The University of Southern California (USC) Department of Contracts and Grants received a $228,934 Project Grant from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) to develop advanced artificial intelligence (AI) techniques to automatically identify and extract tabular data from unstructured paleoclimate files. The goal is to reduce the time scientists spend searching, formatting, and annotating paleoclimate datasets prior to conducting analyses, thereby increasing the availability of data and the reproducibility of scientific results. The 3-year project will leverage machine learning to build a Python toolbox that will allow scientists to programmatically locate and retrieve relevant tables and metadata from paleoclimate data repositories like NOAA and PANGAEA. This effort is part of the NSF's broader initiative to support the development of transformative cyberinfrastructure and data-driven discovery in the geosciences.
Generated 3/4/25, 8:16 AM