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 12, 2026

81106:0021:0008:29 Β· avg 1.4 kt Β· gust 4.3 kt09:19 Β· avg 3.0 kt Β· gust 4.9 kt09:29 Β· avg 2.5 kt Β· gust 4.9 kt09:39 Β· avg 2.5 kt Β· gust 5.9 kt09:49 Β· avg 2.0 kt Β· gust 5.9 kt09:59 Β· avg 1.5 kt Β· gust 3.2 kt10:09 Β· avg 1.1 kt Β· gust 3.2 kt10:19 Β· avg 1.1 kt Β· gust 3.2 kt10:29 Β· avg 0.8 kt Β· gust 2.2 kt10:39 Β· avg 0.5 kt Β· gust 2.2 kt10:49 Β· avg 0.6 kt Β· gust 1.6 kt10:59 Β· avg 0.4 kt Β· gust 1.6 kt11:09 Β· avg 0.4 kt Β· gust 1.6 kt11:19 Β· avg 5.8 kt Β· gust 10.3 kt11:29 Β· avg 7.7 kt Β· gust 10.3 kt11:39 Β· avg 7.8 kt Β· gust 10.8 kt11:49 Β· avg 8.8 kt Β· gust 10.8 kt11:59 Β· avg 10.5 kt Β· gust 13.0 kt12:09 Β· avg 10.1 kt Β· gust 13.0 kt12:19 Β· avg 10.2 kt Β· gust 13.0 kt12:29 Β· avg 10.4 kt Β· gust 13.0 kt12:39 Β· avg 10.4 kt Β· gust 13.0 kt12:49 Β· avg 10.8 kt Β· gust 13.5 kt12:59 Β· avg 10.9 kt Β· gust 13.5 kt13:09 Β· avg 10.6 kt Β· gust 13.5 kt13:19 Β· avg 11.6 kt Β· gust 14.6 kt13:29 Β· avg 11.2 kt Β· gust 13.5 kt13:39 Β· avg 11.0 kt Β· gust 14.6 kt13:49 Β· avg 11.1 kt Β· gust 13.5 kt13:59 Β· avg 11.0 kt Β· gust 14.6 kt14:09 Β· avg 10.8 kt Β· gust 13.5 kt14:19 Β· avg 10.8 kt Β· gust 13.0 kt14:29 Β· avg 11.4 kt Β· gust 13.5 kt14:39 Β· avg 10.4 kt Β· gust 13.5 kt14:49 Β· avg 10.8 kt Β· gust 14.6 kt14:59 Β· avg 10.8 kt Β· gust 13.5 kt15:09 Β· avg 11.2 kt Β· gust 13.5 kt15:19 Β· avg 10.9 kt Β· gust 15.1 kt15:29 Β· avg 10.9 kt Β· gust 14.6 kt15:39 Β· avg 11.1 kt Β· gust 13.5 kt15:49 Β· avg 10.7 kt Β· gust 15.1 kt15:59 Β· avg 10.6 kt Β· gust 13.5 kt16:09 Β· avg 10.3 kt Β· gust 13.0 kt16:19 Β· avg 10.4 kt Β· gust 13.0 kt16:29 Β· avg 10.5 kt Β· gust 13.0 kt16:39 Β· avg 10.5 kt Β· gust 13.0 kt16:49 Β· avg 9.2 kt Β· gust 10.8 kt16:59 Β· avg 9.0 kt Β· gust 13.0 kt17:09 Β· avg 9.3 kt Β· gust 11.9 kt17:19 Β· avg 8.9 kt Β· gust 10.3 kt17:29 Β· avg 9.2 kt Β· gust 11.9 kt17:39 Β· avg 9.7 kt Β· gust 11.9 kt17:49 Β· avg 9.2 kt Β· gust 11.9 kt17:59 Β· avg 8.9 kt Β· gust 10.8 kt18:09 Β· avg 8.8 kt Β· gust 10.8 kt18:19 Β· avg 8.8 kt Β· gust 10.8 kt18:29 Β· avg 8.5 kt Β· gust 10.8 kt
avg wind gust ignition (8 kt) session (11 kt)
For Oct 12, 2026 Β· as written at the time

MAYBE

dew-point spread 2.0Β°C β€” air too moist, solar energy lost to evaporation

πŸ€– ML β€” logistic experimental NO GO GO 18% Β· MAYBE 22% Β· NO GO 60%

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

πŸ€– ML β€” HGB Β· black box experimental NO GO GO 0% Β· MAYBE 2% Β· NO GO 98%

Most distinctive inputs: Innsbruck pressure, overnight cloud, Bolzano 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.