Water Resources Management

, Volume 31, Issue 4, pp 1105–1119 | Cite as

Online Ensemble Modeling for Real Time Water Level Forecasts

Article

Abstract

Accurate and reliable flood forecasting is essential to mitigate the threats brought by floods. Ensemble approaches have been used in limited studies to improve the forecasts of component models. In this paper an ensemble model based on neural-fuzzy inference system (NFIS) and three real time updating approaches were used to synthesize the water level forecasts from a Adaptive-Network-based Fuzzy Inference System (ANFIS) model and the Unified River Basin Simulator (URBS) model for three stations in Lower Mekong. The NFIS ensemble model results are compared with the simple average model (SAM) which is adopted as a benchmark ensemble model. The ensemble model of offline learning without real time updating (EN-OFF), ensemble model with real time updating using offline learning (EN-RTOFF), ensemble model with real time updating using online learning (EN-RTON1) and ensemble model with real time updating using online learning and sub-models (EN-RTON2) were studied in this paper. Statistical analysis of the models for all the three stations indicated the superiority of the EN-RTON2 model over EN-RTOFF, EN-RTON1 models, SAM and the EN-OFF model. Not only the spikes in the URBS model were eliminated, but also the time shift problems in the ANFIS model results were decreased.

Keywords

Ensemble model Real time Online learning DENFIS Lower Mekong 

Notes

Acknowledgments

The measured data and the results of the URBS model were generously provided by the Mekong River Commission.

Compliance with Ethical Standards

The authors declare that they have no conflict of interest.

Supplementary material

11269_2016_1539_MOESM1_ESM.docx (447 kb)
Supplementary Fig. S1 (DOCX 447 kb)
11269_2016_1539_MOESM2_ESM.docx (80 kb)
Supplementary Fig. S2 (DOCX 79 kb)
11269_2016_1539_MOESM3_ESM.docx (80 kb)
Supplementary Fig. S3 (DOCX 80 kb)
11269_2016_1539_MOESM4_ESM.docx (81 kb)
Supplementary Fig. S4 (DOCX 81 kb)
11269_2016_1539_MOESM5_ESM.docx (15 kb)
Supplementary Table S1 (DOCX 14 kb)

References

  1. Akbari-Alashti H, Bozorg Haddad O, Mariño MA (2015) Evaluation of a developed discrete time-series method in flow forecasting models. Water Resour Manag 29:3211–3225. doi: 10.1007/s11269-015-0991-1 CrossRefGoogle Scholar
  2. Carroll DG (2004) URBS: A Rainfall Runoff Routing Model for Flood Forecasting and Design. Version 4.00. Available at www.URBS.com.au
  3. Franchini M, Pacciani M (1991) Comparative analysis of several conceptual rainfall-runoff models. J Hydrol 122:161–219. doi: 10.1016/0022-1694(91)90178-K CrossRefGoogle Scholar
  4. Goswami M, O’Connor KM (2007) Real-time flow forecasting in the absence of quantitative precipitation forecasts: a multi-model approach. J Hydrol 334:125–140. doi: 10.1016/j.jhydrol.2006.10.002 CrossRefGoogle Scholar
  5. Green IRA, Stephenson D (1986) Criteria for comparison of single event models. Hydrol Sci J 31:395–411. doi: 10.1080/02626668609491056 CrossRefGoogle Scholar
  6. Gupta H, Sorooshian S, Yapo P (1999) Status of automatic calibration for hydrologic models: comparison with multilevel expert calibration. J Hydrol Eng 4:135–143. doi: 10.1061/(ASCE)1084-0699(1999)4:2(135) CrossRefGoogle Scholar
  7. Hsiao L-F et al (2013) Ensemble forecasting of typhoon rainfall and floods over a mountainous watershed in Taiwan. J Hydrol 506:55–68. doi: 10.1016/j.jhydrol.2013.08.046 CrossRefGoogle Scholar
  8. Jang JSR (1993) ANFIS: adaptive-network-based fuzzy inference system systems. IEEE Trans Man Cybern 23:665–685. doi: 10.1109/21.256541 CrossRefGoogle Scholar
  9. Kasabov NK, Song Q (2002) DENFIS: dynamic evolving neural-fuzzy inference system and its application for time-series prediction. IEEE Trans Fuzzy Syst 10:144–154. doi: 10.1109/91.995117 CrossRefGoogle Scholar
  10. Kasiviswanathan KS, Cibin R, Sudheer KP, Chaubey I (2013) Constructing prediction interval for artificial neural network rainfall runoff models based on ensemble simulations. J Hydrol 499:275–288. doi: 10.1016/j.jhydrol.2013.06.043 CrossRefGoogle Scholar
  11. Latt ZZ, Wittenberg H (2014) Improving flood forecasting in a developing country: a comparative study of stepwise multiple linear regression and artificial neural network. Water Resour Manag 28:2109–2128. doi: 10.1007/s11269-014-0600-8 CrossRefGoogle Scholar
  12. Lohani AK, Goel NK, Bhatia KKS (2014) Improving real time flood forecasting using fuzzy inference system. J Hydrol 509:25–41. doi: 10.1016/j.jhydrol.2013.11.021 CrossRefGoogle Scholar
  13. MRC (2009) System performance evaluation report. Phnom Penh, CambodiaGoogle Scholar
  14. Nash JE, Sutcliffe JV (1970) River flow forecasting through conceptual models part I — a discussion of principles. J Hydrol 10:282–290. doi: 10.1016/0022-1694(70)90255-6 CrossRefGoogle Scholar
  15. Nguyen PKT, Chua LHC (2012) The data-driven approach as an operational real-time flood forecasting model. Hydrol Process 26:2878–2893. doi: 10.1002/hyp.8347 CrossRefGoogle Scholar
  16. Rathinasamy M, Adamowski J, Khosa R (2013) Multiscale streamflow forecasting using a new Bayesian model average based ensemble multi-wavelet Volterra nonlinear method. J Hydrol 507:186–200. doi: 10.1016/j.jhydrol.2013.09.025 CrossRefGoogle Scholar
  17. Seann R, John S, Ziya Z (2007) A distributed hydrologic model and threshold frequency-based method for flash flood forecasting at ungauged locations. J Hydrol 337:402–420. doi: 10.1016/j.jhydrol.2007.02.015 CrossRefGoogle Scholar
  18. See L, Openshaw S (2000) A hybrid multi-model approach to river level forecasting. Hydrol Sci J 45:523–536. doi: 10.1080/02626660009492354 CrossRefGoogle Scholar
  19. Seni G, Elder JF (2010) Ensemble methods in data mining: improving accuracy through combining predictions. Synthesis lectures on data mining and knowledge discovery. Morgan & Claypool Publishers, San RafaelGoogle Scholar
  20. Shamseldin AY, O’Connor KM (2003) A “consensus” real-time river flow forecasting model for the Blue Nile River. Water Resources Systems-Hydrological Risk, Management and Development, SapporoGoogle Scholar
  21. Silvestro F, Rebora N, Ferraris L (2011) Quantitative flood forecasting on small- and medium-sized basins: a probabilistic approach for operational purposes. J Hydrometeorol 12:1432–1446. doi: 10.1175/JHM-D-10-05022.1 CrossRefGoogle Scholar
  22. Soleymani SA, Goudarzi S, Anisi MH, Hassan WH, Idris MYI, Shamshirband S, Noor NM, Ahmedy I (2016) A novel method to water level prediction using RBF and FFA. Water Resour Manag 30:3265–3283. doi: 10.1007/s11269-016-1347-1 CrossRefGoogle Scholar
  23. Takagi T, Sugeno M (1985) Fuzzy identification of systems and its applications to modeling and control. IEEE Trans Syst Man Cybern SMC-15:116–132. doi: 10.1109/tsmc.1985.6313399 CrossRefGoogle Scholar
  24. Vieira J, Føns J, Cecconi G (1993) Statistical and hydrodynamic models for the operational forecasting of floods in the Venice Lagoon. Coast Eng 21:301–331. doi: 10.1016/0378-3839(93)90012-w CrossRefGoogle Scholar
  25. Xiong LH, Shamseldin AY, O’Connor KM (2001) A non-linear combination of the forecasts of rainfall-runoff models by the first-order Takagi-Sugeno fuzzy system. J Hydrol 245:196–217. doi: 10.1016/S0022-1694(01)00349-3 CrossRefGoogle Scholar
  26. Yu PS, Yang TC (1997) A probability-based renewal rainfall model for flow forecasting. Nat Hazards 15:51–70. doi: 10.1023/A:1007946628274 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2017

Authors and Affiliations

  1. 1.School of Civil and Environmental EngineeringNanyang Technological UniversitySingaporeSingapore
  2. 2.Maritime Research Centre (MRC)Nanyang Technological UniversitySingaporeSingapore
  3. 3.Nanyang Environment and Water Research Institute (NEWRI)SingaporeSingapore
  4. 4.School of EngineeringDeakin UniversityWaurn PondsAustralia

Personalised recommendations