From remote sensing and machine learning to the history of the Silk Road: large scale material identification on wall paintings

A groundbreaking interdisciplinary approach, combining remote sensing, machine learning, and spectroscopic techniques, has successfully identified hidden writings and mapped material variations on large-scale wall paintings within the UNESCO World Heritage Site of Mogao Caves. This method allowed for non-invasive analysis of materials at inaccessible heights by clustering reflectance spectra with accessible regions, significantly advancing our understanding of ancient artworks. The study also provided new insights into the dating of Cave 465, narrowing its construction period to the late twelfth to thirteenth century based on palaeographic and archaeological evidence. This research exemplifies how cutting-edge technology can shed light on the history and cultural significance of the Silk Road.

Kogou, S., Shahtahmassebi, G., Lucian, A., Liang, H., Shui, B., Zhang, W., Su, B., & van Schaik, S. (2020). From remote sensing and machine learning to the history of the Silk Road: large scale material identification on wall paintings. Scientific Reports, 10(1). https://doi.org/10.1038/s41598-020-76457-9