Graph-based AI model finds hidden links between science and art to suggest novel materials

Researchers at MIT have developed an advanced AI model that integrates generative knowledge extraction with graph-based representation to uncover hidden connections between disparate fields, such as science and art. By analyzing a dataset of 1,000 scientific papers on biological materials, the AI constructed a knowledge graph revealing intricate relationships and patterns. This approach, inspired by category theory, enables the AI to identify abstract structural similarities across different domains. For instance, the model drew parallels between the complexity of biological tissues and Beethoven’s “Symphony No. 9,” and suggested innovative material designs by linking the abstract patterns in Wassily Kandinsky’s “Composition VII” to the hierarchical structures of mycelium-based composites. This methodology holds promise for accelerating scientific discovery by facilitating the generation of novel ideas and designs that transcend traditional disciplinary boundaries.

For more details, please continue reading the full article under the following link:


Please consult also the Quantum Server Marketplace platform for the outsourcing of computational science R&D projects to external expert consultants through remote collaborations:

#materials #materialsscience #materialsengineering #computationalchemistry #modelling #chemistry #researchanddevelopment #research #MaterialsSquare #ComputationalChemistry #Tutorial #DFT #simulationsoftware #simulation