Paraglidable is an AI-based flying conditions forecasting program for paragliding.
It uses state-of-the-art artificial intelligence algorithms to interpret weather forecasts from multiple sources as comprehensible flying condition parameters. The AI examines the precipitations, cloud cover, wind at different altitudes etc. to know if you will be able to fly or not. Paraglidable studies for you ~200 weather parameters for each day and produces a clear summary. Futhermore, Paraglidable is able to predict how good the day will be for cross country flying.
To learn more about how it actually works, please follow this link.
To go even further and contribute, you can now find Paraglidable open-sourced on GitHub.
Probability that a flight will be reported, given the full weather vector of the day, assuming a given paragliders local population.
Probability that a flight of 60 points or more (using PWC scoring) will be reported, given the full weather vector of the day, assuming a given paragliders local population.
1 - 3/2 * (probability that a flight will be reported, given the wind-related weather parameters, assuming a given paragliders local population)
1 - 3/2 * (probability that a flight will be reported, given the humidity-related weather parameters, assuming a given paragliders local population)
The paraglidable API let you integrate freely our forecasts into any website/service/application.
You can get a key by providing an email address.
You are limited to 10 spots by key.
Paraglidable.com uses deep learning to analyse standard weather models forecasts.
Paraglidable.com uses an artifical neural network to compute "flyability" and "crossability" scores by analysing ~200 weather parameters for each day.
The neural network is trained over ground truth data spanning the last 10 years.
The ground truth data is composed of weather archives and available online flights databases (~2 000 000 flights).
During training, the neural network learns the correlation between weather conditions and reported flights (their number, distance, max vario, max altitude...).
Correlation results can be visualised here.
For computing forecast, paraglidable.com downloads the last weather forecasts from multiple sources to feed the neural network. The neural network outputs a prediction of the flying condition.