Documentation

Summary

This product, developed at Chalmers University of Technology (Sweden), provides probabilistic retrievals of precipitation over Africa by an artificial neural network. The network consists of a fully convolutional, quantile regression neural network, trained and evaluated using nearly four years of collocations of SEVIRI level 1.5 data and the GPM DPR and GMI Combined Precipitation L2B. The network infers the precipitation probability distribution for each pixel in SEVIRI image, using all thermal infrared channels and a satellite angle. This enables retrievals independent of the time of day.

Note: We no longer offer a continuous stream of retrievals, but you can implement your own using the code at GitHub.

Data access

We are offering many Rain over Africa retrievals via the Registry of Open Data on AWS at the following address: https://registry.opendata.aws/roa.

Article

Amell, A., Hee, L., Pfreundschuh, S., & Eriksson, P. (2025). Probabilistic near-real-time retrievals of Rain over Africa using deep learning. Journal of Geophysical Research: Atmospheres, 130, e2025JD044595. https://doi.org/10.1029/2025JD044595

Code

The code for executing Rain over Africa retrievals is available on GitHub.