Effect of temporal sampling mismatches between satellite rainfall estimates and rain gauge observations on modelling extreme rainfall in the Upper Awash Basin, Ethiopia

摘要

Matching the temporal sampling of Satellite Rainfall Estimates (SREs) with rain gauge data is a prerequisite for evaluating the accuracy of SREs. However, some of the previous studies have evaluated the performance of SREs without considering the timing of the daily rain gauge observations. Such uncertainties may affect the application of SREs for studying the statistics of rainfall extremes. Therefore, this study aims to assess the effect of temporal sampling mismatch on the frequency analysis of daily rainfall extremes over a mountainous region in Ethiopia, the Upper Awash basin. For this purpose, we consider the 0-hr, 1-hr, 3-hr, 5-hr, and 6-hr temporal mismatches between SREs and gauges, which emerge from the use of different definitions of daily precipitation in these data sources. To represent those mismatches, the sub-daily TRMM 3B42v7 and sub-hourly IMERG v06B SREs are aggregated for different time windows, and their impacts on the estimation of the Metastastical Extreme Value Distribution (MEVD) parameters, and high-quantile extremes are then quantified using the relative error metrics. Results show that the 1-hr and 3-hr temporal discrepancies between SREs and gauges produce a comparable result in reproducing the observed MEVD parameters and high quantiles of daily rainfall. However, we found different results when the temporal mismatch between SREs and gauges increases from 3-hr to 6-hr. For all temporal mismatches, IMERG v06B outperforms TRMM 3B42v7 for estimating the MEVD parameters and high quantiles of daily rainfall. Both SREs provide the best estimation of high-quantile extremes for shorter return periods than the longer ones. Additionally, the uncertainty of the MEVD parameters is substantial in the lowland (Elevation 2000 m) regions of the basin. Overall, the temporal discrepancy between SREs and gauges leads to discrepancies in rainfall statistics. Therefore, more caution is necessary when applying the