Near real-time estimation of high spatiotemporal resolution rainfall from cloud top properties of the MSG satellite and commercial microwave link rainfall intensities

High spatiotemporal resolution rainfall is needed in predicting flash floods, local climate impact studies and agriculture management. Rainfall estimation techniques like satellites the commercial microwave links (MWL) have independently made significant advancements high estimation. However, their combination for has received little attention, while it could benefit many applications ungauged areas. This study investigated usability of random forest (RF) algorithm trained with MWL Meteosat Second Generation (MSG) based cloud top properties estimating sparsely gauged Kenyan Rift Valley. Our approach retrieved use as predictor variables from rain areas estimated MSG data path average intensities to serve target variable. We validated RF using parameters derived through optimal parameter tuning. The intensity estimates were compared gauge, MWL, Global Precipitation Measurement (GPM) Integrated Multi-satellitE Retrievals GPM (IMERG) European Organisation Exploitation Meteorological Satellites (EUMETSAT) Multisensor Estimate (MPE) evaluate its point spatial perspectives. results can be described good, considering they achieved near real-time, pointing towards a promising alternative on applied data. applicative benefits this technique huge, that growing network and, future, Third (MTG) coverage.