DOI QR코드

DOI QR Code

Comparison of Bayesian Methods for Estimating Parameters and Uncertainties of Probability Rainfall Distribution

확률강우분포의 매개변수 및 불확실성 추정을 위한 베이지안 기법의 비교

  • Seo, Youngmin (Department of Constructional and Environmental Engineering, Kyungpook National University) ;
  • Park, Jaeho (Department of Constructional and Environmental Engineering, Kyungpook National University) ;
  • Choi, Yunyoung (Department of Constructional and Environmental Engineering, Kyungpook National University)
  • 서영민 (경북대학교 건설환경공학과) ;
  • 박재호 (경북대학교 건설환경공학과) ;
  • 최윤영 (경북대학교 건설환경공학과)
  • Received : 2018.08.21
  • Accepted : 2018.11.28
  • Published : 2019.01.31

Abstract

This study investigates the performance of four Bayesian methods, Random Walk Metropolis (RWM), Hit-And-Run Metropolis (HARM), Adaptive Mixture Metropolis (AMM), and Population Monte Carlo (PMC), for estimating the parameters and uncertainties of probability rainfall distribution, and the results are compared with those of conventional parameter estimation methods; namely, the Method Of Moment (MOM), Maximum Likelihood Method (MLM), and Probability Weighted Method (PWM). As a result, Bayesian methods yield similar or slightly better results in parameter estimations compared with conventional methods. In particular, PMC can reduce parameter uncertainty greatly compared with RWM, HARM, and AMM methods although the Bayesian methods produce similar results in parameter estimations. Overall, the Bayesian methods produce better accuracy for scale parameters compared with the conventional methods and this characteristic improves the accuracy of probability rainfall. Therefore, Bayesian methods can be effective tools for estimating the parameters and uncertainties of probability rainfall distribution in hydrological practices, flood risk assessment, and decision-making support.

References

  1. Alam, M. A., Farnham, C., Emura, K., 2018, Bayesian modeling of flood frequency analysis in Bangladesh using Hamiltonian Monte Carlo techniques, Water, 10, 900. https://doi.org/10.3390/w10070900
  2. Cappe, O., Guillin, A., Marin, J. M., Robert, C., 2004, Population Monte Carlo, J. Comput. Graph. Stat., 13, 907-929. https://doi.org/10.1198/106186004X12803
  3. Chen, M., Schmeiser, B., 1992, Performance of the Gibbs, hit-and-run and Metropolis samplers, J. Comput. Graph. Stat., 2, 251-272.
  4. Chung, E. S., Kim, S. U., 2013, Bayesian rainfall frequency analysis with extreme value using the informative prior distribution, KSCE J. Civ. Eng., 17, 1502-1514. https://doi.org/10.1007/s12205-013-0189-0
  5. Coles S. G., Tawn J. A., 1996, A Bayesian analysis of extreme rainfall data, J. R. Stat. Soc. C-Appl., 45, 463-478.
  6. Coles, S., Pericchi, L., 2003, Anticipating catastrophes through extreme value modeling, J. R. Stat. Soc. C-Appl., 52, 405-416. https://doi.org/10.1111/1467-9876.00413
  7. Dawson, C. W., Abrahart, R. J., See, L. M., 2007, HydroTest: A web-based toolbox of evaluation metrics for the standardized assessment of hydrological forecasts. Environ., Model. Softw., 22, 1034-1052. https://doi.org/10.1016/j.envsoft.2006.06.008
  8. Gilks, W. R., Roverts, G., 1996, Strategies for improving MCMC, in: Gilks, W. R., Richardson, S., Spiegelhalter, D. (eds.), Markov chain Monte Carlo in practice, Chapman & Hall, Boca Raton, Florida, 89-114.
  9. Isikwue, M. O., Onoja, S. B., Naakaa, D. S., 2015, Classical and Bayesian Markov chain Monte Carlo (MCMC) modeling of extreme rainfall (1979-2014) in Makurdi, Nigeria, Int. J. Water Res. Environ. Eng., 7, 123-131. https://doi.org/10.5897/IJWREE2015.0588
  10. Kim, S. U., Lee, K. S., 2008a, At-site low flow frequency analysis using Bayesian MCMC: I. Theoretical background and construction of prior distribution, J. Korea Water Resour. Assoc., 41, 35-47. https://doi.org/10.3741/JKWRA.2008.41.1.035
  11. Kim, S. U., Lee, K. S., 2008b, Regional low flow frequency analysis using Bayesian multiple regression, J. Korea Water Resour. Assoc., 41, 325-340. https://doi.org/10.3741/JKWRA.2008.41.3.325
  12. Kim, S. U., Lee, K. S., 2008c, Identification of uncertainty in fitting rating curve with Bayesian regression, J. Korea Water Resour. Assoc., 41, 943-958. https://doi.org/10.3741/JKWRA.2008.41.9.943
  13. Kim, S. U., Lee, K. S., Park, Y. J., 2010, Analysis of uncertainty of rainfall frequency analysis including extreme rainfall events, J. Korea Water Resour. Assoc., 43, 337-351. https://doi.org/10.3741/JKWRA.2010.43.4.337
  14. Muller, A., Bacro, J. N., Lang, M., 2008, Bayesian comparison of different rainfall depth-duration-frequency relationships, Stoch. Env. Res. Risk A., 22, 33-46. https://doi.org/10.1007/s00477-006-0095-9
  15. Ragulina, G., Reitan, T., 2017, Generalized extreme value shape parameter and its nature for extreme precipitation using long time series and the Bayesian approach, Hydrolog. Sci. J., 62, 863-879. https://doi.org/10.1080/02626667.2016.1260134
  16. Reis Jr., D. S., 2005, Flood frequency analysis employing Bayesian regional regression and imperfect historical information, Ph. D. Dissertation, Cornell University, New York, USA.
  17. Roberts, G., Rosenthal, J., 2009, Examples of adaptive MCMC, Comput. Stat. Data Anal., 18, 349-367.
  18. Seo, Y. M., 2011, Risk analysis in water resources planning: Flood risk analysis with consideration of rainfall uncertainty, Ph. D. Disseration, Yeungnam University, Gyeongsan, South Korea.
  19. Seo, Y. M., Park, K. B., 2011, Uncertainty analysis for parameters of probability distribution in rainfall frequency analysis by Bayesian MCMC and Metropolis Hastings algorithm, J. Environ. Sci. Int., 20, 329-340. https://doi.org/10.5322/JES.2011.20.3.329
  20. Seo, Y. M., Park, K. B., Kim, S., 2011, Uncertainty analysis of parameters of spatial statistical model using Bayesian method for estimating spatial distribution of probability rainfall, J. Environ. Sci. Int., 20, 1541-1551. https://doi.org/10.5322/JES.2011.20.12.1541
  21. Son, G. T., 2014, Introduction to computational statistics using R, Freedom Academy, Inc.