New methods boost accuracy of interatomic potential models

Researchers have developed novel methods, Physics-Aware Neighborhood (PAN) pooling and Physics-Guided Spectral (PGS) mixers, to enhance the accuracy of short-range equivariant interatomic potentials. These techniques focus on improving the scalar channels within neural network potentials, which are crucial for aggregating and resolving energy surfaces. When applied to the MACE scaffold, these scalar-pathway corrections led to significant reductions in force and energy errors across various materials and molecules, with only a minor increase in computational cost. The improvements were also observed in other models like Allegro and NequIP, suggesting the portability of these scalar-pathway fidelity enhancements across different short-range equivariant architectures. AI

RANK_REASON Academic paper detailing novel methods for improving interatomic potentials. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Allegro
• Fuyu Li
• LiF
• MACE
• MD17
• NequIP
• Physics-Aware Neighborhood (PAN)
• Physics-Guided Spectral (PGS)
• rMD17

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →