AI Model NuCLR Advances Nuclear Structure Analysis

Researchers have developed NuCLR (Nuclear Co-Learned Representations), an AI model designed to analyze nuclear data. This multi-task model learns from experimental information across the chart of nuclides to predict charge radii and electric-quadrupole transition strengths. NuCLR demonstrates performance competitive with state-of-the-art nuclear models, achieving an RMS deviation of 0.0147 fm for charge radii and 0.192 e²b² for B(E2) strengths. The model also estimates prediction accuracy across different nuclides, identifying areas where new data could enhance understanding. AI

IMPACT Enhances data-driven empirical baselines for theoretical extrapolations and experimental design in nuclear physics.

RANK_REASON Academic paper detailing a new AI model for scientific research. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Influence Flower
• NuCLR
• ScienceCast
• Sokratis Trifinopoulos

• paper
• other

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