On Magicseaweed, a star rating highlighted quality swell, and traffic lights highlighted good wind. On Surfline, a single rating judges the quality of the surf based on surf height, wind speed, and wind direction.
What sets Surfline's rating apart from Magicseaweed? Surfline has a human forecast team that has gathered daily observations of surf conditions for 35 years. We use those observations to train a machine learning model to predict a Quality Rating based on the expected swell and wind for nearly every spot we provide forecasts for.
Our forecast team will occasionally manually make changes to what rating the model selects to better reflect current & expected conditions. GOOD and EPIC ratings cannot be automatically applied, only manually by a forecaster.
How do ratings work?
Surfline has 7 ratings, ranging from VERY POOR to EPIC.
- The best rating our model can give is FAIR TO GOOD
- The GOOD and EPIC ratings are reserved for our human forecasters to issue. If you see purple, you know one of our team is confident you’ll score.
Rather than simply commenting on model output, our forecasters actively adjust our own proprietary wave model. Our expert forecasters correct surf height readings & ratings up to 7 days into the future. They influence the 6 am, 12 pm and 6 pm slots and the model corrects everything else accordingly.
How to report an issue with the rating?
The rating scale is just one measure of overall quality, and we suggest you use it in combination with your local knowledge (e.g. banks, sandbars, tides, etc.) to make the best possible decision on when and where to surf.
What do we need? The machine learns from a snapshot of conditions and a rating. Therefore, we can use your feedback in a similar way.
A screenshot of the forecast, to help us see the conditions informing the rating you're reading.
We need to know the exact date/time you're checking the surf in order to ingest it. Without this, there is very little we can do.
Some kind of supporting evidence will fast-track your feedback and help us use it reliably. Example: video, photo taken at spot, cam screenshot, Rewind clip, Sessions clip.
Ingestion of inaccurate information would be counterproductive, so bear with our support staff while they confirm all the necessary specifics before logging your feedback with the forecast engineers.