Innovative Resources: MorFa3D: A Platform for Reconstructing 3D Morphology of Foraminifera from 2D Images

Planktic foraminifera are tiny, single-celled organisms with calcium carbonate shells found throughout the open oceans. These shells have left behind a remarkably detailed fossil record, which scientists use extensively to learn about past environments and evolutionary changes. Scientists study these fossilized foraminifera shells to reconstruct ancient environments and understand how species evolved over time. Each species has unique characteristics in the shape of its shell, which can also vary depending on environmental factors. Recent advances in technology have allowed researchers to examine the three-dimensional structure of these shells in great detail. However, current methods like micro computed tomography (micro-CT) scanning are expensive and time-consuming. The new approach will use existing robotic imaging devices and cutting-edge Artificial Intelligence (AI) tools making research more accessible. This method will allow scientists to reconstruct the 3D shape of foraminifera shells from simple two-dimensional microscope images. The goal is to create an affordable and scalable cyber-infrastructure that can be used by scientists, their students and even citizen scientists. This infrastructure includes reliable imaging systems and flexible software that can be updated with new models and analytical tools in the future.The cyber-infrastructure will be built using robotic devices the project team has developed for imaging both dry and wet samples. leading to the creation of a dataset that includes specimens imaged with these robotic devicess, along with images from micro-CT scans. To enhance this dataset, computer-generated models are added which have been designed specifically for this project. The goal is to develop an AI model that can reconstruct the 3D shape of specimens from just a few 2D microscope images—sometimes even just one. The resulting model from each analysis will be accessible through a web portal, allowing scientists and their teams as well as citizen scientists to use it for their research. Project team members are partnering with educators to involve K-12 teachers and students in capturing new images using the imaging system. This additional data will help improve the synthetic data generation process and lead to better understanding of how specimens are categorized. The aim of developing these resources, is to broaden the study of foraminifera morphology and its applications in paleontology and paleoclimate research. This project has the potential to democratize access to advanced imaging techniques and foster collaboration across scientific communities.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.