University co-leads $2m project using AI to study vulnerable deep-sea habitats

The project has been awarded funding through the Bezos Earth Fund’s AI for Climate and Nature Grand Challenge

3 November 2025

The ��ù��Ƶ and ��ù��Ƶ Marine Laboratory (PML) have been awarded funding through the Bezos Earth Fund’s AI for Climate and Nature Grand Challenge.

The $2million two-year initiative will use AI to greatly accelerate mapping of vulnerable marine ecosystems (VME) such as cold-water coral reefs and sponge fields in the deep Atlantic.

It will apply AI models to analyse thousands of images to generate the largest ever, high-quality dataset describing the spatial distribution of VME indicator species.

Combined with in-situ environmental data, this will enable the research team to understand the conditions each species requires and develop models that can predict where they occur based on environmental conditions.

This data will also generate the evidence needed to support legal protections for these ecosystems and create AI tools to enable upscaling, ultimately to the entire global ocean.

The project is being led by Professor Kerry Howell , Professor of Deep-Sea Ecology at the ��ù��Ƶ and PML, and a project team that includes former PhD researcher and BSc (Hons) Marine Biology graduate Dr Giulia La Bianca.

It aligns with the Grand Challenge’s ambition to “scale artificial intelligence solutions that address the world’s most pressing environmental challenges – from biodiversity loss and food insecurity to climate change”.

As the deep-sea becomes more accessible for exploitation, there is an urgent need to map its ecosystems to enable the conservation of biodiversity in this, the last wild frontier on Earth.

This is exactly the evidence needed by decision-makers responsible for implementing legislation to protect VME, including the new High Seas Treaty. This award enables us to accelerate our work and we’re delighted to have been chosen to receive funding. The project legacy will be improved protection of deep-sea biodiversity in the North Atlantic and scalable AI tools which will accelerate conservation across the entire Atlantic Basin and beyond. AI is undoubtedly the way to overcome human annotation limitations and enable a step-change in mapping and protection of life in the deep ocean.

Professor Kerry Howell
Professor of Deep-Sea Ecology

The project builds on extensive research by scientists in ��ù��Ƶ over the past two decades. In 2020, this resulted in the formation of the Challenger 150 programme – subsequently designated as a United Nations Ocean Decade Action – to generate new geological, physical, biogeochemical, and biological data through a global cooperative of science and innovation, including the application of new technology.

AI for Climate and Nature

Launched in 2024, the is a $100 million initiative designed to harness the power of artificial intelligence to tackle the dual crises of climate change and biodiversity loss.

The program connects innovators with resources and mentorship from leading technology partners including AWS, Google.org, NVIDIA Corporation, Microsoft Research, AI2, and Esri.

“These projects show how AI, when developed responsibly and guided by science and local knowledge, can strengthen environmental action and ensure its overall impact on the planet is positive,” said Dr Amen Ra Mashariki, Director of AI and Data Strategies at the Bezos Earth Fund.

Support our work to solve the world's greatest challenges:

Find out how your donations benefit our researchers and students

��ù��Ƶ