Extraction and Interpretation of Gold Exploration Indexes in Jinya-Mingshan Area Based on Association Rule Algorithm and Statistical Analysis
Open Access
Abstract
Geochemical data serve as crucial references for prospecting, and the effective extraction of prospecting information from such data determines the success rate of exploration. In the era of big data, novel prospecting methods based on geochemical data offer new ideas for exploring various ore deposits. By employing advanced data analysis techniques like machine learning and artificial intelligence, it becomes possible to identify elusive patterns and trends that are challenging to detect using traditional approaches, thereby significantly enhancing the success rate of prospecting endeavors. In this study, we selected drainage sediment geochemical data (Au, Ba, Mo, Sb, V, W, Zn) in the Jinya-Mingshan area to explore potential Carlin-type gold deposits. Traditional geochemical processing methods along with an association rule algorithm were employed for conducting comprehensive data mining analysis. The results demonstrate that the element combinations within the study area can be categorized into strong positive associations and enrichments (Mo, Sb, Zn) associated with vulcanization, strong negative associations, and decarbonation-related migration elements (Ba), as well as strong positive associations and weakly enriched elements (W) and weak positive associations and weakly enriched elements (V) not significantly related to mineralization. In comparison to Mo and Sb, which are closely linked to Au as revealed by cluster analysis and factor analysis, the association rule algorithm also reveals a relatively close correlation between Ba, Zn, and Au. Based on the element correlations obtained through the association rule algorithm, a new prospecting index was constructed for the study area. This new index is more reasonable than traditional indices. In conclusion, the association rule algorithm possesses unique advantages in information mining of geochemical data and holds promising applications in geological exploration.Keywords
Funding Information
- China Geological Survey, Ministry of Natural Resources (DD20242629)
This publication has 20 references indexed in Scilit:
- Mineral prospectivity mapping using machine learning techniques for gold exploration in the Larder Lake area, Ontario, CanadaJournal of Geochemical Exploration, 2023
- Texture and geochemistry of pyrite from the Jinya, Nakuang and Gaolong gold deposits in the Youjiang Basin: implications for basin-scale gold mineralizationMineralium Deposita, 2022
- Introducing a new approach of geochemical anomaly intensity index (GAII) for increasing the probability of exploration of shear zone gold mineralizationGeochemistry, 2021
- Machine Learning-Based 3D Modeling of Mineral Prospectivity Mapping in the Anqing Orefield, Eastern ChinaNatural Resources Research, 2021
- Multi-stage tectonics and metallogeny associated with Phanerozoic evolution of the South China Block: A holistic perspective from the Youjiang BasinEarth-Science Reviews, 2020
- Data for factor analysis of hydro-geochemical characteristics of groundwater resources in IranshahrData in Brief, 2018
- Machine Learning of Mineralization-Related Geochemical Anomalies: A Review of Potential MethodsNatural Resources Research, 2017
- Gold mineralization in China: Metallogenic provinces, deposit types and tectonic frameworkGondwana Research, 2016
- Analysis and mapping of soil geochemical anomalies: Implications for bedrock mapping and gold exploration in Giyani area, South AfricaJournal of Geochemical Exploration, 2015
- Factor analysis in geochemical explorationJournal of Geochemical Exploration, 1979