Abstract In this paper, the capabilities of demotic unsupervised learning approaches were investigated to improve the procedure of geochemical anomaly identification. The separation of anomalous concentrations from the background is a crucial task in the mathematical analysis of geochemical data. The conventional methods rely on the statistical thresholds routinely; however, determining such boundary values fundamentally entails a normally distributed data and the involvement of expert knowledge. The unsupervised machine learning provides state-of-the-art facilities based on the information theory that leveraged to classify the geochemical data into the anomaly and background concentrations with specific characteristics. To examine the integrity of performance of geochemical data processing tools, the prevalent unsupervised learning methods of k -means, k -medoids, k -medians, expectation-maximization (EM) clustering, density-based spatial clustering of applications with noise (DBSCAN), and self-organizing maps (SOM), as well as traditional threshold-based techniques of the mean plus two standard deviations ( $$\bar {x} + 2S$$ ) and the concentration-number (C-N) fractal model were subjected to the separation of Cu anomalies from the background within 300 rock samples collected from Shadan porphyry copper deposit, northeast Iran. The efficiency of methods was quantitatively measured using criteria comprising student’s t -test, signal to noise ratio, and the pooled coefficient of variation. The appraisal criteria have confirmed that most of the unsupervised techniques manage to isolate the geochemical anomalies from the background with a more significant contrast compared to the conventional methods of $$\bar {x} + 2S$$ and C-N fractal model. The EM clustering has revealed the best performance among them so that it allocates the anomalies with the maximum resolution and distinguishes the weak anomalies from the high background. The anomaly Cu map obtained by the EM method has represented a significant spatial pattern that is properly consistent with the geological and mineralization evidences within the study area. The utilization of unsupervised learning methods substantially enjoys some advantages such as anomaly intensification, automaticity, being fast and non-parametric, and the capability to expand to the multivariate analysis.

中文翻译：

---

异常与背景分布的地球化学数据处理方法对比分析

摘要 在本文中，研究了人口无监督学习方法的能力，以改进地球化学异常识别的过程。从背景中分离异常浓度是地球化学数据数学分析中的一项关键任务。传统方法通常依赖于统计阈值；然而，确定这样的边界值从根本上需要正态分布的数据和专家知识的参与。无监督机器学习提供了基于信息论的最先进设施，利用该信息理论将地球化学数据分类为具有特定特征的异常和背景浓度。为了检查地球化学数据处理工具的性能完整性，流行的无监督学习方法，包括 k-means、k-medoids、k-median、期望最大化 (EM) 聚类、基于密度的噪声应用空间聚类 (DBSCAN) 和自组织图 (SOM)，以及作为传统的基于阈值的平均值加两个标准差 ($$\bar {x} + 2S$$) 和浓度-数 (CN) 分形模型的技术，将 300 块岩石内的 Cu 异常与背景分离从伊朗东北部沙丹斑岩铜矿床采集的样品。使用包括学生 t 检验、信噪比和合并变异系数的标准来定量测量方法的效率。评估标准已经证实，与$$\bar {x} + 2S$$和CN分形模型的常规方法相比，大多数无监督技术能够以更显着的对比度将地球化学异常与背景隔离。EM聚类揭示了它们之间的最佳性能，因此它以最大分辨率分配异常并将弱异常与高背景区分开来。EM方法获得的异常Cu图代表了一个显着的空间格局，与研究区内的地质和矿化证据完全一致。无监督学习方法的利用在很大程度上享有一些优势，例如异常强化、自动化、快速和非参数化以及扩展到多变量分析的能力。