| Popis: |
Abstract Monthly precipitation data from 58 synoptic stations throughout Botswana, spanning 1981–2016, were used in this study. The data were examined using multivariate analysis to determine regions exhibiting distinct precipitation variability patterns and regimes. To accomplish this, the T-mode of principal component analysis was applied to the correlation matrix of the data. Based on the maximum loading values of the rotational principal component scores, the T-mode indicated three separate subregions with varying precipitation patterns over time. Four clusters with distinct rainfall patterns were identified when cluster analysis was performed on the principal component scores. An assessment of the homogeneity of the clusters was performed using L-moment’s heterogeneity measure (H). Statistical analysis was employed to model annual rainfall data using five commonly used rainfall analysis probability distribution functions: normal, lognormal, gamma, Weibull, and Gumbel. The probability distributions with the greatest fit were determined based on the maximum overall score, which was calculated by adding the individual point scores of three chosen goodness-of-fit tests. Each cluster exhibited distinct probability distribution functions, with the gamma, Gumbel, lognormal, and Weibull distributions providing the most accurate descriptions. |
Full text from SpringerLink