用完全可微密度泛函理论从自然界学习交换相关泛函
Learning the exchange-correlation functional from nature with fully differentiable density functional theory
摘要：
提高从头算模拟中分子性质的预测能力对于新材料的发现至关重要。尽管最近在利用机器学习方面取得了进展，但利用深度神经网络来改进量子化学建模仍然受到适当实验数据的稀缺性和异质性的严重限制。在这里，我们展示了如何训练神经网络，以取代交换相关功能在一个完全可微的三维Kohn-Sham密度泛函理论（DFT）框架可以大大提高模拟精度。仅使用双原子分子上的8个实验数据点，我们训练的交换相关网络可以提高104个分子的原子化能量的预测准确性，这些分子包含训练数据集中不存在的新键和原子。
英文摘要：
Improving the predictive capability of molecular properties in ab initio simulations is essential for advanced material discovery. Despite recent progress making use of machine learning, utilizing deep neural networks to improve quantum chemistry modelling remains severely limited by the scarcity and heterogeneity of appropriate experimental data. Here we show how training a neural network to replace the exchange-correlation functional within a fully-differentiable three-dimensional Kohn-Sham density functional theory (DFT) framework can greatly improve simulation accuracy. Using only eight experimental data points on diatomic molecules, our trained exchange-correlation networks enable improved prediction accuracy of atomization energies across a collection of 104 molecules containing new bonds and atoms that are not present in the training dataset.
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。
