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 18, 2026

81106:0021:0006:15 · avg 1.1 kt · gust 3.2 kt06:29 · avg 3.9 kt · gust 6.5 kt06:39 · avg 3.9 kt · gust 6.5 kt06:49 · avg 1.2 kt · gust 3.2 kt06:59 · avg 0.8 kt · gust 2.2 kt07:09 · avg 0.4 kt · gust 2.2 kt07:19 · avg 0.8 kt · gust 2.2 kt07:29 · avg 1.0 kt · gust 2.2 kt07:39 · avg 1.4 kt · gust 3.2 kt07:49 · avg 1.5 kt · gust 3.2 kt07:59 · avg 1.3 kt · gust 3.2 kt08:09 · avg 0.9 kt · gust 2.2 kt08:19 · avg 0.3 kt · gust 1.6 kt08:29 · avg 0.6 kt · gust 2.2 kt08:39 · avg 2.0 kt · gust 3.2 kt08:49 · avg 1.2 kt · gust 2.2 kt08:59 · avg 1.1 kt · gust 2.2 kt09:09 · avg 0.8 kt · gust 2.2 kt09:19 · avg 0.3 kt · gust 1.6 kt09:29 · avg 0.1 kt · gust 0.5 kt09:39 · avg 0.2 kt · gust 1.6 kt09:49 · avg 0.2 kt · gust 1.6 kt09:59 · avg 0.6 kt · gust 3.2 kt10:09 · avg 6.1 kt · gust 13.5 kt10:19 · avg 10.8 kt · gust 14.6 kt10:29 · avg 9.8 kt · gust 13.0 kt10:39 · avg 9.4 kt · gust 13.5 kt10:49 · avg 8.9 kt · gust 13.5 kt10:59 · avg 10.0 kt · gust 15.1 kt11:09 · avg 8.4 kt · gust 13.0 kt11:19 · avg 8.5 kt · gust 13.0 kt11:29 · avg 7.2 kt · gust 11.9 kt11:39 · avg 5.8 kt · gust 11.9 kt11:49 · avg 6.4 kt · gust 11.9 kt11:59 · avg 8.9 kt · gust 13.0 kt12:09 · avg 6.7 kt · gust 10.8 kt12:19 · avg 7.1 kt · gust 9.2 kt12:29 · avg 6.1 kt · gust 10.3 kt12:39 · avg 1.2 kt · gust 6.5 kt12:49 · avg 0.5 kt · gust 4.3 kt12:59 · avg 3.7 kt · gust 5.9 kt13:09 · avg 3.6 kt · gust 4.9 kt13:19 · avg 4.2 kt · gust 11.9 kt13:29 · avg 6.0 kt · gust 11.9 kt13:39 · avg 2.0 kt · gust 4.3 kt13:49 · avg 5.4 kt · gust 8.6 kt13:59 · avg 6.0 kt · gust 7.6 kt14:09 · avg 3.1 kt · gust 4.9 kt14:19 · avg 1.7 kt · gust 3.2 kt14:29 · avg 2.8 kt · gust 5.9 kt14:39 · avg 3.4 kt · gust 6.5 kt14:49 · avg 3.1 kt · gust 8.6 kt14:59 · avg 5.9 kt · gust 10.3 kt15:09 · avg 3.0 kt · gust 8.6 kt15:19 · avg 2.4 kt · gust 4.9 kt15:29 · avg 1.6 kt · gust 3.2 kt15:39 · avg 1.7 kt · gust 3.2 kt15:49 · avg 1.9 kt · gust 9.2 kt15:59 · avg 9.6 kt · gust 25.9 kt16:09 · avg 4.9 kt · gust 9.2 kt16:19 · avg 4.3 kt · gust 7.6 kt16:29 · avg 2.0 kt · gust 4.9 kt16:39 · avg 1.4 kt · gust 4.3 kt16:49 · avg 2.3 kt · gust 7.6 kt16:59 · avg 5.0 kt · gust 7.6 kt17:09 · avg 1.0 kt · gust 3.2 kt17:19 · avg 0.9 kt · gust 3.2 kt17:29 · avg 2.0 kt · gust 4.3 kt17:39 · avg 1.4 kt · gust 3.2 kt17:49 · avg 1.7 kt · gust 3.2 kt17:59 · avg 2.8 kt · gust 4.3 kt18:00 · avg 2.2 kt · gust 3.2 kt18:29 · avg 4.6 kt · gust 10.3 kt18:39 · avg 4.3 kt · gust 9.2 kt18:49 · avg 3.1 kt · gust 8.6 kt18:59 · avg 2.0 kt · gust 6.5 kt19:09 · avg 2.0 kt · gust 3.2 kt19:15 · avg 1.7 kt · gust 2.2 kt
avg wind gust ignition (8 kt) session (11 kt)
For Jul 18, 2026 · as written at the time

NO GO

88% daytime cloud + only 380 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 13% · MAYBE 13% · NO GO 73%

Strongest inputs — (−) pressure Δ (thermik), CAPE, morning solar.

🤖 ML — HGB · black box experimental NO GO GO 5% · MAYBE 22% · NO GO 72%

Most distinctive inputs: morning solar, Innsbruck pressure, daytime cloud.

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.