20.500.12556/RUL-186738 Forecast-error diagnostics in neural weather models Deep learning (DL) weather prediction models offer notable advantages over traditional physics-based models, including auto-differentiability and low computational cost, enabling detailed diagnostics of forecast errors. Using our convolutional encoder–decoder model, ConvCastNet, we relax selected subdomains of the forecast fields systematically towards “true” weather states (ECMWF ERA5 reanalysis) and monitor the forecast skill gain in other regions. Our results show that a medium-range midlatitude forecast improves substantially when the stratosphere and boundary layer are relaxed, while relaxation of the tropical atmosphere has a limited effect. This underscores the need for a more accurate representation of the stratosphere and the planetary boundary layer to improve medium-range weather predictability. Additionally, we investigate the relationship between the forecast-error sensitivity to initial conditions and relaxation experiments. By utilising auto-differentiability, we identify overlapping regions of large error sensitivity and strong forecast skill improvement from relaxation. Average midlatitude error sensitivity to initial conditions shows negligible influence from the Tropics, corroborating the results of the tropical relaxation experiments. The error sensitivity shows a physically consistent influence of upstream weather dynamics and sea-surface temperatures on forecast accuracy. The latter also highlights the importance of representing the atmosphere–ocean coupling accurately in numerical weather prediction models. This combined approach could provide valuable heuristics for diagnosing neural model errors and guiding targeted model improvements. meteorology weather prediction models convolutional neural networks deep learning meteorologija napovedovanje vremena konvolucijske nevronske mreže globoko učenje true false true Angleški jezik Slovenski jezik Članek v reviji 2026-09-04 12:43:12 2026-09-04 12:43:14 2026-09-06 03:37:41 0000-00-00 00:00:00 2026 0 0 20 str. iss. 779, art. no. e70212 Vol. 152 Jul. 2026 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 551.509 0035-9009 10.1002/qj.70212 280424963 https://rmets.onlinelibrary.wiley.com/doi/epdf/10.1002/qj.70212 1 6de3eedc-a84d-11f1-8bc5-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=246095 Quart_J_Royal_Meteoro_Soc_-_2026_-_Perkan_-_Forecast‐Error_Diagnostics_in_Neural_Weather_Models.pdf Quart_J_Royal_Meteoro_Soc_-_2026_-_Perkan_-_Forecast‐Error_Diagnostics_in_Neural_Weather_Models.pdf 1 9BC775CF3D9B3A847B04741485D511D5 d659cef1b02495a3c611bb9bbd8352d456fa557d4b4dd3e445cc94229d675d05 d8a63269-a84d-11f1-8bc5-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=246098 Fakulteta za matematiko in fiziko 0 0 0