Learning From the Sea : Scaling the Biomimetic Performance of Seashell Structures for Carbon Reduction in Gridshell Buildings

Fagan, Des and Tomczyk, Ben and Barnes, Andy and Rock DeLuigi, Camila (2025) Learning From the Sea : Scaling the Biomimetic Performance of Seashell Structures for Carbon Reduction in Gridshell Buildings. In: World Design Congress, 2025-09-09 - 2025-09-10, Barbican Centre.

Text (FINAL_POSTER_ACCEPTED)
FINAL_POSTER_ACCEPTED.pdf - Accepted Version
Available under License Creative Commons Attribution.
Download (1MB)

Abstract

Our project explores the use of Machine Learning (ML) to gen¬erate structural and carbon surrogates from images of seashells, reducing carbon in the construction of gridshell buildings. Seashells exhibit evolved geometries that are optimised over hundreds of millions of years for load distribution, structural resilience and material efficiency. By leveraging the natural curvature, spiral growth and aperture scaling of seashells, our project extracts quantifiable performance patterns from real shell specimens. Machine Learning (ML) enables us to reverse-engineer those forms from photographs to reconstruct them parametrically in Grasshopper (Rhino3D) software. The resulting digital twin is subjected to structural and carbon evaluation using surrogate models, allowing us to test how morphological changes - such as compression, elongation, or scaling affect the shell’s efficiency as a building. This approach transforms natural structures into generative, low-carbon design tools.