Alstom has joined forces with Swedish start‑up Flox Intelligence to trial a new artificial intelligence system designed to detect and deter wildlife from railway tracks — a move that could significantly improve safety, punctuality and sustainability across rail networks.
Field trials carried out in Sweden have demonstrated that the AI‑based system can identify animals in real time and activate targeted deterrents to keep them away from the track. Wildlife collisions remain one of the most common causes of rail disruption in the country, with thousands reported each year, leading to delays, repair costs and emotional strain on train drivers.
The technology combines AI‑powered cameras with tailored audio signals that are triggered the moment animals are detected near the line. Early trials showed strong accuracy in identifying multiple species, including moose, roe deer, foxes and wild boar, highlighting the system’s potential to reduce incidents while protecting biodiversity.
“Our field tests show that AI has the potential to identify animals with high precision. By combining our expertise in wildlife deterrence with Alstom’s leadership in railway innovation, we create a solution that both protects animals and increases operational reliability,” says Sara Nozkova, CEO of Flox Intelligence.
Improving safety, sustainability and operational performance
According to Alstom, the trials have already provided new insights into animal behaviour around railway environments, including the presence of smaller species and birds that have historically been under‑reported in rail statistics. Each detection is categorised, allowing the AI to continuously learn and improve its accuracy over time.
“Having been given the opportunity to evaluate the system is a big step forward for both safety and sustainability in Swedish rail traffic. We were pleasantly surprised at how many animals we could observe from just a single train, on sections that had many collisions. By reducing trainwildlife collisions, we will protect passengers and wildlife while also addressing operational and societal costs associated with these incidents,” says Maria Signal Martebo, Managing Director Alstom Sweden.
The second phase of testing, which began in April 2026, expanded the trials to include the full system — combining live video detection with automated sound deterrence. The project is being delivered in collaboration with regional train authority Tåg i Bergslagen and operator VR, covering several routes including Dalabanan and Bergslagsbanan.
A model for future rail innovation
The project is supported by Vinnova, Sweden’s innovation agency, and is seen as an important contribution to both national and EU ambitions for safer, more sustainable transport systems.
With around 5,000 wildlife collisions reported annually on Swedish railways alone, the potential benefits are significant — not just in reducing delays and costs, but also in improving the working environment for drivers and minimising harm to animals.
The trials are also closely linked to Alstom’s Innovation Station in Stockholm, which has acted as a hub for collaboration with start‑ups and operators across the Nordic region since opening in 2023.
As rail networks across the UK and Europe continue to focus on safety, resilience and sustainability, the results of these trials are likely to be watched closely by infrastructure managers and operators alike.
Image and video credits: Alstom
