Deconvolution and Analysis of the 1 H NMR Spectra of Crude Reaction Mixtures
Not Available
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Engineering topics
Venetos, Maxwell C.
Publications and source records attributed to Venetos, Maxwell C..
CoeffNet : predicting activation barriers through a chemically-interpretable, equivariant and physically constrained graph neural network
CoeffNet uses coefficients of molecular orbitals of reactants and products to predict activation barriers.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Machine Learning Full NMR Chemical Shift Tensors of Silicon Oxides with Equivariant Graph Neural Networks
The nuclear magnetic resonance (NMR) chemical shift tensor is a highly sensitive probe of the electronic structure of an atom and furthermore its local structure. Recently, machine learning has been applied to NMR in the prediction of isotropic chemical shifts from a structure. Current machine learning models, however, often ignore the full chemical shift tensor for the easier-to-predict isotropic chemical shift, effectively ignoring a multitude of structural information available in the NMR chemical shift tensor. Here we use an equivariant graph neural network (GNN) to predict full 29 Si chemical shift tensors in silicate materials. The equivariant GNN model predicts full tensors to a mean absolute error of 1.05 ppm and is able to accurately determine the magnitude, anisotropy, and tensor orientation in a diverse set of silicon oxide local structures. When compared with other models, the equivariant GNN model outperforms the state-of-the-art machine learning models by 53%. The equivariant GNN model also outperforms historic analytical models by 57% for isotropic chemical shift and 91% for anisotropy. The software is available as a simple-to-use open-source repository, allowing similar models to be created and trained with ease.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
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-Q 4 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 R 2 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.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗