Establishing a satellite-based IoT communication system

Relevant ecological processes and incidents that are of interest in environmental change research typically occur in remote areas beyond the reach of terrestrial communication infrastructures. Data generated in the field using animal tags in these regions can often only be transmitted with a delay of days or even weeks. To overcome this delay and ensure no delay in the early-warning system, GAIA develops a satellite communication module for the tags as well as a nanosatellite operating in low earth orbit (LEO): In order to be able to transmit collected data and information directly from the transmitting node to the LEO satellite (Low Earth Orbit), a high-performance satellite IoT radio module will be integrated into the new tags. This guarantees immediate, secure and energy-efficient transmission of the extracted data. The communication system is based on the terrestrial mioty® technology and will be adapted to satellite-typical frequency bands such as L- and S-band for the project. Typical communication protocols, which are sometimes used in the IoT sector, are usually designed for small packet sizes. Further development of the mioty® system will therefore also aim to increase the data rate and message size to enable application scenarios such as image transmissions.

A significant share of the GAIA research and development was funded by the German Space Agency (DLR). This provided not only budgets for the development of the mioty® communication modules in the tags and first modules and concepts of the nanosatellites, but also access to an ecosystem of space-tech stakeholders. The start-up Rapidcubes became a key partner in the Initiative for the satellite development and plans for subsequent project phases include collaboration with existing DLR infrastructure such as the Heinrich Hertz satellite. 

The adaptation of the terrestrial mioty® protocols for satellite communication were successful. With the Ariane 6, an experimental nanosatellite was launched into a low earth orbit in July 2024. Since then, communication protocols are tested and refined for future application for the GAIA early-warning system.

Developing a new generation of animal tags and concepts for a digital swarm intelligence in networks of devices

To meet the goal of the GAIA Initiative to develop and put into practice a high-tech early-warning system for environmental changes, a new generation of animal tags is a key component. GAIA teams are working on the hardware and software development of miniaturized animal tags with lowest-power sensor technology with camera and image processing. The tags will be energy-autonomous, optimally adapted to the anatomy of vultures and are the basis for further technological features under development such as on-board artificial intelligences for behaviour detection and image recognition as well as a satellite-based IoT communication system.

Additionally, GAIA is developing concepts of distributed artificial intelligence and networks of micro-processors – animal tags that act just like a swarm. Analogous to natural swarm intelligence, the GAIA initiative is mapping digital swarm intelligence in an ad hoc network of microprocessors. These spontaneously forming networks are the foundation for distributed and sensor-based analysis of large amounts of data. Following this path will make it possible for vulture tags, for example, that are present at the same location during feeding events, to link and share tasks such as artificial intelligence analyses and data transmission.

A key factor for the success of this building block is the interdisciplinary and cross-sectoral cooperation of the GAIA partners: The Leibniz-IZW provided biological and veterinary knowledge about vultures and provided goals for the technical design of the new tags. The Fraunhofer IIS provided expertise in energy-efficient hardware, electronics and mechanics as well as in software for the miniature units. The Zoo Berlin provided environment and access to animals to aid the design and test the prototypes at various stages. Partner organisations in Africa such as Uganda Conservation Foundation provided an environment for in-depth field tests of the tag prototypes.

After several years of design and development, prototypes of the new tag system were tested in the wild in Uganda in November 2024. Wild white-backed vultures were equipped with prototypes called “data collection tag” (DCT) that featured many (albeit not all) innovations of the GAIA tag. The tags were released after 14 days from the vultures and collected using GPS and VHF signals, allowing for thorough examination of hardware and software performance as well as evaluation of collected data. These analyses will greatly help further developing the system.

Artificial intelligence(s) for behaviour recognition, carcass detection and image recognition

For ecological research as well as for GAIA use cases, it is necessary to reliably and accurately recognise the behaviour of different animal species over a long period of time in remote wilderness regions. To do this, GAIA scientists have developed and trained an artificial intelligence (AI) that can perform behavioural classification from GPS and acceleration data and tell us exactly what, for example, white-backed vultures fitted with animal tags are doing at any given time and place. This AI will eventually run directly on the GAIA animal tags and generate behavioural information from sensor data. In a second step, the scientists combined the behaviour thus classified with the GPS data from the tags. Using algorithms for spatial clustering, they identified locations where certain behaviours occurred more frequently. In this way, they obtained spatially and temporally finely resolved locations where vultures fed. Last but not least, GAIA is developing an AI for image recognition that will analyse photos taken by the integrated camera of the new tag system. All those algorithms will run directly on the tag and can perform efficient embedded data processing. This also places very special demands on image recognition AI, which must operate particularly sparingly and with small amounts of data. To this end, GAIA teams are developing appropriate strategies and models for sparse AI.

This building block stands on the shoulders of two major enabling factors. First, the combination of expertise in wildlife biology and data analysis/artificial intelligence development in one staff member. It proved absolutely essential to have great experience in wildlife ecology and vulture behaviour in particular as well as the development of code and the training of algorithms of the AI. Second, the acquisition of a large set of training data – one of the key factors for a successful AI development – was only possible through the cooperation of a wildlife research institute and a zoological organisation. With vultures in captivity in a large aviary, both data collection with a tag and video recordings of relevant behaviour could be conducted. Only this allowed for synced pairs of reference data and a training of the AI algorithms.

In this building block, GAIA achieved various tangible outcomes: First, the development of two integrated AI algorithms for vulture behaviour classification based on sensor data and for feeding cluster and carcass detection was completed and published in a peer-reviewed scientific journal (https://doi.org/10.1111/1365-2664.14810). The AI analysis pipeline has been running effectively for several years on sensor data from commercially available tags and provided many hundreds of potential carcass sites with a GPS location – an essential source of information for ranger patrols on the ground. Second, a similar AI pipeline has been developed for ravens. It is similarly efficient and can be utilized for mortality monitoring in North America or Europe, for example. Third, GAIA demonstrated that an extremely sparse image recognition AI can be trained to detect species from photos from the new tag camera. An fourth, a GAIA concept study showed that tags present at the same locality could form ad-hoc networks (digital swarms) within which AI calculations and other tasks such as joint backhauling can be shared.

Advancing animal-borne remote sensing, GPS tracking and monitoring

Satellites and aircrafts play a crucial role in gathering environmental data from the distance, helping us to better understand our climate and ecosystems. Remote sensing, often conducted from aircraft, balloons, or satellites, allows us to monitor large areas and remote regions over extended periods. These “eyes in the sky” are invaluable complements to land-based observations, helping us understand ocean and air currents, land cover changes, and climate change. However, animals also possess extraordinary senses and a unique ability to detect changes in their habitats. By combining animal capabilities with remote sensing technologies, GAIA aims at enhancing our ability to monitor and understand our planet. Animals have superior sensory abilities and behavioural strategies that enable them to sense subtle and dramatic changes in their ecosystems, as well as to detect critical incidents. Vultures, for example, act as “sentinel species” and can elevate the concept of remote sensing to new heights. They regularly patrol vast areas in search of food, operating without emissions, additional resources, or repairs. Furthermore, their patrols are guided by their exceptional vision and the mission to find carcasses. The way they patrol, what they search for, and the incidents they lead us to may be linked to specific environmental changes and ecological events.

To fully exploit the potential of vulture-borne remote sensing, GAIA focuses on two essential aspects. Firstly, powerful tracking devices are attached to vultures to monitor their movements and behaviour on detailed temporal and spatial scales. Secondly, new technological solutions are being developed to better understand what the animals observe and do. This includes a newly developed camera tag featuring an integrated camera, artificial intelligence algorithms for behaviour detection and image recognition, and satellite uplink for real-time coverage in remote regions. With these tools, animals can capture imagery and provide data of their surroundings faster, with higher resolution and specificity than satellite imagery. This innovative approach allows us to see nature through the eyes of animals.

GAIA was able to deploy around 130 commercially available tags to vultures all across southern and East Africa. This relatively high number provided opportunity to study in great depth (both spatially and temporally) how the data from tagged sentinel species such as scavenging white-backed vultures can support ecosystem monitoring. Second, this building block is enabled by collaboration with, for example, Endangered Wildlife Trust, Kenya Bird of Prey Trust or Uganda Conservation Foundation. 

The GAIA studies have proven that the sensory capabilities and intelligence of sentinel species are indeed a great asset in ecosystem monitoring. Investigating vultures and ravens and analysing data from tags carried by these “eyes in the sky” have demonstrated they are highly superior to man and machine in localising carcasses in vast landscapes and can help monitoring mortality in ecosystems. And second, the GAIA studies confirmed that high-tech approaches are a means to connect to this valuable knowledge and utilize it for monitoring, research and conservation. Modern humans have notably disconnected from nature, failing to “read” and “listen to” nature. By means of innovative AI-powered tracking technology, not only animal-borne remote sensing for research and conservation is elevated, but also a connection to nature re-established.

Understanding scavengers, their communities, ecosystems and conservation challenges

Vultures are a highly intelligent group of birds that provide important ecosystem services. Yet, populations of old-world vultures decreased dramatically in the last decades owing to anthropogenic factors. Efficient conservation strategies that address critical threats such as indiscriminate poisoning or depleted food sources need to be developed. At the same time, their behaviour including social interactions is still poorly understood. Building on high-tech tracking equipment and AI-based analytical tools, GAIA aims at better understanding how vultures communicate, interact and cooperate, forage, breed and rear their young. Additionally, the GAIA scientists research the social foraging strategies of white-backed vultures and the information transfer within carnivore-scavenger-communities. In the animal kingdom it is common across taxa that the search for food is undertaken not only as individuals but in a group. Animals forage together or rely on knowledge from other individuals to find food. This so-called social foraging presumably yields benefits, for example concerning the amount of food that is found, the size of prey that can be hunted or the time required to access food. GAIA investigates species-specific mechanisms in behaviour and communication as well as the incentives, benefits and possible disadvantages for individuals.

This building block is enabled by experience, funding and access: GAIA had the resources to hire excellent scientists with years of experience in investigating animal behaviour, spatial ecology, carnivore-scavenger interaction, intraspecific communication and human-wildlife conflicts. Additionally, GAIA stands on the shoulders of several decades of integration into science and stakeholder communities in wildlife management and conservation in southern Africa. This allowed access to protected/restricted areas with research permits to tag birds and collar carnivores for example. 

Newly published research results from the project (https://doi.org/10.1016/j.ecolmodel.2024.110941) confirm the benefits of cooperation and social information for foraging success. The results highlight social foraging strategies such as “chains of vultures” or “local enhancement” as overall more advantageous than the non-social strategy. The “chains of vultures” strategy outperformed “local enhancement” only in terms of searching efficiency under high vulture densities. Furthermore, the findings suggest that vultures in our study area likely adopt diverse foraging strategies influenced by variations in vulture and carcass density. The model developed in this study is potentially applicable beyond the specific study site, rendering it a versatile tool for investigating diverse species and environments.

AAA Sustainability Quality Program

In order to increase resilience to climate change, coffee farming households need the knowledge and skills to apply regenerative agricultural practices that can increase biodiversity, enrich soil health, improve watersheds, and enhance ecosystem services.

Nespresso’s AAA Sustainable Quality Program empowers coffee farmers through three pillars: coffee quality, farm productivity, and social and environmental sustainability. Improvements in these areas can boost farmers’ financial security while also helping their communities and protecting nature.

From July 2022 to April 2024, AAA agronomists — nearly half of them women — delivered monthly lessons to small, self-selected focal farmer groups of roughly 25 coffee farming households. Modules included a wide range of relevant topics, including regenerative agricultural topics (Coffee Pruning and Rejuvenation, Soil Health, Coffee Planting, and Shade Management and Climate Change), household nutrition topics (Nutrition Basics, and Establishment and Planting of Kitchen Gardens), and gender equality topics. With the establishment of demonstration plots, farmers learned through this hands-on, field-based training. 

  • Evident, long-term interest and trusted relationships between Nespresso, TechnoServe, and farmers and cooperatives in DRC since 2019. 
  • Leveraging economic incentives through sustainable use of natural resources and respect for production standards.
  • Close collaboration with local stakeholders: recruiting community members as AAA agronomists and focal farmers to train and model each practice leveraged their local knowledge to make the information relevant to the famers’ context.
  • Cooperation between private companies and small-scale farmers helped to empower producers and secure greater access to the large commodity markets for improved incomes and livelihoods. 
  • The AAA Academy was effective in supporting and amplifying knowledge of  local farmers through training on regenerative agriculture, household nutrition, and gender equality. 
  • The level of support needed for smallholders is increasing as more producers are involved in the trade of fully washed specialty coffee from South Kivu.
Working with communities to ensure them sustainable economic activities and justice

The forestry sector is suffering from corruption and is limiting benefits for local and Indigenous communities. Our solution allows local communities to tackle forest illegalities and land rights violations and at the same time to secure their land rights and economic rights over forest resources by monitoring and protecting their territory, reinforcing sustainable development and autonomy.  Data collected through the tool also supports judicial or non-judicial cases when local and indigenous communities suffer human rights abuses. 

  • A good understanding of the current economic activities of the communities is needed 
  • Financial means to engage legal procedures is a must 
  • Collaborate with local partners specialised in legal actions or in sustainable business activities 
  • Parallel advocacy work to secure individual and collective land rights   
  • Sensitization on sustainable economic activities is key for the project success, and it must include all groups of the local or Indigenous community and have specific sensitization for women and girls. 
  • Staff trained or specialised in the different fields (justice/law & sustainable economy) is needed Women and girls are key change agents who have to be fully integrated in projects  
Adaptable & Efficient Reporting and Monitoring tool

Our solution is based on a digital tool whose goal is to collect and facilitate the analyse of the data sent by community observers and our partners. This tool's efficiency relies on the fact that it is digital, easy to use and low costs for local and Indigenous communities. It enables us to work with hard-to-reach areas around the world, to have quantitative data to support national and international advocacy and to get supporting evidence for legal cases. The adaptability of our solution also lies in the fact that it can be used to monitor a variety of issues (illegal logging - artisanal or industrial, mining, carbon market projects' impact, GBV, etc.), in a variety of contexts.  

  • Sufficient financial resources for the tool to keep running and for the observers to keep apply it 
  • Having a strong technical and development staff team  
  • Building partners’ capacity in using the tool and train community monitors to use it  
  • Ensuring its adaptability to changes in partners' expectations 
  • Having coordination staff team within our organisation and within partners organisations to ensure the efficiency in using the tool 
  • In-person training is the most important thing to ensure the digital tool good use and efficiency. Partners have to be able to understand fully how the tool works and keep being trained for the overall period of the tool implementation 
  • Liase constantly with the partners to ensure the tool and hardwares are working as expected is key 
  • Be aware of all the external factors (political, social, meteorological...)  which can slow down or stop data from being collected on the tool 
  • Ensure that complementary training of environmental law and human rights are proposed to local partners and communities, so that they can take efficient law enforcement actions and access to justice and reparations. 

Working hand in hand with grassroots organisations/Indigenous and local communities

The evidence is building that granting Indigenous peoples and other local communities' control over their territories improves forest protection. This is because they are directly invested in the survival of forests and want to ensure that future generations can continue to live and thrive in them. Yet a lot of development and environmental and climate-related programs are not created in collaboration with the people who will be impacted by them. Therefore, our solution arose from the challenges that grassroots organisations and Indigenous and local communities brought to our attention. Those communities are the ones living all the forests illegalities and land tenure violations therefore by directly tackling their challenge it ensures the solution to be genuine and efficient. Working with them directly helps us to better understand the contexts they are facing and adapt the tool in consequence. 

  • Build strong and lasting relationships with partners and people using the tool 
  • Having an adaptable tool which allows to be reactive to changes  
  • Adequate financial resources  
  • Collaborating with Indigenous and local, grassroots organisations  
  • Building strong relationships requires cultural sensitivity, time and efforts. It is important to listen closely  to stories and challenges people share to be sure that the tools respond to their needs and contexts.  
  • Having beforehand researched on the cultural, traditional and socio-economic context strengthens the collaboration and to make the tool more relevant and impactful. Working with Indigenous-led or locally-led organisations to truly address their challenges