A joint project of the universities of Bremen and Gießen and the RoFlexs company is researching and developing a pasture fence that uses artificial intelligence (AI) to detect and deter wolves. The system is designed to better protect grazing livestock and promote coexistence among people, livestock, and wolves.
Livestock breeding and farming are essential elements of German agriculture. Now that wolves have returned to Germany and their population rises, a major conflict with the goals of nature conservation comes to the fore. On the one hand, pasture farming is welcome as it offers a number of advantages compared to pure indoor farming: It is better for animal welfare, helps in conserving nature reserves, and enables the use of dikes to protect against flooding. However, with several thousand kills per year of sheep, goats, calves, ponies, and foals, wolves pose an increasing threat to grazing animals and psychological stress to their owners.
A “wolf-proof” fence that meets the ecological and economic demands of agriculture, livestock owners, and society does not yet exist. The existing fences are designed as permanent fixtures, a fact that often prevents them from being used in conservation areas or means a high additional amount of work on the part of the livestock owners due to the special design of the fence. In addition, electric fences are not as effective during periods of drought or frost. They also cannot be additionally reinforced with stakes or undermining protection. However, this is needed in regions with special conditions such as dikes, conservation areas, and shallow soils. A wolf fence “arms race” would also lead to a landscape fragmentation: Wildlife would be restricted in their movement – and with it their food sources and genetic diversity.
Alternative ways of herd protection are associated with considerable effort and other serious disadvantages. Livestock guardian dog are expensive to buy and own, and conflicts easily occur near human settlements or with other dogs. Also, employing shepherds around the clock is not feasible – each flock would require at least three people.
Psychological Barriers Complement Physical Ones
But a solution is now being researched. As part of the mAInZaun project (modular, autonomous and intelligent herd protection and predator repelling fence) of the universities of Bremen and Gießen and the RoFlexs company, the project partners will use sensors and AI methods to develop a “smart” fence that recognizes the approach of a wolf and carries out defense measures.
Detection of dangers, be it wolves or manipulation of the fence by storm or third parties, is recognized immediately and communicated to the farmer. An optional integration of external control centers in the event of pasture outbreaks, e.g. police, road maintenance services, or railway supervisors in the alert chain are planned. The sensors and actuators with their own power supply can be used independently of an existing fence. The use without a classic fence can also open up new areas of application in impassable regions.
Cost-Effective, Smart, and Energy-Efficient
“The system is based on existing technologies, but there are still some challenges to overcome in order for it to become operational,” explains Professor Anna Förster from the University of Bremen’s Center for Computing Technologies (TZI). “The sensor technology and the defense measures are to be cost-effective, smart and, above all, energy-efficient, because the mAInZaun fence must operate without external energy supplies.
At the same time, these solutions must work with great accuracy. For example, our goal is for the AI to learn not only to distinguish wolves from other species, but also to distinguish individual wolves from each other. That way, the wolf-defense solutions can be individualized so that individual animals don’t become used to certain defense methods.”
This is important because wolves are very intelligent and adaptable. “One of the biggest challenges of this project is to develop the defense measures in such a way that they remain effective over both the short and long term,” emphasizes behavioral scientist Uta König von Borstel, professor at Justus Liebig University Giessen. “At the same time, of course, no grazing animals, humans, or dogs must be harmed. We are confident: Our approach of identifying and scaring away the wolves individually allows us to accommodate all these requirements.”
Fence Manufacturer Ensures Feasibility
Once these challenges have been successfully overcome, the research results can be put into practice. RoFlexs GmbH (Salzwedel) contributes its metalworking and electrical engineering expertise. “One of our tasks is to develop solid and weather-resistant housing for the sensors and actuators,” reports managing director Torsten Menzel. “At the same time, another task is to develop a flexible and self-sufficient power supply solution for the modules and to constantly optimize it over the project period.” As RoFlexs has been producing and marketing mobile fences for15 years, these existing channels could be used for distribution worldwide.
The three-year project is scheduled to be completed by mid-2024. It is funded by the German Ministry of Food and Agriculture (BMEL) with 1.1 million euros.
On Tuesday, September 14, 2021, the mAInZaun project invites anyone interested to attend the kick-off workshop from 8:30 a.m. to 3:30 p.m. at the park “Alternativer Bärenpark Worbis” (Duderstädter Allee 49, 37339 Leinefelde-Worbis). After the project presentation, there will be a discussion on the requirements for herd protection from different perspectives. The event will be held in German. Information and Registration:
University of Bremen
Center for Computing Technologies (TZI)
Phone: +49 421 218-64093
Criteria of this press release:
Business and commerce, Journalists, Scientists and scholars, Students, Teachers and pupils, all interested persons
Biology, Environment / ecology, Information technology, Social studies, Zoology / agricultural and forest sciences
You can combine search terms with and, or and/or not, e.g. Philo not logy.
You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).
Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.
You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).
If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).