History
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 โ logistic (experimental)
ML-based forecast โ HistGradientBoosting (black-box model, experimental)
Actual measurements (session โฅ 1 h)
Thu Jun 25
Fri Jul 24
session (โฅ 1 h โฅ 11 kt)
marginal (โฅ 1 h โฅ 8 kt)
no wind
no data
thunderstorm (forecast rows: predicted ยท actual row: observed)
Jul 24, 2026
For today, Jul 24, 2026
GO
13 of 14 rules green.
๐ค ML โ logistic
experimental
NO GO
GO 24% ยท
MAYBE 17% ยท
NO GO 58%
Strongest inputs โ
(+) morning solar; (โ) pressure ฮ (thermik), dew-point spread.
๐ค ML โ HGB ยท black box
experimental
NO GO
GO 2% ยท
MAYBE 1% ยท
NO GO 98%
Most distinctive inputs: morning solar, Innsbruck pressure, Bolzano pressure.
Experimental shadow models โ they never drive the verdict.
How good are they? โ
How the day was forecast at the time, before the rules were recalibrated โ shown for comparison only.