Effective Local Geometry Descriptor for 29Si NMR Q4 Anisotropy

The nuclear shielding anisotropy, ζ, is a useful nuclear magnetic resonance (NMR) shielding tensor parameter in describing the extent of electron cloud distortion about an atom. Despite the advantages afforded by NMR in structural characterization, the relationship between ζ and local structure of an atom in high-symmetry environments, such as Si–Q4 sites, is poorly understood. Here, we use a data-driven approach combining random forest feature ranking and the Sure Independence Screening and Sparsifying Operator (SISSO) approach to derive a simple and accurate geometric descriptor for ζ with a root-mean-squared prediction error of 6.77 ppm and an R2 of 0.761. We then apply this descriptor to describe the local geometric distortion of zeolites Sigma-2 and silica-ZSM-5 whose chemical shift anisotropy tensor has been reported. We envision that this geometric descriptor will allow for structural description and refinement in previously difficult-to-describe materials.核屏蔽各向异性（nuclear shielding anisotropy, ζ）是描述原子周围电子云畸变程度的实用核磁共振（Nuclear Magnetic Resonance, NMR）屏蔽张量参数。尽管核磁共振技术在结构表征领域具备显著优势，但针对高对称环境（如Si-Q4位点（Si–Q4 sites））中原子的局域结构与ζ之间的关联，目前学界仍缺乏深入认知。本研究采用结合随机森林特征排序与独立筛选稀疏算子（Sure Independence Screening and Sparsifying Operator, SISSO）方法的数据驱动策略，为ζ推导得到了一项简洁精准的几何描述符，其均方根预测误差为6.77 ppm，决定系数（R²）为0.761。随后，我们将该描述符用于表征Sigma-2型沸石（zeolites Sigma-2）与硅质ZSM-5（silica-ZSM-5）的局域几何畸变，这两类材料的化学位移各向异性张量已有文献报道。我们预计，该几何描述符将为此前难以表征的材料提供结构描述与精修手段。