Preikestolen and the Lysefjord area are among Norway’s most visited natural attractions, and the number of visitor have grown steadily for years. This puts increased pressure on both the natural surroundings and infrastructure.

The local tourism operators are obliged to document environmental and social effects through schemes like “Sustainable Destination” and “National Tourist Trails”.

SINTEF and Lysefjorden Utvikling (Lysefjord Development) have now shown that it is possible to predict when and where visitor numbers will peak, through smart use of data. Without gathering any new information, the model responds to a large and shared need of many who work in the area.

Data on visits, weather, traffic and cruise calls already exist. But, data are scattered among various players and used only to a small extent to predict what is to come. A data-driven forecast can give a more precise picture of when visitor peaks are expected.

“The value is not just in knowing how many people come per day, but also at what time of day they come,” says Johannes C. Apon, tourism developer at Lysefjorden Utvikling.

“An hourly forecast gives us a better basis for staffing, traffic management and information. This will both provide a better experience for the guests and a better day for the employees.”

The researchers trained a machine learning model (LightGBM) based on two years of data collected from the trail counters at Preikestolen. They combined this with weather data, traffic figures from the Norwegian Public Roads Administration and information on cruise calls in Stavanger.

The model was asked to predict visitor numbers 24 hours into the future, and was tested against actual visitor numbers from 2025 and 2026.

The result surprised us – in a positive sense. The model was able to capture the systematic patterns in visitor behaviour, since season, day of the week, weather and cruise calls explain a big part of the variation from hour to hour.

“We really just wanted to see if this could be done at all. That a simple model produced such clear results shows that it has great potential,” says Nathalie Labonnote, head of research and innovation at SINTEF and the project manager for VisitorLAB.

“This means that we don’t need new data, we ‘just’ need to structure and connect what already exists.”

SINTEF has also interviewed various actors in Lysefjord – ranging from tour operators and boat companies to municipalities and Norwegian People’s Aid. Almost everyone wanted the same thing: better forecasts for visits, and a common understanding of what happens in the fjord from day to day.

“What surprised us the most was the strong consensus among the various actors. Large and small, private and public. Everyone pointed to the same need for better forecasts and a common picture of the situation. It suggests that this actually solves a problem that the tourism industry is familiar with on a daily basis,” says Labonnote.

Tour operators can use predictive tools to deploy extra shuttle buses, adjust staffing and notify visitors when it is in their interest to come another day.

The model is not fine-tuned, and the underlying data currently has to be retrieved manually from various systems. For such a solution to be used in practice, the data needs to flow automatically. The model will be developed further with more data sources and increased precision.

The researchers propose to use a joint dashboard that will give the actors in Lysefjord a better picture of the situation. The aim is to move from current operations and short-term forecasts to seasonal planning and long-term, sustainable development of the area.

Lysefjorden Utvikling and SINTEF want to further develop and test the solution at full scale. The goal is to enable the methodology to be used by other Norwegian natural attractions with similar challenges.

VisitorLAB is a pilot project funded by the Rogaland Regional Research Fund (RFF Rogaland) and carried out by Lysefjorden Utvikling AS and SINTEF.