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 2, 2026

81106:0021:0007:49 ยท avg 3.5 kt ยท gust 6.5 kt08:33 ยท avg 6.2 kt ยท gust 6.5 kt09:17 ยท avg 4.3 kt ยท gust 7.6 kt09:22 ยท avg 4.5 kt ยท gust 5.9 kt09:39 ยท avg 4.2 kt ยท gust 7.6 kt09:49 ยท avg 3.4 kt ยท gust 4.9 kt09:59 ยท avg 2.8 kt ยท gust 4.3 kt10:09 ยท avg 2.4 kt ยท gust 4.3 kt10:19 ยท avg 2.9 kt ยท gust 4.9 kt10:29 ยท avg 2.9 kt ยท gust 4.9 kt10:39 ยท avg 2.1 kt ยท gust 4.3 kt10:49 ยท avg 1.2 kt ยท gust 2.2 kt10:59 ยท avg 1.0 kt ยท gust 3.2 kt11:09 ยท avg 4.5 kt ยท gust 10.3 kt11:19 ยท avg 7.9 kt ยท gust 10.8 kt11:29 ยท avg 9.2 kt ยท gust 10.8 kt11:39 ยท avg 8.3 kt ยท gust 10.3 kt11:49 ยท avg 8.6 kt ยท gust 10.8 kt11:59 ยท avg 8.8 kt ยท gust 10.8 kt12:09 ยท avg 8.6 kt ยท gust 10.8 kt12:19 ยท avg 8.4 kt ยท gust 10.8 kt12:29 ยท avg 8.6 kt ยท gust 11.9 kt12:39 ยท avg 9.1 kt ยท gust 13.0 kt12:49 ยท avg 8.2 kt ยท gust 10.8 kt12:59 ยท avg 8.2 kt ยท gust 10.8 kt13:04 ยท avg 9.1 kt ยท gust 11.9 kt
avg wind gust ignition (8 kt) session (11 kt)
For Nov 2, 2026

NO GO

96% daytime cloud + only 350 W/mยฒ solar โ€” no insolation to drive a thermal

๐Ÿค– ML โ€” logistic experimental NO GO GO 24% ยท MAYBE 24% ยท NO GO 52%

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

๐Ÿค– ML โ€” HGB ยท black box experimental NO GO GO 16% ยท MAYBE 20% ยท NO GO 64%

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.