arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.09814physics.comp-phcs.LGphysics.chem-phstat.ML
收藏

机器学习预测电子动力学的分子哈密顿量

Machine Learning a Molecular Hamiltonian for Predicting Electron Dynamics

University of California, Merced(加州大学默塞德分校)

Harish S. Bhat, Karnamohit Ranka, Christine M. Isborn

摘要:

我们开发了一种计算方法,从矩阵值的电子密度时间序列中学习分子的哈密顿矩阵。正如我们对三个小分子所展示的那样,所得到的哈密顿算子可以用于电子密度演化,即使在训练数据之外传播1000个时间步长时也能产生高度准确的结果。作为一个更严格的测试,我们使用学习的哈密顿来模拟电子动力学的存在下施加的电场,外推到一个问题,这是超出了无场训练数据。我们发现,由此产生的电子动力学预测我们学到的哈密顿量是在密切的定量协议与地面真相。我们的方法依赖于结合一个降维的,线性统计模型的哈密顿量与时间离散化的量子刘维尔方程随时间变化的哈特里-福克理论。我们使用最小二乘求解器训练模型,避免了大量CPU密集型优化步骤。对于无场和有场问题,我们量化了训练和传播误差,突出了未来发展的领域。

英文摘要:

We develop a computational method to learn a molecular Hamiltonian matrix from matrix-valued time series of the electron density. As we demonstrate for three small molecules, the resulting Hamiltonians can be used for electron density evolution, producing highly accurate results even when propagating 1000 time steps beyond the training data. As a more rigorous test, we use the learned Hamiltonians to simulate electron dynamics in the presence of an applied electric field, extrapolating to a problem that is beyond the field-free training data. We find that the resulting electron dynamics predicted by our learned Hamiltonian are in close quantitative agreement with the ground truth. Our method relies on combining a reduced-dimensional, linear statistical model of the Hamiltonian with a time-discretization of the quantum Liouville equation within time-dependent Hartree Fock theory. We train the model using a least-squares solver, avoiding numerous, CPU-intensive optimization steps. For both field-free and field-on problems, we quantify training and propagation errors, highlighting areas for future development.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑