Skip to main content
SpringerLink
Log in

Flood outlier detection using PCA and effect of how to deal with them in regional flood frequency analysis via L-moment method

  • Water Resources and the Regime of Water Bodies
  • Published:
Water Resources Aims and scope Submit manuscript

Abstract

Regional flood frequency analysis (RFFA) is the major instrument for studying of the flood regime at locations where little or no information is available. Outliers have an important effect on the flood frequency analysis and the existence of them in hydrologic data sets affects the regional flood frequency analysis. Outlier analysis is composed of two steps, outlier detection and outlier treatment. After detecting outlier, one should determine how to deal with it. This has the particular role in outlier analysis. In this research, flood frequency analysis was done for the Dez River basin located in south-western Iran. First of all, the studied basin was separated in two hydrological homogeneous regions according their physiographical, climatic and vegetation characteristics. Then, outliers were detected in each region by using Principal component analysis method (PCA). We considered two approaches to survey and compare the effect of the outliers in RFFA. In the first approach outliers were retained, while in the second approach frequency analysis was done after removal the years which contain outliers. Result of RFFA via L-moment method showed that the estimated quantiles in two approaches, particularly in highly return period have a lot of difference. These results illustrate that dealing with the outliers in flood frequency analysis is of the special importance.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Barnett, V. and Lewis, T., Outliers in Statistical Data, Chichester, N.Y.: John Wiley, 1978, 3rd edition.

    Google Scholar 

  2. Cunnane, C., Review of statistical methods for flood frequency estimation, in Hydrologic Frequency Modeling, Singh, V.P., Ed., 1987, pp. 49–95.

    Chapter  Google Scholar 

  3. Dalrymple, T., Flood frequency analysis, US Geol. Survey Water Supply Paper, 1960, 543A.

    Google Scholar 

  4. Dixon, W.J., Analysis of extreme values, Annals Math. Statistics, 1950, vol. 21, pp. 488–506.

    Article  Google Scholar 

  5. Grubbs, F.E. and Beck, G., Extension of sample sizes and percentage points for significance tests of outlying observations, Technometrics, 1972, vol. 4, no. 14, pp. 847–853.

    Article  Google Scholar 

  6. Hosking, J.R.M. and Wallis, J.R., Some statistics useful in regional frequency analysis, J. Water Resour. Res., 1993, vol. 20, pp. 271–281.

    Article  Google Scholar 

  7. Hosking, J.K.M. and Wallis, J.R., Regional frequency analysis, an approach based on L-moments, Cambridge Univ. Press, 1997.

    Book  Google Scholar 

  8. Iglewicz, B. and Hoaglin, D.C., How to detect and handle outliers, American Soc. for Quality, Milwaukee, WI, 1993.

    Google Scholar 

  9. Jackson, D. and Chen, Y., Robust principal component analysis and outlier detection with ecological data, Environ., 2004, vol. 15, pp. 129–139.

    Google Scholar 

  10. Jackson, J.E., Quality control methods for several related variables, Technometrics, 1959, vol. 1, pp. 359–377.

    Article  Google Scholar 

  11. Johnson, R.A. and Wichern, D.W., Applied Multivariate Statistical Analysis, Englewood Cliffs, USA: Prentice-Hall Inc., 1982.

    Google Scholar 

  12. Kottegoda, N.T., Investigation of outliers in annual maximum flow series, J. Hydrol., 1984, vol. 72, nos. 1–2, pp. 105–137.

    Article  Google Scholar 

  13. Kumar, R., Chatterjee, C., Kumar, S., Lohani, A.K., and Singh, R.D., Development of regional flood frequency relationships using L-moments for middle Ganga plains subzone 1(f) of India, Water Resour. Management, 2003, vol. 17, pp. 243–257.

    Article  Google Scholar 

  14. Mahalanobis, P.C., On the generalized distance in statistics, Proc. National Inst. Sci. India, 1936, vol. 2, no. 1, pp. 49–55.

    Google Scholar 

  15. Martel, B., Quadra, T.B.M.J., Barbet, M., Bruneau, P., Latraverse, M., and Kamali Nazhad, M., Regional frequency analysis of autumnal floods in the province of Quebec, Canada, Nat Hazards, 2011, vol. 59, pp. 681–698.

    Article  Google Scholar 

  16. Pearson, C.P., New Zealand regional flood frequency analysis using L-moments, J. Hydrol., 1991, vol. 30, no. 2, pp. 53–63.

    Google Scholar 

  17. Rousseeuw, P.J. and Leroy, A.M., Robust Regression and Outlier Detection, N.Y.: John Wiley and Sons, 1987.

    Book  Google Scholar 

  18. Siyi, Hu., Problem with outliers test methods in flood frequency analysis, J. Hydrol., 1987, vol. 96, pp. 375–383.

    Article  Google Scholar 

  19. Spencer, C.S. and McCuen, R.H., Detection of outliers in pearson type iii data, J. Hydrol. Eng., vol. 1, pp. 2–10, 1996.

    Article  Google Scholar 

  20. Wallis, J.R., Regional frequency studies using L-moments, IBM Res. Rep., 1989, p. 17.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Civil Engineering Department, Roudehen Branch, Islamic Azad University, Roudehen, Iran

    A. P. Sarraf

Authors
  1. A. P. Sarraf
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to A. P. Sarraf.

Additional information

The article is published in the original.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sarraf, A.P. Flood outlier detection using PCA and effect of how to deal with them in regional flood frequency analysis via L-moment method. Water Resour 42, 448–459 (2015). https://doi.org/10.1134/S0097807815040132

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S0097807815040132

Keywords

Search

Navigation