Comprehensive evaluation of machine learning models for suspended sediment load inflow prediction in a reservoir

Abstract

Suspended sediment load (SSL) flowing into a reservoir contributes to the overall safety of dam. Owing to the complexity and stochastic nature of sedimentation, accurate prediction of reservoir SSL inflow is still challenging. Moreover, research and application of machine learning (ML) techniques for reservoir sedimentation are still deficient. A comprehensive evaluation of six ML models for a reservoir SSL inflow prediction was performed in this study. ML techniques including artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), radial basis function neural network (RBFNN), support vector machine (SVM), genetic programming (GP), and deep learning (DL) were applied to develop predictive models of daily SSL inflow at Sangju Weir, South Korea. Significant input vectors for each model were selected with streamflow, water temperature, water stage, reservoir outflow for different time lags. Model performances were evaluated using various statistical indices including the coefficient of determination (R2), mean absolute error (MAE), percentage of bias (PBIAS), Willmott index (WI), Nash–Sutcliffe efficiency (NSE), root mean square error (RMSE), and Pearson correlation coefficient (PCC). The best input combinations were found to be unique for each ML model, but all six models performed reasonably well for SSL inflow predictions. ANN model outperformed other models with R2 = 0.821, MAE = 4.244 tons/day, PBIAS = 0.055, WI = 0.891, NSE = 0.991, RMSE = 11.692 tons/day, PCC = 0.826. The models were ranked based on their SSL prediction capabilities as ANN > ANFIS > DL > RBFNN > SVM > GP from best to worst. The findings are expected to be useful for future dam safety and risk assessment, and for achieving sustainability of reservoir operation through comprehensive sediment management.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

References

  1. Anderson D, Moggridge H, Warren P, Shucksmith J (2015) The impacts of ‘run-of-river’ hydropower on the physical and ecological condition of rivers. Water Environ J 29:268–276. https://doi.org/10.1111/wej.12101

    Article  Google Scholar 

  2. Annandale G, Morris G, Karki P (2016) Extending the life of reservoirs: sustainable sediment management for dams and run-of-river hydropower. World Bank, Washington

    Google Scholar 

  3. ASCE Task Committee on Application of Artificial Neural Networks in Hydrology (2000a) Artificial neural networks in hydrology. I: Preliminary Concepts. J Hydrol Eng 5:115–123. https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(115)

    Article  Google Scholar 

  4. ASCE Task Committee on Application of Artificial Neural Networks in Hydrology (2000b) Artificial neural networks in hydrology. II: Hydrologic applications. J Hydrol Eng 5:124–137. https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(124)

    Article  Google Scholar 

  5. Aytek A, Kişi Ö (2008) A genetic programming approach to suspended sediment modelling. J Hydrol 351:288–298. https://doi.org/10.1016/j.jhydrol.2007.12.005

    Article  Google Scholar 

  6. Bagtzoglou AC, Hossain F (2009) Radial basis function neural network for hydrologic inversion: an appraisal with classical and spatio-temporal geostatistical techniques in the context of site characterization. Stoch Environ Res Risk Assess 23:933–945. https://doi.org/10.1007/s00477-008-0262-2

    Article  Google Scholar 

  7. Barjasteh A (2019) The impact of active faulting on the geotechnical properties of the Upper Gotvand Dam, southwest Iran. Bull Eng Geol Environ 78:709–722. https://doi.org/10.1007/s10064-017-1163-8

    Article  Google Scholar 

  8. Bharti B, Pandey A, Tripathi SK, Kumar D (2017) Modelling of runoff and sediment yield using ANN, LS-SVR, REPTree and M5 models. Hydrol Res 48:1489–1507. https://doi.org/10.2166/nh.2017.153

    Article  Google Scholar 

  9. 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. Water Resour Manag 31:1343–1359. https://doi.org/10.1007/s11269-017-1581-1

    Article  Google Scholar 

  10. Chai T, Draxler RR (2014) Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature. Geosci Model Dev 7:1247–1250

    Article  Google Scholar 

  11. Chang M-J, Lin G-F, Lee F-Z, Wang Y-C, Chen P-A, Wu M-C, Lai J-S (2020) Outflow sediment concentration forecasting by integrating machine learning approaches and time series analysis in reservoir desilting operation. Stoch Environ Res Risk Assess 34:849–866. https://doi.org/10.1007/s00477-020-01802-3

    Article  Google Scholar 

  12. de Andrade GJBSO, Berchin II, Garcia J, Neiva SdD, Jonck AV, Faraco RA, Silva de Amorim W, Ribeiro JMP (2020) A literature-based study on the water–energy–food nexus for sustainable development. Stoch Environ Res Risk Assess. https://doi.org/10.1007/s00477-020-01772-6

    Article  Google Scholar 

  13. Di Bucchianico A (2008) Coefficient of determination (R2). Encycl Stat Qual Reliab. https://doi.org/10.1002/9780470061572.eqr173

    Article  Google Scholar 

  14. Efthimiou N (2019) The role of sediment rating curve development methodology on river load modeling. Environ Monit Assess 191:108. https://doi.org/10.1007/s10661-018-7167-4

    Article  Google Scholar 

  15. Elsey-Quirk T, Graham SA, Mendelssohn IA, Snedden G, Day JW, Twilley RR, Shaffer G, Sharp LA, Pahl J, Lane RR (2019) Mississippi river sediment diversions and coastal wetland sustainability: Synthesis of responses to freshwater, sediment, and nutrient inputs. Estuar Coast Shelf Sci 221:170–183. https://doi.org/10.1016/j.ecss.2019.03.002

    CAS  Article  Google Scholar 

  16. Emamgholizadeh S, Demneh RK (2018) A comparison of artificial intelligence models for the estimation of daily suspended sediment load: a case study on the Telar and Kasilian rivers in Iran. Water Supply 19:165–178. https://doi.org/10.2166/ws.2018.062

    Article  Google Scholar 

  17. Fang W, Wang C, Chen X, Wan W, Li H, Zhu S, Fang Y, Liu B, Hong Y (2019) Recognizing global reservoirs from Landsat 8 images: A deep learning approach. IEEE J Sel Top Appl earth Obs Remote Sens 12:3168–3177

    Article  Google Scholar 

  18. Furnans J, Austin B (2008) Hydrographic survey methods for determining reservoir volume. Environ Model Softw 23:139–146. https://doi.org/10.1016/j.envsoft.2007.05.011

    Article  Google Scholar 

  19. Garg SK (2007) Irrigation engineering and hydraulic structures, 21st edn. Khanna Publishers, Dehli

    Google Scholar 

  20. Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning. MIT Press, Cambridge

    Google Scholar 

  21. Govindaraju RS, Rao AR (2013) Artificial neural networks in hydrology. Springer, Berlin

    Google Scholar 

  22. Graf WL, Wohl E, Sinha T, Sabo JL (2010) Sedimentation and sustainability of western American reservoirs. Water Resour Res. https://doi.org/10.1029/2009WR008836

    Article  Google Scholar 

  23. Huang CC, Fang HT, Ho HC, Jhong BC (2019) Interdisciplinary application of numerical and machine-learning-based models to predict half-hourly suspended sediment concentrations during typhoons. J Hydrol 573:661–675. https://doi.org/10.1016/j.jhydrol.2019.04.001

    Article  Google Scholar 

  24. Hussain A, Sarangi GK, Pandit A, Ishaq S, Mamnun N, Ahmad B, Jamil MK (2019) Hydropower development in the Hindu Kush Himalayan region: Issues, policies and opportunities. Renew Sustain Energy Rev 107:446–461. https://doi.org/10.1016/j.rser.2019.03.010

    Article  Google Scholar 

  25. Jabbar YC, Yadav SM (2019) Development of a relationship between hydrometric and hydrographic observations to predict reservoir capacity loss. Acta Geophys 67:1451–1469. https://doi.org/10.1007/s11600-019-00323-0

    Article  Google Scholar 

  26. Karaboga D, Kaya E (2019) Adaptive network based fuzzy inference system (ANFIS) training approaches: a comprehensive survey. Artif Intell Rev 52:2263–2293. https://doi.org/10.1007/s10462-017-9610-2

    Article  Google Scholar 

  27. Karna N, Hari Prasad KS, Giri S, Lodhi AS (2015) Intrusion of fine sediments into river bed and its effect on river environment – a research review. ISH J Hydraul Eng 21:142–150. https://doi.org/10.1080/09715010.2014.982000

    Article  Google Scholar 

  28. Kelly-Richards S, Silber-Coats N, Crootof A, Tecklin D, Bauer C (2017) Governing the transition to renewable energy: a review of impacts and policy issues in the small hydropower boom. Energy Policy 101:251–264. https://doi.org/10.1016/j.enpol.2016.11.035

    Article  Google Scholar 

  29. Khosravi K, Mao L, Kisi O, Yaseen ZM, Shahid S (2018) Quantifying hourly suspended sediment load using data mining models: Case study of a glacierized Andean catchment in Chile. J Hydrol 567:165–179. https://doi.org/10.1016/j.jhydrol.2018.10.015

    Article  Google Scholar 

  30. Kim HY (2016) Optimization of Sangju Weir operations to mitigate sedimentation problems. Dissertation, Colorado State Univerity

  31. Kim HY, Fontane DG, Julien PY, Lee JH (2017) Multiobjective Analysis of the Sedimentation behind Sangju Weir, South Korea. J Water Resour Plan Manag 144:1–12. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000851

    Article  Google Scholar 

  32. Kim HY, Julien PY (2018) Hydraulic Thresholds to Mitigate Sedimentation Problems at Sangju Weir, South Korea. J Hydraul Eng 144:1–13. https://doi.org/10.1061/(ASCE)HY.1943-7900.0001467

    Article  Google Scholar 

  33. Kumar A, Kumar P, Singh VK (2019) Evaluating different machine learning models for runoff and suspended sediment simulation. Water Resour Manag 33:1217–1231. https://doi.org/10.1007/s11269-018-2178-z

    Article  Google Scholar 

  34. Kumar D, Ashish P, Nayan S, Wolfgang-Albert F (2015) Modeling suspended sediment using artificial neural networks and TRMM-3B42 version 7 rainfall dataset. J Hydrol Eng 20:C4014007. https://doi.org/10.1061/(ASCE)HE.1943-5584.0001082

    Article  Google Scholar 

  35. Lafdani EK, 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

    Article  Google Scholar 

  36. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444

    CAS  Article  Google Scholar 

  37. Malik A, Kumar A, Kisi O, Shiri J (2019) Evaluating the performance of four different heuristic approaches with Gamma test for daily suspended sediment concentration modeling. Environ Sci Pollut Res 26:22670–22687. https://doi.org/10.1007/s11356-019-05553-9

    Article  Google Scholar 

  38. Mirumachi N, Torriti J (2012) The use of public participation and economic appraisal for public involvement in large-scale hydropower projects: case study of the Nam Theun 2 Hydropower Project. Energy Policy 47:125–132. https://doi.org/10.1016/j.enpol.2012.04.034

    Article  Google Scholar 

  39. Moges MA, Zemale FA, Alemu ML et al (2016) Sediment concentration rating curves for a monsoonal climate: upper Blue Nile. Soil 2:337

    Article  Google Scholar 

  40. Moriasi DN, Arnold JG, Van Liew MW et al (2007) Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Trans ASABE 50:885–900

    Article  Google Scholar 

  41. Morrill JC, C. BR, H. CM, (2005) Estimating stream temperature from air temperature: implications for future water quality. J Environ Eng 131:139–146. https://doi.org/10.1061/(ASCE)0733-9372(2005)131:1(139)

    CAS  Article  Google Scholar 

  42. Mustafa MR, Isa MH, Rezaur RB (2012) Artificial neural networks modeling in water resources engineering: infrastructure and applications. World Acad Sci Eingineering Technol 6:341–349

    Google Scholar 

  43. Nones M (2019) Dealing with sediment transport in flood risk management. Acta Geophys 67:677–685. https://doi.org/10.1007/s11600-019-00273-7

    Article  Google Scholar 

  44. Petts GE, Gurnell AM (2005) Dams and geomorphology: Research progress and future directions. Geomorphology 71:27–47. https://doi.org/10.1016/j.geomorph.2004.02.015

    Article  Google Scholar 

  45. Renaud O, Victoria-Feser M-P (2010) A robust coefficient of determination for regression. J Stat Plan Inference 140:1852–1862. https://doi.org/10.1016/j.jspi.2010.01.008

    Article  Google Scholar 

  46. Sadeghi SH, Saeidi P (2010) Reliability of sediment rating curves for a deciduous forest watershed in Iran. Hydrol Sci J 55:821–831

    Article  Google Scholar 

  47. Samet K, Hoseini K, Karami H, Mohammadi M (2019) Comparison between soft computing methods for prediction of sediment load in rivers: Maku Dam case study. Iran J Sci Technol Trans Civ Eng 43:93–103. https://doi.org/10.1007/s40996-018-0121-4

    Article  Google Scholar 

  48. Sattari MT, Apaydin H, Shamshirband S, Mosavi A (2020) Comparative analysis of Kernel-based versus BFGS-ANN and deep learning methods in monthly reference evaporation estimation. Hydrol Earth Syst Sci Discuss 1–24

  49. Schleiss AJ, Franca MJ, Juez C, De Cesare G (2016) Reservoir sedimentation. J Hydraul Res 54:595–614. https://doi.org/10.1080/00221686.2016.1225320

    Article  Google Scholar 

  50. Shaktawat A, Vadhera S (2020) Risk management of hydropower projects for sustainable development: a review. Environ Dev Sustain. https://doi.org/10.1007/s10668-020-00607-2

    Article  Google Scholar 

  51. Shanmuganathan S (2016) Artificial neural network modelling: an introduction. In: Shanmuganathan S, Samarasinghe S (eds) Artificial neural network modelling. Springer, Cham, pp 1–14

    Google Scholar 

  52. Singh D, Singh B (2019) Investigating the impact of data normalization on classification performance. Appl Soft Comput. https://doi.org/10.1016/j.asoc.2019.105524

    Article  Google Scholar 

  53. Tahseen S, Karney BW (2017) Reviewing and critiquing published approaches to the sustainability assessment of hydropower. Renew Sustain Energy Rev 67:225–234. https://doi.org/10.1016/j.rser.2016.09.031

    Article  Google Scholar 

  54. Tang W, Li Z, Tu Y (2018) Sustainability risk evaluation for large-scale hydropower projects with hybrid uncertainty. Sustainability. https://doi.org/10.3390/su10010138

    Article  Google Scholar 

  55. Tortajada C, Saklani U (2018) Hydropower-based collaboration in South Asia: the case of India and Bhutan. Energy Policy 117:316–325. https://doi.org/10.1016/j.enpol.2018.02.046

    Article  Google Scholar 

  56. Trussart S, Messier D, Roquet V, Aki S (2002) Hydropower projects: a review of most effective mitigation measures. Energy Policy 30:1251–1259. https://doi.org/10.1016/S0301-4215(02)00087-3

    Article  Google Scholar 

  57. Vassoney E, Mammoliti Mochet A, Comoglio C (2017) Use of multicriteria analysis (MCA) for sustainable hydropower planning and management. J Environ Manage 196:48–55. https://doi.org/10.1016/j.jenvman.2017.02.067

    Article  Google Scholar 

  58. Voegeli G, Hediger W, Romerio F (2019) Sustainability assessment of hydropower: Using causal diagram to seize the importance of impact pathways. Environ Impact Assess Rev 77:69–84. https://doi.org/10.1016/j.eiar.2019.03.005

    Article  Google Scholar 

  59. Wagner B, Hauer C, Habersack H (2019) Current hydropower developments in Europe. Curr Opin Environ Sustain 37:41–49. https://doi.org/10.1016/j.cosust.2019.06.002

    Article  Google Scholar 

  60. Wild TB, Reed MP, Loucks DP, Mallen-Cooper M (2019) Balancing hydropower development and ecological impacts in the mekong: tradeoffs for Sambor Mega Dam. J Water Resour Plan Manag 145:5018019. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001036

    Article  Google Scholar 

  61. Willmott CJ, Robeson SM, Matsuura K (2012) A refined index of model performance. Int J Climatol 32:2088–2094. https://doi.org/10.1002/joc.2419

    Article  Google Scholar 

  62. Yang J, Yang YCE, Chang J, Zhang J, Yao J (2019) Impact of dam development and climate change on hydroecological conditions and natural hazard risk in the Mekong River Basin. J Hydrol 579:124177. https://doi.org/10.1016/j.jhydrol.2019.124177

    Article  Google Scholar 

  63. Young KH et al (2018) Multiobjective analysis of the sedimentation behind Sangju Weir, South Korea. J Water Resour Plan Manag 144:5017019. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000851

    Article  Google Scholar 

  64. Yucesan M, Kahraman G (2019) Risk evaluation and prevention in hydropower plant operations: a model based on Pythagorean fuzzy AHP. Energy Policy 126:343–351. https://doi.org/10.1016/j.enpol.2018.11.039

    Article  Google Scholar 

  65. Zhang D, Lin J, Peng Q, Wang D, Yang T, Sorooshian S, Liu X, Zhuang J (2018) Modeling and simulating of reservoir operation using the artificial neural network, support vector regression, deep learning algorithm. J Hydrol 565:720–736

    Article  Google Scholar 

  66. Zhang W, Wei X, Jinhai Z et al (2012) Estimating suspended sediment loads in the Pearl River Delta region using sediment rating curves. Cont Shelf Res 38:35–46

    CAS  Article  Google Scholar 

  67. Zhao H, Yang S, Yang B, Huang Y (2017) Quantifying anthropogenic and climatic impacts on sediment load in the sediment-rich region of the Chinese Loess Plateau by coupling a hydrological model and ANN. Stoch Environ Res Risk Assess 31:2057–2073. https://doi.org/10.1007/s00477-017-1381-4

    Article  Google Scholar 

  68. Zhang L, Li S, Wu Z et al (2020) Variation in runoff, suspended sediment load, and their inter-relationships in response to climate change and anthropogenic activities over the last 60 years: a case study of the Upper Fenhe River Basin. China Water 12:1757

    Article  Google Scholar 

  69. Zhong Y, Guo S, Liu Z, Wang Y, Yin J (2018) Quantifying differences between reservoir inflows and dam site floods using frequency and risk analysis methods. Stoch Environ Res Risk Assess 32:419–433. https://doi.org/10.1007/s00477-017-1401-4

    Article  Google Scholar 

Download references

Funding

This research was supported by a grant(2020-MOIS33-006) of Lower-level and Core Disaster-Safety Technology Development Program funded by Ministry of Interior and Safety (MOIS, Korea).

Author information

Affiliations

Authors

Corresponding author

Correspondence to Tae-Woong Kim.

Ethics declarations

Conflict of interest

The authors have no conflict of interest.

Availability of data and material

All the datasets used in this research are available online. For further information, see ‘Sect. 2′ of this article.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix

Appendix

See Tables 6, 7 and 8.

Table 6 Performance indicators for SSL modelling using various ANN model architecture (transfer function: logsig)
Table 7 Performance indicators for various ANFIS models (optimization method: hybrid)
Table 8 Performance indicators for various RBFNN models

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Idrees, M.B., Jehanzaib, M., Kim, D. et al. Comprehensive evaluation of machine learning models for suspended sediment load inflow prediction in a reservoir. Stoch Environ Res Risk Assess (2021). https://doi.org/10.1007/s00477-021-01982-6

Download citation

Keywords

  • Suspended sediment load
  • Machine learning models
  • Risk assessment
  • Sedimentation hazard
  • Sangju weir