This page provides an overview of regional forecast skill for the SON 2025 period. Forecast scores are updated automatically every week throughout the competitive period. The current data includes forecasts initialized between Thursday 14th August 2025 and Thursday 18th September 2025 (inclusive). For a detailed description of the outputs, please refer to the section's overview.
Regional skill score files
All regional RPSSs are available to download via the following link:
SON 2025 Regional RPSSs (Excel format)
Regional scores for the top 10 teams of global, period-aggregated, variable-averaged RPSSs
| Team name | Team rank | Model name | Model rank | Global | Tropics | NHem. ExTro. | SHem. ExTro. | NHem. Polar | SHem. Polar | Europe | N. Amer. | S. Amer. | Africa | Asia | Oceania |
|---|
| MicroEnsemble | 1 | MicroDuet | 1 | 0.073 | 0.116 | 0.032 | 0.053 | 0.024 | 0.021 | 0.018 | 0.044 | 0.082 | 0.072 | 0.069 | 0.117 | | MicroEnsemble | 1 | StillLearning | 3 | 0.067 | 0.108 | 0.029 | 0.048 | 0.018 | 0.017 | 0.019 | 0.039 | 0.071 | 0.097 | 0.059 | 0.125 | | MicroEnsemble | 1 | Huracan | 9 | 0.027 | 0.032 | 0.019 | 0.035 | 0.014 | 0.008 | 0.014 | 0.038 | 0.006 | -0.036 | 0.039 | 0.043 | | CMAandFDU | 2 | FengshunAdjust | 2 | 0.07 | 0.14 | 0.017 | 0.016 | -0.016 | -0.02 | 0.013 | 0.038 | 0.138 | 0.105 | 0.046 | 0.087 | | CMAandFDU | 2 | FengshunHybrid | 4 | 0.065 | 0.119 | 0.019 | 0.02 | 0.008 | 0.002 | -0.002 | 0.06 | 0.096 | 0.101 | 0.045 | 0.044 | | CMAandFDU | 2 | Fengshun | 10 | 0.012 | 0.031 | 0.006 | -0.008 | 0.006 | -0.053 | 0.023 | 0.023 | 0.024 | -0.01 | 0.031 | -0.05 | | LP | 3 | LPM | 5 | 0.049 | 0.074 | 0.026 | 0.042 | 0.019 | -0.0 | -0.012 | 0.045 | 0.058 | 0.035 | 0.054 | 0.052 | | AIFS | 4 | AIFShera | 6 | 0.04 | 0.05 | 0.031 | 0.018 | 0.024 | 0.013 | 0.019 | 0.029 | 0.071 | 0.027 | 0.048 | 0.019 | | AIFS | 4 | AIFSgaia | 7 | 0.037 | 0.065 | 0.017 | 0.008 | 0.006 | -0.014 | 0.007 | 0.025 | 0.052 | 0.041 | 0.036 | -0.012 | | AIFS | 4 | AIFSthalassa | 8 | 0.036 | 0.058 | 0.018 | 0.004 | 0.022 | 0.002 | -0.0 | 0.022 | 0.049 | 0.02 | 0.04 | 0.012 | | scienceAI | 5 | findforecast | 11 | 0.001 | -0.001 | -0.003 | 0.019 | -0.009 | 0.007 | -0.015 | 0.028 | -0.006 | -0.014 | -0.014 | 0.031 | | scienceAI | 5 | zephyr | 12 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | scienceAI | 5 | ngcm | 12 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | KITKangu | 6 | KanguPlusPlus | 12 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | KITKangu | 6 | KanguParametricPrediction | 12 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | KITKangu | 6 | KanguS2SEasyUQ | 35 | -1.063 | -1.154 | -0.984 | -1.074 | -0.847 | -1.001 | -0.952 | -1.0 | -1.177 | -1.145 | -0.957 | -1.321 | | CliMA | 7 | CliMAWeather2 | 16 | -0.13 | -0.143 | -0.178 | -0.114 | -0.084 | -0.003 | -0.112 | -0.133 | -0.147 | -0.203 | -0.156 | -0.104 | | CliMA | 7 | CliMAWeather | 22 | -0.259 | -0.303 | -0.256 | -0.327 | -0.232 | -0.119 | -0.224 | -0.166 | -0.287 | -0.34 | -0.332 | -0.37 | | WindBorne | 8 | WeatherMesh | 17 | -0.166 | -0.125 | -0.163 | -0.296 | -0.14 | -0.424 | -0.2 | -0.208 | -0.151 | -0.163 | -0.123 | -0.226 | | FengWuW2S | 9 | FengWu2 | 18 | -0.191 | -0.198 | -0.289 | -0.043 | -0.158 | -0.026 | -0.219 | -0.117 | -0.083 | -0.315 | -0.358 | -0.224 | | FengWuW2S | 9 | FengWu | 19 | -0.236 | -0.332 | -0.194 | -0.111 | -0.074 | -0.172 | -0.146 | -0.139 | -0.339 | -0.427 | -0.276 | -0.278 | | HAPPY | 10 | AZN | 20 | -0.244 | -0.259 | -0.255 | -0.538 | -0.299 | 0.069 | -0.072 | -0.299 | -0.303 | -0.219 | -0.316 | -0.443 |
|
| Team name | Team rank | Model name | Model rank | Global | Tropics | NHem. ExTro. | SHem. ExTro. | NHem. Polar | SHem. Polar | Europe | N. Amer. | S. Amer. | Africa | Asia | Oceania |
|---|
| MicroEnsemble | 1 | MicroDuet | 1 | 0.046 | 0.081 | -0.001 | 0.063 | 0.009 | 0.034 | -0.031 | 0.052 | 0.077 | 0.06 | 0.022 | 0.086 | | MicroEnsemble | 1 | StillLearning | 2 | 0.043 | 0.078 | -0.002 | 0.052 | 0.005 | 0.033 | -0.031 | 0.044 | 0.066 | 0.075 | 0.019 | 0.089 | | MicroEnsemble | 1 | Huracan | 7 | 0.009 | 0.016 | -0.019 | 0.054 | 0.003 | 0.018 | -0.043 | 0.051 | 0.024 | -0.034 | -0.016 | 0.031 | | CMAandFDU | 2 | FengshunAdjust | 3 | 0.033 | 0.071 | 0.004 | 0.01 | -0.009 | 0.004 | -0.003 | 0.036 | 0.06 | 0.084 | 0.011 | 0.038 | | CMAandFDU | 2 | FengshunHybrid | 4 | 0.029 | 0.059 | 0.002 | 0.024 | -0.016 | 0.018 | -0.01 | 0.048 | 0.045 | 0.058 | -0.001 | 0.023 | | CMAandFDU | 2 | Fengshun | 13 | -0.006 | 0.002 | 0.003 | 0.0 | -0.005 | -0.047 | 0.009 | 0.024 | 0.001 | -0.015 | -0.002 | -0.046 | | LP | 3 | LPM | 5 | 0.022 | 0.037 | -0.004 | 0.026 | 0.012 | 0.023 | -0.04 | 0.056 | 0.039 | 0.021 | 0.008 | 0.013 | | AIFS | 4 | AIFSgaia | 6 | 0.013 | 0.032 | -0.003 | -0.012 | -0.005 | 0.008 | -0.018 | 0.051 | 0.054 | 0.001 | -0.015 | -0.008 | | AIFS | 4 | AIFShera | 8 | 0.004 | 0.013 | -0.009 | -0.015 | -0.006 | 0.01 | -0.016 | 0.024 | 0.054 | -0.011 | -0.023 | 0.007 | | AIFS | 4 | AIFSthalassa | 15 | -0.016 | -0.035 | -0.008 | -0.01 | 0.002 | 0.023 | -0.021 | 0.037 | 0.006 | -0.113 | -0.023 | -0.013 | | KITKangu | 5 | KanguPlusPlus | 9 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | KITKangu | 5 | KanguParametricPrediction | 9 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | scienceAI | 5 | zephyr | 9 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | scienceAI | 5 | ngcm | 9 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | scienceAI | 5 | findforecast | 14 | -0.01 | -0.018 | -0.009 | 0.028 | 0.004 | 0.0 | -0.01 | 0.027 | -0.024 | -0.015 | -0.025 | 0.019 | | KITKangu | 5 | KanguS2SEasyUQ | 34 | -1.086 | -1.202 | -1.004 | -1.025 | -0.84 | -1.003 | -1.014 | -1.106 | -1.168 | -1.326 | -0.955 | -1.132 | | CliMA | 7 | CliMAWeather2 | 16 | -0.186 | -0.227 | -0.245 | -0.145 | -0.086 | -0.013 | -0.206 | -0.152 | -0.22 | -0.304 | -0.226 | -0.187 | | CliMA | 7 | CliMAWeather | 21 | -0.33 | -0.389 | -0.333 | -0.368 | -0.286 | -0.2 | -0.318 | -0.109 | -0.355 | -0.49 | -0.435 | -0.416 | | FengWuW2S | 8 | FengWu2 | 17 | -0.199 | -0.261 | -0.265 | 0.029 | -0.105 | 0.09 | -0.108 | -0.226 | -0.117 | -0.33 | -0.331 | -0.178 | | FengWuW2S | 8 | FengWu | 18 | -0.255 | -0.38 | -0.205 | -0.065 | -0.064 | -0.136 | -0.109 | -0.203 | -0.37 | -0.491 | -0.252 | -0.269 | | HAPPY | 9 | AZN | 19 | -0.291 | -0.328 | -0.268 | -0.688 | -0.338 | 0.021 | -0.214 | -0.396 | -0.468 | -0.227 | -0.254 | -0.569 | | NordicS2S | 10 | NordicS2S1 | 20 | -0.305 | -0.248 | -0.334 | -0.343 | -0.387 | -0.335 | -0.48 | -0.24 | -0.289 | -0.28 | -0.333 | -0.306 | | NordicS2S | 10 | NordicS2S3 | 25 | -0.492 | -0.577 | -0.385 | -0.298 | -0.451 | -0.59 | -0.534 | -0.267 | -0.522 | -0.694 | -0.483 | -0.559 | | NordicS2S | 10 | NordicS2S2 | 27 | -0.591 | -0.615 | -0.609 | -0.591 | -0.513 | -0.603 | -0.727 | -0.465 | -0.717 | -0.631 | -0.573 | -0.545 |
|
Figures showing aggregated RPSSs for best-performing model from top 10 teams
Figures showing percentage of grid points with positive period-aggregated RPSSs
