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 — logistic (experimental)
ML-based forecast — HistGradientBoosting (black-box model, experimental)
Actual measurements (session ≥ 1 h)
Thu Aug 20
Fri Sep 18
session (≥ 1 h ≥ 11 kt)
marginal (≥ 1 h ≥ 8 kt)
no wind
no data
thunderstorm (forecast rows: predicted · actual row: observed)
Sep 14, 2026
avg wind
gust
ignition (8 kt)
session (11 kt)
For Sep 14, 2026
NO GO
88% daytime cloud + only 368 W/m² solar — no insolation to drive a thermal
🤖 ML — logistic
experimental
NO GO
GO 19% ·
MAYBE 36% ·
NO GO 44%
Strongest inputs —
(+) dew-point spread; (−) morning solar, pressure Δ (thermik).
🤖 ML — HGB · black box
experimental
NO GO
GO 27% ·
MAYBE 2% ·
NO GO 71%
Most distinctive inputs: morning solar, Innsbruck pressure, Bolzano pressure.
Experimental shadow models — they never drive the verdict.
How good are they? →
How the day was forecast at the time, before the rules were recalibrated — shown for comparison only.