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 15, 2026

81106:0021:0009:55 · avg 10.3 kt · gust 18.9 kt10:39 · avg 0.9 kt · gust 2.2 kt10:42 · avg 2.2 kt · gust 5.9 kt11:09 · avg 7.6 kt · gust 10.8 kt11:19 · avg 11.0 kt · gust 18.9 kt11:29 · avg 7.6 kt · gust 14.6 kt11:39 · avg 9.8 kt · gust 13.0 kt11:49 · avg 7.6 kt · gust 13.5 kt11:59 · avg 6.4 kt · gust 9.2 kt12:19 · avg 5.5 kt · gust 9.2 kt12:29 · avg 5.2 kt · gust 9.2 kt12:39 · avg 4.8 kt · gust 9.2 kt12:49 · avg 7.0 kt · gust 10.3 kt12:59 · avg 8.4 kt · gust 10.8 kt13:09 · avg 6.4 kt · gust 9.2 kt13:19 · avg 5.9 kt · gust 9.2 kt13:29 · avg 3.6 kt · gust 6.5 kt13:39 · avg 3.6 kt · gust 6.5 kt13:49 · avg 3.6 kt · gust 5.9 kt13:59 · avg 4.1 kt · gust 5.9 kt14:09 · avg 4.0 kt · gust 5.9 kt14:19 · avg 2.0 kt · gust 3.2 kt14:29 · avg 1.6 kt · gust 3.2 kt14:39 · avg 0.8 kt · gust 3.2 kt14:49 · avg 0.4 kt · gust 3.2 kt14:59 · avg 0.5 kt · gust 2.2 kt15:09 · avg 1.1 kt · gust 4.3 kt15:19 · avg 4.8 kt · gust 13.5 kt15:29 · avg 13.1 kt · gust 22.1 kt15:39 · avg 12.2 kt · gust 17.3 kt15:49 · avg 11.3 kt · gust 17.8 kt16:32 · avg 10.8 kt · gust 11.9 kt17:38 · avg 1.7 kt · gust 4.3 kt17:49 · avg 3.2 kt · gust 3.2 kt17:59 · avg 2.0 kt · gust 4.9 kt18:00 · avg 4.3 kt · gust 4.3 kt18:19 · avg 1.9 kt · gust 3.2 kt18:29 · avg 1.1 kt · gust 2.2 kt18:30 · avg 0.0 kt · gust 1.6 kt19:19 · avg 4.3 kt · gust 6.5 kt
avg wind gust ignition (8 kt) session (11 kt)
For Jul 15, 2026 · as written at the time

NO GO

700 hPa crossflow 28 kt — valley decoupled

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

🤖 ML — logistic experimental GO GO 51% · MAYBE 25% · NO GO 23%

Strongest inputs — (+) morning solar, pressure Δ (thermik); (−) rained yesterday.

🤖 ML — HGB · black box experimental MAYBE GO 9% · MAYBE 88% · NO GO 3%

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.