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)

Nov 3, 2026

81106:0021:0011:34 ยท avg 7.3 kt ยท gust 10.3 kt12:19 ยท avg 7.6 kt ยท gust 8.6 kt12:21 ยท avg 8.6 kt ยท gust 9.2 kt13:09 ยท avg 7.1 kt ยท gust 9.2 kt13:55 ยท avg 8.4 kt ยท gust 13.0 kt14:39 ยท avg 8.1 kt ยท gust 10.8 kt14:43 ยท avg 7.7 kt ยท gust 10.8 kt
avg wind gust ignition (8 kt) session (11 kt)
For Nov 3, 2026

NO GO

100% daytime cloud + only 201 W/mยฒ solar โ€” no insolation to drive a thermal

๐Ÿค– ML โ€” logistic experimental NO GO GO 13% ยท MAYBE 14% ยท NO GO 73%

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

๐Ÿค– ML โ€” HGB ยท black box experimental NO GO GO 0% ยท MAYBE 0% ยท NO GO 100%

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.