August 2026– date –
-
Berkeley Lab Accelerates Advanced Materials Development with New AI-Thermodynamics Modeling Approach: Enhancing Solid-Phase Reaction Prediction
Berkeley Lab USA Overview A new modeling framework, leveraging accurate thermodynamics and machine learning, precisely and rapidly predicts a sequence of events in solid-phase reactions, including intermediate compounds, final products, ... -
Kolmogorov–Arnold Networks Revolutionize Thermoelectric Materials Design: Achieving High-Accuracy and Interpretable Property Prediction
PMC USA Overview This research introduced Kolmogorov–Arnold Networks (KANs) for thermoelectric property prediction to provide accurate and interpretable models for high-performance thermoelectric materials design. KANs achieved predictiv... -
Northwestern University Develops Novel AI-Driven Computational Method to Unravel Complex Atomic Structures at Material Interfaces
McCormick School of Engineering (Northwestern University) USA Overview Northwestern University researchers developed a new AI-driven computational method to reveal the complex atomic structures at material interfaces. This approach combi... -
DOE Advances AI Innovation Ecosystem, Leveraging Foundation Models for New Battery Electrolyte Research
Department of Energy USA Overview The U.S. Department of Energy (DOE) is actively promoting the AI innovation ecosystem, with a specific focus on advancing foundation models. A team led by materials scientist Vijay Murugesan, in collabor... -
Massive Discovery of 9,139 Low-Dimensional Materials from Materials Project via Universal Computational Strategy, Including 887 Exfoliable 2D Materials
ACS Chemistry of Materials USA Overview This research combined universal machine learning interatomic potentials (UMLIPs) with an advanced force constant (FC)-based dimensionality classification method to massively discover new low-dimen... -
Argonne National Laboratory Accelerates New Materials Discovery from Months to Days Using AI Agents
Argonne National Laboratory USA Overview Researchers at Argonne National Laboratory demonstrated an AI-driven system automating powerful simulation methods for predicting atomic interactions in materials. This system utilizes multiple AI... -
OAE Publishing Unveils AI-eChemist Autonomous Laboratory to Accelerate Electrocatalysis Research
OAE Publishing Inc. Unknown Overview OAE Publishing Inc. announced the development of the 'AI-eChemist Laboratory,' a self-driving lab (SDL) designed to dramatically accelerate electrocatalysis research. This platform integrates intellig... -
SLAC and Four Institutions Demonstrate AI-Enhanced Catalyst Development for Fuel Production, Highlighting Need for Standardization
Facebook (SLAC National Accelerator Laboratory) USA Overview Researchers from SLAC, Stanford, Penn State, and UC Santa Barbara collaborated to demonstrate AI's potential in developing catalysts for fuel production. However, inconsistenci... -
Transferable Machine Learning Interatomic Potential Accurately Predicts Thermodynamics, Structure, and Dynamics of Entangled Polymers from Oligomer Training
arXiv USA Overview This paper investigates machine learning interatomic potential (MLIP) development for polymers, identifying Atomic Cluster Expansion (ACE) as the most effective descriptor for polyethylene. It demonstrates that ACE pot... -
ACS Materials Au Publishes Comprehensive Tutorial on Machine Learning Tools for Electrocatalysis Simulations
ACS Materials Au USA Overview ACS Materials Au has released a tutorial on machine learning tools for electrocatalysis simulations, showcasing instruments like ML exchange-correlation functionals, Gaussian process optimizers, and ML inter...
