We are pleased to share that our partner, the Consiglio Nazionale delle Ricerche (CNR), has published an open-access article in Scientific Reports, a Springer Nature journal, as part of the BIO-SUSHY consortium’s ongoing research.
The article, “GrapheNet: a deep learning framework for predicting the physical and electronic properties of nanographenes using images,” introduces an artificial intelligence model that predicts key material properties quickly and accurately.
Turning Structures into Predictions with AI
This innovation is based on representing the atomic structure of nanographenes, complex carbon-based materials, as two-dimensional images. The GrapheNet deep learning model analyzes these images to predict electronic properties relevant to emerging technologies.
This approach offers both accuracy and efficiency, enabling researchers to screen thousands of potential structures significantly faster than traditional methods.
Implications for the BIO-SUSHY Project
Within the BIO-SUSHY project, CNR provides expertise in multi-scale and data-driven high-performance simulations.
While GrapheNet was developed for nanographenes, its methodology can accelerate the discovery and optimization of advanced materials. This work reflects the consortium’s commitment to using data-driven tools to advance sustainable coatings.
This research demonstrates our partners’ progress in advancing knowledge and accelerating the development of PFAS-free solutions.
Access the Full Study
We invite you to learn more about this research. The article is open-access and available online to read, download, or share.
Read the full open-access article here.
