Comparative Verification of IFS-Control, AIFS, and WeatherNext 2 Mean for Short-Range (6–84 h) Temperature and Precipitation Forecasts over Inner Mongolia

Whether advances in global weather forecasting translate into local forecast skill requires regional verification. Using observations at 117 stations in Inner Mongolia during the June–August 2026 flood season, we compared three publicly distributed forecast fields at 6–84 h lead times: the Integrated Forecasting System control forecast (IFS-Control), the Artificial Intelligence Forecasting System (AIFS), and WeatherNext 2’s 64-member ensemble mean (WN2). Because WN2 is an ensemble mean and the others are single deterministic forecasts, this compares operational products, not the underlying models. Verification of 2 m temperature and precipitation used Murphy error decomposition and block-bootstrap sensitivity tests. Temperature mean absolute error was approximately 15.7% lower for AIFS and 13.1% lower for WN2 than for IFS-Control, mainly through smaller correlation-error terms, though IFS-Control had the smallest systematic bias. Both AI products outperformed IFS-Control for 6 h moderate rain (≥4 mm). IFS-Control robustly outperformed AIFS for 6 h heavy rain (≥13 mm), but its advantage over WN2 did not survive the stricter multiple-comparison correction. Both AI products under-forecast heavy-rain frequency and extremes; a limited member experiment suggests ensemble averaging may contribute, though not separably from model differences. Findings apply only to the product versions, region, and season evaluated.