Postprocessing East African rainfall forecasts using a generative machine learning model
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 based method to improve precipitation...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Wiley
2025
|
| _version_ | 1824459054576041984 |
|---|---|
| author | Antonio, RA McRae, ATT McLeod, D Cooper, F Marsham, J Aitchison, L Palmer, TN Watson, PAG |
| author_facet | Antonio, RA McRae, ATT McLeod, D Cooper, F Marsham, J Aitchison, L Palmer, TN Watson, PAG |
| author_sort | Antonio, RA |
| collection | OXFORD |
| description | 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 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 6-18h lead times, at 0.1° resolution. We combine the cGAN predictions with a novel neighbourhood version of quantile mapping, to integrate the strengths of machine learning 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 2018 March–May season, which had extremely high rainfall, indicating that the approach has some ability to generalise 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 characterised by a mixture of under- and overdispersion. Overall our results demonstrate how the strengths of machine learning and conventional postprocessing methods can be combined, and illuminate what benefits ma38 chine learning approaches can bring to this region.
|
| first_indexed | 2025-02-19T04:35:41Z |
| format | Journal article |
| id | oxford-uuid:00b3beeb-c87a-4740-ae88-6c77b6785e97 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-02-19T04:35:41Z |
| publishDate | 2025 |
| publisher | Wiley |
| record_format | dspace |
| spelling | oxford-uuid:00b3beeb-c87a-4740-ae88-6c77b6785e972025-01-31T12:34:51ZPostprocessing East African rainfall forecasts using a generative machine learning modelJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:00b3beeb-c87a-4740-ae88-6c77b6785e97EnglishSymplectic ElementsWiley2025Antonio, RAMcRae, ATTMcLeod, DCooper, FMarsham, JAitchison, LPalmer, TNWatson, PAGExisting 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 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 6-18h lead times, at 0.1° resolution. We combine the cGAN predictions with a novel neighbourhood version of quantile mapping, to integrate the strengths of machine learning 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 2018 March–May season, which had extremely high rainfall, indicating that the approach has some ability to generalise 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 characterised by a mixture of under- and overdispersion. Overall our results demonstrate how the strengths of machine learning and conventional postprocessing methods can be combined, and illuminate what benefits ma38 chine learning approaches can bring to this region. |
| spellingShingle | Antonio, RA McRae, ATT McLeod, D Cooper, F Marsham, J Aitchison, L Palmer, TN Watson, PAG Postprocessing East African rainfall forecasts using a generative machine learning model |
| 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 |
| work_keys_str_mv | AT antoniora postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel AT mcraeatt postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel AT mcleodd postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel AT cooperf postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel AT marshamj postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel AT aitchisonl postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel AT palmertn postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel AT watsonpag postprocessingeastafricanrainfallforecastsusingagenerativemachinelearningmodel |