Density-Based Long-Range Electrostatic Descriptors - Datasets

2024/06/25 by C. Faller, Faller, Carolin, Georg Kresse +4 · 7 citations
Computer Science · #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2406.17595

Abstract

Datasets in the VASP ML_AB format. ML_AB_NaCl_liqiud: 64 Na atoms, 64 Cl atoms, 1014 configurationsML_AB_NaCl_solid: 64 Na atoms, 64 Cl atoms, 1151 configurationsML_AB_point_charges: 32 +1 charged atoms, 32 -1 charged atoms, 2000 configurationsML_AB_ZrO2: 32 Zr atoms, 64 O atoms, 592 configurations For more details, see preprint: https://arxiv.org/abs/2406.17595

Cited by

• Long-range electrostatics for machine learning interatomic potentials is easier than we thought
• Knowledge Distillation of a Protein Language Model Yields a Foundational Implicit Solvent Model
• Reciprocal Space Attention for Learning Long-Range Interactions
• msmJAX: Fast and Differentiable Electrostatics on the GPU in Python
• Equivariant machine learning of Electric Field Gradients -- Predicting the quadrupolar coupling constant in the MAPbI₃ phase transition
• A universal augmentation framework for long-range electrostatics in machine learning interatomic potentials
• Neural Network-Driven Molecular Insights into Alkaline Wet Etching of GaN: Toward Atomistic Precision in Nanostructure Fabrication

Related

• High-Entropy Solid Electrolytes Discovery: A Dual-Stage Machine Learning Framework Bridging Atomic Configurations and Ionic Transport Properties
• Systematic Improvement of Empirical Energy Functions in the Era of Machine Learning
• A representation-independent electronic charge density database for crystalline materials
• Calculated state-of-the art results for solvation and ionization energies of thousands of organic molecules relevant to battery design
• Scaled charges for ions: an improvement but not the final word for modeling electrolytes in water