Postprocessing East African Rainfall Forecasts Using a Generative Machine Learning Model

Abstract Existing weather models are known to have poor skill at forecasting rainfall over East Africa. Improved forecasts could reduce the effects of extreme weather events and provide significant socioeconomic benefits to the region. We present a novel machine learning (ML)‐based method to improve...

Full description

Saved in:
Bibliographic Details
Main Authors: Bobby Antonio, Andrew T. T. McRae, David MacLeod, Fenwick C. Cooper, John Marsham, Laurence Aitchison, Tim N. Palmer, Peter A. G. Watson
Format: Article
Language:English
Published: American Geophysical Union (AGU) 2025-03-01
Series:Journal of Advances in Modeling Earth Systems
Subjects:
Online Access:https://doi.org/10.1029/2024MS004796
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850047500820414464
author Bobby Antonio
Andrew T. T. McRae
David MacLeod
Fenwick C. Cooper
John Marsham
Laurence Aitchison
Tim N. Palmer
Peter A. G. Watson
author_facet Bobby Antonio
Andrew T. T. McRae
David MacLeod
Fenwick C. Cooper
John Marsham
Laurence Aitchison
Tim N. Palmer
Peter A. G. Watson
author_sort Bobby Antonio
collection DOAJ
description Abstract Existing weather models are known to have poor skill at forecasting rainfall over East Africa. Improved forecasts could reduce the effects of extreme weather events and provide significant socioeconomic benefits to the region. We present a novel machine learning (ML)‐based method to improve precipitation forecasts in East Africa, using postprocessing based on a conditional generative adversarial network (cGAN). This addresses the challenge of realistically representing tropical rainfall, where convection dominates and is poorly simulated in conventional global forecast models. We postprocess hourly forecasts made by the European Centre for Medium‐Range Weather Forecasts Integrated Forecast System at 6–18 hr lead times, at 0.1° resolution. We combine the cGAN predictions with a novel neighborhood version of quantile mapping, to integrate the strengths of ML and conventional postprocessing. Our results indicate that the cGAN substantially improves the diurnal cycle of rainfall, and improves predictions up to the 99.9th percentile (∼10mm/hr). This improvement extends to the March–May 2018 season, which had extremely high rainfall, indicating that the approach has some ability to generalize to more extreme conditions. We explore the potential for the cGAN to produce probabilistic forecasts and find that the spread of this ensemble broadly reflects the predictability of the observations, but is also characterized by a mixture of under‐ and over‐dispersion. Overall our results demonstrate how the strengths of ML and conventional postprocessing methods can be combined, and illuminate what benefits ML approaches can bring to this region.
format Article
id doaj-art-9acb1e64d748435c8ec11b9308416fad
institution DOAJ
issn 1942-2466
language English
publishDate 2025-03-01
publisher American Geophysical Union (AGU)
record_format Article
series Journal of Advances in Modeling Earth Systems
spelling doaj-art-9acb1e64d748435c8ec11b9308416fad2025-08-20T02:54:12ZengAmerican Geophysical Union (AGU)Journal of Advances in Modeling Earth Systems1942-24662025-03-01173n/an/a10.1029/2024MS004796Postprocessing East African Rainfall Forecasts Using a Generative Machine Learning ModelBobby Antonio0Andrew T. T. McRae1David MacLeod2Fenwick C. Cooper3John Marsham4Laurence Aitchison5Tim N. Palmer6Peter A. G. Watson7Department of Physics University of Oxford Oxford UKDepartment of Physics University of Oxford Oxford UKSchool of Earth and Environmental Sciences University of Cardiff Cardiff UKDepartment of Physics University of Oxford Oxford UKSchool of Earth and Environment University of Leeds Leeds UKMachine Learning and Computational Neuroscience Unit University of Bristol Bristol UKDepartment of Physics University of Oxford Oxford UKSchool of Geographical Sciences University of Bristol Bristol UKAbstract Existing weather models are known to have poor skill at forecasting rainfall over East Africa. Improved forecasts could reduce the effects of extreme weather events and provide significant socioeconomic benefits to the region. We present a novel machine learning (ML)‐based method to improve precipitation forecasts in East Africa, using postprocessing based on a conditional generative adversarial network (cGAN). This addresses the challenge of realistically representing tropical rainfall, where convection dominates and is poorly simulated in conventional global forecast models. We postprocess hourly forecasts made by the European Centre for Medium‐Range Weather Forecasts Integrated Forecast System at 6–18 hr lead times, at 0.1° resolution. We combine the cGAN predictions with a novel neighborhood version of quantile mapping, to integrate the strengths of ML and conventional postprocessing. Our results indicate that the cGAN substantially improves the diurnal cycle of rainfall, and improves predictions up to the 99.9th percentile (∼10mm/hr). This improvement extends to the March–May 2018 season, which had extremely high rainfall, indicating that the approach has some ability to generalize to more extreme conditions. We explore the potential for the cGAN to produce probabilistic forecasts and find that the spread of this ensemble broadly reflects the predictability of the observations, but is also characterized by a mixture of under‐ and over‐dispersion. Overall our results demonstrate how the strengths of ML and conventional postprocessing methods can be combined, and illuminate what benefits ML approaches can bring to this region.https://doi.org/10.1029/2024MS004796machine learningpostprocessingprecipitationEast Africaforecastingtropical
spellingShingle Bobby Antonio
Andrew T. T. McRae
David MacLeod
Fenwick C. Cooper
John Marsham
Laurence Aitchison
Tim N. Palmer
Peter A. G. Watson
Postprocessing East African Rainfall Forecasts Using a Generative Machine Learning Model
Journal of Advances in Modeling Earth Systems
machine learning
postprocessing
precipitation
East Africa
forecasting
tropical
title Postprocessing East African Rainfall Forecasts Using a Generative Machine Learning Model
title_full Postprocessing East African Rainfall Forecasts Using a Generative Machine Learning Model
title_fullStr Postprocessing East African Rainfall Forecasts Using a Generative Machine Learning Model
title_full_unstemmed Postprocessing East African Rainfall Forecasts Using a Generative Machine Learning Model
title_short Postprocessing East African Rainfall Forecasts Using a Generative Machine Learning Model
title_sort postprocessing east african rainfall forecasts using a generative machine learning model
topic machine learning
postprocessing
precipitation
East Africa
forecasting
tropical
url https://doi.org/10.1029/2024MS004796
work_keys_str_mv AT bobbyantonio postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel
AT andrewttmcrae postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel
AT davidmacleod postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel
AT fenwickccooper postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel
AT johnmarsham postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel
AT laurenceaitchison postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel
AT timnpalmer postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel
AT peteragwatson postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel