An AI system for detecting animals is at the centre of broad trials. Alstom and Swedish startup Flox Intelligence are testing the technology. The technology identifies wild animals near railway tracks. It is also designed to move them away from the line. This is reported by the railway transport news portal Railway Supply.

AI system for detecting animals enters Alstom trials
AI system for detecting animals enters Alstom trials

The system uses AI-based detection technology. According to Alstom, early test results show high potential for reducing wildlife collision risks. Such collisions are among Sweden’s most frequent causes of rail disruption.

Sara Nozkova is CEO of Flox Intelligence. She said: “Our field tests show that artificial intelligence can identify animals with a high degree of accuracy. By combining our experience in wildlife protection solutions with Alstom’s expertise in rail innovation, we are developing technology that protects both animals and the operational reliability of the network,”

Don’t miss…VIA Rail 2025 annual report shows flat ridership

Maria Signal Martebo is CEO of Alstom Sweden. She said: “The project represents an important step for the safety and sustainability of Swedish rail transport. According to her, the teams involved were surprised by the large number of animals observed even over short distances, particularly on sections where accidents frequently occurred,”

AI system for detecting animals in real time

The solution developed by Alstom and Flox Intelligence relies on AI-assisted video cameras. When animals are identified close to the track, the system activates adapted sound signals. The signals are intended to scare them away from the railway area.

In the first testing stage, the technology detected several species. These included moose, deer, foxes, and wild boars. As of April 2026, the project has entered a new implementation phase. It combines video-based detection with acoustic warning systems.

Testing is taking place on several Swedish railway routes, including Dalabanan and Bergslagsbanan. The work is being carried out with Tåg i Bergslagen, the regional rail transport authority. It also involves the operator VR. In addition, the project receives funding from Vinnova, Sweden’s innovation agency. It is considered an important step toward safety and sustainability goals. Those goals are promoted by the European Union.

Wildlife collisions and Swedish rail transport

The AI system is not limited to large wildlife. Also, it detects smaller animals and birds. These had previously appeared almost never in railway statistics. Each identification is analyzed and classified. This helps the algorithms improve over time.

During the tests, the technology showed especially strong accuracy in detecting domestic animals and birds. These included crows and pigeons. Still, moose and deer required further AI training before detection performance improved.

Sweden reports around 5,000 train-animal collisions each year. These incidents affect wildlife. In addition, they lead to delays, repair expenses, and psychological strain for train engineers. The project aims to reduce the number of such accidents. It also aims to improve punctuality and lower environmental impact. The project also aims to improve working conditions across the rail sector.

News on railway transport, industry, and railway technologies from Railway Supply that you might have missed:

Don’t miss…U.S. port imports forecast turns lower after June