Description
The widespread adoption of Electronic Laboratory Notebooks (ELNs), repositories, and other Research Data Management (RDM) and Research Software Engineering (RSE) tools has created a wealth of digital research artifacts. However, the lack of standardized formats and metadata hampers the efficient extraction, sharing, and reuse of these valuable resources. By developing a system to extract scientific data from diverse file formats, standardize it according to common standards, and publish the original data with rich metadata, we can unlock the full potential of these digital assets. The benefits of this approach are multifaceted. By achieving data interoperability, researchers can combine data from disparate sources, fostering novel insights and accelerating the discovery process. The automatic generation of machine-readable formats and metadata enables the integration of data into various systems, streamlining the research workflow. Moreover, the rich automated metadata generated through this process facilitates the reproducibility of research results, allowing scientists to verify and build upon existing findings with confidence. We show our first project results that aim to create a foundation for a more open, collaborative, and efficient scientific ecosystem. Harnessing the power of AI to create interoperable research data could be a major use case for generative AI for data stewards.
| Abstract | Poster |
|---|
