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)
Wed Sep 23 Thu Oct 22
session (≥ 1 h ≥ 11 kt) marginal (≥ 1 h ≥ 8 kt) no wind no data thunderstorm (forecast rows: predicted · actual row: observed)

Oct 10, 2026

81106:0021:0008:49 · avg 2.7 kt · gust 4.3 kt09:39 · avg 2.8 kt · gust 4.3 kt10:27 · avg 1.7 kt · gust 3.2 kt12:08 · avg 0.0 kt · gust 0.0 kt12:59 · avg 0.4 kt · gust 1.6 kt13:02 · avg 0.5 kt · gust 1.6 kt13:19 · avg 1.4 kt · gust 2.2 kt13:20 · avg 0.5 kt · gust 0.5 kt13:49 · avg 0.0 kt · gust 0.0 kt13:52 · avg 0.0 kt · gust 0.0 kt14:57 · avg 0.8 kt · gust 2.2 kt15:09 · avg 0.3 kt · gust 1.6 kt15:19 · avg 0.8 kt · gust 2.2 kt15:22 · avg 0.5 kt · gust 0.5 kt16:08 · avg 0.2 kt · gust 1.6 kt17:44 · avg 2.2 kt · gust 6.5 kt
avg wind gust ignition (8 kt) session (11 kt)
For Oct 10, 2026 · as written at the time

NO GO

83% daytime cloud + only 121 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 18% · MAYBE 23% · NO GO 58%

Strongest inputs — (+) dew-point spread; (−) morning solar, rained yesterday.

🤖 ML — HGB · black box experimental MAYBE GO 0% · MAYBE 50% · NO GO 50%

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