Immersive media artist, Refik Anadol, has announced the first open-source generative AI-model dedicated to nature, diverging from large language AI models that rely on human intelligence.
The model, titled large nature model, has been developed for Refik Anadol Studio’s future museum and Web3 platform, Dataland, dedicated to data visualisation and AI arts.
The first installation of early experimental outputs based on the large nature model, titled Living Archive: Nature, will be unveiled at the 54th annual World Economic Forum in Davos-Klosters, Switzerland, 15-19 January 2024. The installation is intended as a multimodal experience that includes visuals, sound, and scent elements, highlighting the interplay between ecosystem through generative AI.
The installation will be presented on a 12mx4m media wall, featuring the longest 3D generative AI outputs on nature yet created, including detailed rainforest flora and fauna simulations.
Custom-designed generative sound and scent will offer an opportunity to interact with the raw dataset, the foundation of the model, with a process videowall incorporated into the installation to provide an explanation on the interdisciplinary AI research behind the outputs.
Refik Anadol commented: “Our vision for the Large Nature Model goes beyond being a repository or a creative research initiative. It is a tool for insight, education, and advocacy for the shared environment of humanity. Blending art, technology, and nature, our model aims to raise awareness about environmental issues and inspire innovative solutions by finding connections among isolated archives. Moreover, by engaging people on multiple sensory levels, the outputs of the model make the abstract concept of environmental conservation tangible, encouraging a collective responsibility to act.”