Abstract:Taking the daily average discharge of Lishi (2) station in the Wujiang river basin for an example, two flood frequency analysis models, respectively based on peaks-over-threshold (POT) and annual maximum series (AMS), are compared. POT model has better flexibility describing floods and the flood generating process than AMS model; thus is suitable for flood frequency analysis under changing environment. Threshold selection approaches are applied to choose the threshold value, which is tested by the relationship of estimated results of parameters of the POT model and designed floods with changing thresholds afterwards. The POT samples are fitted by the generalized Pareto (GP) distribution with a Poisson model for arrival. Compare POT model based on the GP distribution and AMS model based on the P-III distribution and discuss whether the frequent occurrence of large return period flood is influenced by undue frequency analysis method(the large return period flood-prone by the undue influenced of the frequency analysis). The results show that, threshold selected by combined approaches is able to ensure the sample independence and stability of the POT model. When estimating the designed flood peak of large return period, result estimated by the AMS model based on P-III distribution is smaller than the POT model based on GP distribution, the 100-year flood is estimated that the results of differences greater than 6%, visible AMS model underestimate of the phenomenon of large return period designed flood peak, which is one of the reasons of the frequent occurrence of large return period floods in recent years.

No abstract