NIMBE, CEA, CNRS, Université Paris-Saclay, CEA-Saclay, F-91191 Gif-sur-Yvette Cedex, France.
Phys Chem Chem Phys. 2019 Oct 9;21(39):21709-21725. doi: 10.1039/c9cp02803j.
Machine learning (ML) approaches are investigated for the prediction of nuclear magnetic resonance (NMR) parameters in aluminosilicate glasses, for which NMR has proven to be a cutting-edge method over the last decade. DFT computations have emerged as a new dimension for complementing these NMR methods although suffering from severe limitations in terms of size, time and computational resources consumption. While previous approaches tend to use DFT-GIPAW calculations for the prediction of NMR parameters in glassy systems, we propose to employ ML methods, characterized by a speed similar to that of classical molecular dynamics while the accuracy of ab initio methods can be reached. We design ML procedures to predict the isotropic magnetic shielding (σiso) for different multicomponent relevant glass compositions. The ML predictions of σiso deviate from DFT-GIPAW calculations, when including relaxed and room-temperature structures, by 0.7 ppm for 29Si (1.0% of the total span of the calculated ) and 1.5 ppm for 17O (1.9%) in SiO2 glasses, 1.4 ppm for 23Na (1.5%) in Na2O-SiO2 and 1.5 ppm for 27Al (2.1%) in Al2O3-Na2O-SiO2 systems. We compare the performances obtained for a set of three descriptors suitable for encoding atomic local environments information (atom-centered representations) together with seven popular ML algorithms with a focus on the simple (but robust) linear ridge regression (LRR) and the popular smooth overlap of atomic positions (SOAP) descriptor.
机器学习 (ML) 方法被用于预测铝硅酸盐玻璃中的核磁共振 (NMR) 参数，在过去十年中，NMR 已被证明是一种前沿方法。尽管在尺寸、时间和计算资源消耗方面存在严重限制，但密度泛函理论 (DFT) 计算已成为补充这些 NMR 方法的新维度。虽然以前的方法倾向于使用 DFT-GIPAW 计算来预测玻璃系统中的 NMR 参数，但我们建议采用 ML 方法，其速度与经典分子动力学相似，同时可以达到从头算方法的准确性。我们设计了 ML 程序来预测不同多组分相关玻璃成分的各向同性磁屏蔽 (σiso)。当包括弛豫和室温结构时，ML 对 σiso 的预测与 DFT-GIPAW 计算的偏差为 0.7 ppm（对于 SiO2 玻璃中的 29Si 为总计算跨度的 1.0%）和 1.5 ppm（对于 17O 为 1.9%），23Na（1.5%）在 Na2O-SiO2 中，27Al（2.1%）在 Al2O3-Na2O-SiO2 系统中为 1.5 ppm。我们比较了一组适合编码原子局部环境信息的三个描述符（原子中心表示）与七种流行的 ML 算法的性能，重点是简单（但稳健）的线性岭回归 (LRR) 和流行的原子位置平滑重叠 (SOAP) 描述符。
