Application of Machine Learning and Remote Sensing for Gap-filling Daily Precipitation Data of a Sparsely Gauged Basin in East Africa

This work is supported by the University of Oulu, Finland. Open Access funding provided by University of Oulu including Oulu University Hospital. Open Access funding provided by University of Oulu including Oulu University Hospital.

The online version contains supplementary material available at https://doi. org/10.1007/s40710-023-00625-y. y Precipitation products data were downloaded through Google Earth Engine Java Script API (Gorelick et al. 2017; https://earthengine.google.com/, Assessed on https://developers.google.com/s/results/ earth-engine/datasets?q=precipitaiton&text=precipitaiton). Daily in-situ precipitation data are accessible upon request from Tanzania Ministry of Energy (https://www.nishati.go.tz/, accessed by personal contact) and MERRA-2 data were obtained from NASA website (https://gmao.gsfc.nasa.gov/reanalysis/MERRA-2/, Assessed on https://developers.google.com/s/results/earth-engine/datasets?q=MERRA2&text=MERRA2). All figures were made with Matplotlib (Caswell et al. 2020; Hunter 2007), seaborn (Waskom et al. 2017), and MATLAB (2019).