Graduate School of Engineering, Chiba University, 1-33 Yayoi-cho Inage-ku, Chiba 263-8522, Japan.
Japan Atomic Energy Agency, Muramatsu 4-33, Tokai, Ibaraki 319-1194, Japan.
J Phys Chem A. 2023 Feb 2;127(4):973-986. doi: 10.1021/acs.jpca.2c08880. Epub 2023 Jan 19.
Structural determination of adsorbed atoms on layered structures such as clay minerals is a complex subject. Radioactive cesium (Cs) is an important element for environmental conservation, so it is vital to understand its adsorption structure on clay. The nuclear magnetic resonance (NMR) parameters of Cs, which can be determined from solid-state NMR experiments, are sensitive to the local neighboring structures of adsorbed Cs. However, determining the Cs positions from NMR data alone is difficult. This paper describes an approach for identifying the expected atomic positions on clay minerals by combining machine learning (ML) with experimentally observed chemical shifts. A linear ridge regression model for ML is constructed from the smooth overlap of atomic position descriptor and gauge-including projector augmented wave (GIPAW) ab initio data. The constructed ML model predicts the GIPAW data to within a 3 ppm root-mean-squared error. At this stage, the Cs chemical shifts can be instantaneously calculated from the Cs positions on any clay layers using ML. The inverse analysis, which derives the atomic positions from experimentally observed chemical shifts, is developed from the ML model. The input data for the inverse analysis are the layer structure and the experimentally observed chemical shifts. The Cs positions for the targeted chemical shifts are then output. Inverse analysis is applied to montmorillonite, and the resultant Cs positions are found to be consistent with previous results (Ohkubo, T.; et al. , , 9326-9337). The Cs positions on saponite clay are also clarified from experimentally observed chemical shifts and inverse analysis.
层状结构（如粘土矿物）上吸附原子的结构确定是一个复杂的课题。放射性铯（Cs）是环境保护的重要元素，因此了解其在粘土上的吸附结构至关重要。可以通过固态 NMR 实验确定的 Cs 的核磁共振（NMR）参数对吸附 Cs 的局部邻近结构敏感。然而，仅从 NMR 数据确定 Cs 位置是困难的。本文描述了一种通过将机器学习（ML）与实验观察到的化学位移相结合来识别粘土矿物上预期原子位置的方法。从原子位置描述符和包含规范的投影增强波（GIPAW）从头算数据的平滑重叠构建了用于 ML 的线性脊回归模型。构建的 ML 模型将 GIPAW 数据的预测值与 3 ppm 的均方根误差范围内。在这个阶段，可以使用 ML 从任何粘土层上的 Cs 位置即时计算 Cs 的化学位移。从 ML 模型开发了从实验观察到的化学位移推导出原子位置的逆分析。逆分析的输入数据是层结构和实验观察到的化学位移。然后输出针对目标化学位移的 Cs 位置。将逆分析应用于蒙脱石，所得 Cs 位置与先前的结果一致（Ohkubo，T.；等人，9326-9337）。还从实验观察到的化学位移和逆分析阐明了皂石粘土上的 Cs 位置。
