Materials Informatics– category –
-
MIT Develops Information Theory-Based MLP to Significantly Enhance Metal Alloy Behavior Modeling Accuracy
MIT News USA Overview MIT researchers have developed a novel framework for modeling metallic behavior using machine learning potentials (MLPs) trained on datasets that efficiently capture diverse atomic environments in chemically disorde... -
MLIP Enhanced Sampling Simulations Uncover Dynamic Conformations and Catalytic Implications of Au9 Nanocluster Confined in UiO-66-NH2 MOF
ChemRxiv USA Overview This research meticulously investigated the structural and dynamic behavior of an Au9 nanocluster confined within a UiO-66-NH2 MOF using machine learning interatomic potential (MLIP)-driven enhanced sampling simulat... -
LLM Automates Thermal Transport Screening in Co-Cr-Ni Medium-Entropy Alloys, Proving Concept for Autonomous Materials Discovery Workflow
ChemRxiv USA Overview This study presents a reproducible, closed-loop workflow integrating a Large Language Model (LLM) decision module with molecular dynamics simulations to automate thermal transport screening in Co-Cr-Ni medium-entrop... -
U.S. Department of Energy (DOE) Partners with Microsoft to Leverage AI for Battery Electrolyte and Clean Energy Material Discovery
OSTI (Office of Scientific and Technical Information) USA Overview The U.S. Department of Energy (DOE) is actively advancing its AI innovation ecosystem, collaborating with Microsoft to identify new battery electrolyte materials through ... -
SpinQ Launches Gate-Model Quantum Computing Platform to Enhance Quantum Simulation, Accelerating Materials Science and Drug Discovery
SpinQ China Overview SpinQ has unveiled a gate-model quantum computing platform designed to enhance quantum simulation for chemistry and materials science. The platform emphasizes its ability to more accurately model molecules and conden... -
ACS Publications Reveals MACE-QEq Potential, Addressing MLIP Challenges in Long-Range Electrostatics and Charge Transfer, Boosting Accuracy for ZnO and Water Systems
Journal of Chemical Theory and Computation (ACS Publications) USA Overview This research augments the equivariant Multi-Atomic Cluster Expansion (MACE) potential with a charge equilibration (QEq) framework to address challenges in machin... -
Major Manufacturers Invest Billions in Quantum Computing to Accelerate Atomic-Level Materials R&D
Forbes USA Overview Leading manufacturers are aggressively adopting quantum computing for materials R&D, investing billions in atomic-level material simulations. Quantum computers offer a unique advantage in modeling complex atomic i... -
Reliability-Gated First-Principles Feedback Framework ‘InvDesMobility’ Accelerates Closed-Loop Materials Discovery with Carrier Mobility Prediction
ResearchGate USA Overview This paper introduces 'InvDesMobility,' a reliability-gated first-principles feedback framework for closed-loop inverse materials design. Focusing on discovering structures based on target functionality, InvDesM... -
arXiv Introduces MMGNN: Multi-level, Multi-color Graph Neural Networks Decompose Molecular Graphs for Enhanced Property Prediction
arXiv (via ResearchGate) USA Overview A new Multi-level, Multi-color Graph Neural Network (MMGNN) has been introduced on arXiv, a hierarchical framework that decomposes molecular graphs into overlapping atom-type-pair-specific subgraphs.... -
Information Theory and Machine Learning Fusion Achieves High-Precision Alloy MLP Models for Stacking-Fault Energy and Phase Diagram Prediction
Science Advances (PubMed) USA Overview This research introduces a novel approach that combines information theory with machine learning to optimize the design of machine learning potentials (MLPs) for metallic alloys. The method effectiv...
