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 โ€” logistic (experimental)
ML-based forecast โ€” HistGradientBoosting (black-box model, experimental)
Actual measurements (session โ‰ฅ 1 h)
Mon Oct 12 Tue Nov 10
session (โ‰ฅ 1 h โ‰ฅ 11 kt) marginal (โ‰ฅ 1 h โ‰ฅ 8 kt) no wind no data thunderstorm (forecast rows: predicted ยท actual row: observed)

Oct 27, 2026

81106:0021:0008:19 ยท avg 3.2 kt ยท gust 4.3 kt08:21 ยท avg 4.6 kt ยท gust 4.9 kt08:49 ยท avg 4.0 kt ยท gust 4.9 kt08:55 ยท avg 3.5 kt ยท gust 4.3 kt09:39 ยท avg 3.2 kt ยท gust 4.9 kt09:49 ยท avg 4.3 kt ยท gust 6.5 kt09:59 ยท avg 4.2 kt ยท gust 4.9 kt10:09 ยท avg 4.3 kt ยท gust 4.9 kt10:19 ยท avg 4.1 kt ยท gust 4.9 kt10:29 ยท avg 4.2 kt ยท gust 4.9 kt10:36 ยท avg 4.4 kt ยท gust 4.9 kt10:49 ยท avg 4.3 kt ยท gust 4.9 kt10:58 ยท avg 4.3 kt ยท gust 4.9 kt11:43 ยท avg 3.2 kt ยท gust 4.3 kt12:44 ยท avg 2.2 kt ยท gust 3.2 kt13:45 ยท avg 0.5 kt ยท gust 0.5 kt14:47 ยท avg 1.8 kt ยท gust 2.2 kt14:59 ยท avg 8.3 kt ยท gust 11.9 kt15:09 ยท avg 9.6 kt ยท gust 11.9 kt15:19 ยท avg 9.7 kt ยท gust 13.0 kt15:29 ยท avg 7.3 kt ยท gust 11.9 kt15:39 ยท avg 4.0 kt ยท gust 7.6 kt15:49 ยท avg 3.7 kt ยท gust 7.6 kt15:59 ยท avg 3.0 kt ยท gust 7.6 kt16:09 ยท avg 4.8 kt ยท gust 9.2 kt16:19 ยท avg 3.5 kt ยท gust 6.5 kt16:29 ยท avg 4.7 kt ยท gust 8.6 kt16:38 ยท avg 3.1 kt ยท gust 6.5 kt
avg wind gust ignition (8 kt) session (11 kt)
For Oct 27, 2026

MAYBE

ฮ”=-1.6 hPa โ€” pressure gradient pushing against the thermal

๐Ÿค– ML โ€” logistic experimental GO GO 50% ยท MAYBE 29% ยท NO GO 20%

Strongest inputs โ€” (+) dew-point spread, Bolzano pressure; (โˆ’) morning solar.

๐Ÿค– ML โ€” HGB ยท black box experimental MAYBE GO 32% ยท MAYBE 53% ยท NO GO 15%

Most distinctive inputs: Innsbruck pressure, Bolzano pressure, Munich pressure.

Experimental shadow models โ€” they never drive the verdict. How good are they? โ†’

Previous forecast method

How the day was forecast at the time, before the rules were recalibrated โ€” shown for comparison only.