Simulation– tag –
-
arXiv Paper Presents ‘AutoPot’: Automated, Massively Parallel Workflow for Constructing Machine-Learning Potentials
arXiv USA Overview A new preprint on arXiv introduces 'AutoPot,' an automated and massively parallelized workflow for constructing Machine Learning Interatomic Potentials (MLIPs). MLIPs bring quantum accuracy to atomic modeling, enabling... -
arXiv Paper Identifies Six Open Questions in Machine-Learned Interatomic Potential Foundation Models
arXiv USA Overview A new arXiv paper reviews the rapid advancements of machine learning (ML) in atomic modeling and the growing centrality of interatomic potentials in materials science. It discusses six open questions as key challenges ... -
German Federal Ministry of Education and Research Funds ASCEND Project with €30M to Accelerate AI-Driven Catalyst Development via Autonomous Labs
e-conversion Germany Overview The German Federal Ministry of Education and Research (BMFTR) launched the 'ASCEND' project, investing €30 million across six research and industry partners, including Helmholtz-Zentrum Berlin and BASF, to a... -
SCM Releases ‘AMS2026’ Software, Accelerating Materials Chemistry Simulations with ML Potentials and GPU Optimization
SCM (Scientific Computing & Modelling) Netherlands Overview SCM announced the release of 'AMS2026' software, featuring major advancements in machine learning potentials (eSEN, MACE, UMA) that expand chemical coverage for biomolecules, ca... -
International Team, Including Tohoku University, Accelerates Methane Pyrolysis Catalyst Discovery with AI-Driven Platform ‘DigMethpy’
Tohoku University Japan Overview An international research team, including Tohoku University, developed 'DigMethpy,' an AI-driven digital catalyst platform to accelerate methane pyrolysis catalyst discovery. The platform integrates scien... -
London Researchers Dramatically Reduce Qubit Count for Crystalline Material Simulations on Quantum Computers
Quantum Zeitgeist UK Overview Researchers at the London Centre for Nanotechnology (LCN) have developed a 'periodic symmetry-adapted encoding' framework, significantly reducing the number of qubits required for electronic structure simula... -
arXiv: PolyGraphPy Unifies Atomistic Simulation and ML-Driven Polymer Design in a Python Framework
arXiv Unknown Overview A new paper on arXiv introduces "PolyGraphPy," a unified Python framework for atomistic simulation and machine learning (ML)-driven polymer design. This open-source framework seamlessly integrates atomistic simulat... -
Topsoe Declares AI the “Fifth Paradigm” in Materials Science, Poised to Revolutionize Catalysis, Electrolysis, and Battery Design
Topsoe デンマーク Overview Topsoe, a global leader in catalyst technology, has announced that AI is emerging as the "fifth paradigm" in materials science, fundamentally transforming material discovery and design. Their AI systems combine... -
ResearchGate: NequIP GNN Predicts Amorphous Material Many-Body Interactions at 10,000x Lower Cost than DFT
ResearchGate Unknown Overview Recent research applied NequIP, an equivariant message passing graph neural network (GNN), to predict many-body interactions in model soft glasses of solvent-free polymer-grafted nanoparticles (PGNs). NequIP... -
arXiv Publishes Review on Generative Models, Multimodal Learning, and Closed-Loop Workflows in Inverse Materials Design
arXiv Unknown Overview A new review paper published on arXiv outlines advancements in generative models, multimodal learning, and closed-loop workflows for inverse materials design. The study highlights a shift in materials science from ...
