Dam Inflow Time Series Regression Models Minimising Loss of Hydropower Opportunities

  • Yasuno TakatoEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11154)


Recently, anomalies in dam inflows have occurred in Japan and around the world. Owing to the sudden and extreme characteristics of rainfall events, it is very difficult to predict dam inflows and to operate dam outflows. Hence, dam operators prefer faster and more accurate methods to support decision-making to optimise hydroelectric operation. This paper proposes a machine learning method to predict dam inflows. It uses data from rain gauges in the dam regions and upstream river level sensors from previous three hours and predicts the dam inflow in the next three hours. The method can predict the time of rise to the peak, the maximum level at the peak, and the hydrograph shapes to estimate the volume. The paper presents several experiments applied to inflow time series data for 10 years from the Kanto region in Japan, containing 55 floods events and 20,627 time stamped dam in-flow points measured at 15-min intervals. It compares the performance of four regression prediction models: generalised linear model, additive generalised linear model, regression tree and gradient boosting machine and discusses the results.


Dam inflow time series Upstream river sensor Time series regression Hydropower opportunities loss 



I wish to thank the DaMEMO committee and referees for their time and valuable comments. I also wish to thank Yachiyo Engineering Co., Ltd. for various support based on big data and AI project outcomes since 2012. I am also grateful to Mizuno Takashi for providing development opportunities and Amakata Masazumi for providing domain knowledge in river and dam engineering.


  1. 1.
    UN News Centre: EM-DAT International Disaster Database (2016). &
  2. 2.
    Munich, R.: Geo risks research: NatCatSERVICE. Accessed 31 December 2017
  3. 3.
    Japan floods: city of Joso hit by ‘unprecedented’ rain BBC, 10 September 2016 Accessed 31 December 2017
  4. 4.
    Othman, F., et al.: Reservoir inflow forecasting using artificial neural network. Int. J. Phys. Sci. 6(3), 434–440 (2011)Google Scholar
  5. 5.
    Attygalle, D., et al.: Ensemble forecast for monthly reservoir inflow: a dynamic neural network approach (2016).
  6. 6.
    Shortridge, J.E., et al.: Machine learning methods for empirical streamflow simulation: a comparison of model accuracy, interpretability and uncertainty in seasonal watersheds. Hydrol. Earth Syst. Sci. 20, 2611–2628 (2016)CrossRefGoogle Scholar
  7. 7.
    Li, B., et al.: Comparison of random forests and other statistical methods for the prediction of lake water level: a case study of the Poyang Lake in China. Hydrol Res. 47(S1), 69–83 (2016)CrossRefGoogle Scholar
  8. 8.
    Yang, J.-H., et al.: A time-series water level forecasting model based on imputation and variable selection method. Comput. Intell. Neurosci. 1–11 (2017)Google Scholar
  9. 9.
    Moeeni, H., et al.: Monthly reservoir inflow forecasting using a new hybrid sARIMA genetic programming approach. J. Earth Syst. Sci. 126, 18 (2017)CrossRefGoogle Scholar
  10. 10.
    Hofmann, M., Klinkenberg, R.: RAPID MINER: Data Mining Use Cases and Business Analytics Applications. Data Mining and knowledge Discovery Series. CRC Press, Cambridge (2014)Google Scholar
  11. 11.
    Kotu, V., Deshpande, B.: Predictive Analytics and Data Mining: Concepts and Practice with Rapidminer. Morgan Kaufmann, New York (2015)Google Scholar
  12. 12.
    International Hydropower Association (IHA): cost-benefit and economic performance. Hydropower Sustainability Assessment Protocol. Accessed 16 February 2018Google Scholar
  13. 13.
    Mattmann, M., et al.: Hydropower externalities: a meta-analysis. Energy Econ. 57, 66–77 (2016)CrossRefGoogle Scholar
  14. 14.
    International Renewable Energy Agency (IRENA): renewable energy technologies: cost analysis series. Hydropower vol. 1: Power Sector (2012)Google Scholar
  15. 15.
    Domingos, P.: MetaCost: A General framework for making classifiers cost-sensitive. In: ACM Conference on Knowledge Discovery in Databases, pp. 165–174 (1999).
  16. 16.
    Ling, C.X., et al.: Cost-sensitive learning and the class imbalance problem. In: Sammut, C. (ed.) Encyclopedia of machine learning. Springer, Berlin (2008)Google Scholar
  17. 17.
    Pavlyshenko, B.M.: Linear, machine learning and probabilistic approaches for time series analysis. In: IEEE International Conference on Data Stream Mining and Processing (2016)Google Scholar
  18. 18.
    Wedderburn, R.W.M.: Quasi-likelihood functions, generalized linear models and the Gauss–Newton method. Biometrika 61(3), 439–447 (1974)MathSciNetzbMATHGoogle Scholar
  19. 19.
    McCullagh, P., Nelder, J.: Generalized Linear Models. Monographs on Statistics and Applied Probability. Chapman & Hall, London (1983)CrossRefGoogle Scholar
  20. 20.
    Hardin, J.W., Hilbe, J.M.: Generalized Linear Models and Extensions, 3rd edn. Stata Press, College Station (2012)zbMATHGoogle Scholar
  21. 21.
    Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning; Data Mining, Inference and Prediction, 2nd edn. Springer, Berlin (2009)zbMATHGoogle Scholar
  22. 22.
    Hastie, T., Tibshirani, R.: Generalize additive models. Stat. Sci. 1, 297–318 (1986)CrossRefGoogle Scholar
  23. 23.
    Brieman, L., Friedman, J. et al.: Classification and Regression Trees. Wadsworth (1984)Google Scholar
  24. 24.
    Ripley, B.D.: Pattern Recognition and Neural Networks. Cambridge University Press, Cambridge (1996)CrossRefGoogle Scholar
  25. 25.
    Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting (with discussion). Ann. Stat. 28, 307–337 (2000)CrossRefGoogle Scholar
  26. 26.
    Friedman, J.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29(5), 1189–1232 (2001)MathSciNetCrossRefGoogle Scholar
  27. 27.
    Scholkopf, B., Freund, Y.: Boosting: Foundations and Algorithms. MIT Press, Cambridge (2012)zbMATHGoogle Scholar
  28. 28.
    Efron, B., Hastie, T.: Computer Age Statistical Inference: Algorithms, Evidence and Data Science. Cambridge University Press, Cambridge (2016)CrossRefGoogle Scholar
  29. 29.
    Yee, T.W., Wild, C.J.: Vector generalized additive models. J. R. Stat. Soc. Ser. B 58(3), 481–493 (1996)MathSciNetzbMATHGoogle Scholar
  30. 30.
    Amer, M., Goldstein, M., et al.: Enhancing one-class support vector machines for unsupervised anomaly detection. In: 11th ODD’2013, Chicago (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Yachiyo Engineering Co., LtdTokyoJapan

Personalised recommendations