A Binned Triple Collocation for Estimating Regime-Dependent Uncertainties of Precipitation
Abstract
Triple collocation (TC)-based methods have become popular to estimate the uncertainty of many geophysical variables retrieved from satellite observations. The true advantage of these methods is that no ground-based truth is required and they can thus be applied on a global scale. So far, the TC-based methods have been limited to estimate the STandard Deviation (STD) at grid scale. These estimates represent an overall STD error for the precipitation products over each grid. Such information is useful to investigate sources of errors such as topography or surface properties, but as “static” information, it is limited and cannot represent precipitation error for a particular time step. Regime-dependent uncertainties of the satellite products are mandatory to better assess their quality and combine them a posteriori . In this letter, a simple and easy-to-implement method is introduced to estimate regime-dependent STD error of precipitation with the TC framework. Instead of considering collocation at grid scale, the method relies on clustering to distinguish various precipitation regimes. The method then estimates the corresponding STD errors of the three precipitation datasets for each one of the bins (i.e., clusters). These regime-dependent STDs offer a temporal as well as a spatial description of the error statistics. Tests are conducted for multisource precipitation estimates over Europe.
Not Available