, Siekmann JH, Tadeusiewicz R, Zadeh LA (eds) Artificial intelligence and soft computing—ICAISC 2004. Springer, Berlin, Heidelberg, pp 166–171 Cristianini N, Ricci E (2008) Support vector machines. In: Kao M-Y (ed) Encyclopedia of algorithms. Springer US, Boston, pp 928–932 Dang TH, Coynel A, Orange D et al (2010) Long-term monitoring (1960–2008) of the river-sediment transport in the Red River Watershed (Vietnam): temporal variability and dam-reservoir impact. Sci Total Environ 408:4654–4664. https://doi.org/10.1016/j.scitotenv.2010.07.007 Essam Y, Huang YF, Birima AH et al (2022) Predicting suspended sediment load in Peninsular Malaysia using support vector machine and deep learning algorithms. Sci Rep 12:302. https://doi.org/10.1038/s41598-021-04419-w Ferguson RI (1986) River loads underestimated by rating curves. Water Resour Res 22:74–76. https://doi.org/10.1029/WR022i001p00074 Friedman JH, Hastie T, Tibshirani R (2010) Regularization paths for generalized linear models via coordinate descent. J Stat Softw 33:1–22. https://doi.org/10.18637/jss.v033.i01 Gomez B, Church M (1989) An assessment of bed load sediment transport formulae for gravel bed rivers. Water Resour Res 25:1161–1186. https://doi.org/10.1029/WR025i006p01161 Halbe J, Pahl-Wostl C, Sendzimir J, Adamowski J (2013) Towards adaptive and integrated management paradigms to meet the challenges of water governance. Water Sci Technol 67:2651–2660. https://doi.org/10.2166/wst.2013.146 Hiep NH, Luong ND, Viet Nga TT et al (2018) Hydrological model using ground- and satellite-based data for river flow simulation towards supporting water resource management in the Red River Basin, Vietnam. J Environ Manage 217:346–355. https://doi.org/10.1016/j.jenvman.2018.03.100 Horowitz AJ (2003) An evaluation of sediment rating curves for estimating suspended sediment concentrations for subsequent flux calculations. Hydrol Process 17:3387–3409. https://doi.org/10.1002/hyp.1299 Hu K, Ding P, Wang Z, Yang S (2009) A 2D/3D hydrodynamic and sediment transport model for the Yangtze Estuary, China. J Mar Syst 77:114–136. https://doi.org/10.1016/j.jmarsys.2008.11.014 James G, Witten D, Hastie T, Tibshirani R (2021) An introduction to statistical learning: with applications in R, 2021 edition, 2nd edn. Springer, New York Jansson MB (1996) Estimating a sediment rating curve of the Reventazón river at Palomo using logged mean loads within discharge classes. J Hydrol 183:227–241. https://doi.org/10.1016/0022-1694(95)02988-5 Khanchoul K, Jansson M (2008) Sediment rating curves developed on stage and seasonal means in discharge classes for the Mellah Wadi, Algeria. Geogr Annaler Ser Phys Geogr 90:227–236. https://doi.org/10.1111/j.1468-0459.2008.341.x Kişi Ö (2004) River Flow modeling using artificial neural networks. J Hydrol Eng 9:60–63. https://doi.org/10.1061/(ASCE)10840699(2004)9:1(60) Kreibich H, Van Loon AF, Schröter K et al (2022) The challenge of unprecedented Floods and droughts in risk management. Nature 608:80–86. https://doi.org/10.1038/s41586-022-04917-5 Kurniawan I, Hayder G, Mustafa HM (2021) Predicting water quality parameters in a complex river system. J Ecol Eng 22:250–257. https://doi.org/10.12911/22998993/129579 Lafdani E, Moghaddam Nia A, Ahmadi A (2013) Daily suspended sediment load prediction using artificial neural networks and support vector machines. J Hydrol 478:50–62. https://doi.org/10.1016/j.jhydrol.2012.11.048 Le TPQ, Billen G, Garnier J et al (2005) Nutrient (N, P) budgets for the Red River Basin (Vietnam and China). Glob Biogeochem Cycles 19:1–16. https://doi.org/10.1029/2004GB002405 Le TPQ, Garnier J, Billen G et al (2007) The changing flow regime and sediment load of the Red River, Viet Nam. J Hydrol 334:199–214. https://doi.org/10.1016/j.jhydrol.2006.10.020 Lu XX, Oeurng C, Le TPQ, Thuy DT (2015) Sediment budget as affected by construction of a sequence of dams in the lower Red River, Viet Nam. Geomorphology 248:125–133. https://doi.org/10.1016/j.geomorph.2015.06.044 Mohamed I, Shah I (2018) Suspended sediment concentration modeling using conventional and machine learning approaches in the Thames River, London Ontario. J Water Manage Model. https://doi.org/10.14796/JWMM.C453 Nash JE, Sutcliffe JV (1970) River flow forecasting through conceptual models part I — a discussion of principles. J Hydrol 10:282–290. https://doi.org/10.1016/0022-1694(70)90255-6 Neitsch S, Arnold J, Kiniry J, Temple et al (2011) https://swat.tamu.edu/media/99192/swat2009-theory.pdf Nhu V-H, Khosravi K, Cooper JR et al (2020) Monthly suspended sediment load prediction using artificial intelligence: testing of a new random subspace method. Hydrol Sci J 65:2116–2127. https://doi.org/10.1080/02626667.2020.1754419 Ouellet-Proulx S, St-Hilaire A, Courtenay SC, Haralampides KA (2016) Estimation of suspended sediment concentration in the Saint John River using rating curves and a machine learning approach. Hydrol Sci J 61:1847–1860. https://doi.org/10.1080/02626667.2015.1051982 Ouillon S (2018) Why and how do we study sediment transport? Focus on coastal zones and ongoing methods. Water 10:390. https://doi.org/10.3390/w10040390 Rajaee T, Mirbagheri SA, Zounemat-Kermani M, Nourani V (2009) Daily suspended sediment concentration simulation using ANN and neuro-fuzzy models. Sci Total Environ 407:4916–4927. https://doi.org/10.1016/j.scitotenv.2009.05.016 Sharafati A, Haji Seyed Asadollah SB, Motta D, Yaseen ZM (2020) Application of newly developed ensemble machine learning models for daily suspended sediment load prediction and related uncertainty analysis. Hydrol Sci J 65:2022–2042. https://doi.org/10.1080/02626667.2020.1786571 Sok T, Oeurng C, Ich I et al (2020) Assessment of Hydrology and Sediment Yield in the Mekong River Basin using SWAT model. Water 12:3503. https://doi.org/10.3390/w12123503 Tyralis H, Papacharalampous G, Langousis A (2019) A brief review of random forests for water scientists and practitioners and their recent history in water resources. Water 11:910. https://doi.org/10.3390/w11050910 Vinh VD, Ouillon S, Thanh TD, Chu LV (2014) Impact of the Hoa Binh dam (Vietnam) on water and sediment budgets in the Red River basin and delta. Hydrol Earth Syst Sci 18:3987–4005. https://doi.org/10.5194/hess-18-3987-2014 Vu DV, Ouillon S, Nguyen VT, Nguyen NT (2016) Numerical simulations of suspended sediment dynamics due to seasonal forcing in the Mekong Coastal Area. Water 8:255. https://doi.org/10.3390/w8060255 Wei X, Sauvage S, Le TPQ et al (2019) A modeling approach to diagnose the impacts of global changes on discharge and suspended sediment concentration within the Red River Basin. Water 11:958. https://doi.org/10.3390/w11050958 Wei X, Sauvage S, Ouillon S et al (2021) A modelling-based assessment of suspended sediment transport related to new damming in the Red River basin from 2000 to 2013. CATENA 197:104958. https://doi.org/10.1016/j.catena.2020.104958 Williams GP (1989) Sediment concentration versus water discharge during single hydrologic events in rivers. J Hydrol 111:89–106. https://doi.org/10.1016/0022-1694(89)90254-0 Wischmeier WH, Smith DD (1978) Predicting rainfall erosion losses: a guide to conservation planning. Department of Agriculture, Science and Education Administration. The USDA Agricultural Handbook No. 537, Maryland, USA Wolpert D, Roy R, Köppen M, Ovaska S, Furuhashi T, Hoffmann F (2001) The supervised learning no-free-lunch theorems. In: Roy R, Köppen M, Ovaska S, Furuhashi T, Hoffmann F (eds) Soft computing and industry. Springer, London. https://doi.org/10.1007/978-1-4471-0123-9_3 Zounemat-Kermani M, Kisi O, Adamowski J, Ramezani-Charmahineh A (2016) Evaluation of data driven models for river suspended sediment concentration modeling. J Hydrol. https://doi.org/10.1016/j.jhydrol.2016.02.012