How do you measure underwater visibility?

We don't read it off a single satellite number. We combine multiple satellite ocean-color sources (NOAA CoastWatch and Copernicus) into an estimate of the water's optical properties (how strongly it absorbs and scatters light), then run a physics light-transport model to get how far a diver can actually see, capped by depth. We adjust for what changes day to day (wave- and tide-driven sediment, river plumes, runoff, algal blooms) and continuously reconcile against real in-water measurements and divers' post-dive reports. Every estimate comes with an uncertainty range and the data source behind it.

Why do other apps not have this?

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 real clarity forecast requires satellite turbidity data, river plume tracking, and geometry-aware reasoning, work that hasn't historically been done outside scientific research.

Is the forecast accurate?

It's built on published ocean optics (radiative transfer for visibility; Lee 2015 for the Secchi relationship, R²=0.96) and continuously calibrated against real in-water measurements (the EPA Water Quality Portal and AERONET-OC) and divers' post-dive reports. Every estimate carries explicit uncertainty bounds (p10/p50/p90), widens them when your spot is unlike anything we've calibrated on, and flags where we're leaning on proxies or have no direct data. It sharpens as more reports and measurements accumulate.

Water clarity

The first honest water clarity forecast.

You can't spear what you can't see. You can't enjoy a dive when the water's a brown soup. And yet every other app ignores this signal or uses surface chop as a proxy, which doesn't work in bays, sounds, or estuaries. Submarius is the first app built around a real underwater-visibility forecast.

Check today's visibility

How the forecast works.

The visibility number is the output of an ocean-optics model, not a lookup table. Five stages, built to be credible from day one and to sharpen over time:

Step 1 · Rebuild the optics

Satellite ocean-color → the water's optical properties

Multiple satellite ocean-color sources (NOAA CoastWatch VIIRS and Copernicus) are combined into an estimate of the water's inherent optical properties: how much it absorbs and scatters light. Where multi-sensor data isn't available, we derive them from Kd490 and chlorophyll (a Kirk decomposition).

Step 2 · Run the physics

Radiative-transfer light model

A radiative-transfer forward model (Mobley + Duntley) turns those optical properties into real horizontal diver visibility, and caps it at the depth, because you can't see past the seafloor.

Step 3 · Account for what muddies it

Physical modifiers

Physical models for wave- and tide-driven sediment resuspension, river-discharge plumes, rainfall runoff, and harmful algal blooms pull visibility down, or let it recover.

Step 4 · Calibrate against reality

Data assimilation + a bounded ML correction

A data-assimilation engine (an ensemble Kalman filter) folds in every fresh observation: satellite passes, in-water sensors (Water Quality Portal, AERONET-OC), and divers' one-tap post-dive reports. A machine-learning correction (trained on those real measurements and bounded by the physics) removes systematic error, refit weekly. The estimate sharpens with every dive.

Step 5 · Honest uncertainty

A range, not fake precision

Every estimate is a range (p10/p50/p90), not a single fake-precise number. Spots unlike anything we've calibrated on get wider bands, and where we have no direct data we say so instead of inventing 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 attenuated by Beer-Lambert optics at the current viz 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. If we don't have direct turbidity data for your region yet (many inland lakes, remote coastlines), we tell you that, not invent a number.

For every dive-mode verdict, the dialog includes an always-on caveat: "We don't yet have direct water-clarity data for this location. Apply local knowledge." 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.

"Best viz window this week."

Applying the same model to forecasted future feature vectors gives you the three-hour stretch in the next seven days with the highest predicted clarity. Unique to Submarius. Essential for anyone planning a weekend trip.

Private even from us.

Community viz reports contribute to the model, but your precise dive location never crosses the wire. Only an H3-tile-fuzzed (~1 km) coordinate is submitted with the report. Personal dive logs (with exact GPS) live in device storage only. If a Submarius employee queried the database tomorrow, they'd see who dove in what general area, not your spots.

See how clear today actually is.

Open Submarius