Metraipolis › archive › dc_debc47280f57
Online Reinforcement Learning in the Met Office Unified Model through Distributed Model-Agent Coupling — arXiv:2609.02566
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02566
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:00:53.093Z
- SHA-256 of the archived text
205f56d2047c6e9a9c71013dddaf76b0190fd985091f3016484d12fde0752809- Stable URL of this page
https://metraipolis.com/documento/dc_debc47280f57
How to cite
Online Reinforcement Learning in the Met Office Unified Model through Distributed Model-Agent Coupling — arXiv:2609.02566 — arXiv (en), https://arxiv.org/abs/2609.02566 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_debc47280f57 (Metraipolis archive dc_debc47280f57, sha256 205f56d2047c6e9a9c71013dddaf76b0190fd985091f3016484d12fde0752809)
BibTeX
@misc{dcdebc47280f57,
title = {Online Reinforcement Learning in the Met Office Unified Model through Distributed Model-Agent Coupling — arXiv:2609.02566},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02566},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_debc47280f57; sha256 205f56d2047c6e9a9c71013dddaf76b0190fd985091f3016484d12fde0752809},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02566. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Machine-learnt corrections can complement numerical weather prediction provided that they operate stably within an evolving numerical model. In this study, we couple the Met Office (UKMO) Unified Model (UM) with distributed reinforcement-learning agents through rank-local tensors. A column-aware deep deterministic policy gradient (DDPG) actor uses local vertical structure together with full-column context to apply bounded corrections to potential temperature and horizontal wind. During training, we perform ten nudged 6-hr 12-min forecasts, with nudging towards the UKMO operational analysis providing an immediate counterfactual target from which the policy learns. The resulting actor is then frozen and applied to a non-nudged forecast without access to analysis inputs or further weight updates. Relative to a matched non-nudged native forecast at +6 h, the corrected forecast reduces global latitude-weighted MAE by 2.85% for $Z_{500}$, 2.16% for MSLP, 5.16% for $T_{500}$ and 2.27% for $T_{1.5\textrm{m}}$, with an observed 3.57% wall-time overhead compared to native execution. Even though training and inference share the same initialisation, this single-case experiment demonstrates significant promise and feasibility, laying the groundwork for RL-based bias correction and parametrisations within operational systems.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.02566 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T04:09:43.330Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).