How the Paddle Score Works

The Score

Every spot gets a single number from 1.0 to 5.0, computed fresh when you load a forecast. Scores snap to half-point steps (3.0, 3.5, 4.0…) and are clamped to the 1–5 range. One question is being answered: how favorable are conditions for paddling right now?

Example card — production styling.

Displays shade continuously through seven bands rather than three flat colours — a 4.5 is visibly better than a 4.0:

The exact colour stops the forecast pages use.

The score is a starting point, not a green light. A “Worth it” score does not mean conditions are safe for every paddler in every craft. Always apply your own judgment.

The 3-Day Heatmap

Forecast pages score every daylight hour (6 AM to 8 PM) for the next three days and blend them into one band per day, so you can pick your launch hour instead of just your day. This is not a mock-up — the component below is the forecast page’s heatmap, rendering a live 3-day outlook. Tap a bar to open an hour:

Rendered by the production Heatmap component.

Data Sources

Weather comes from WeatherAPI.com — three feeds fetched in parallel for every score: current conditions, a 3-day hourly forecast with government weather alerts, and marine data (wave height, swell, water temperature) where the location has coverage.

• Wind — sustained and gust speed, direction, mapped to the Beaufort scale
• Air temperature — actual and feels-like, °C
• Water temperature — from marine data where available; estimated conservatively from air temperature otherwise
• Waves — significant height, swell period and direction (used for steepness and wind-against-swell checks)
• UV index, visibility, humidity, cloud cover
• Precipitation — amount in mm and probability
• Official warnings — active weather alerts for the area

Where a value is missing it is estimated conservatively or omitted — never silently defaulted to a flattering number.

The Pipeline

Each score passes through six stages, in this order:

If the model service is unreachable, a rule-based fallback produces the score from the same inputs — starting at 3.0, rewarding calm wind (+0.8 under 5 mph) and comfortable temperatures (+0.3 for 18–30°C), and subtracting for strong wind (−1.2 over 20 mph), active warnings (−0.8), high UV and poor visibility. Fallback scores are marked with lower confidence.

Hard Limits

After calibration, safety rules subtract points the model is never allowed to argue back. Most are small nudges for gusts, waves, heat, UV, visibility and rain — but a few are worth calling out, because they can sink an otherwise perfect day on their own:

• Dangerous wind — above 25 mph (Beaufort 6), the score loses two full points. No model output survives that.
• Cold water — below 5°C is an immersion hazard regardless of how sunny it looks, and is penalized hard.
• Active official warnings — any government weather alert for the area drags the score down, always.

Crowd-Sourced Calibration Beta

This loop is in beta — ratings are being collected and validated now, and per-lake offsets are applied conservatively while the sample grows.

The model’s labels came from people, and its corrections do too. When paddlers rate a real session, that rating flows back into the system:

• Each rating is stored against the score the model had predicted for that spot at that time
• Condition chips (chop, wind, crowding…) are validated server-side against the actual weather at submission time, and GPS proximity is recorded as a quality signal — ratings from people demonstrably at the lake weigh more
• Persistent bias per lake — the model consistently over- or under-scoring — becomes that lake’s stored calibration offset, applied as stage five of every future score

Anti-abuse, concretely: one rating per device fingerprint per spot per day, with a two-hour window to revise your own submission, plus IP-based daily rate limits. The fingerprint exists to stop ballot-stuffing, not to identify you — no account, no name, no email.

Safety — Read This

Wear a life jacket. Every time, every body of water, regardless of what the score says. A PFD (personal flotation device) is the single most effective thing you can do to stay safe on the water.

• The Paddle Score is guidance, not clearance. It reflects weather data and model predictions — it cannot account for your skill level, your equipment, water currents, boat traffic, or hazards specific to your launch site.
• Check local conditions in person. Wind on the water can be very different from what a weather station reports. Look at the water before you launch.
• Tell someone your plan. Let someone know where you're paddling, when you expect to return, and what to do if you don't.
• Know your limits. Beginners should paddle in calm, sheltered water regardless of the score. A "Worth it" rating is not a substitute for experience.
• Weather changes fast. Conditions can deteriorate between forecast intervals. If the sky looks wrong, get off the water.

Limitations

The score is a decision aid, not a guarantee. Things we cannot measure or predict:

• Localized wind funneling through valleys, canyons, or narrow channels
• Sudden thunderstorm development between forecast intervals
• Water currents, tides, dam releases, or underwater hazards
• Boat traffic, construction, or temporary closures
• Your personal fitness, swimming ability, experience, or equipment
• Water quality, algae blooms, or contamination advisories

The Paddle Score supplements your judgment — it does not replace it. When in doubt, don't go out.

Terms of Use

By using Kaayko Paddling Out, you acknowledge and agree to the following:

• The Paddle Score, forecasts, and all information on this site are provided "as is" for informational purposes only. They do not constitute professional safety advice.
• Kaayko is not responsible for any injury, loss, or damage arising from decisions made using this tool. You assume all risk associated with your paddling activities.
• Weather data is sourced from third-party providers and may be delayed, incomplete, or inaccurate. We do not guarantee the accuracy, timeliness, or completeness of any data displayed.
• The ML model is continuously improving but is not infallible. Scores may occasionally misrepresent actual conditions.
• You are solely responsible for assessing on-site conditions, wearing appropriate safety gear (including a life jacket), and making your own go/no-go decision.