The atmosphere, learned and solved, side by side
weathermaps.ai tracks the machine-learning weather models against the physics models they are measured against. One model's map carries almost no information, because every model draws a plausible Tuesday. What carries information is where two of them, run at the same hour, stop agreeing.
Most contested cities
Where AIFS, HRES, WeatherNext 2 and the ensemble mean disagree most, measured against how much the ensemble itself expects. From the 16 Sep 12Z run. All 602 cities →
| City | DI | Driven by | Highs, °C | to Thu 17 12Z |
|---|---|---|---|---|
| BaghdadIraq | 44 | temperature | 43434343 | spread 0° |
| EdmontonCanada | 43 | temperature | 20181818 | spread 2° |
| BeijingChina | 39 | temperature | 31313030 | spread 1° |
| BenxiChina | 39 | temperature | 27272626 | spread 1° |
| BirminghamUnited States | 39 | temperature | 33323132 | spread 2° |
| ChangchunChina | 39 | temperature | 29272627 | spread 3° |
| Kuwait CityKuwait | 39 | temperature | 41404142 | spread 2° |
| CalgaryCanada | 37 | temperature | 18151715 | spread 3° |
| MeerutIndia | 37 | temperature | 30293029 | spread 1° |
| OuagadougouBurkina Faso | 37 | temperature | 31343033 | spread 4° |
| TashkentUzbekistan | 37 | temperature | 29303030 | spread 1° |
| MosulIraq | 35 | temperature | 39393838 | spread 1° |
| City | DI | Driven by | Highs, °C | to Sat 19 12Z |
|---|---|---|---|---|
| CalgaryCanada | 53 | temperature | 20172018 | spread 3° |
| MemphisUnited States | 53 | temperature | 36363437 | spread 3° |
| NiameyNiger | 53 | temperature | 34323332 | spread 2° |
| LahorePakistan | 52 | temperature | 34313131 | spread 3° |
| DohaQatar | 47 | temperature | 38383638 | spread 2° |
| EdmontonCanada | 47 | temperature | 21202019 | spread 2° |
| AndorraAndorra | 46 | temperature | 16161817 | spread 2° |
| JilinChina | 46 | temperature | 27252525 | spread 2° |
| ManaguaNicaragua | 46 | temperature | 34333232 | spread 2° |
| AtlantaUnited States | 45 | temperature | 33353235 | spread 3° |
| BuffaloUnited States | 45 | temperature | 22222221 | spread 1° |
| PortlandUnited States | 45 | temperature | 22242124 | spread 3° |
| City | DI | Driven by | Highs, °C | to Mon 21 12Z |
|---|---|---|---|---|
| LubumbashiCongo (Kinshasa) | 73 | temperature | 23322531 | spread 9° |
| BrasíliaBrazil | 60 | temperature | 31312931 | spread 2° |
| EdmontonCanada | 60 | temperature | 24212322 | spread 3° |
| MemphisUnited States | 60 | temperature | 36383438 | spread 4° |
| AsunciónParaguay | 59 | pressure | 35313332 | spread 4° |
| JiningChina | 58 | temperature | 24292529 | spread 5° |
| CuritibaBrazil | 57 | pressure | 21252123 | spread 4° |
| Cape TownSouth Africa | 56 | temperature | 23272125 | spread 6° |
| LusakaZambia | 56 | temperature | 22302430 | spread 8° |
| LudhianaIndia | 55 | temperature | 35323132 | spread 4° |
| ShangqiuChina | 55 | temperature | 22282328 | spread 6° |
| XuzhouChina | 54 | temperature | 24292429 | spread 5° |
| City | DI | Driven by | Highs, °C | to Wed 23 12Z |
|---|---|---|---|---|
| BrasíliaBrazil | 69 | temperature | 33343133 | spread 3° |
| LilongweMalawi | 65 | temperature | 26302629 | spread 4° |
| GoiâniaBrazil | 63 | temperature | 35373436 | spread 3° |
| JiningChina | 61 | temperature | 28322831 | spread 4° |
| ShangqiuChina | 61 | temperature | 28322730 | spread 5° |
| LusakaZambia | 58 | temperature | 28302830 | spread 2° |
| ChișinăuMoldova | 57 | pressure | 14211516 | spread 7° |
| HezeChina | 57 | temperature | 28312830 | spread 3° |
| LubumbashiCongo (Kinshasa) | 56 | pressure | 29323030 | spread 3° |
| XuzhouChina | 56 | temperature | 28312630 | spread 5° |
| ZaozhuangChina | 55 | temperature | 28302629 | spread 4° |
| ShuyangChina | 54 | pressure | 29312530 | spread 6° |
| City | DI | Driven by | Highs, °C | to Sat 26 12Z |
|---|---|---|---|---|
| BrasíliaBrazil | 69 | pressure | 32322833 | spread 5° |
| Belo HorizonteBrazil | 63 | pressure | 27332629 | spread 7° |
| HuamboAngola | 60 | temperature | 30252826 | spread 5° |
| LubumbashiCongo (Kinshasa) | 58 | pressure | 29333031 | spread 4° |
| LilongweMalawi | 57 | pressure | 26302829 | spread 4° |
| MadridSpain | 57 | temperature | 29302729 | spread 3° |
| GoiâniaBrazil | 56 | pressure | 35373236 | spread 5° |
| DenverUnited States | 55 | pressure | 23192123 | spread 4° |
| Ft. WorthUnited States | 55 | pressure | 31222831 | spread 9° |
| EdmontonCanada | 54 | temperature | 12231916 | spread 11° |
| TunisTunisia | 54 | pressure | 22262726 | spread 5° |
| VallettaMalta | 54 | pressure | 23232524 | spread 2° |
Runs coming in
Each model's newest run and how far through its forecast the rendered maps have reached. Unfinished runs come first.
Model Board
Sorted by family, then by newest run. Click a column to sort it, and a model to open it in the explorer.
| Model | Status | Newest run | Horizon | Fields | Grid | Rendered by |
|---|---|---|---|---|---|---|
| AIFS SingleECMWF · Deterministic | On time | 16 Sep 12Z13 h ago | f360 | 11 | 0.25° | forecasteuro.com |
| WeatherNext 2Google DeepMind · Ensemble (64 members) | On timeExperimental | 16 Sep 12Z13 h ago | f360 | 4 | 0.25° | forecasteuro.com |
| IFS HRESECMWF · Deterministic | On time | 16 Sep 12Z13 h ago | f360 | 24 | 0.1° | forecasteuro.com |
| IFS ENSECMWF · Ensemble | On time | 16 Sep 12Z13 h ago | f360 | 72 | 0.25° | forecasteuro.com |
| GFSNOAA NCEP · Deterministic | On time | 16 Sep 18Z7 h ago | f240 | 8 | 0.117° | forecasteagle.com |
Open a model
Every explorer uses the same colours, places and timeline, so switching models changes only the forecast.
Why this site exists
The baseline moved
For fifty years, better forecasts meant a better dynamical core and a bigger machine. Then a model that had never been told what a pressure gradient is started beating one built out of them. That is worth watching closely rather than through a press release.
Difference is the signal
One model's map tells you almost nothing. What carries information is where two of them, run at the same hour, stop agreeing, so this site is built around comparing models rather than around any one of them.
Coarse, and honest about it
The global learned models here run at a quarter degree, about 28 km. Where detail appears at a finer scale than the grid, it was generated rather than forecast, and the page says which.