Stalagmites offer nearly continuous records of past climate in continental settings at high temporal resolution. The climatic records preserved in stalagmites are commonly investigated by examining compositional characteristics such as mineralogy, organic content, and lamination patterns. These proxies provide valuable insights into the environmental conditions during stalagmite formation. However, the methods used to obtain information about these proxies are relatively destructive. This study uses hyperspectral imaging, a non-contact technique, to identify mineral composition, organic matter content, and laminations in stalagmites. It is the first wide spectrum imaging analysis in speleothem research, using both visible–near infrared and shortwave infrared wavelengths. Results obtained from hyperspectral imaging were compared by point spectral analysis using an ASD spectroradiometer and a grayscale profile along the growth axis of a stalagmite. Petrographic observation of thin sections and X-ray diffraction (XRD) analyses on selected stalagmite layers were performed to cross-validate the hyperspectral data. A travertine sample was also used to replicate the method on calcite. To automate mineral identification, a machine learning algorithm was developed to map spatial distribution and quantify relative proportions of minerals across the sample. Our findings are in good agreement with traditionally used methods for mineral identification, i.e. XRD and petrography, aiding in the interpretation of paleoclimate proxies, and offer a spatial guide for U–Th dating analyses. It also provides insight for future investigations of stalagmites using hyperspectral data and classification through machine learning algorithms.