THIS CONTENT IS BROUGHT TO YOU BY NILU - read more
This digital trainer knows when you should skip your outdoor run
Researchers have developed a new way to help people exercise better.
Published
When summer is over and the pouring rain and wind of autumn take over, it can be difficult to follow a training programme that suggests going for an outdoor run.
Rain, snow, or cold weather can sap anyone's motivation. The result is more time spent sitting indoors.
What if a fitness app could suggest workouts that take into account both the user's physique and preferences, as well as environmental obstacles?
Imagine a digital fitness and motivation system that considers the weather. And what if it could also explain why it is recommending a particular routine when giving you personalised training advice?
A smart digital trainer
Ayan Chatterjee is a researcher at NILU's Department of Digital Technologies. He recently published a study, in collaboration with Nurilla Avazov at the University of Inland Norway.
They have developed a smart digital trainer that uses artificial intelligence (AI). It can give you tailored training advice based on the current weather.
“Many eCoaching systems are designed to help people reduce sedentary behaviour by tracking their activity and motivating them to become more physically active," explains Chatterjee.
He adds that most of these systems provide only general advice.
"They rely mainly on a person's activity history, with little consideration of contextual factors such as weather or environmental conditions,” he says.
Research has shown that weather conditions can have a big impact on how physically active people choose to be.
“While many studies have explored the relationship between weather and physical activity, few translate real-world weather conditions into personalised exercise recommendations. That's the gap we wanted to address," the researcher says.
Logical explanations increase trust
What makes this technology special is that it is not only accurate but also transparent. The system uses so-called explainable AI (X-AI), enabling it to explain why it gives a particular recommendation. This allows users to check the logic behind its advice.
“Many existing systems use AI to recommend physical activities, but they rarely explain why a particular activity is suggested. By making the reasoning visible, we can help users better understand and trust the recommendations,” says Chatterjee.
All the knowledge in the system is organised in a logical map. This enables the digital trainer to 'think' and give advice that is both sensible and coherent.
“We wanted to develop a system that not only makes recommendations but can also explain the reasoning behind them,” says Chatterjee.
He explains that machine learning helps the system understand weather conditions, while the knowledge model enables it to explain why a particular activity is recommended for that specific situation.
Encourages physical activity
The goal of the digital trainer is to remove environmental obstacles. This could make it easier to stay active all year round and avoid illness.
“Our solution combines weather data with personal preferences and information about how physically active the user is. In this way, the advice can be adapted to both the surroundings and the individual,” says the researcher.
Extensive tests carried out under changing Norwegian weather conditions confirm that the system is very reliable. The AI model picks the right type of activity in over 99 per cent of cases.
What does the system do if the weather forecast predicts torrential rain and it sees that the user has been inactive for the past week?
"It suggests an easy indoor workout. If, on the other hand, the weather is nice and the user has been still a lot, the recommendation may be to go for a walk or cycle,” says Chatterjee.
No more excuses
With this technology onboard, there is no excuse for staying on the sofa, regardless of the weather.
Chatterjee explains that by combining AI with a knowledge model, they have created a system that can reason more systematically.
“It makes the recommendations more personal, more reliable, and easier to understand. This is important if AI is to be used in decisions related to health,” the researcher believes.
At present, the fitness and motivation system developed by the NILU researcher is not yet available for the general public. Chatterjee hopes to publish a prototype in the future.
Reference:
Chatterjee, A. & Avazov, N. Contextual recommendation modeling in eCoaching with machine learning, X-AI, and semantic ontology, Frontiers in Digital Health, 2026. DOI: 10.3389/fdgth.2026.1811976
More content from NILU:
-
Researchers have found a new way to track this greenhouse gas
-
No health risk in Norway from Canadian wildfires
-
Summer in Central Europe: Drought and wildfires to be expected
-
How do you design a healthier place to live?“I would prioritise easy, car-free access to everything you need in your daily life"
-
Fires in tropical forests affect more than just the forests
-
Engineer Sam Celentano found 222 grams of gold in a laboratory. What was it doing there?
