Browse > Article
http://dx.doi.org/10.9765/KSCOE.2020.32.5.322

Outliers and Level Shift Detection of the Mean-sea Level, Extreme Highest and Lowest Tide Level Data  

Lee, Gi-Seop (UST, KIOST School, University of Science and Technology)
Cho, Hong-Yeon (Ocean Big Data Center, Korea Institute of Ocean Science and Technology)
Publication Information
Journal of Korean Society of Coastal and Ocean Engineers / v.32, no.5, 2020 , pp. 322-330 More about this Journal
Abstract
Modeling for outliers in time series was carried out using the MSL and extreme high, low tide levels (EHL, HLL) data set in the Busan and Mokpo stations. The time-series model is seasonal ARIMA model including the components of the AO (additive outliers) and LS (level shift). The optimal model was selected based on the AIC value and the model parameters were estimated using the 'tso' function (in 'tsoutliers' package of R). The main results by the model application, i.e.. outliers and level shift detections, are as follows. (1) The two AO are detected in the Busan monthly EHL data and the AO magnitudes were estimated to 65.5 cm (by typhoon MAEMI) and 29.5 cm (by typhoon SANBA), respectively. (2) The one level shift in 1983 is detected in Mokpo monthly MSL data, and the LS magnitude was estimated to 21.2 cm by the Youngsan River tidal estuary barrier construction. On the other hand, the RMS errors are computed about 1.95 cm (MSL), 5.11 cm (EHL), and 6.50 cm (ELL) in Busan station, and about 2.10 cm (MSL), 11.80 cm (EHL), and 9.14 cm (ELL) in Mokpo station, respectively.
Keywords
outlier model; additive outliers; level shifts; MSL; extreme high and low tide levels (EHL, ELL);
Citations & Related Records
Times Cited By KSCI : 5  (Citation Analysis)
연도 인용수 순위
1 Box, G.E., Jenkins, G.M. and Reinsel, G.C. (2008). Time Series Analysis Forecasting and Control, Fourth Edition, Chap. 9, John Wiley & Sons.
2 Chen, C. and Liu, L.M. (1993). Joint estimation of model parameters and outlier effects in time series. J. of American Statistical Association (JASA), 88(Issue. 121), 284-297.
3 Cho, H.Y., Jeong, S.T. and Lee, U.J. (2020). Spatial correlation analysis of the mean sea level data sets in the coastal seas. Korea. J. of KSCOE, 32(1), 85-93 (in Korean).
4 Cho, H.Y., Lee, G.S. and Ahn, S.M. (2016). Impact of outliers on the statistical measures of the environmental monitoring data in Busan coastal sea. Ocean and Polar Research, 38(2), 149-159 (in Korean).   DOI
5 Davison, A.C. and Hinkley, D.V. (1997), Bootstrap Methods and Their Application. Cambridge University Press.
6 Hyndman, R.J. and Khandakar, Y. (2008). Automatic time series forecasting: the forecast package for R. Journal of Statistical Software, 26(3).
7 Lopez-de-Lacalle, J. (2019). tsoutliers: Detection of Outliers in Time Series. R package version 0.6-8. https://CRAN.R-project.org/package=tsoutliers.
8 Jung, B.S., Lee, O.J., Kim, K.M. and Kim, S.D. (2018). Non-stationary frequency analysis of extreme sea level using POT approach. J. of Korean Society of Hazard Mitigation, 18(7), 631-638 (in Korean).   DOI
9 Kang, J.W. and Moon, S.R. (2000). Frequency analysis of extreme high water level at Mokpo Harbor considering tidal environment changes. J. of KSCOE, 12(4), 203-209 (in Korean).
10 Korea Hydrographic and Oceanographic Administration, Korea Ocean Observing And Forcecating System. http://www.khoa.go.kr/oceangrid/koofs/kor/tide/tide.do Accessed 2020-09-22.
11 Mann, H.B. (1945). Nonparametric tests against trend. Econometrica, 13, 245-259.   DOI
12 McLeod, A.I. (2011). Kendall: Kendall rank correlation and Mann-Kendall trend test. R package version 2.2. https://CRAN.R-project.org/package=Kendall.
13 Moritz, S. and Bartz-Beielstein, T. (2017). imputeTS: time series missing value imputation in R. The R Journal, 9(1), 207.   DOI
14 Tsay, R.S. (1988). Outliers, Level shifts, and Variance changes in time series. J. of Forecasting, 7, 1-20.   DOI