Saved in:
Bibliographic Details
Main Authors: Cooper, Fenwick C., Nath, Shruti, McRae, Andrew T. T., Antonio, Bobby, Weisheimer, Antje, Palmer, Tim, Gudoshava, Masilin, Kalladath, Nishadh, Amidhun, Ahmed, Kinyua, Jason, Kimani, Hannah, Koros, David, Mwai, Zacharia, Maswi, Christine, Chanzu, Benard, Abebe, Samrawit, Tamene, Bekalu, Kebebe, Bekele, Teshome, Asaminew, Pappenberger, Florian, Chantry, Matthew, Obai, Isaac, Mason, Jesse
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.24525
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917177850855424
author Cooper, Fenwick C.
Nath, Shruti
McRae, Andrew T. T.
Antonio, Bobby
Weisheimer, Antje
Palmer, Tim
Gudoshava, Masilin
Kalladath, Nishadh
Amidhun, Ahmed
Kinyua, Jason
Kimani, Hannah
Koros, David
Mwai, Zacharia
Maswi, Christine
Chanzu, Benard
Abebe, Samrawit
Tamene, Bekalu
Kebebe, Bekele
Teshome, Asaminew
Pappenberger, Florian
Chantry, Matthew
Obai, Isaac
Mason, Jesse
author_facet Cooper, Fenwick C.
Nath, Shruti
McRae, Andrew T. T.
Antonio, Bobby
Weisheimer, Antje
Palmer, Tim
Gudoshava, Masilin
Kalladath, Nishadh
Amidhun, Ahmed
Kinyua, Jason
Kimani, Hannah
Koros, David
Mwai, Zacharia
Maswi, Christine
Chanzu, Benard
Abebe, Samrawit
Tamene, Bekalu
Kebebe, Bekele
Teshome, Asaminew
Pappenberger, Florian
Chantry, Matthew
Obai, Isaac
Mason, Jesse
contents Ensemble forecasting has proven over the years to be a vital tool for predicting extreme or only partially predictable weather events. In particular life-threatening weather events. Many National Meteorological Services in East Africa do not have the computing resources to enable them to run their local area models in full ensemble mode over the full period of the 2 week medium range. As a result, weather users in these countries are not being given sufficient information about weather risk that is needed to make reliable decisions about taking preventative action. Consequently, society in many parts of the world is not as resilient to weather events as they could be. In this paper we test the performance of our forecast system, cGAN, which is the only high-resolution (10 km) ensemble rainfall product that does real-time, probabilistic correction of global forecasts for East Africa. Compared to existing state-of-the-art AI models, our system offers higher spatial resolution. It is cheap to train/run and requires no additional post-processing. It is run on laptops and can generate many thousands of ensemble members at little computational cost (compared with physical local area models). It is ideally suited to Meteorological Services with limited computational facilities.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24525
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rainfall forecasts in daily use over East Africa improved by machine learning
Cooper, Fenwick C.
Nath, Shruti
McRae, Andrew T. T.
Antonio, Bobby
Weisheimer, Antje
Palmer, Tim
Gudoshava, Masilin
Kalladath, Nishadh
Amidhun, Ahmed
Kinyua, Jason
Kimani, Hannah
Koros, David
Mwai, Zacharia
Maswi, Christine
Chanzu, Benard
Abebe, Samrawit
Tamene, Bekalu
Kebebe, Bekele
Teshome, Asaminew
Pappenberger, Florian
Chantry, Matthew
Obai, Isaac
Mason, Jesse
Atmospheric and Oceanic Physics
Ensemble forecasting has proven over the years to be a vital tool for predicting extreme or only partially predictable weather events. In particular life-threatening weather events. Many National Meteorological Services in East Africa do not have the computing resources to enable them to run their local area models in full ensemble mode over the full period of the 2 week medium range. As a result, weather users in these countries are not being given sufficient information about weather risk that is needed to make reliable decisions about taking preventative action. Consequently, society in many parts of the world is not as resilient to weather events as they could be. In this paper we test the performance of our forecast system, cGAN, which is the only high-resolution (10 km) ensemble rainfall product that does real-time, probabilistic correction of global forecasts for East Africa. Compared to existing state-of-the-art AI models, our system offers higher spatial resolution. It is cheap to train/run and requires no additional post-processing. It is run on laptops and can generate many thousands of ensemble members at little computational cost (compared with physical local area models). It is ideally suited to Meteorological Services with limited computational facilities.
title Rainfall forecasts in daily use over East Africa improved by machine learning
topic Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2512.24525