Within the Northeastern United States, the Gulf of Maine represents one of the vital biologically numerous marine ecosystems on the planet — dwelling to whales, sharks, jellyfish, herring, plankton, and tons of of different species. However whilst this ecosystem helps wealthy biodiversity, it’s present process fast environmental change. The Gulf of Maine is warming quicker than 99 p.c of the world’s oceans, with penalties which might be nonetheless unfolding.
A brand new analysis initiative creating at MIT Sea Grant, known as LOBSTgER — quick for Studying Oceanic Bioecological Techniques By way of Generative Representations — brings collectively synthetic intelligence and underwater pictures to doc the ocean life left susceptible to those adjustments and share them with the general public in new visible methods. Co-led by underwater photographer and visiting artist at MIT Sea Grant Keith Ellenbogen and MIT mechanical engineering PhD pupil Andreas Mentzelopoulos, the challenge explores how generative AI can develop scientific storytelling by constructing on field-based photographic information.
Simply because the Nineteenth-century digital camera remodeled our skill to doc and reveal the pure world — capturing life with unprecedented element and bringing distant or hidden environments into view — generative AI marks a brand new frontier in visible storytelling. Like early pictures, AI opens a inventive and conceptual area, difficult how we outline authenticity and the way we talk scientific and creative views.
Within the LOBSTgER challenge, generative fashions are skilled solely on a curated library of Ellenbogen’s authentic underwater images — every picture crafted with creative intent, technical precision, correct species identification, and clear geographic context. By constructing a high-quality dataset grounded in real-world observations, the challenge ensures that the ensuing imagery maintains each visible integrity and ecological relevance. As well as, LOBSTgER’s fashions are constructed utilizing customized code developed by Mentzelopoulos to guard the method and outputs from any potential biases from exterior information or fashions. LOBSTgER’s generative AI builds upon actual pictures, increasing the researchers’ visible vocabulary to deepen the general public’s connection to the pure world.
This ocean sunfish (Mola mola) picture was generated by LOBSTgER’s unconditional fashions.
AI-generated picture: Keith Ellenbogen, Andreas Mentzelopoulos, and LOBSTgER.
At its coronary heart, LOBSTgER operates on the intersection of artwork, science, and know-how. The challenge attracts from the visible language of pictures, the observational rigor of marine science, and the computational energy of generative AI. By uniting these disciplines, the crew shouldn’t be solely creating new methods to visualise ocean life — they’re additionally reimagining how environmental tales could be instructed. This integrative strategy makes LOBSTgER each a analysis software and a inventive experiment — one which displays MIT’s long-standing custom of interdisciplinary innovation.
Underwater pictures in New England’s coastal waters is notoriously troublesome. Restricted visibility, swirling sediment, bubbles, and the unpredictable motion of marine life all pose fixed challenges. For the previous a number of years, Ellenbogen has navigated these challenges and is constructing a complete file of the area’s biodiversity by way of the challenge, Area to Sea: Visualizing New England’s Ocean Wilderness. This huge dataset of underwater photos offers the inspiration for coaching LOBSTgER’s generative AI fashions. The pictures span numerous angles, lighting circumstances, and animal behaviors, leading to a visible archive that’s each artistically putting and biologically correct.
Picture synthesis through reverse diffusion: This quick video exhibits the de-noising trajectory from Gaussian latent noise to photorealistic output utilizing LOBSTgER’s unconditional fashions. Iterative de-noising requires 1,000 ahead passes by way of the skilled neural community.
Video: Keith Ellenbogen and Andreas Mentzelopoulos / MIT Sea Grant
LOBSTgER’s customized diffusion fashions are skilled to copy not solely the biodiversity Ellenbogen paperwork, but additionally the creative type he makes use of to seize it. By studying from 1000’s of actual underwater photos, the fashions internalize fine-grained particulars comparable to pure lighting gradients, species-specific coloration, and even the atmospheric texture created by suspended particles and refracted daylight. The result’s imagery that not solely seems visually correct, but additionally feels immersive and shifting.
The fashions can each generate new, artificial, however scientifically correct photos unconditionally (i.e., requiring no consumer enter/steerage), and improve actual images conditionally (i.e., image-to-image era). By integrating AI into the photographic workflow, Ellenbogen will have the ability to use these instruments to recuperate element in turbid water, alter lighting to emphasise key topics, and even simulate scenes that will be practically not possible to seize within the subject. The crew additionally believes this strategy might profit different underwater photographers and picture editors going through comparable challenges. This hybrid technique is designed to speed up the curation course of and allow storytellers to assemble a extra full and coherent visible narrative of life beneath the floor.
Left: Enhanced picture of an American lobster utilizing LOBSTgER’s image-to-image fashions. Proper: Unique picture.
Left: AI genertated picture by Keith Ellenbogen, Andreas Mentzelopoulos, and LOBSTgER. Proper: Keith Ellenbogen
In a single key sequence, Ellenbogen captured high-resolution photos of lion’s mane jellyfish, blue sharks, American lobsters, and ocean sunfish (Mola mola) whereas free diving in coastal waters. “Getting a high-quality dataset shouldn’t be straightforward,” Ellenbogen says. “It requires a number of dives, missed alternatives, and unpredictable circumstances. However these challenges are a part of what makes underwater documentation each troublesome and rewarding.”
Mentzelopoulos has developed authentic code to coach a household of latent diffusion fashions for LOBSTgER grounded on Ellenbogen’s photos. Creating such fashions requires a excessive stage of technical experience, and coaching fashions from scratch is a posh course of demanding tons of of hours of computation and meticulous hyperparameter tuning.
The challenge displays a parallel course of: subject documentation by way of pictures and mannequin improvement by way of iterative coaching. Ellenbogen works within the subject, capturing uncommon and fleeting encounters with marine animals; Mentzelopoulos works within the lab, translating these moments into machine-learning contexts that may lengthen and reinterpret the visible language of the ocean.
“The aim isn’t to switch pictures,” Mentzelopoulos says. “It’s to construct on and complement it — making the invisible seen, and serving to individuals see environmental complexity in a approach that resonates each emotionally and intellectually. Our fashions goal to seize not simply organic realism, however the emotional cost that may drive real-world engagement and motion.”
LOBSTgER factors to a hybrid future that merges direct commentary with technological interpretation. The crew’s long-term aim is to develop a complete mannequin that may visualize a variety of species discovered within the Gulf of Maine and, ultimately, apply comparable strategies to marine ecosystems all over the world.
The researchers counsel that pictures and generative AI kind a continuum, somewhat than a battle. Pictures captures what’s — the feel, mild, and animal habits throughout precise encounters — whereas AI extends that imaginative and prescient past what’s seen, towards what may very well be understood, inferred, or imagined based mostly on scientific information and creative imaginative and prescient. Collectively, they provide a strong framework for speaking science by way of image-making.
In a area the place ecosystems are altering quickly, the act of visualizing turns into extra than simply documentation. It turns into a software for consciousness, engagement, and, finally, conservation. LOBSTgER remains to be in its infancy, and the crew appears ahead to sharing extra discoveries, photos, and insights because the challenge evolves.
Reply from the lead picture: The left picture was generated utilizing utilizing LOBSTgER’s unconditional fashions and the proper picture is actual.
For extra data, contact Keith Ellenbogen and Andreas Mentzelopoulos.
