digiLab AI cuts performance prediction error by 85% ahead of one of the world's toughest solo sailing race

10th June – Exeter, UK

World-leading AI company digiLab has announced new results from its collaboration with British offshore sailor Joss Creswell following his participation in the 2026 La Solitaire du Figaro Paprec, one of the most demanding sailing races in the world - which he attempted solo.

The three-stage race, covering approximately 1,500 nautical miles, pits sailors against some of the sport's most accomplished competitors, including sailors who have gone on to win the Vendée Globe. Every competitor races the same boat, with identical sails, foils and equipment..

Over the last 12 months, digiLab's research team, theLab, has worked alongside Creswell to develop a personalised performance model trained on his own sailing data rather than relying on the manufacturer's generic factory polar.

The results have been significant. Using data gathered throughout the previous racing season, digiLab's model reduced average speed prediction error by 33% compared with the factory polar, creating a more accurate representation of how Creswell actually sails his Figaro 3 in real racing conditions.

The model continued to improve as new race data was incorporated. Following retraining using data collected during the Solo Guy Cotten race – one of the opening races of the Classe Figaro Bénéteau season and a key test of sailors' offshore racing performance – average prediction error fell from 2.91 knots to just 0.43 knots, an improvement of more than 85%. The model now explains more than 93% of observed variation in boat speed.

Alongside every forecast, digiLab's AI produces calibrated uncertainty ranges that successfully capture real-world outcomes approximately 95% of the time, helping distinguish between situations where the model is highly confident and those where uncertainty remains high. For a sailor making tactical decisions hundreds of miles offshore, that difference matters.

Professor Tim Dodwell, CEO and Founder of digiLab: "Offshore racing is one of the most demanding environments imaginable for decision-making. Conditions change constantly, information is incomplete, and the consequences of getting it wrong are immediate.

"That's exactly why it's such a powerful testbed for our technology. The same challenge exists across energy, infrastructure, defence and maritime operations, where organisations need to make critical decisions despite uncertainty. Our goal is to help people move beyond guesswork and make better decisions with greater confidence, even when the stakes are at their highest."

The collaboration provides a real-world demonstration of digiLab's expertise in trustworthy AI and uncertainty quantification, showing how decision intelligence can be built in environments where data is constantly evolving and certainty is impossible.

While developed through elite offshore racing, the principles behind the technology have far-reaching applications. From optimising vessel performance and route planning to supporting critical infrastructure and energy systems, uncertainty-aware AI has the potential to help organisations make faster, more informed decisions in complex, high-stakes environments.

Joss Creswell, Next Step Racing: "La Solitaire lived up to its reputation as one of the toughest challenges in sailing. We faced everything from a 45-knot gale and three-metre seas to equipment failures and retirements across the fleet, so simply getting to the finish required constant focus and resilience.

What makes working with digiLab so exciting is that every mile sailed and every challenge faced becomes part of a growing body of knowledge. The model keeps learning from my racing, helping me better understand my performance and explore different scenarios before I get back on the water.

This race proved to me that I can compete at this level, but it also showed me how much more there is to learn. That's the exciting part. I crossed the finish line already thinking about the next race and how we can use everything we've learned this season to come back stronger."

For both Creswell and digiLab, this year's La Solitaire was never simply about a finishing position. It was about proving what was possible. Having completed one of sailing's toughest tests and gathered a season's worth of real-world performance data, the partnership now looks ahead to the next stage of development - on the racecourse and beyond.

The partnership also offers a glimpse into the future of maritime decision intelligence. As the industry seeks greater efficiency and lower emissions, technologies that help operators better understand performance, risk and uncertainty could play an increasingly important role in creating smarter, more sustainable operations at sea.