Regional Frequency Analysis of Annual Maximum Rainfall in Monsoon Region of Pakistan using L-moments

Abstract

Estimation of magnitude and frequency of extreme rainfall has immense importance to make decisions about hydraulic structures like spillways, dikes and dams etc. This research involves the estimation of regional rainfall quantiles of 23 sites using L-moment based index flood regional frequency analysis. Initially, different tests are applied to check the assumptions of independence, stationarity and identical distribution. An L-moment based discordancy measure is used to detect discordant sites. Since in Pakistan, highly elevated area receive more rainfall. On the basis of this characteristic, the study region is divided into three regions which satisfy the L-moment based heterogeneity statistics using Monte Carlo simulations from Kappa distribution. The regional quantile estimates are obtained from GEV, GNO and GLO distributions which are found to be best choices for all three regions based on L-moment ratio diagram, Z-Statistics and average weighted difference values. For robust regional estimates, some accuracy measures are calculated using a simulation study of regional L-moment algorithm. On the basis of relative bias, relative absolute bias and relative RMSE, GNO is found be best robust for regional quantile estimation at lager return periods of 50, 100, 500 and 1000 and GEV at return periods of 1, 2, 5, 10 and 20 for all three regions.

A review: regiopnal frequency analysis of annual maximum rainfall in Monsoon region of pakistan using l-moments

“…Remaining 21 gaged sites were made of 3 homogeneous regions, region 1 having 11 sites, region 2 and 3 each having 5 sites. The three regions satisfied the heterogeneity statistics (Table 4, [20]). L-moment ratio diagram plotted above is depicting the regional average L-C s and L-C k of final three regions.…”

“…A total of 23 gaged stations were included in the study having record lengths from 24 to 60 years ( Figure 1, Shahzadi et al [20]). Assumptions of stationarity, identically and independently distributed were satisfied by Mann-Whitney test, Kendall's tau test and Ljung-Box Q-statistic.…”

“…Assumptions of stationarity, identically and independently distributed were satisfied by Mann-Whitney test, Kendall's tau test and Ljung-Box Q-statistic. Site 17, Multan showed significant autocorrelations (Table 1) (Table 2, [20]). Sites 2 and 20 did not form any homogeneous region with their nearest sites, so they were discarded from analysis.…”

“…Using L-moments regional algorithm, regional growth curves of GEV, GNO and GLO for all regions were estimated for various return periods (Table 8, [20]) plotted here. The growth curves are approximately equal for low return periods but after return period 50, regional quantiles become large from GLO distribution for all three regions.…”

“…A bulk of literature is available on regional frequency analysis of rainfall, e.g. see Section 1 Shahzadi et al [20].…”