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 1, 2026

81106:0021:0009:28 ยท avg 9.7 kt ยท gust 11.9 kt09:59 ยท avg 5.9 kt ยท gust 9.2 kt10:09 ยท avg 8.3 kt ยท gust 11.9 kt10:19 ยท avg 7.4 kt ยท gust 13.0 kt10:29 ยท avg 6.5 kt ยท gust 11.9 kt10:59 ยท avg 7.4 kt ยท gust 10.3 kt11:09 ยท avg 6.5 kt ยท gust 9.2 kt11:19 ยท avg 7.3 kt ยท gust 11.9 kt11:27 ยท avg 8.9 kt ยท gust 13.5 kt12:09 ยท avg 9.2 kt ยท gust 11.9 kt12:19 ยท avg 8.5 kt ยท gust 10.8 kt12:29 ยท avg 7.4 kt ยท gust 10.3 kt12:39 ยท avg 7.0 kt ยท gust 10.3 kt12:49 ยท avg 8.4 kt ยท gust 11.9 kt12:59 ยท avg 10.0 kt ยท gust 13.5 kt13:09 ยท avg 8.6 kt ยท gust 13.5 kt13:19 ยท avg 9.0 kt ยท gust 11.9 kt13:29 ยท avg 8.2 kt ยท gust 10.3 kt13:39 ยท avg 9.9 kt ยท gust 13.5 kt13:49 ยท avg 10.5 kt ยท gust 15.1 kt13:59 ยท avg 9.2 kt ยท gust 14.6 kt14:09 ยท avg 7.8 kt ยท gust 13.0 kt14:19 ยท avg 7.7 kt ยท gust 10.8 kt14:29 ยท avg 8.8 kt ยท gust 13.0 kt14:39 ยท avg 4.4 kt ยท gust 8.6 kt14:49 ยท avg 4.5 kt ยท gust 10.3 kt14:59 ยท avg 9.7 kt ยท gust 14.6 kt15:09 ยท avg 10.6 kt ยท gust 13.5 kt15:13 ยท avg 10.7 kt ยท gust 13.0 kt15:39 ยท avg 7.6 kt ยท gust 9.2 kt15:49 ยท avg 6.2 kt ยท gust 9.2 kt15:52 ยท avg 6.3 kt ยท gust 7.6 kt
avg wind gust ignition (8 kt) session (11 kt)
For Nov 1, 2026 ยท as written at the time

NO GO

98% daytime cloud + only 138 W/mยฒ solar โ€” no insolation to drive a thermal

๐Ÿค– ML โ€” logistic experimental NO GO GO 12% ยท MAYBE 24% ยท NO GO 64%

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

๐Ÿค– ML โ€” HGB ยท black box experimental NO GO GO 8% ยท MAYBE 3% ยท NO GO 89%

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.