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 β€” logistic (experimental)
ML-based forecast β€” HistGradientBoosting (black-box model, experimental)
Actual measurements (session β‰₯ 1 h)
Wed Sep 23 Thu Oct 22
session (β‰₯ 1 h β‰₯ 11 kt) marginal (β‰₯ 1 h β‰₯ 8 kt) no wind no data thunderstorm (forecast rows: predicted Β· actual row: observed)

Oct 8, 2026

81106:0021:0008:29 Β· avg 1.3 kt Β· gust 2.2 kt08:39 Β· avg 0.4 kt Β· gust 1.6 kt08:49 Β· avg 0.1 kt Β· gust 1.6 kt08:59 Β· avg 0.5 kt Β· gust 1.6 kt09:09 Β· avg 0.0 kt Β· gust 0.0 kt09:19 Β· avg 0.1 kt Β· gust 0.5 kt09:29 Β· avg 1.8 kt Β· gust 3.2 kt09:39 Β· avg 0.7 kt Β· gust 1.6 kt09:46 Β· avg 1.1 kt Β· gust 2.2 kt10:19 Β· avg 0.0 kt Β· gust 0.0 kt10:29 Β· avg 0.0 kt Β· gust 0.0 kt10:39 Β· avg 0.1 kt Β· gust 1.6 kt10:49 Β· avg 0.2 kt Β· gust 0.5 kt10:59 Β· avg 0.5 kt Β· gust 2.2 kt11:09 Β· avg 2.3 kt Β· gust 4.3 kt11:19 Β· avg 3.6 kt Β· gust 10.3 kt11:29 Β· avg 9.4 kt Β· gust 10.8 kt11:39 Β· avg 9.2 kt Β· gust 10.8 kt11:49 Β· avg 9.7 kt Β· gust 13.0 kt11:59 Β· avg 9.7 kt Β· gust 13.0 kt12:09 Β· avg 9.4 kt Β· gust 11.9 kt12:19 Β· avg 9.3 kt Β· gust 11.9 kt12:29 Β· avg 8.8 kt Β· gust 10.8 kt12:39 Β· avg 8.5 kt Β· gust 13.0 kt12:49 Β· avg 7.9 kt Β· gust 13.0 kt13:36 Β· avg 8.6 kt Β· gust 11.9 kt14:19 Β· avg 7.6 kt Β· gust 8.6 kt14:29 Β· avg 8.6 kt Β· gust 10.8 kt14:39 Β· avg 8.7 kt Β· gust 10.8 kt14:43 Β· avg 7.9 kt Β· gust 9.2 kt16:00 Β· avg 3.2 kt Β· gust 4.3 kt16:29 Β· avg 0.8 kt Β· gust 1.6 kt16:59 Β· avg 11.2 kt Β· gust 17.3 kt
avg wind gust ignition (8 kt) session (11 kt)
For Oct 8, 2026 Β· as written at the time

NO GO

92% daytime cloud + only 310 W/mΒ² solar β€” no insolation to drive a thermal

⚑ Storm risk: the thermal often runs well until the front β€” watch the sky, come in early.

πŸ€– ML β€” logistic experimental NO GO GO 22% Β· MAYBE 14% Β· NO GO 65%

Strongest inputs β€” (+) FΓΆhn Ξ”; (βˆ’) morning solar, pressure Ξ” (thermik).

πŸ€– ML β€” HGB Β· black box experimental NO GO GO 23% Β· MAYBE 0% Β· NO GO 77%

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

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

Previous forecast method

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