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)
Mon Oct 12
Tue Nov 10
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 23, 2026
avg wind
gust
ignition (8 kt)
session (11 kt)
For Oct 23, 2026 Β·
as written at the time
NO GO
850 hPa 20 kt from 200Β° (SSE) β counters the N-thermal
π€ ML β logistic
experimental
MAYBE
GO 21% Β·
MAYBE 46% Β·
NO GO 34%
Strongest inputs β
(+) FΓΆhn Ξ; (β) morning solar, dew-point spread.
π€ ML β HGB Β· black box
experimental
GO
GO 71% Β·
MAYBE 0% Β·
NO GO 29%
Most distinctive inputs: morning solar, Innsbruck pressure, Bolzano pressure.
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.