Equivariant neural network for Green's functions of molecules and materials
arXiv:2312.14680 · doi:10.1103/PhysRevB.109.075112
Abstract
The many-body Green's function provides access to electronic properties beyond density functional theory level in ab inito calculations. In this manuscript, we propose a deep learning framework for predicting the finite-temperature Green's function in atomic orbital space, aiming to achieve a balance between accuracy and efficiency. By predicting the self-energy matrices in Lehmann representation using an equivariant message passing neural network, our method respects its analytical property and the equivariance. The Green's function is obtained from the predicted self-energy through Dyson equation with target total number of electrons. We present proof-of-concept benchmark results for both molecules and simple periodic systems, showing that our method is able to provide accurate estimate of physical observables such as energy and density of states based on the predicted Green's function.
References in corpus (9)
- Machine learning for many-body physics: The case of the Anderson impurity model
- General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian
- A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules
- Transferable E(3) equivariant parameterization for Hamiltonian of molecules and solids
- Analytical Continuation of Matrix-Valued Functions: Carathéodory Formalism
- Fully Self-Consistent Finite-Temperature in Gaussian Bloch Orbitals for Solids
- Robust analytic continuation of Green's functions via projection, pole estimation, and semidefinite relaxation
- Efficient excitations and spectra within a perturbative renormalization approach
- Excitations and spectra from equilibrium real-time Green's functions