Regionalization of Rainfall Characteristics in Semiarid Botswana Using Gridded Data and L-Moments

The monthly CHIRPS ver. 2 gridded rainfall dataset from 1981 to 2016 was employed to analyze distinct precipitation variability patterns and regimes in semi-arid Botswana. An S-mode eigen analysis was performed on the correlation matrix of the rainfall data to extract principal components. The principal component scores (pc-scores) were further rotated using the Varimax eigen analysis method to yield unique precipitation patterns. The rotated pc-scores indicated three separate sub-regions displaying varying precipitation patterns over time. The application of non-hierarchal clustering (K-means) on the pc-scores identified four distinct zones characterized by unique rainfall patterns. A regional frequency study of rainfall in the sub-regions was performed using L-moments. Probabilistic analysis was utilized to model annual rainfall using six common regional frequency analysis probability distribution functions (pdfs): Pearson Type 3 (PE III); three-parameter Weibull; generalized; extreme value (GEV), normal (GNO), logistic (GLO), and Pareto (GPA). The pdfs that demonstrated the optimal correspondence were determined by the goodness-of-fit test, utilizing the Z-statistic. Each cluster displayed unique pdfs and goodness-of-fit pdfs, with the GLO, GEV, GNO, and Weibull offering the most precise representations.