Settle.
loading

Today's visibility was decided
days ago.

Six days of swell and wind history at each site, run through bottom-stirring physics, then allowed to settle three days forward. Every weather model is carried through separately, so what you get is a distribution, not a guess with a decimal point.

Fetching ECMWF, MFWAM, GFS-Wave, GWAM and ICON…

Right now

10th–90th percentile Median Bottom stirring Now — measured history to the left Gate: go / marginal / no-go

Where this is

satellite
Site No-take MPA zone

Next three days

daylight hours

Where the uncertainty comes from

Wave models disagree Wind models disagree Site parameters unknown

Dive log

Import history

one line per dive

Paste past dives, one per line — date, time, site, visibility. Order does not matter and the parser is lenient: 2025-06-14, 09:00, Buffels, 6 and 2025/07/02 14h bakoven 3.5 both work. Each dive gets its own ten days of archived swell and wind pulled from ERA5, so the fit is reproducible.

Raw values

3-hourly · ensemble median · SAST
Site profile

These are my guesses about your sites, and they are the weakest part of the model. Move them until the output matches dives you remember, or log dives and let the fit move the ones it can actually see. Anything you change here becomes the prior the fit starts from.

Add a site

Pick from the curated list of Cape Peninsula sites above, or add your own by name and position. Geometry (which way it faces the swell, wind shelter) is filled in from a coarse Atlantic-seaboard-vs-False-Bay heuristic — close enough to get a first forecast running, not a substitute for local knowledge. The freediving safety gates are never guessed: every new site starts at a fixed, cautious placeholder () and stays editable in the panel above the moment the site is added.

How the number is made