IMERG BraMaL: An improved gridded monthly rainfall product for Brazil based on satellite-based IMERG estimates and machine learning techniques

Precipitation is one of the main components of the hydrological cycle and its precise quantification is fundamental to providing information for the understanding and prediction of physical processes. Precipitation observations based on ground-based devices (manual and automatic rain gauges) are highly accurate but have limited spatial coverage. On the other hand, remote sensing products cover large areas but with lower accuracy. In this context, this study aims to provide a more accurate monthly precipitation estimating product, with lower latency than other products but without directly relying on field data. The methodology consists of applying a machine learning method (k-nearest neighbours algorithm) to satellite-based remote sensing data (IMERG Early Run product) and re-analysis-based (MERRA-2) variables with a particular connection to precipitation. The method was applied over the Brazilian territory, which features a large range of precipitation regimes. This methodology resulted in the development of an adjusted IMERG product (IMERG BraMaL). Compared with the original IMERG products (Early Run and Final Run), IMERG BraMaL has improved the evaluated metrics between ground-based and satellite data in almost all analyses. For instance, KGE (Kling-Gupta efficiency) went from lower values (0.70 and 0.82 for Early and Late Run, respectively) to values above 0.86 in the IMERG BraMaL. The adjusted product also presented superior performance statistics compared with other global precipitation products (CHIRPS, PERSIANN-CDR, and MSWEP). The main advantages of IMERG BraMaL compared with IMERG Final Run are (i) much faster availability to the end-users; (ii) non-dependency on any field data, allowing its application in areas where rain gauge data is unavailable or of low quality; (iii) the non-relationship of errors to local features; and (iv) the much-improved estimations in regions in Brazil where, historically, satellite-based products usually underestimate the observed data.