Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Postprocessing East African rainfall forecasts using a generative machine learning model

Antonio, Bobby, McRae, Andrew T. T., MacLeod, David ORCID: https://orcid.org/0000-0001-5504-6450, Cooper, Fenwick C., Marsham, John, Aitchison, Laurence, Palmer, Tim N. and Watson, Peter A. G. 2025. Postprocessing East African rainfall forecasts using a generative machine learning model. Journal of Advances in Modeling Earth Systems 17 (3) , e2024MS004796. 10.1029/2024ms004796

[thumbnail of J Adv Model Earth Syst - 2025 - Antonio - Postprocessing East African Rainfall Forecasts Using a Generative Machine.pdf] PDF - Published Version
Download (12MB)
License URL: http://creativecommons.org/licenses/by/4.0/
License Start date: 6 March 2025

Abstract

AbstractExisting 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 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 percentile . 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.

Item Type: Article
Date Type: Published Online
Status: Published
Schools: Schools > Earth and Environmental Sciences
Additional Information: License information from Publisher: LICENSE 1: URL: http://creativecommons.org/licenses/by/4.0/, Start Date: 2025-03-06
Publisher: Wiley
ISSN: 1942-2466
Date of First Compliant Deposit: 21 March 2025
Date of Acceptance: 30 January 2025
Last Modified: 21 Mar 2025 10:31
URI: https://orca.cardiff.ac.uk/id/eprint/177066

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics