Revolutionary Project Combines Artificial Intelligence and Underwater Photography to Document Ocean Life
Published Date: 25 Jun 2025
In the Northeastern United States, the Gulf of Maine is home to one of the most biologically diverse marine ecosystems on the planet, with a wide range of species including whales, sharks, and jellyfish. However, this ecosystem is undergoing rapid environmental change, with the Gulf of Maine warming faster than 99 percent of the world's oceans. To document the ocean life left vulnerable to these changes, a new research initiative is using artificial intelligence and underwater photography to share the story of this ecosystem with the public in new and innovative ways.
The project, known as LOBSTgER, brings together artificial intelligence and underwater photography to build on field-based photographic data and expand scientific storytelling. By training generative models on a curated library of original underwater photographs, the project aims to create new visual ways to document ocean life and share it with the public.
The use of generative AI in this project marks a new frontier in visual storytelling, similar to how the 19th-century camera transformed our ability to document and reveal the natural world. The project's models are trained exclusively on a curated library of original underwater photographs, each image crafted with artistic intent, technical precision, and clear geographic context.
The resulting imagery not only appears visually accurate but also feels immersive and moving, with the models able to generate new, synthetic, but scientifically accurate images unconditionally, and enhance real photographs conditionally. This hybrid approach is designed to accelerate the curation process and enable storytellers to construct a more complete and coherent visual narrative of life beneath the surface.
The project operates at the intersection of art, science, and technology, drawing from the visual language of photography, the observational rigor of marine science, and the computational power of generative AI. By uniting these disciplines, the team is developing new ways to visualize ocean life and reimagining how environmental stories can be told.
Underwater photography in New England's coastal waters is notoriously difficult, with limited visibility, swirling sediment, and unpredictable movement of marine life posing constant challenges. Despite these challenges, the project's lead photographer has been building a comprehensive record of the region's biodiversity through the project, Space to Sea: Visualizing New England's Ocean Wilderness.
The custom diffusion models used in the project are trained to replicate not only the biodiversity documented but also the artistic style used to capture it. By learning from thousands of real underwater images, the models internalize fine-grained details such as natural lighting gradients, species-specific coloration, and atmospheric texture created by suspended particles and refracted sunlight.
The team believes that this approach may benefit other underwater photographers and image editors facing similar challenges, and that it can help to make the invisible visible and drive real-world engagement and action. The project's long-term goal is to develop a comprehensive model that can visualize a wide range of species found in the Gulf of Maine and apply similar methods to marine ecosystems around the world.
The project reflects a parallel process: field documentation through photography and model development through iterative training. The lead photographer works in the field, capturing rare and fleeting encounters with marine animals, while the AI expert works in the lab, translating those moments into machine-learning contexts that can extend and reinterpret the visual language of the ocean.
The combination of artificial intelligence and underwater photography in this project offers a powerful framework for communicating science through image-making, and has the potential to raise awareness, drive engagement, and ultimately contribute to the conservation of marine ecosystems. As the project continues to evolve, it will be exciting to see the new discoveries, images, and insights that emerge.