Many of the sandstones at cultural heritage sites around the world are susceptible to chemical weathering, and long-term monitoring of the chemical weathering would be of great value for heritage conservation and would also provide reference data for environmental protection policies and projects. Reflectance spectroscopy is a potential tool for monitoring sandstone weathering due to its non-destructive characteristics. In this paper, we present the results of an investigation into the reflectance spectra of sandstones at the Yungang Grottoes, China, where the sandstones are variously fresh, calcite-dissolved, or argillitic-altered. We found several spectral absorptions, including those at 490, 675, 900, 1410, 1918, 2205, 2330, 2350, and 2380 nm. The absorptions at 490, 675, and 900 nm are related to hematite cement, while that at 2330 nm is associated with calcite cement. The absorptions at 1410, 2205, 2350, and 2380 nm are induced by the Al–OH vibration of kaolinite, and that at 1918 nm is related to crystal water. The calcite-dissolved sandstones have lower absorption intensities at 2330 nm than fresh sandstones, and the argillitic-altered sandstones have lower absorption intensities at 490, 675, and 900 nm than the fresh sandstones. In the 1st-derivative reflectance plots, the absorption peaks at ∼1400 nm shift towards shorter wavelengths with increasing kaolinite contents. The spectral features of the fresh, calcite-dissolved, and argillitic-altered sandstones are all different, and this means they can be distinguished spectroscopically, which demonstrates the usefulness of reflectance spectroscopy for the long-term monitoring of sandstone weathering in the Yungang Grottoes.

Standard traditional gem identification requires expert supervision, while sophisticated modern methods are time-consuming and expensive. In contrast, reflectance spectroscopy coupled with artificial intelligence is economical and convenient and does not require specialist supervision. This study established an artificial neural network model that consists of standard multilayered, feed-forward, and back-propagation neural networks, and obtained reflectance spectra of a transparent gem (almandine), an opaque gem (turquoise), several almandine imitations (agate, plastic, and glass), and several treated turquoise samples (dyed, impregnated, and Zachery treated) using an Analytical Spectral Devices spectrometer. The acquired spectra were used to train and test the artificial neural network model. The results show that the model can effectively discriminate between genuine and imitation gems of different classes. However, discrimination between natural and treated gems of same class is not as effective as discrimination of gems of different classes. The results suggest that an artificial neural network based on reflectance spectroscopy could serve as a useful tool for preliminary gem identification, and the advanced identification needs further training and investigation.