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 7 forecasts initialized between Thursday 14th August 2025 and Thursday 25th 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 | 0.071 | 0.108 | 0.038 | 0.061 | 0.035 | 0.018 | 0.01 | 0.052 | 0.075 | 0.068 | 0.074 | 0.128 | | MicroEnsemble | 1 | StillLearning | 2 | 0.065 | 0.098 | 0.038 | 0.053 | 0.032 | 0.023 | 0.013 | 0.048 | 0.064 | 0.09 | 0.067 | 0.121 | | MicroEnsemble | 1 | Huracan | 9 | 0.03 | 0.029 | 0.026 | 0.043 | 0.03 | 0.017 | 0.002 | 0.05 | -0.0 | -0.044 | 0.046 | 0.069 | | CMAandFDU | 2 | FengshunHybrid | 3 | 0.058 | 0.103 | 0.023 | 0.024 | 0.017 | -0.003 | -0.0 | 0.058 | 0.091 | 0.102 | 0.046 | 0.052 | | CMAandFDU | 2 | FengshunAdjust | 4 | 0.058 | 0.116 | 0.015 | 0.017 | -0.009 | -0.008 | 0.009 | 0.036 | 0.122 | 0.104 | 0.038 | 0.072 | | CMAandFDU | 2 | Fengshun | 11 | 0.001 | 0.022 | -0.007 | -0.016 | 0.001 | -0.069 | 0.012 | 0.022 | 0.016 | -0.006 | 0.015 | -0.036 | | LP | 3 | LPM | 5 | 0.045 | 0.062 | 0.034 | 0.038 | 0.033 | -0.002 | -0.006 | 0.047 | 0.049 | 0.029 | 0.062 | 0.065 | | AIFS | 4 | AIFShera | 6 | 0.04 | 0.048 | 0.035 | 0.023 | 0.039 | 0.002 | 0.019 | 0.042 | 0.068 | 0.026 | 0.051 | 0.042 | | AIFS | 4 | AIFSgaia | 7 | 0.038 | 0.063 | 0.021 | 0.01 | 0.022 | -0.014 | 0.013 | 0.037 | 0.049 | 0.045 | 0.039 | 0.026 | | AIFS | 4 | AIFSthalassa | 8 | 0.03 | 0.047 | 0.019 | 0.018 | 0.027 | -0.006 | 0.005 | 0.026 | 0.042 | 0.022 | 0.039 | 0.033 | | scienceAI | 5 | findforecast | 10 | 0.001 | 0.001 | -0.008 | 0.025 | -0.001 | 0.01 | -0.016 | 0.032 | -0.006 | -0.013 | -0.018 | 0.039 | | 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 | 34 | -1.074 | -1.185 | -0.987 | -1.039 | -0.866 | -0.931 | -1.017 | -0.992 | -1.242 | -1.2 | -0.992 | -1.242 | | CliMA | 7 | CliMAWeather2 | 16 | -0.12 | -0.14 | -0.153 | -0.117 | -0.067 | -0.015 | -0.104 | -0.108 | -0.148 | -0.192 | -0.135 | -0.098 | | CliMA | 7 | CliMAWeather | 21 | -0.31 | -0.359 | -0.323 | -0.387 | -0.262 | -0.145 | -0.286 | -0.149 | -0.338 | -0.396 | -0.411 | -0.449 | | FengWuW2S | 8 | FengWu2 | 17 | -0.177 | -0.197 | -0.257 | -0.019 | -0.134 | -0.015 | -0.201 | -0.126 | -0.097 | -0.312 | -0.315 | -0.131 | | FengWuW2S | 8 | FengWu | 19 | -0.227 | -0.326 | -0.18 | -0.096 | -0.061 | -0.167 | -0.146 | -0.137 | -0.337 | -0.432 | -0.242 | -0.223 | | WindBorne | 9 | WeatherMesh | 18 | -0.182 | -0.16 | -0.139 | -0.311 | -0.129 | -0.482 | -0.2 | -0.202 | -0.202 | -0.164 | -0.105 | -0.24 | | HAPPY | 10 | AZN | 20 | -0.233 | -0.251 | -0.245 | -0.491 | -0.295 | 0.084 | -0.098 | -0.324 | -0.257 | -0.191 | -0.281 | -0.515 |
|
| 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 | 0.054 | 0.088 | 0.013 | 0.061 | 0.022 | 0.033 | -0.015 | 0.058 | 0.061 | 0.065 | 0.038 | 0.101 | | MicroEnsemble | 1 | StillLearning | 2 | 0.05 | 0.082 | 0.015 | 0.047 | 0.022 | 0.037 | -0.017 | 0.051 | 0.051 | 0.08 | 0.039 | 0.093 | | MicroEnsemble | 1 | Huracan | 7 | 0.017 | 0.023 | -0.004 | 0.05 | 0.017 | 0.021 | -0.031 | 0.055 | 0.006 | -0.034 | 0.006 | 0.055 | | CMAandFDU | 2 | FengshunAdjust | 3 | 0.043 | 0.086 | 0.009 | 0.008 | 0.002 | 0.008 | -0.0 | 0.041 | 0.065 | 0.102 | 0.024 | 0.047 | | CMAandFDU | 2 | FengshunHybrid | 4 | 0.038 | 0.071 | 0.009 | 0.022 | 0.0 | 0.019 | -0.005 | 0.051 | 0.039 | 0.065 | 0.018 | 0.042 | | CMAandFDU | 2 | Fengshun | 9 | 0.004 | 0.019 | 0.005 | -0.01 | 0.005 | -0.054 | 0.013 | 0.04 | 0.011 | -0.002 | 0.006 | -0.04 | | LP | 3 | LPM | 5 | 0.028 | 0.046 | 0.004 | 0.018 | 0.022 | 0.025 | -0.033 | 0.054 | 0.024 | 0.018 | 0.027 | 0.04 | | AIFS | 4 | AIFSgaia | 6 | 0.022 | 0.043 | 0.0 | -0.004 | 0.009 | 0.016 | -0.016 | 0.051 | 0.054 | 0.015 | 0.0 | 0.015 | | AIFS | 4 | AIFShera | 8 | 0.015 | 0.024 | 0.001 | -0.005 | 0.014 | 0.017 | -0.006 | 0.024 | 0.052 | 0.013 | -0.003 | 0.027 | | AIFS | 4 | AIFSthalassa | 15 | -0.004 | -0.017 | -0.003 | -0.004 | 0.014 | 0.025 | -0.014 | 0.034 | 0.008 | -0.084 | -0.007 | 0.014 | | KITKangu | 5 | KanguPlusPlus | 10 | -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 | 10 | -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 | 10 | -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 | 10 | -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 | -0.004 | -0.009 | -0.006 | 0.025 | 0.012 | 0.004 | -0.001 | 0.032 | -0.022 | -0.003 | -0.021 | 0.026 | | KITKangu | 5 | KanguS2SEasyUQ | 32 | -1.124 | -1.244 | -1.05 | -1.073 | -0.91 | -0.99 | -0.999 | -1.143 | -1.171 | -1.411 | -1.032 | -1.132 | | CliMA | 7 | CliMAWeather2 | 16 | -0.156 | -0.189 | -0.212 | -0.12 | -0.065 | -0.022 | -0.17 | -0.128 | -0.18 | -0.256 | -0.193 | -0.163 | | CliMA | 7 | CliMAWeather | 20 | -0.35 | -0.403 | -0.371 | -0.397 | -0.287 | -0.225 | -0.258 | -0.154 | -0.35 | -0.478 | -0.483 | -0.47 | | FengWuW2S | 8 | FengWu2 | 17 | -0.186 | -0.251 | -0.243 | 0.029 | -0.09 | 0.08 | -0.128 | -0.2 | -0.125 | -0.32 | -0.297 | -0.122 | | FengWuW2S | 8 | FengWu | 18 | -0.243 | -0.371 | -0.19 | -0.066 | -0.051 | -0.123 | -0.117 | -0.185 | -0.374 | -0.478 | -0.228 | -0.238 | | HAPPY | 9 | AZN | 19 | -0.261 | -0.318 | -0.232 | -0.604 | -0.25 | 0.007 | -0.182 | -0.322 | -0.429 | -0.239 | -0.205 | -0.544 | | WindBorne | 10 | WeatherMesh | 21 | -0.352 | -0.364 | -0.193 | -0.64 | -0.271 | -0.732 | -0.243 | -0.359 | -0.369 | -0.239 | -0.222 | -0.628 |
|
Figures showing aggregated RPSSs for best-performing model from top 10 teams
Figures showing evolution of skill scores
Figures showing percentage of grid points with positive period-aggregated RPSSs
Figures showing observed conditions with respect to defined ERA5 climatology