[2507.18937] CNN-based Surface Temperature Forecasts with Ensemble Numerical Weather Prediction

Physics > Atmospheric and Oceanic Physics arXiv:2507.18937 (physics) [Submitted on 25 Jul 2025 (v1), last revised 8 Apr 2026 (this version, v3)] Title:CNN-based Surface Temperature Forecasts with Ensemble Numerical Weather Prediction Authors:Takuya Inoue, Takuya Kawabata (Meteorological Research Institute, Tsukuba, Japan) View a PDF of the paper titled CNN-based Surface Temperature Forecasts with Ensemble Numerical Weather Prediction, by Takuya Inoue and 3 other authors View PDF Abstract:Due to limited computational resources, medium-range temperature forecasts typically rely on low-resolution numerical weather prediction (NWP) models, which are prone to systematic and random errors. We propose a method that integrates a convolutional neural network (CNN) with an ensemble of low-resolution NWP models (40-km horizontal resolution) to produce high-resolution (5-km) surface temperature forecasts with lead times extending up to 5.5 days (132 h). First, CNN-based post-processing (bias correction and spatial downscaling) is applied to individual ensemble members to reduce systematic errors and perform downscaling, which improves the deterministic forecast accuracy. Second, this member-wise correction is applied to all 51 ensemble members to construct a new high-resolution ensemble forecasting system with an improved probabilistic reliability and spread-skill ratio that differs from the simple error reduction mechanism of ensemble averaging. Whereas averaging reduces forecast err...