Machine Learning Interatomic Potential– tag –
-
Unlocking Real-World Performance: Thermodynamics-Based ML for Energy Material Discovery
arXiv Overview A new perspective article advocates for 'thermodynamics-based machine learning' to overcome the zero-temperature limitations of current AI models in energy material discovery. By integrating crucial factors like entropy an... -
New Ontology Proposed to Standardize Machine Learning Interatomic Potentials (MLIPs), Boosting Reproducibility and Comparability
arXiv Overview An arXiv preprint introduces the 'MLIPs ontology,' an OWL 2 DL framework designed to systematically describe Machine Learning Interatomic Potentials (MLIPs), their hyperparameters, and training/benchmarking data. By standa... -
AI-Powered Simulations Unlock Next-Gen Battery Design: How MLIPs Bridge the Gap Between DFT and Classical MD
ResearchGate Overview A recent review highlights how Machine Learning Interatomic Potentials (MLIPs) are effectively addressing persistent challenges in computational materials science for battery development. By bridging the gap between... -
Atomicrex: Open-Source Platform Unlocks Large-Scale Atomic Interaction Models for Faster Materials Discovery
atomicrex Overview A new open-source code, 'atomicrex,' is poised to accelerate computational materials science by dramatically simplifying the construction of interatomic potentials for simulations involving thousands of atoms or more. ... -
Energy-Constrained MLIP Embedding Improves Prediction Accuracy for Hydrogen Evolution Electrocatalysts
ACS Publications (Journal of Chemical Information and Modeling) Overview Researchers developed an "energy-constrained" machine learning framework integrating MLIP-derived energy descriptors with pre-trained Crystal Hamiltonian Graph Neur... -
Machine Learning Interatomic Potentials: Foundation Models Reshape Materials Discovery
Review of Peer-Reviewed Articles Overview A new comprehensive review critically examines Machine Learning Interatomic Potentials (MLIPs), a transformative technology bridging the accuracy of quantum mechanics with the efficiency of class... -
OMol25-Trained MLIPs Predict Na-Ion Battery Electrolyte Solvation Structures with DFT-Level Accuracy, Outperforming Inorganic-Only Models
ACS Publications (Journal of Physical Chemistry Letters) Overview This study demonstrates that machine learning interatomic potentials (MLIPs) trained with the Open Molecules 2025 (OMol25) dataset accurately predict and experimentally ve... -
Iterative Fine-Tuning Strategy for Universal Machine Learning Interatomic Potentials (uMLIPs) Yields Stable, High-Accuracy Models for Out-of-Domain Tasks
PubMed Overview Research on universal machine learning interatomic potentials (uMLIPs) demonstrates that "iterative fine-tuning" effectively generates stable molecular dynamics simulations and high-accuracy models for out-of-domain tasks... -
Unlocking Precision: Iterative Fine-Tuning Overcomes Bias in Universal MLIPs for Enhanced Material Simulations
Unknown Source Unknown Overview Universal Machine Learning Interatomic Potentials (uMLIPs) promise broad applicability across the periodic table, yet accurate out-of-domain predictions demand specialized fine-tuning. This study reveals t... -
AI’s Three Pillars: Accelerating Materials Discovery with Predictive Models, Generative Design, and Machine Learning Interatomic Potentials
Source Unknown USA Overview Artificial intelligence is fundamentally transforming materials science through three key advancements: highly accurate property prediction, autonomous generative design, and revolutionary machine learning int...
