Met Office Unified Model with RL Agents
Online Reinforcement Learning in the Met Office Unified Model through Distributed Model-Agent Coupling
Demonstrates RL bias correction feasibility in operational weather forecasting, potentially improving accuracy across tropical regions.
The Met Office Unified Model coupled with distributed RL agents through rank-local tensors. A DDPG actor applies bounded potential-temperature corrections across 70 vertical levels. Training used ten nudged forecasts with UKMO operational analysis as target. The frozen policy reduced Z$_{500}$ MAE by 45.8% and 40.8% in northern and southern tropics at +6 h.
Online Reinforcement Learning in the Met Office Unified Model through Distributed Model-Agent Coupling
Machine-learnt corrections can complement numerical weather prediction only if they adapt to the evolving model state while preserving dynamical consistency and numerical stability. To test this within a global forecasting model, we couple the Met Office (UKMO) Unified Model (UM) with distributed RL agents through rank-local tensors. A DDPG actor shares weights across the 70 vertical model levels of each atmospheric column and applies bounded potential-temperature corrections to the model tendencies. Across ten nudged training forecasts, nudging calculations towards the UKMO operational analysis provides an immediate counterfactual target. The frozen policy is then evaluated in a non-nudged forecast for inference. The coupled workflow successfully completes training and remains numerically stable in the evaluated case. Relative to a matched native UM forecast at +6 h, the learnt policy reduces Z$_{500}$ MAE in four of six latitude bands, including reductions of 45.8% and 40.8% in the northern and southern tropics. MSLP error too decreases in three bands, with a maximum reduction of 27.3% at 0-30°N. This single-case experiment demonstrates significant promise and feasibility of distributed online learning followed by non-nudged inference, laying the groundwork for RL-based bias correction and parametrisations within operational systems.
