New neural network models molecular electronic states for chemistry

Researchers have developed a novel neural network architecture and training procedure designed to model electronic ground and excited states of molecular systems. This approach learns an implicit basis representation of the electronic-state Hamiltonian, enabling a unified treatment of multiple electronic states, conical intersections, and non-adiabatic couplings. The model was trained and evaluated on photochemical systems like thymine and azobenzene, accurately reproducing energies and oscillator strengths for ground and excited states, and studying critical molecular geometries. AI

IMPACT This research could accelerate simulations in computational chemistry and photochemistry.

RANK_REASON The cluster contains a research paper detailing a new neural network architecture for molecular simulations. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• azobenzene
• CatalyzeX Code Finder for Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Influence Flower
• Latent unified smooth Hamiltonians for excited state chemistry
• ScienceCast
• thymine

• paper
• other

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