Abstract The forecasting skill of numerical weather prediction (NWP) models critically depends on the accurate initial conditions, also known as analysis, provided by data assimilation (DA). Traditional DA methods often face a trade‐off between computational cost and accuracy due to complex linear algebra computations and the high dimensionality of the model, especially in non‐linear systems. Moreover, processing massive data in real‐time requires substantial computational resources. To address this, we introduce an artificial intelligence‐based data assimilation framework (ADAF) to generate high‐quality kilometer‐scale analysis. This study is the pioneering work using real‐world observations from varied locations and multiple sources to verify the AI method's efficacy in DA, including sparse surface weather observations and satellite imagery. We implemented ADAF for four near‐surface variables in the Contiguous United States (CONUS). The results demonstrate that ADAF consistently aligns closely with actual observations, providing high‐quality analysis fields capable of reconstructing extreme events, such as tropical cyclone wind fields. Sensitivity experiments reveal that ADAF can generate high‐quality analysis even with low‐accuracy backgrounds and extremely sparse surface observations. ADAF can assimilate multi‐source observations within a three‐hour window at low computational cost, taking about two seconds on an AMD MI200 graphics processing unit (GPU). ADAF‐generated analysis fields improved short‐term (0–6 hr) forecasts of an AI‐based weather prediction model, outperforming HRRRDAS‐initialized forecasts. ADAF has been shown to be efficient and effective in real‐world DA, underscoring its potential role in operational weather forecasting.
Xiang et al. (Mon,) studied this question.