Quantifying predictive uncertainty in satellite precipitation data correction using ensemble learning

We present the first ensemble learning methods for quantifying predictive uncertainty in satellite precipitation data correction, as well as the large-scale comparison of these methods. Ensemble learning was performed by combining in multiple ways a variety of machine learning algorithms that are particularly suited for the task of interest. Monthly precipitation data from across the contiguous United States supported the comparison, which predominantly relied on skill scores and referred to the ability of the ensemble learning methods in delivering predictive quantiles at many levels. The results allow the ordering from the best to the worst of the ensemble learning methods. Acknowledgements: The research project was supported by the Hellenic Foundation for Research and Innovation (H.F.R.I.) under the “3rd Call for H.F.R.I. Research Projects to support Post-Doctoral Researchers” (Project Number: 7368).