Three element tabs

index.html

@@ -72,7 +72,7 @@ svg{width:100%;height:auto;display:block}.lg{display:flex;flex-wrap:wrap;gap:6px
 <div class="mbody"><div id="lmap"></div><iframe id="wfr" title="Live weather map" hidden></iframe></div>
 <div class="mft" id="mft"></div></div></div>
 <div class="etabs" id="etabs" role="tablist" aria-label="Weather element">
-<button type="button" class="et on" data-e="tmax">Max temperature</button><button type="button" class="et" data-e="tmin">Min temperature</button><button type="button" class="et" data-e="wind">Wind</button><button type="button" class="et" data-e="precip">Precipitation</button></div>
+<button type="button" class="et on" data-e="tmax">Max temperature</button><button type="button" class="et" data-e="tmin">Min temperature</button><button type="button" class="et" data-e="wind">Wind</button></div>
 <main>
 <noscript><h1>Global Weather Model Leaderboard</h1><p>Daily accuracy ranking of global weather forecast models, AI and physics: Darwin-Prediction-Weather, ECMWF AIFS, ECMWF IFS, GFS, AIGFS, ICON, JMA, GEM and MET Norway, scored against ERA5 for 24 world cities since 2026-01-01, with a 10-day outlook. 2026 year to date, RMSE of daily maximum temperature in °C at 1, 3, 5 and 7 days ahead: Darwin-Prediction-Weather (VIDRAFT, AI) 0.84, 1.17, 1.59, 2.09. ECMWF AIFS (AI) 1.35, 1.59, 1.90, 2.42. ECMWF IFS (Physics) 1.44, 1.77, 2.21, 2.85. Data: <a href="https://huggingface.co/datasets/FINAL-Bench/Weather-Model-Forecast-Archive">Weather-Model-Forecast-Archive</a>. Contact: vidraft@mail.vidraft.net</p></noscript>
 <div class="ctl">
@@ -99,7 +99,7 @@ svg{width:100%;height:auto;display:block}.lg{display:flex;flex-wrap:wrap;gap:6px
 <h3 class="h3">By period and forecast day, 24 cities</h3><div class="tw"><table class="wt" id="wper"></table></div>
 <h3 class="h3" style="margin-top:16px">By city and forecast day, 2026 year to date</h3><div class="tw"><table class="wt" id="wcity"></table></div><div class="lg" id="lg3"></div></div>
 <div class="pn" style="margin-top:14px"><h2>How it is scored</h2>
-<p class="note">Every day each model's forecast is recorded for up to 10 days ahead. When the observed value for a day is published, every forecast made for that day is scored and the cumulative record is updated, once a day. A forecast issued N days earlier is compared with the ERA5 value for the same UTC day at each city. Each element has its own tab and its own ranking: daily maximum temperature, daily minimum temperature, daily maximum wind speed and daily precipitation total. Lower RMSE ranks higher. Models are compared on the same cases: days and cities where every listed model issued a forecast. Type shows how a model works: <b>AI</b> models learn the forecast from data, <b>Physics (Supercomputer)</b> models solve the equations of the atmosphere on supercomputers. ERA5 is published about five days after the fact, so the latest verification date trails today. Forecasts 1 to 7 days ahead are scored from 2026-01-01; forecasts 8 to 10 days ahead are archived from 2026-11-13 and enter the ranking as their target days are verified. <b>Darwin-Prediction-Weather</b> is VIDRAFT's fusion engine: local bias correction plus skill-weighted fusion of the public models, fitted only on days before the one being scored. It is ranked on exactly the same cases as the public models. In the 10-day outlook the fusion for days beyond the longest scored lead uses that lead's calibration.</p></div>
+<p class="note">Every day each model's forecast is recorded for up to 10 days ahead. When the observed value for a day is published, every forecast made for that day is scored and the cumulative record is updated, once a day. A forecast issued N days earlier is compared with the ERA5 value for the same UTC day at each city. Each element has its own tab and its own ranking: daily maximum temperature, daily minimum temperature, and daily maximum wind speed. Lower RMSE ranks higher. Models are compared on the same cases: days and cities where every listed model issued a forecast. Type shows how a model works: <b>AI</b> models learn the forecast from data, <b>Physics (Supercomputer)</b> models solve the equations of the atmosphere on supercomputers. ERA5 is published about five days after the fact, so the latest verification date trails today. Forecasts 1 to 7 days ahead are scored from 2026-01-01; forecasts 8 to 10 days ahead are archived from 2026-11-13 and enter the ranking as their target days are verified. <b>Darwin-Prediction-Weather</b> is VIDRAFT's fusion engine: local bias correction plus skill-weighted fusion of the public models, fitted only on days before the one being scored. It is ranked on exactly the same cases as the public models. In the 10-day outlook the fusion for days beyond the longest scored lead uses that lead's calibration.</p></div>
 <footer>Full daily record since 2026-01-01 (every model forecast and the ERA5 value): <a href="https://huggingface.co/datasets/FINAL-Bench/Weather-Model-Forecast-Archive">Weather-Model-Forecast-Archive</a>. Weather data by <a href="https://open-meteo.com/">Open-Meteo.com</a> (CC BY 4.0). Verification: ERA5, Copernicus Climate Change Service. Model sources: ECMWF, NOAA NCEP, DWD, JMA, ECCC, MET Norway. Engine: <a href="https://huggingface.co/FINAL-Bench/Darwin-Prediction-Weather">Darwin-Prediction-Weather</a>. Leaderboard application: Apache License 2.0. Compiled record and model: CC BY-NC 4.0. Contact: <a href="mailto:vidraft@mail.vidraft.net">vidraft@mail.vidraft.net</a></footer>
 </main><script>
 const CITIES={"Seoul":[37.57,126.98],"Busan":[35.18,129.08],"Tokyo":[35.68,139.69],"Beijing":[39.90,116.40],"Singapore":[1.35,103.82],"Delhi":[28.61,77.21],"Dubai":[25.20,55.27],"Moscow":[55.76,37.62],"Berlin":[52.52,13.40],"London":[51.51,-0.13],"Paris":[48.86,2.35],"Madrid":[40.42,-3.70],"Cairo":[30.04,31.24],"Nairobi":[-1.29,36.82],"Johannesburg":[-26.20,28.05],"New York":[40.71,-74.01],"Chicago":[41.88,-87.63],"Los Angeles":[34.05,-118.24],"Mexico City":[19.43,-99.13],"Sao Paulo":[-23.55,-46.63],"Buenos Aires":[-34.60,-58.38],"Sydney":[-33.87,151.21],"Anchorage":[61.22,-149.90],"Reykjavik":[64.15,-21.94]};