arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.02347physics.chem-phstat.ML
收藏

SE(3)-分子波函数和电子密度的等变预测

SE(3)-equivariant prediction of molecular wavefunctions and electronic densities

Oliver T. Unke, Mihail Bogojeski, Michael Gastegger, Mario Geiger, Tess Smidt, Klaus-Robert Müller

摘要:

机器学习已经能够以高精度和高效率预测量子化学性质,从而可以绕过计算成本高昂的从头计算。最近的方法试图学习电子波函数(或密度)作为原子系统的中心量,而不是在一组固定的属性上进行训练,所有其他可观测量都可以从中导出。这是复杂的事实,波函数变换下的分子旋转,这使得他们成为一个具有挑战性的预测目标。为了解决这个问题,我们引入了一般的SE(3)-等变运算和构建块,用于构建几何点云数据的深度学习架构,并将其应用于以前所未有的精度重建原子系统的波函数。与从头算方法相比,我们的模型实现了超过三个数量级的加速,并且与以前的最新技术相比,预测误差减少了两个数量级。这种准确性使得可以以端到端的方式直接从波函数中获得能量和力等属性。我们展示了我们的方法在迁移学习应用中的潜力,在迁移学习应用中,在低精度参考波函数上训练的模型隐式地学习从在更高理论水平上计算的观测值中校正电子多体相互作用。这种机器学习的波函数替代品为新的半经验方法铺平了道路,提供了电子水平的分辨率,同时大大降低了计算成本。此外,预测的波函数可以作为传统从头算方法中的初始猜测,减少达到收敛解所需的迭代次数,从而在不损失准确性或鲁棒性的情况下显着加速。

英文摘要:

Machine learning has enabled the prediction of quantum chemical properties with high accuracy and efficiency, allowing to bypass computationally costly ab initio calculations. Instead of training on a fixed set of properties, more recent approaches attempt to learn the electronic wavefunction (or density) as a central quantity of atomistic systems, from which all other observables can be derived. This is complicated by the fact that wavefunctions transform non-trivially under molecular rotations, which makes them a challenging prediction target. To solve this issue, we introduce general SE(3)-equivariant operations and building blocks for constructing deep learning architectures for geometric point cloud data and apply them to reconstruct wavefunctions of atomistic systems with unprecedented accuracy. Our model achieves speedups of over three orders of magnitude compared to ab initio methods and reduces prediction errors by up to two orders of magnitude compared to the previous state-of-the-art. This accuracy makes it possible to derive properties such as energies and forces directly from the wavefunction in an end-to-end manner. We demonstrate the potential of our approach in a transfer learning application, where a model trained on low accuracy reference wavefunctions implicitly learns to correct for electronic many-body interactions from observables computed at a higher level of theory. Such machine-learned wavefunction surrogates pave the way towards novel semi-empirical methods, offering resolution at an electronic level while drastically decreasing computational cost. Additionally, the predicted wavefunctions can serve as initial guess in conventional ab initio methods, decreasing the number of iterations required to arrive at a converged solution, thus leading to significant speedups without any loss of accuracy or robustness.

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。

↑