Submarius
The water clarity forecast.
Published April 16, 2026 · Last updated October 14, 2026
Submarius estimates horizontal underwater visibility, in feet or meters, for any coastal point. It starts from that location's typical clarity for the time of year, built from diver surveys and in water measurements with satellite ocean color filling the gaps, then adjusts for what changes day to day: wave stirring judged against depth and bottom type, and tide driven water movement. Each estimate shows a low to high range and a confidence percentage.
Most marine apps use surface chop as a stand in for visibility, which fails in bays, sounds, and estuaries. Submarius forecasts the visibility itself.
How the forecast works.
The visibility number comes out of a model, not a lookup table. It works in five stages:
Each stretch of coast gets a typical visibility for every month of the year, built from diver surveys and in water measurements. Where those records are thin, satellite ocean color fills the gap.
Wave and tide driven stirring of sediment pulls visibility down, or lets it recover, judged against depth and the bottom. In months when a spot's water usually runs greener with algae, the low end of the range widens. We make no call on whether a bloom is harmful.
Where we have no record of a spot's typical clarity, an older model answers instead. It works out how much the water absorbs and scatters light from satellite ocean color (NOAA CoastWatch VIIRS and Copernicus), turns that into horizontal diver visibility with a light model (Mobley and Duntley), and adjusts for river discharge, runoff and blooms seen in satellite chlorophyll.
A calibration layer scores the model against public in water measurements (the Water Quality Portal, AERONET OC ocean color sites) and refits its priors weekly. A bounded machine learning correction, trained on those real measurements and constrained by the physics, removes systematic error. Fresh post dive reports nearby can nudge an estimate for a few hours, within tight limits. They never train or check the model.
Every estimate is a range (a low, a typical and a high figure), not one falsely precise number. Spots unlike anything we've calibrated on get wider ranges, every estimate carries a confidence percentage, and if the model can't produce an estimate for a spot, the tile shows "no data" instead of a number.
What the drawer actually shows you.
Tap the Visibility card in the app and you drop into an immersive underwater scene: a dogtooth tuna swimming at 20 feet, a diver silhouette at 40 feet, both faded with Beer Lambert light attenuation at the current vis level. The fish fades. The diver fades harder. You can see what the number means, not just read it.
Below the scene: the visibility estimate, confidence percentage, reason, and a 24 hour forecast trend. No hype. No "WATER IS GREAT!" buttons.
Honesty over hype.
A cornerstone principle at Submarius is the data honesty rule: we never claim what we don't measure. If we're using a proxy (like swell height as a "surface state" hint), we label it as a proxy.
Every estimate carries a confidence percentage, and if the model can't produce an estimate for a spot, the visibility tile shows "no data" instead of a number. A user who's burned by a "GOOD" verdict on a blown out day loses trust forever. Trust is the product.
Yes, there's machine learning in it, but on a short leash: a bounded correction on top of a physics model, trained on real in water measurements, with every input and the uncertainty always shown. Not an "AI" black box that invents a number.
Looking past today.
The Water Clarity map layer runs 48 hours ahead in 3 hour steps, and it's free. Pro carries the visibility estimate through days 2 to 8 of the forecast. The best window on the Today screen is a different thing: the best 3 hours in the next 24, picked on the whole verdict for your activity, not on clarity alone.
Your spot stays private.
Vis reports are anonymous. Fresh ones nearby can nudge the estimate for a few hours, within tight limits, and they never train or check the model. When you rate the visibility after a dive, the app sends the location you're looking at, and the server snaps it to a grid cell about 5 km across before anything is saved. The exact point is never stored. If a Submarius employee queried the database tomorrow, they'd see a rating in a general area, not your spot.
Common questions.
We don't read it off a single satellite number. The forecast starts from each location's typical clarity for the time of year, built from diver surveys and in water measurements, with satellite ocean color filling the gaps. Then it adjusts for what changes day to day: wave stirring judged against depth and bottom type, and tide driven water movement. Every estimate shows a low to high range and a confidence percentage.
Most marine weather apps use surface only signals (wave height, swell) as a proxy for visibility. That breaks down in estuaries, bays, and coastlines where the water can be turbid regardless of how flat the surface is. A clarity forecast has to start from what the water at that spot is usually like and then account for what's stirring it up, which a wave model alone can't do.
It's checked against public in water measurements (the EPA Water Quality Portal and AERONET OC ocean color sites). The older fallback model draws on the Lee 2015 relationship, which reports R² = 0.96 in the reference literature; that is the published theory, not our field accuracy. We are preparing a public calibration page with our own measured error by region. Every estimate carries a confidence percentage, and if the model can't produce an estimate for a spot, the app shows no data instead of a number.
Evidence and related reading.
- Diving conditions by location, where each location page shows the visibility estimate.
- Spearfishing conditions by location, with the same estimate for every spot, plus the spearfishing map.
- Weekly water clarity reports: the model's regional reads, published every Tuesday.
- How to read diving conditions: the plain English guide to the signals.
- Ocean conditions glossary: 77 terms, from Secchi depth to slack tide.
- How to predict water visibility and the Kd490 deep dive.
- Public methodology docs: data source citations and feature explainers.
See today's visibility estimate for your spot.
Want to measure it yourself?
We are designing an affordable clarity sensor you could anchor at your own spot, from open ocean to an inland spring. Tell us what it would need to do.
Take the 3 minute survey