History

30 days of forecast vs. what actually happened at the lake. Click a single day to see its details.

Last 30 days

Rule-based forecast (actually used)
ML-based forecast — logistic (experimental)
ML-based forecast — HistGradientBoosting (black-box model, experimental)
Actual measurements (session ≥ 1 h)
Thu Jun 25 Fri Jul 24
session (≥ 1 h ≥ 11 kt) marginal (≥ 1 h ≥ 8 kt) no wind no data thunderstorm (forecast rows: predicted · actual row: observed)

Jul 8, 2026

81106:0021:0007:39 · avg 7.6 kt · gust 8.6 kt08:09 · avg 8.1 kt · gust 11.9 kt08:19 · avg 9.7 kt · gust 10.8 kt08:29 · avg 9.2 kt · gust 13.5 kt08:39 · avg 10.9 kt · gust 17.3 kt08:49 · avg 10.8 kt · gust 11.9 kt08:59 · avg 13.1 kt · gust 20.0 kt09:09 · avg 14.4 kt · gust 22.1 kt09:19 · avg 11.0 kt · gust 15.1 kt09:29 · avg 12.3 kt · gust 17.8 kt09:39 · avg 14.9 kt · gust 20.5 kt09:49 · avg 15.1 kt · gust 20.5 kt09:59 · avg 15.5 kt · gust 20.0 kt10:49 · avg 14.2 kt · gust 20.5 kt10:59 · avg 14.4 kt · gust 20.5 kt11:09 · avg 15.2 kt · gust 23.2 kt11:19 · avg 13.3 kt · gust 20.0 kt11:29 · avg 13.0 kt · gust 17.3 kt11:39 · avg 12.6 kt · gust 20.5 kt11:49 · avg 10.9 kt · gust 16.2 kt11:52 · avg 11.5 kt · gust 17.8 kt12:19 · avg 9.2 kt · gust 10.8 kt12:20 · avg 7.6 kt · gust 10.3 kt13:09 · avg 10.4 kt · gust 14.6 kt13:10 · avg 8.6 kt · gust 9.2 kt13:37 · avg 8.6 kt · gust 9.2 kt14:39 · avg 6.8 kt · gust 9.2 kt14:49 · avg 6.9 kt · gust 10.8 kt14:59 · avg 2.8 kt · gust 6.5 kt15:04 · avg 3.9 kt · gust 7.6 kt15:39 · avg 9.0 kt · gust 11.9 kt15:48 · avg 9.2 kt · gust 11.9 kt16:33 · avg 8.1 kt · gust 9.2 kt16:59 · avg 5.9 kt · gust 6.5 kt17:49 · avg 7.3 kt · gust 10.3 kt17:53 · avg 7.3 kt · gust 9.2 kt18:19 · avg 5.9 kt · gust 7.6 kt18:29 · avg 7.1 kt · gust 9.2 kt18:39 · avg 6.4 kt · gust 9.2 kt18:49 · avg 6.4 kt · gust 8.6 kt18:56 · avg 6.4 kt · gust 8.6 kt19:39 · avg 3.2 kt · gust 4.3 kt19:43 · avg 2.7 kt · gust 4.9 kt20:15 · avg 3.2 kt · gust 4.3 kt
avg wind gust ignition (8 kt) session (11 kt)
For Jul 8, 2026

NO GO

72% daytime cloud + only 206 W/m² solar — no insolation to drive a thermal

⚡ Storm risk: the thermal often runs well until the front — watch the sky, come in early.

🤖 ML — logistic experimental NO GO GO 4% · MAYBE 20% · NO GO 76%

Strongest inputs — (−) morning solar, pressure Δ (thermik), dew-point spread.

🤖 ML — HGB · black box experimental NO GO GO 1% · MAYBE 6% · NO GO 93%

Most distinctive inputs: morning solar, Innsbruck pressure, Bolzano pressure.

Experimental shadow models — they never drive the verdict. How good are they? →

Previous forecast method

How the day was forecast at the time, before the rules were recalibrated — shown for comparison only.