It is a great pleasure for me to introduce this special issue of Magnetic Resonance in Chemistry illustrating recent developments in the field of quantum chemical computation and machine learning in NMR. Since its inception, the progress of NMR spectroscopy has been linked with the advances made in computer sciences. Not counting the most obvious applications related with acquisition and processing of NMR spectra, a wide variety of useful tasks such as automation, data analysis, and simulations have only become possible thanks to the impressive processing capacity of modern computers. Computational routines have been particularly important for the prediction of chemical shifts and coupling constants. From early incremental methods to modern DFT or ab initio approaches, the possibility to translate 2D and 3D information into simulated NMR data has become a leading strategy in structural and stereochemical elucidation. Such is the progress in computational NMR that those tools are employed routinely in high impact literature as part of the elucidation stage of complex molecular architectures. The use of artificial intelligence represents another example of how computers are revolutionizing NMR in a wide variety of topics, ranging from analytical, imaging, signal processing, to automatic structure verification and NMR prediction. In fact, the ability of machine learning strategies to emulate NMR properties at almost the level of DFT accuracy but at much lower computational cost seems to have opened a Pandora's box within the field. It is expected that truly exciting, innovative and breakthrough research will be published in years to come. This special issue presents recent work made in these vibrant fields by leading researchers who have made significant contribution in the recent past. We are glad to offer 13 contributions including original research articles, reviews and mini-reviews, highlighting the power of quantum chemistry and machine learning in the field of NMR. I hope the readers enjoy this special issue. I would like to thank the Co-Editors-in-chief, Drs. Roberto R. Gil and Gary Martin for their confidence, Dr. Craig Butts for his kind invitation to guest edit this special issue, and all of the Editorial Staff especially Paul Trevorrow, for their constant assistance. Finally, I would like to express my gratitude to all the authors who trusted me to Guest Edit this special issue to publish their valuable contributions.

中文翻译：

---

核磁共振中的量子化学计算和机器学习

我很高兴介绍这一期特刊《化学中的磁共振》，说明量子化学计算和核磁共振机器学习领域的最新发展。自诞生以来，核磁共振波谱的进步与计算机科学的进步息息相关。不包括与 NMR 谱的采集和处理相关的最明显的应用，自动化、数据分析和模拟等各种有用的任务只有由于现代计算机令人印象深刻的处理能力才成为可能。计算程序对于预测化学位移和耦合常数特别重要。从早期的增量方法到现代 DFT 或 ab initio 方法，将 2D 和 3D 信息转换为模拟 NMR 数据的可能性已成为结构和立体化学阐明的主要策略。这就是计算 NMR 的进步，以至于这些工具在高影响力文献中被常规使用，作为复杂分子结构的阐明阶段的一部分。人工智能的使用代表了计算机如何在各种主题中彻底改变核磁共振的另一个例子，从分析、成像、信号处理到自动结构验证和核磁共振预测。事实上，机器学习策略模拟 NMR 特性的能力几乎可以达到 DFT 精度水平，但计算成本要低得多，这似乎在该领域打开了潘多拉魔盒。预计真正令人兴奋的是，创新和突破性研究将在未来几年发表。本期特刊介绍了近期做出重大贡献的领先研究人员在这些充满活力的领域所做的最新工作。我们很高兴提供 13 篇贡献，包括原始研究文章、评论和迷你评论，突出了 NMR 领域中量子化学和机器学习的力量。我希望读者喜欢这个特刊。我要感谢共同主编，博士。感谢 Roberto R. Gil 和 Gary Martin，感谢 Craig Butts 博士对本期特刊的客座编辑，感谢所有编辑人员，尤其是 Paul Trevorrow，感谢他们不断的帮助。最后，