Prediction of chemical shift in NMR using machine learning methods is typically done with the maximum amount of data available to achieve the best results. In some cases, such large amounts of data are not available, e.g. for heteronuclei. We demonstrate a novel machine learning model which is able to achieve good results with comparatively low amounts of data. We show this by predicting 19F and 13C NMR chemical shifts of small molecules in specific solvents.
TransPeakNet: Solvent-Aware 2D NMR Prediction via Multi-Task Pre-Training and Unsupervised Learning
Brandeis University（布兰迪斯大学）；Harvard Medical School（哈佛医学院）；Complex Carbohydrate Research Center, University of Georgia（佐治亚大学复合碳水化合物研究中心）；Boston College（波士顿学院）
$^{27}\text{Al }$ NMR chemical shift of $\text{Al}(\text{OH})_{4}^{-}$ from first principles. Assessment of error cancellation in NMR chemical shift computations in chemically distinct reference and targeted systems
NMR Chemical Shift Computations at Second-Order Møller-Plesset Perturbation Theory Using Gauge-Including Atomic Orbitals and Cholesky-Decomposed Two-Electron Integrals
IMPRESSION -- Prediction of NMR Parameters for 3-dimensional chemical structures using Machine Learning with near quantum chemical accuracy
IMPRESSION（Intelligent Machine Prediction of Shift and Scalar Information Of Nuclei）机器学习系统为从三维化学结构预测NMR参数提供了一条高效准确的途径。在这里，我们证明了在NMR参数的量子化学计算值上训练的机器学习预测基本上与量子化学计算（每个分子数小时/天）一样准确，但计算效率更高（每个分子数十毫秒）。在量子化学而不是实验数据上训练机器学习系统，避免了对大型，结构多样，无错误的实验数据库存在的需求，并使IMPRESSION适用于解决分子构象和异构性等三维问题
QE-CONVERSE: An open-source package for the Quantum ESPRESSO distribution to compute non-perturbatively orbital magnetization from first principles, including NMR chemical shifts and EPR parameters
Decoding the Competing Effects of Dynamic Solvation Structures on Nuclear Magnetic Resonance Chemical Shifts of Battery Electrolytes via Machine Learning
Efficient prediction of Nucleus Independent Chemical Shifts for polycyclic aromatic hydrocarbons
核磁共振（NMR）是表征分子和受限液体结构的最有力的实验技术之一。然而，所研究的系统的复杂性通常需要补充计算研究来解释NMR结果。在这项工作中，我们专注于多环芳烃（PAHs），一类重要的有机分子，已被普遍用作更复杂系统，如多孔无序碳的光谱特性的简单类似物。用密度泛函理论计算了34种多环芳烃的~（13）C化学位移和核独立化学位移。结果显示了两个量的明确的分子尺寸依赖性，以及13 C NMR位移朝向石墨烯观察到的值的收敛。然后，我们提出了两个计算便宜的模型预测简单的多环芳烃的NICS。我们表明，虽然一个简单的偶极模型不能产生准确的值，微扰紧结合的方法可以成功地应用于预测NICS在这一系列的分子，包括一些非平面的含有5-和7-元环。该模型比DFT计算快一到两个数量级，非常有前途，可以进一步改进，以研究更复杂的复杂系统。
