Two-dimensional nuclear magnetic resonance (NMR) is crucial for molecule structure determination. Nitrogen-vacancy centers in diamond serve as quantum sensors for nanoscale NMR, but efficient data acquisition and processing are needed. This paper presents a method combining deep learning and sparse matrix completion to accelerate 2D nanoscale NMR spectroscopy. An artificial intelligence protocol enhances the signal-to-noise ratio by 5.7 ± 1.3 dB with 10% sampling coverage on a single nuclear spin cluster, improving sensitivity by intrinsically suppressing noise.

Xi Kong, Leixin Zhou, Zhijie Li, Zhiping Yang, Bensheng Qiu, Xiaodong Wu, Fazhan Shi, Jiangfeng Du