Walchensee wind: forecast and measurements

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 Aug 20 Fri Sep 18
session (≥ 1 h ≥ 11 kt) marginal (≥ 1 h ≥ 8 kt) no wind no data thunderstorm (forecast rows: predicted · actual row: observed)

Aug 25, 2026

81106:0021:0009:29 · avg 10.7 kt · gust 13.5 kt09:39 · avg 11.9 kt · gust 13.0 kt09:49 · avg 12.0 kt · gust 15.1 kt09:59 · avg 11.7 kt · gust 14.6 kt10:09 · avg 11.7 kt · gust 15.1 kt10:12 · avg 10.3 kt · gust 11.9 kt10:39 · avg 10.8 kt · gust 11.9 kt10:49 · avg 10.4 kt · gust 14.6 kt10:59 · avg 11.0 kt · gust 15.1 kt11:08 · avg 11.9 kt · gust 15.1 kt11:10 · avg 11.9 kt · gust 14.6 kt12:12 · avg 12.4 kt · gust 18.9 kt12:57 · avg 10.1 kt · gust 13.5 kt13:09 · avg 8.6 kt · gust 13.5 kt13:19 · avg 9.4 kt · gust 13.0 kt13:22 · avg 7.0 kt · gust 7.6 kt13:48 · avg 8.9 kt · gust 10.3 kt14:19 · avg 7.3 kt · gust 9.2 kt14:29 · avg 5.3 kt · gust 8.6 kt14:39 · avg 3.0 kt · gust 7.6 kt14:49 · avg 2.3 kt · gust 4.3 kt14:59 · avg 2.2 kt · gust 4.9 kt15:09 · avg 2.8 kt · gust 6.5 kt15:19 · avg 3.9 kt · gust 5.9 kt15:29 · avg 3.1 kt · gust 4.9 kt15:39 · avg 1.7 kt · gust 3.2 kt15:49 · avg 1.0 kt · gust 4.3 kt15:59 · avg 0.0 kt · gust 0.5 kt16:09 · avg 0.0 kt · gust 0.0 kt16:19 · avg 0.4 kt · gust 2.2 kt16:29 · avg 0.5 kt · gust 2.2 kt16:39 · avg 0.2 kt · gust 2.2 kt16:49 · avg 1.4 kt · gust 4.3 kt16:59 · avg 1.6 kt · gust 3.2 kt17:09 · avg 1.6 kt · gust 3.2 kt17:19 · avg 1.4 kt · gust 3.2 kt17:29 · avg 0.1 kt · gust 1.6 kt17:39 · avg 0.7 kt · gust 2.2 kt17:49 · avg 0.1 kt · gust 2.2 kt17:59 · avg 0.0 kt · gust 0.0 kt18:09 · avg 0.0 kt · gust 0.0 kt18:19 · avg 0.0 kt · gust 0.0 kt18:29 · avg 0.0 kt · gust 0.0 kt18:39 · avg 1.9 kt · gust 3.2 kt18:49 · avg 1.8 kt · gust 3.2 kt18:50 · avg 1.6 kt · gust 1.6 kt
avg wind gust ignition (8 kt) session (11 kt)
For Aug 25, 2026 · as written at the time

NO GO

100% daytime cloud + only 110 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 16% · MAYBE 9% · NO GO 75%

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

🤖 ML — HGB · black box experimental NO GO GO 0% · MAYBE 8% · NO GO 92%

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