Machine Learning Interatomic Potential– tag –
-
Machine Learning Potentials Accelerate Quantum Chemistry by Up to 1 Million-Fold, Revolutionizing Materials Science
ACS Central Science USA Overview Rapid advancements in machine learning interatomic potentials (MLIPs) are poised to accelerate quantum chemistry calculations by up to a million times, fundamentally transforming chemical and materials sc... -
arXiv Paper Evaluates Universal MLIPs, Finds DFT Fine-Tuning Essential for Accuracy in Reactive Processes
arXiv USA Overview A new arXiv study evaluated five universal machine-learning interatomic potentials (MLIPs) for quantitative materials modeling involving reactive events. It revealed that while universal MLIPs are becoming general-purp... -
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... -
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... -
Hugging Face Spotlights CrystalCLR and CHGNet for Enhanced Materials Property Prediction via Machine Learning
Hugging Face USA Overview Hugging Face highlights significant advancements in materials property prediction with the CrystalCLR framework and CHGNet machine learning interatomic potential. CrystalCLR improves material representations thr... -
AI Drives Rapid Design and Modeling of Organic Electrochemical Energy Materials for Advanced Batteries
ChemRxiv USA Overview Artificial intelligence is dramatically transforming the computational design and modeling of organic electrochemical energy materials (OEEMs) through data-driven property prediction, machine learning interatomic po... -
Purdue University Seeks Postdoctoral Researchers in Computational Materials Design and Materials Informatics, Bolstering DFT and MLIPs Research
ApplyKite USA Overview Purdue University has announced a postdoctoral researcher opening in computational materials design and materials informatics. This strategic hire targets researchers with strong expertise in atomistic simulation m... -
ResearchGate Paper: Unconstrained MLIPs Achieve Superior Accuracy and Speed with Large Datasets, Enhancing Static Simulations
ResearchGate (Machine Learning: Science and Technology) Unknown Overview A paper published via ResearchGate demonstrates that unconstrained Machine Learning Interatomic Potentials (MLIPs), when trained on sufficiently large datasets, can... -
UniFFBench Evaluates Universal Machine Learning Force Fields (UMLFFs) Against Experimental Measurements, Assessing Simulation Stability, Structural Fidelity, and Elastic Properties
arXiv International Overview A new benchmark framework, UniFFBench, has been released to evaluate Universal Machine Learning Force Fields (UMLFFs) against experimental measurements for diverse mineral systems. UniFFBench rigorously asses... -
Unconstrained MLIPs Scaled to Large Datasets Outperform Constrained Models in Static Simulations for Accuracy and Speed
ResearchGate International Overview Unconstrained Machine Learning Interatomic Potentials (MLIPs), scaled to large datasets, have demonstrated superior performance in both accuracy and speed for static simulation workflows like geometric...
