Transferable E(3) equivariant parameterization for Hamiltonian of molecules and solids

• URL: http://arxiv.org/abs/2210.16190v1
• Date: Fri, 28 Oct 2022 14:56:24 GMT
• Title: Transferable E(3) equivariant parameterization for Hamiltonian of molecules and solids
• Authors: Yang Zhong, Hongyu Yu, Mao Su, Xingao Gong, Hongjun Xiang
• Abstract summary: We develop an E(3) equivariant neural network called HamNet to predict the ab initio tight-binding Hamiltonian of molecules and solids. The proposed framework provides a general transferable model for accelerating electronic structure calculations.
• Score: 5.512295869673147
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning, especially deep learning, can build a direct mapping from structure to properties with its huge parameter space, making it possible to perform high-throughput screening for the desired properties of materials. However, since the electronic Hamiltonian transforms non-trivially under rotation operations, it is challenging to accurately predict the electronic Hamiltonian while strictly satisfying this constraint. There is currently a lack of transferable machine learning models that can bypass the computationally demanding density functional theory (DFT) to obtain the ab initio Hamiltonian of molecules and materials by complete data-driven methods. In this work, we point out the necessity of explicitly considering the parity symmetry of the electronic Hamiltonian in addition to rotational equivariance. We propose a parameterized Hamiltonian that strictly satisfies rotational equivariance and parity symmetry simultaneously, based on which we develop an E(3) equivariant neural network called HamNet to predict the ab initio tight-binding Hamiltonian of various molecules and solids. The tests show that this model has similar transferability to that of machine learning potentials and can be applied to a class of materials with different configurations using the same set of trained network weights. The proposed framework provides a general transferable model for accelerating electronic structure calculations.

Related papers

• Similarity Equivariant Graph Neural Networks for Homogenization of Metamaterials [3.6443770850509423]
  Soft, porous mechanical metamaterials exhibit pattern transformations that may have important applications in soft robotics, sound reduction and biomedicine. We develop a machine learning-based approach that scales favorably to serve as a surrogate model. We show that this network is more accurate and data-efficient than graph neural networks with fewer symmetries.
  arXiv  Detail & Related papers  (2024-04-26T12:30:32Z)
• Critical behavior of lattice gauge theory Rydberg simulators from effective Hamiltonians [2.9780372446425627]
  We consider multileg ladders of Rydberg atoms which have been proposed as quantum simulators for the compact Abelian Higgs model (CAHM) in 1+1 dimensions. Using numerical methods, we demonstrate the close correspondence between the physical simulator and the effective description for the ground state energy and real-time evolution.
  arXiv  Detail & Related papers  (2023-12-07T17:03:11Z)
• QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules [69.25826391912368]
  We generate a new Quantum Hamiltonian dataset, named as QH9, to provide precise Hamiltonian matrices for 999 or 2998 molecular dynamics trajectories. We show that current machine learning models have the capacity to predict Hamiltonian matrices for arbitrary molecules.
  arXiv  Detail & Related papers  (2023-06-15T23:39:07Z)
• Molecular Geometry-aware Transformer for accurate 3D Atomic System modeling [51.83761266429285]
  We propose a novel Transformer architecture that takes nodes (atoms) and edges (bonds and nonbonding atom pairs) as inputs and models the interactions among them. Moleformer achieves state-of-the-art on the initial state to relaxed energy prediction of OC20 and is very competitive in QM9 on predicting quantum chemical properties.
  arXiv  Detail & Related papers  (2023-02-02T03:49:57Z)
• Machine learning for excitation energy transfer dynamics [0.0]
  We use the hierarchical equations of motion (HEOM) to simulate open quantum dynamics in the biological regime. We generate a set of time dependent observables that depict the coherent propagation of electronic excitations through the light harvesting complexes. We demonstrate the capability of convolutional neural networks to tackle this research problem.
  arXiv  Detail & Related papers  (2021-12-22T14:11:30Z)
• Variational Adiabatic Gauge Transformation on real quantum hardware for effective low-energy Hamiltonians and accurate diagonalization [68.8204255655161]
  We introduce the Variational Adiabatic Gauge Transformation (VAGT) VAGT is a non-perturbative hybrid quantum algorithm that can use nowadays quantum computers to learn the variational parameters of the unitary circuit. The accuracy of VAGT is tested trough numerical simulations, as well as simulations on Rigetti and IonQ quantum computers.
  arXiv  Detail & Related papers  (2021-11-16T20:50:08Z)
• Machine Learning S-Wave Scattering Phase Shifts Bypassing the Radial Schr\"odinger Equation [77.34726150561087]
  We present a proof of concept machine learning model resting on a convolutional neural network capable to yield accurate scattering s-wave phase shifts. We discuss how the Hamiltonian can serve as a guiding principle in the construction of a physically-motivated descriptor.
  arXiv  Detail & Related papers  (2021-06-25T17:25:38Z)
• GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles [60.12186997181117]
  Prediction of a molecule's 3D conformer ensemble from the molecular graph holds a key role in areas of cheminformatics and drug discovery. Existing generative models have several drawbacks including lack of modeling important molecular geometry elements. We propose GeoMol, an end-to-end, non-autoregressive and SE(3)-invariant machine learning approach to generate 3D conformers.
  arXiv  Detail & Related papers  (2021-06-08T14:17:59Z)
• Quantum simulation of electronic structure with a transcorrelated Hamiltonian: improved accuracy with a smaller footprint on the quantum computer [2.640996411999115]
  Quantum simulations of electronic structure with a transformed Hamiltonian that includes some electron correlation effects are demonstrated. A transcorrelated Hamiltonian, paired with extremely compact bases, produces explicitly correlated energies comparable to those from much larger bases. The use of the very compact transcorrelated Hamiltonian reduces the number of CNOT gates required to achieve cc-pVTZ quality by up to two orders of magnitude, and the number qubits by a factor of three.
  arXiv  Detail & Related papers  (2020-06-03T19:15:32Z)
• Graph Neural Network for Hamiltonian-Based Material Property Prediction [56.94118357003096]
  We present and compare several different graph convolution networks that are able to predict the band gap for inorganic materials. The models are developed to incorporate two different features: the information of each orbital itself and the interaction between each other. The results show that our model can get a promising prediction accuracy with cross-validation.
  arXiv  Detail & Related papers  (2020-05-27T13:32:10Z)
• Differentiable Molecular Simulations for Control and Learning [0.9208007322096533]
  We develop new routes for parameterizing Hamiltonians to infer macroscopic models and develop control protocols. We demonstrate how this can be achieved using differentiable simulations where bulk target observables and simulation outcomes can be analytically differentiated with respect to Hamiltonians.
  arXiv  Detail & Related papers  (2020-02-27T04:35:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.