UniWind: Day-Ahead Wind Power Forecasting via Physics-Informed State Routing

UniWind is a wind power forecasting framework that blends physics-informed generation priors with data-driven state-aware corrections. It constructs a site‑calibrated physical prior using a monotone warp and a shared power curve, then refines this prior with a latent state encoder and a state‑aware power corrector guided by pseudo‑labels. Experiments on 24 real‑world datasets show that UniWind achieves strong forecasting accuracy, robustness, and generalization across full‑shot, cross‑farm zero‑shot, and cross‑region zero‑shot scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.