Exploring rainfall variabilities using statistical functional data analysis

Abstract Functional data analysis (FDA) has been widely applied in various scientific fields, including climatological, hydrological, environmental, and biomedical. The flexibility of the FDA incorporating temporal elements into statistical makes method highly demanded compared to conventional approach. This study introduces methods investigate variations patterns rainfall throughout Peninsular Malaysia, which includes 16 rain gauge stations Malaysia from 1999 2019. A descriptive statistic functional depicted mean variation curve over time, while principal component measured variability curve. According findings, first second components accounted for 87.4% all variations. was characterised by eastern region during northeast monsoon since highest observed November January. On other hand, impacted inter-monsoon season were best described component. Based on factor scores derived component, those with comparable features then clustered. Overall, results showed that pattern is strongly influenced their geographical topographical seasonal effect.