{"references": ["Xiang L. 2020. Neoproterozoic Tin-Niobium-Tantalum Metallogenesis in the western part of Jiangnan Orogen. PhD Thesis. Nanjing Univerisity. 198pp.", "Zhang, S. T., Zhang, R. Q., Lu, J. J., Ma, D. S., Ding, T., Gao, S. Y., Zhang, Q., 2019. Neoproterozoic tin mineralization in South China: geology and cassiterite U\u2013Pb age of the Baotan tin deposit in northern Guangxi, Mineralium Deposita 54.8, 1125-1142.", "Xiang, L., Wang, R. C., Romer, R. L., Che, X. D., Hu, H., Xie, L. and Tian, E. N., 2020. Neoproterozoic Nb-Ta-W-Sn bearing tourmaline leucogranite in the western part of Jiangnan Orogen: implications for episodic mineralization in South China. Lithos 360\u2013361, 105450.", "Fu, J., Liu, S., Zhang, B., Guo, R. and Wang, M., 2019. A Neoarchean K-rich granitoid belt in the northern North China Craton. Precambrian Research, 328, pp.193-216.", "Fu, J., Liu, S., Sun, G. and Gao, L., 2021. Two contrasting Neoarchean metavolcanic rock suites in eastern Hebei and their geodynamic implications for the northern North China Craton. Gondwana Research, 95, pp.45-71.", "Fu, J., Liu, S., Cawood, P.A., Wang, M., Hu, F., Sun, G., Gao, L. and Hu, Y., 2018. Neoarchean magmatic arc in the Western Liaoning Province, northern North China Craton: Geochemical and isotopic constraints from sanukitoids and associated granitoids. Lithos, 322, pp.296-311.", "Chen, W. T. , Sun, W. H. , Zhou, M. F. , & Wang, W. . (2017). Ca. 1050 ma intra-continental rift-related a-type felsic rocks in the southwestern yangtze block, south china.\u00a0Precambrian Research 309, 22\u201344", "Sommer, H., Wan, Y., Kr\u00f6ner, A., Xie, H., & Jacob, D.E., 2013. Shrimp zircon ages and petrology of lower crustal granulite xenoliths from the Letseng-La-Terae Kimberlite, Lesotho: Further evidence for a Namaqua-Natal connection. South African J. Geol. 116, 183\u2013198."]}

The dataset contains a total of 4282 original and processed zircon CL images collected from published papers and unpublished personal collections. Igneous, metamorphic, and hydrothermal zircon were classified and labeled manually. The dataset was used for a deep learning classification task which was submitted to "Geoscience Frontiers", and was entitled as "Zircon classification from cathodoluminescence images using deep learning".