Domain-adaptive data assimilation improves ai weather forecasts accuracy
Domain-Adaptive Data Assimilation for Global AI Weather Forecasting
Computational Engineering, Finance, and Science
Summary
AI weather models usually train on data not available in real time, causing problems when used with live weather analyses. The authors propose a technique called Domain-Adaptive Data Assimilation (DADA) that adjusts the starting conditions for pretrained AI weather models using current observations. DADA keeps the AI model fixed but fine-tunes the initial input to better match real observations, improving forecast accuracy without retraining. This method works across multiple AI models and different initial data sources, allowing AI forecasts to adapt to changing input systems.
What this means in practice
- •For operational weather forecast centers: Improve short-range AI weather forecast accuracy when switching between different initial condition sources without retraining.
- •For renewable energy operators: Enhance reliability of AI weather forecasts used for scheduling and managing wind and solar power generation under changing data inputs.
Authors
Minseok Seo, Noah Brenowitz, Doyi Kim, Hyesook Lee, Changick Kim
Abstract
AI weather forecasting models are commonly trained on the ERA5 reanalysis, which is unavailable in real time. Operational deployment therefore relies on initial conditions produced by numerical or AI analysis systems that differ from those encountered during training. This mismatch can degrade forecast skill, while retraining for every analysis system is costly. Here, we present Domain-Adaptive Data Assimilation (DADA), an observation-guided framework that adapts external analyses to pretrained AI weather models. Starting from a background state, DADA optimizes only an initial-state perturbation while keeping the forecast model frozen. The perturbed state is propagated through the model, and its short-range trajectory is constrained by real-world observations through a learned observation operator. The resulting initial condition is shaped jointly by observational constraints and the dynamics learned by the target model. We evaluate DADA across five global AI weather models using backgrounds from the Global Forecast System and the AI-based HealDA. Across deterministic and probabilistic forecasts, DADA substantially reduces short-range skill loss caused by changes in the initial-condition source. More broadly, DADA turns observations into a common interface between independently developed analysis and forecasting systems, enabling pretrained AI weather models to accommodate evolving operational initial conditions without reconstructing ERA5 or retraining the forecast model.