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 โ€” logistic (experimental)
ML-based forecast โ€” HistGradientBoosting (black-box model, experimental)
Actual measurements (session โ‰ฅ 1 h)
Mon Oct 12 Tue Nov 10
session (โ‰ฅ 1 h โ‰ฅ 11 kt) marginal (โ‰ฅ 1 h โ‰ฅ 8 kt) no wind no data thunderstorm (forecast rows: predicted ยท actual row: observed)

Oct 28, 2026

81106:0021:0008:49 ยท avg 2.2 kt ยท gust 3.2 kt08:52 ยท avg 1.8 kt ยท gust 3.2 kt09:39 ยท avg 0.2 kt ยท gust 0.5 kt10:26 ยท avg 2.4 kt ยท gust 4.3 kt11:15 ยท avg 1.6 kt ยท gust 1.6 kt12:16 ยท avg 13.5 kt ยท gust 16.2 kt12:45 ยท avg 14.7 kt ยท gust 24.3 kt
avg wind gust ignition (8 kt) session (11 kt)
For Oct 28, 2026 ยท as written at the time

NO GO

100% daytime cloud + only 64 W/mยฒ solar โ€” no insolation to drive a thermal

๐Ÿค– ML โ€” logistic experimental MAYBE GO 16% ยท MAYBE 50% ยท NO GO 34%

Strongest inputs โ€” (+) pressure ฮ” (thermik), dew-point spread; (โˆ’) morning solar.

๐Ÿค– ML โ€” HGB ยท black box experimental MAYBE GO 3% ยท MAYBE 78% ยท NO GO 19%

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

Experimental shadow models โ€” they never drive the verdict. How good are they? โ†’

Previous forecast method

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