This research introduces an automated workflow for extracting, integrating, and analyzing materials science information from scientific documents using data mining and large language models.

• Combines multi-modal data from simulations and experiments
• Makes scientific information machine-readable and accessible
• Addresses challenges of information locked in unstructured scientific documents
• Creates a knowledge synthesis tool for materials scientists and engineers

This work significantly advances engineering practices by enabling easier discovery of material properties and improving data-driven decision making in materials development and selection processes.

Towards an automated workflow in materials science for combining multi-modal simulative and experimental information using data mining and large language models