Innovative Solutions for a Fragile Planet: The Atos-WWF Partnership in Action

Since November 2023 the partnership between Atos and WWF has focused on developing digital tools to support conservationists in protecting wildlife, monitoring biodiversity, and preventing the spread of zoonotic diseases.

Together with experts from organisations all around the world, we have built an AI-enabled Digital Conservation Tools platform that can host predictive modelling algorithms and decision-support systems using satellite imagery, environmental, demographic and climatic datasets.

The platform is designed to support multiple projects concurrently, providing innovative tools for near real-time monitoring of biodiversity and disease risks and enabling proactive and targeted conservation and mitigation interventions.

Predicting the Unpredictable: Tackling Zoonotic Diseases with AI

Developed with the WWF Counter-Illegal Wildlife Trade Hub for Southeast Asia, the ZRP algorithm uses machine learning to seek patterns in environmental and demographic data to predict potential hotspots for zoonotic disease outbreaks. Initially focused on the Mekong Basin, this algorithm assesses factors such as regional infrastructure, population density, deforestation, biodiversity, and animal diseases to generate a unified index indicating potential locations for future outbreaks.

AI Meets Conservation: Atos and WWF's Vision for monitoring Key Biodiversity Areas

The KBA partnership has mapped over 16,800 Key Biodiversity Areas across the globe. In collaboration with the KBA partnership and WWF Kenya, our project team has built a pilot for automated monitoring of KBAs using satellite imagery and AI. We have developed a suite of algorithms encompassing computer vision, habitat classification and time series analysis to identify threats to the integrity of protected areas. Initially targeting the Savannah and Rangeland ecosystems along the Kenya-Tanzania border, this system tracks ecosystem changes, human intrusion, and farming practices, highlighting potential hotspots to allow more effective targeting of conservation efforts.

From Data to Action: A unified digital platform for conservation

The KBA and ZRP algorithms are hosted in the cloud. Our initial implementation uses the Google Cloud Platform (GCP) however it has been built using an open architecture so that it can be easily deployed on to other technology platforms.

The tool can ingest data in various formats, including satellite imagery, maps, structured and unstructured data to identify patterns in space and time.

We have implemented a variety of different algorithms on the cloud platform to ensure scalability and ease of use for future conservation projects as well as integration of software from across the conservation-tech ecosystem.

Additionally, geospatial analysis capabilities coupled with containerized applications allow us to simultaneously support multiple projects. This helps us to deliver a customized user experience for different stakeholder groups.

Both the ZRP and KBA algorithms are hosted on a single digital conservation tools platform. This unified approach allows for efficient data sharing, algorithm management, and user interface integration. The flexible architecture supports the concurrent operation of multiple projects, enabling WWF to take advantage of advanced technologies to support their conservation efforts.

Providing automated monitoring tools and alerts when environmental threats are observed will enable conservation organisations, NGOs and governments to take timely and effective action to better conserve the planet’s wild places and act more quickly to address threats.

Looking ahead: Our ambitions for the future

In 2025 and beyond we have a wide range of exciting projects that we hope to undertake. For example, working with the WWF Oceans team we are exploring the use of Large Language Models for decision support systems for coral reef restoration, and hope to use geospatial algorithms for mapping seagrasses meadows and protecting mangroves.

Additionally, we are investigating the potential of AI to model wildlife corridors for applications as diverse as the protection of Jaguars in South America or the spread of disease in the Congo basin.

We will be sure to keep TechUK readers updated as these projects progress!

techUK - Committed to Climate Action

Visit our Climate Action Hub to learn more or to register for regular updates.

By 2030, digital technology can cut global emissions by 15%. Cloud computing, 5G, AI and IoT have the potential to support dramatic reductions in carbon emissions in sectors such as transport, agriculture, and manufacturing. techUK is working to foster the right policy framework and leadership so we can all play our part. For more information on how techUK can support you, please visit our Climate Action Hub and click ‘contact us’.