Earth Science Informatics

, Volume 8, Issue 4, pp 787–798 | Cite as

Retrieval of missing values in water temperature series using a data-driven model

Research Article
First Online:
Received:
Accepted:

Abstract

A measurement buoy with attached sensors has been deployed at our study area to monitor hydrodynamics, water properties, and water quality conditions. High-resolution temporal data have been collected and streamed into an online system that is accessible in nearly real-time. However, in certain circumstances the sensors may fail to provide continuous and high quality data. This results in gaps or corrupted values. The aim of this study was to reconstruct the faulty values. This paper proposes a method based on a data-driven model, using an Artificial Neural Network combined with a Genetic Algorithm to generate a synthetic data series. The generated data can be used as a patch for the incomplete measured data. Additional improvements were achieved by removing seasonal patterns from the original time series using a wavelet decomposition prior to the data-driven model training process. Comparisons with a standard missing-data imputation method using the Kohonen self-organizing map were made to further asses the performance of the proposed data-driven model. The algorithm was applied to water temperature data, but the same approach is applicable to other parameters of interest.

Keywords

Water temperature Artificial neural network Genetic algorithm Kohonen self-organizing map Wavelet decomposition Water quality 
This is a preview of subscription content, log in to check access.

Notes

Acknowledgments

The authors are grateful to the Public Utility Board of Singapore for sponsoring this work and to all Tropical Marine Science Institute (TMSI) colleagues for their valuable contributions to the success of this study. We would also like to thank the anonymous reviewers for their insightful comments and suggestions to improve the quality of the paper.

References

  1. Adeloye AJ, Rustum R, Kariyama ID (2011) Kohonen self-organizing map estimator for the reference crop evapotranspiration. Water Resour Res. doi: 10.1029/2011WR010690 Google Scholar
  2. Aguilar-Martinez S, Hsieh WW (2009) Forecasts of tropical pacific sea surface temperatures by neural networks and support vector regression. Int J Oceanogr. doi: 10.1155/2009/167239 Google Scholar
  3. Babovic V, Sannasiraj SA, Chan ES (2005) Error correction of a predictive ocean wave model using local model approximation. J Mar Syst 53:1–17CrossRefGoogle Scholar
  4. Behera MR, Chun C, Sundarambal P, Tkalich P (2013) Temporal variability and climatology of hydrodynamic, water property, and water quality parameters in West Johor Strait of Singapore. Mar Pollut Bull 77:380–395CrossRefGoogle Scholar
  5. Bixler GD, Bhushan B (2012) Biofouling: lessons from nature. Phil Trans R Soc A 370:2381–2417CrossRefGoogle Scholar
  6. Breaker LC, Brewster JK (2009) Predicting offshore temperatures in Monterey Bay based on coastal observation using linear forecast models. Ocean Model 27:82–97CrossRefGoogle Scholar
  7. Chen H, Wei J, Tkalich P, Mallanote-Rizzoli P (2010) The various components of the circulation in the Singapore Strait region: tidal, wind, Eddy-driven circulations and their relative importance. In Papers of the 20th International Offshore and Polar Engineering Conference, ISOPE-2010, Beijing, China, June 20–26Google Scholar
  8. Corani G (2005) Air quality prediction in Milan: feed-forward neural networks, pruned neural networks and lazy learning. Ecol Model 185:513–529CrossRefGoogle Scholar
  9. Daubechies I (1990) The wavelet transform, time–frequency localization and signal analysis. IEEE T Inf Theory 36(5):961–1005CrossRefGoogle Scholar
  10. De Pascalis F, Perez-Ruzafa A, Gilabert J, Marcos C, Umgeisser G (2012) Climate change response of the Mar Menor coastal lagoon (Spain) using a hydrodynamic finite element model. Estuar Coast Shelf Sci 114:118–129CrossRefGoogle Scholar
  11. Delauney L, Compere C, Lehaitre M (2010) Biofouling protection for marine environmental sensors. Ocean Sci 6:503–511CrossRefGoogle Scholar
  12. Elshorbagy W, Azam MH, Elhakeem A (2013) Temperature-salinity modeling for Ruwais coastal area in United Arab Emirates. Mar Pollut Bull 73:170–182CrossRefGoogle Scholar
  13. Faruk DO (2010) A hybrid neural network and ARIMA model for water quality time series prediction. Eng Appl Artif Intell 23:586–594CrossRefGoogle Scholar
  14. Gazzaz NM, Yusoff MK, Aris AZ, Juahir H, Ramli MF (2012) Artificial neutral network modeling of the water quality index for Kinta River (Malaysia) using water quality variables as predictors. Mar Pollut Bull 64:2409–2420CrossRefGoogle Scholar
  15. Goldberg DE (1989) Genetic algorithms in search, optimization and machine learning. Longman Publishing Co., New YorkGoogle Scholar
  16. Hatzikos E, Hatonen J, Bassiliades N, Vlahavas I, Fournou E (2009) Applying adaptive prediction to sea-water quality measurements. Expert Syst Appl 36:6773–6779CrossRefGoogle Scholar
  17. Haykin S (2009) Neural networks and learning machines, 3rd edn. Pearson Prentice Hall, New JerseyGoogle Scholar
  18. Kohonen T, Oja E, Simula O, Visa A, Kangas J (1996) Engineering applications of the self-organizing map. Proc IEEE 84(10):1358–1384CrossRefGoogle Scholar
  19. Lamrini B, Lakhal EK, Le Lann MV, Wehenkel L (2011) Data validation and missing data reconstruction using self-organizing map for water treatment. Neural Comput Applic 20:575–588CrossRefGoogle Scholar
  20. Lavenberg K (1944) A method for the solution of certain non-linear problems in least squares. Quart Appl Math 2:164–168Google Scholar
  21. Mallat S (1989) Multiresolution approximation and wavelet orthonormal bases of L2(R). T Am Math Soc 315:69–87Google Scholar
  22. Manov DV, Chang GC, Dickey TD (2004) Methods for reducing biofouling of moored optical sensors. J Atmos Ocean Technol 21(6):958–968CrossRefGoogle Scholar
  23. Marquardt DW (1963) An algorithm for least-squares estimation of nonlinear parameters. J Soc Ind Appl Math 11:431–441CrossRefGoogle Scholar
  24. May R, Dandy G, Maier H (2011) Review of input variable selection methods for artificial neural networks. In: Suzuki K (ed) Artificial neural networks-methodological advances and biomedical application (pp. InTech, New York, pp 19–44Google Scholar
  25. Mulia IE, Harold T, Roopsekhar K, Tkalich P (2013a) Hybrid ANN-GA model for predicting turbidity and chlorophyll-a concentrations. J Hydro Environ Res 7:279–299CrossRefGoogle Scholar
  26. Mulia IE, Asano T, Tkalich P (2013b) Signal decomposition technique to improve data-driven model for sea temperature data series. Proc JSCE 4:70–74Google Scholar
  27. Mwale FD, Adeloye AJ, Rustum R (2012) Infilling of missing rainfall and streamflow data in the Shire River basin, Malawi – A self organizing map approach. Phys Chem Earth A/B/C 50–52:34–43CrossRefGoogle Scholar
  28. Nelson M, Hill T, Remus T, O’Connor M (1999) Time series forecasting using NNs: Should the data be deseasonalized first? J Forecast 18:359–367CrossRefGoogle Scholar
  29. Pairaud IL, Gatti J, Bensoussan N, Verney R, Garreau P (2011) Hydrology and circulation in a coastal area off Marseille: Validation of a nested 3D model with observations. J Mar Syst 88:20–33CrossRefGoogle Scholar
  30. Pang WC, Tkalich P (2003) Modeling tidal and monsoon driven currents in the Singapore Strait. Singap Marit Port J 151–162Google Scholar
  31. Patil K, Deo MC, Ghosh S, Ravidchandran M (2013) Predicting sea surface temperature in the North Indian Ocean with nonlinear autoregressive neural networks. Int J Oceanogr. doi: 10.1155/2013/302479 Google Scholar
  32. Singh KP, Basant A, Malik A, Jain G (2009) Artificial neural network modeling of the river water quality. A case study. Ecol Model 220:888–895CrossRefGoogle Scholar
  33. Srivastava N, Hinston G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958Google Scholar
  34. Sundarambal P, Liong SY, Tkalich P (2008) An ANN application for water quality forecasting. Mar Pollut Bull 56:1586–1597CrossRefGoogle Scholar
  35. Wei S, Song J, Khan NI (2012) Simulating and predicting river discharge time series using a wavelet-neural network hybrid modelling approach. Hydrol Process 26:281–296CrossRefGoogle Scholar
  36. Zhai L, Tang C, Platt T, Sathyendranath S (2011) Ocean response to attenuation of visible light by phytoplankton in the Gulf of St. Lawrence. J Mar Syst 88:285–297CrossRefGoogle Scholar
  37. Zhang GP (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50:159–175CrossRefGoogle Scholar
  38. Zhang GP, Qi M (2005) Neural network forecasting for seasonal and trend time series. Eur J Oper Res 160:501–514CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Iyan E. Mulia
    • 1
  • Toshiyuki Asano
    • 1
  • Pavel Tkalich
    • 2
  1. 1.Department of Ocean and Civil EngineeringKagoshima UniversityKorimotoJapan
  2. 2.Tropical Marine Science InstituteNational University of SingaporeSingaporeSingapore

Personalised recommendations