Early warning system for environmental change

How can a vulture in a Berlin zoo help its fellow species and their habitat in Namibia? As a role model and patron for a new generation of animal tags: The prototype of an innovative animal tag system, developed by the Leibniz Institute for Zoo and Wildlife Research (Leibniz-IZW) and the Fraunhofer Institute for Integrated Circuits (Fraunhofer IIS), has its premiere celebrated flight on a vulture in Tierpark Berlin today. The tags will be equipped with sensor-based artificial intelligence (AI), a camera, energy-efficient electronics and satellite-based communication technology. This enables completely new insights into the world of animals and their habitats: The tags recognize and transmit animal behavior in real time and are therefore an early warning system for ecological changes.

Climate change, species extinction, pandemics – human influences are changing our planet faster than we can understand and protect it. To keep up with the accelerating pace of environmental change, environmental research and conservation must break new ground and harness the potential of the latest technological developments. Leibniz-IZW and Fraunhofer IIS have therefore been working together since the beginning of 2022 in two major research and development projects funded by the German Aerospace Center (DLR): In the GAIA-Sat-IoT (Guardians of the wilderness with artificial intelligence applications and satellite-based IoT networks) and SyNaKI (Synergy of natural and artificial intelligence in the swarm) projects, they are developing a new generation of animal tags that enable much faster and more accurate insights into ecosystems. The tags will have significant innovations for this: On the one hand, they are divided into two parts, one of which is attached to the back of the vulture and records position and acceleration data, among other things. The second module is equipped with a camera and therefore sits on the front of the birds’ chests. Both parts are connected and work hand in hand. This is made possible by a second innovation: an on-board AI directly on the tag recognizes certain animal behavior patterns in the data, classifies their behavior and thus generates valuable information directly on the tag. The camera then takes photos at crucial moments, which in turn are evaluated by another AI. Last but not least, a new satellite-based communication link ensures that information can be transmitted directly from the tag to a satellite and to the scientists, even in the most remote ecosystems.

“We’re going this route because we can see what’s going on in an ecosystem so much more precisely and quickly,” says Dr. Jörg Melzheimer, GAIA project leader at the Leibniz-IZW. “We develop our tags as an example for use on vultures in southern Africa. These scavengers have amazing sensory abilities and intelligence, each bird individually and together in a wake. They find carrion with enormous precision and speed, which makes them ideal allies for us.” On the one hand, the occurrence of carrion is a completely natural circumstance, but critical changes in the ecosystem can also be identified by irregularities in carrion occurrence, for example outbreaks of wildlife diseases. The tags make it possible to identify such local ecological hotspots in near real time. “We designed the GAIA projects as a network of animal, human and artificial intelligence. We use high-tech and the evolutionary intelligence of animals to identify and solve pressing environmental problems,” says Melzheimer.

The design and development of the GAIA animal tag system is carried out in close cooperation between the specialists in wildlife biology and ecology, artificial intelligence, communication technology and sensor technology at Leibniz-IZW and Fraunhofer IIS. “The processing of the data by an AI directly on the tag is an essential feature, as it allows real-time decisions to be made as to which of the collected data is relevant enough to be sent to the satellite,” says Dipl.-Inf. Nina Holzer, group leader Multimodal Human Sensing and project manager of GAIA-Sat-IoT at Fraunhofer IIS. “Sending all the collected data in real time is practically impossible, a satellite connection does not allow this and would consume too much power.” In addition, the split-tag design is a novelty with its own technical requirements, reports Dipl.-Ing. Jürgen Ernst, senior engineer at Fraunhofer IIS and lead engineer of GAIA-Sat-IoT. “The camera module sits on the front of the vulture’s chest. All other sensors as well as the AI ​​processors and the solar power supply are housed in the tag on the back. Both electronic components must work together smoothly and the entire system must also be perfectly adapted to the anatomy of the animals in order to be able to use it from an animal welfare point of view.”

Tierpark Berlin – one of two zoos in the German capital – is an indispensable cooperation partner of the consortium. Early in the project, GAIA scientists and zookeepers tagged two white-backed vultures in the zoo’s aviary with commercially available tags that record acceleration data (ACC) and GPS positions. ACC data gives a very precise insight into the movements of the tags and the animals. At the same time, the scientists recorded typical vulture behavior with a video camera. The artificial intelligence could be trained by combining ACC data and video recordings. “In the videos we can see to the second when the bird shows which typical behavior and can thus recognize corresponding patterns in the ACC data,” explains Wanja Rast, AI specialist at the Leibniz-IZW. “This training data is the basis of the AI, which in the future will carry out an automated behavior classification directly on the day in a very energy-efficient and accurate manner.” The AI ​​has not yet been implemented on the current prototype and is currently being developed desktop-based with downloaded data, but will be implemented in the The course of the projects has become a unique selling proposition for the new animal tags. “In the SyNaKI project, we will also map the natural swarm intelligence virtually in a swarm of microprocessors,” adds SyNaKI project manager Felix Kreyß from Fraunhofer IIS. “In this way we enable distributed and AI-based data analysis directly in the field, in the wake of the vultures. To do this, we combine natural and artificial intelligence on the animal tags, as well as extreme edge computing approaches.”

Another major challenge in the development of the tags is the efficient and reliable transmission of data from the animal to the user, for example scientists or conservationists. “Since the tag is intended to be used early in the project to collect training data, the transfer function is currently (still) limited. In the next step, we will further develop the transmitter and integrate the AI ​​signal processing electronics,” says Florian Leschka, group leader for system design at Fraunhofer IIS. “Another important work step is the integration of a high-performance satellite IoT radio module into the transmitter in order to ensure the subsequent transmission of the extracted information.” The support of satellite-supported networks is particularly necessary in areas beyond the range of terrestrial communication infrastructures. In order to enable direct transmission from the transmitting node to the satellite, the Fraunhofer experts are developing a communication system based on terrestrial mioty® technology. The result of the developments by Leibniz-IZW and Fraunhofer IIS is a small animal tag that intelligently preprocesses and combines data and only sends relevant environmental information via a satellite-supported communication link.

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of the press releases published on EurekAlert! by contributing institutions or for the use of information about the EurekAlert system.