This Project Grant award from the National Science Foundation's Geosciences Program (CFDA 47.050) provides $899,999.00 to Princeton University to develop new artificial intelligence (AI) technologies that can automatically analyze images of rock cross-sections. The goal is to accelerate scientific discovery and improve reproducibility in geoscience research. The project will address the challenge of limited training data by creating a large volume of labeled synthetic data for rock cross-sections using computer graphics and physics-based simulation techniques. These synthetic data will be used to pre-train foundation AI models, which can then be fine-tuned with a small number of real rock images to perform visual analysis tasks. As a case study, the project will apply the new AI capabilities to investigate the role of the rise of metazoan reefs in the coevolution of animals and their environments during the Cambrian radiation, using an extensive field collection from South Australia. The award integrates the research with undergraduate, graduate, and K-12 outreach activities.
Mod # | Description | Reason For Modification | Federal Obligation (Click to sort descending) | Date (Click to sort ascending) |
|---|---|---|---|---|
| Not listed | $900.0k | 7/14/25 |