and Au {111}.*

Point defect identification in two-dimensional materials enables an understanding of the local environment within a given system, where scanning probe microscopy that takes advantage of hyperspectral tunneling bias spectroscopy acquisition can both image and identify the atomic and electronic landscape. Transition metal dichalcogenides (TMDs) have gained substantial interest for a variety of unique properties in its monolayer form such as serving as a host substrate for photo- and spin- active functionalization and showing promise in tunable band gap control. Here dense spectroscopic volume is collected autonomously via Gaussian process regression, where convolutional neural networks are used in tandem for defect identification and subsequent feedback. Monolayer semiconductor is explored on sulfur vacancies within tungsten disulfide (WS₂), to provide hyperspectral insight into available sulfur-substitution sites within a TMD that is combined with spectral confirmation on the Au{111} herringbone reconstruction for both tip state verification and local fingerprinting. Additionally, we delve into similar investigations of absorbed metal impurities onto pristine W₂ with scanning tunneling microscopy and spectroscopy.