Researchers at Carnegie Mellon University have developed a multimodal machine learning approach to improve catalyst screening for energy storage and sustainable chemical processes. Traditional graph neural networks (GNNs) predict adsorption energy accurately but rely on atomic structure inputs, leaving gaps in leveraging experimental data. The new methodology combines GNNs with a transformer-based language model through multimodal learning and graph-assisted pretraining, reducing the prediction error by up to 9.8%. This system predicts initial energy estimates without requiring detailed atomic coordinates, relying instead on chemical symbols and surface orientations. Published in Nature Machine Intelligence, the work highlights a path toward accessible and interactive ML models for non-computational scientists, aiming to build advanced platforms for catalyst design with reasoning and planning capabilities.
For more details, please continue reading the full article under the following link:
In general, if you enjoy reading this kind of scientific news articles, I would also be keen to connect with fellow researchers based on common research interests in materials science, including the possibility to discuss about any potential interest in the Materials Square cloud-based online platform ( www.matsq.com ), designed for streamlining the execution of materials and molecular atomistic simulations!
Best regards,
Dr. Gabriele Mogni
Technical Consultant and EU Representative
Virtual Lab Inc., the parent company of the Materials Square platform
Website: Home | Virtual Lab Inc.
Email: gabriele@simulation.re.kr
#materials #materialsscience #materialsengineering #computationalchemistry #modelling #chemistry #researchanddevelopment #research #MaterialsSquare #ComputationalChemistry #Tutorial #DFT #simulationsoftware #simulation