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)
Sep 10, 2026
avg wind
gust
ignition (8 kt)
session (11 kt)
For Sep 10, 2026 Β·
as written at the time
GO
9 of 14 rules green.
π€ ML β logistic
experimental
NO GO
GO 15% Β·
MAYBE 22% Β·
NO GO 63%
Strongest inputs β
(β) pressure Ξ (thermik), morning solar, FΓΆhn Ξ.
π€ ML β HGB Β· black box
experimental
NO GO
GO 2% Β·
MAYBE 1% Β·
NO GO 97%
Most distinctive inputs: morning solar, Innsbruck 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.