Three-dimensional mineral prospectivity mapping based on natural language processing and random forests: A case study of the Xiyu diamond deposit, China

• DOI: 10.1016/j.oregeorev.2024.106082
• Publication Date: 2024-05-15T15:29:15Z
• Authors: Guanyun Zhou; Jianping Chen; Wentong An; Chang Liu; Wei Li
• Keywords: Prospectivity mapping; Ore genesis

The advent of the big data era has gradually brought about a new demand for integration geological text in three-dimensional (3D) mineral prospectivity mapping (3DMPM). Here, we report novel workflow suitable application natural language processing 3DMPM. Our study area is Xiyu kimberlite-type diamond deposit Shandong, China, which significant prospecting potential its deep portion. In this study, exploration criteria served as bridge connecting and 3DMPM, were constructed employing mining technologies. A comparative evaluation conventional text-mining-based was also conducted. Considering criteria, reconstructed 3D spatial anomalies quantitatively analyzed ore-controlling factors. random forests classification model, created using obtained through mining, applied to predictions deposit, with superior results being obtained. prediction confirmed applicability demonstrated capacity effective dual coupling knowledge.