Electronic excited states from physically-constrained machine learning. (arXiv:2311.00844v1 [physics.chem-ph])

Data-driven techniques are increasingly used to replace electronic-structure
calculations of matter. In this context, a relevant question is whether machine
learning (ML) should be applied directly to predict the desired properties or
be combined explicitly with physically-grounded operations. We present an
example of an integrated modeling approach, in which a symmetry-adapted ML
model of an effective Hamiltonian is trained to reproduce electronic
excitations from a quantum-mechanical calculation. The resulting model can make
predictions for molecules that are much larger and …

arxiv context data data-driven electronic example machine machine learning matter modeling operations physics symmetry