30 days of forecast vs. what actually happened at the lake. Click a single day to see its details.
Aug 28, 2026
avg wind
gust
ignition (8 kt)
session (11 kt)
For Aug 28, 2026 Β·
as written at the time
NO GO
700 hPa crossflow 33 kt β valley decoupled
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 31% Β·
MAYBE 21% Β·
NO GO 48%
Strongest inputs β
(+) FΓΆhn Ξ; (β) dew-point spread, CAPE.
π€ ML β HGB Β· black box
experimental
NO GO
GO 14% Β·
MAYBE 0% Β·
NO GO 86%
Most distinctive inputs: Innsbruck pressure, Bolzano pressure, Munich pressure.
Experimental shadow models β they never drive the verdict.
How good are they? β