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)
Thu Aug 20
Fri Sep 18
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)
Aug 20, 2026
avg wind
gust
ignition (8 kt)
session (11 kt)
For Aug 20, 2026
GO
9 of 14 rules green.
β‘ Storm risk: the thermal often runs well until the front β watch the sky, come in early.
π€ ML β logistic
experimental
NO GO
GO 34% Β·
MAYBE 16% Β·
NO GO 50%
Strongest inputs β
(+) FΓΆhn Ξ; (β) CAPE, Innsbruck pressure.
π€ ML β HGB Β· black box
experimental
NO GO
GO 4% Β·
MAYBE 12% Β·
NO GO 84%
Most distinctive inputs: Innsbruck pressure, Bolzano pressure, overnight cloud.
Experimental shadow models β they never drive the verdict.
How good are they? β
How the day was forecast at the time, before the rules were recalibrated β shown for comparison only.