Search

[Display omitted] • Sphalerite chemistry combined with ML methods were used to classify deposit types. • KNN, NN, and RF algorithms are more efficient than other ML methods in the classification tasks. • Ge, Sn, Co, Mn, Ga, and In in sphalerite are the most important discriminant elements. • Binary discrimination diagrams based on PCA and PLS-DA are provided. Sphalerite can form in different geological environments and is the main ore mineral of most Pb-Zn deposits. Trace elements in sphalerite combined with machine learning (ML) methods have been used for deposit type discrimination. However, the performance of different multivariate and ML methods is not systematically compared. Here more than four thousand laser ablation inductively coupled plasma mass spectrometry data from more than one hundred deposits were compiled and investigated by different multivariate and ML methods. Unsupervised multivariate and ML methods including principal component analysis (PCA) and t -distributed stochastic neighbor embedding (t -SNE), and supervised multivariate and ML methods including partial least squares-discriminant analysis (PLS-DA), logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), random forest (RF), naïve Bayes (NB), and neural network (NN) are used to classify deposit types. The models are constructed for five deposit types, Mississippi Valley-type (MVT), Volcanogenic Massive Sulfide (VMS), sedimentary exhalative (SEDEX), Epithermal, and Skarn deposits, based on twelve elements in sphalerite, Fe, Pb, Mn, Co, Cu, Ga, Ge, Ag, Cd, In, Sn, and Sb. The PCA and PLS-DA methods show similar clustering results, where Epithermal, MVT, SEDEX, and Skarn deposits can be separated from other deposit types. The t -SNE method is only efficient in discriminating MVT, SEDEX, and Epithermal deposits. The KNN, RF, and NN methods show better performance than LR, SVM, and NB in terms of average accuracy and precision. The PCA, t -SNE, and PLS-DA methods have advantages in data visualization, whereas KNN, NN, and RF methods are more suitable for classification tasks. Feature importance analyses of the PLS-DA and RF methods show that the most important discriminant elements in the classification are Ge, Mn, In, Sn, Ga, and Sb. The models based on PCA, PLS-DA, KNN, NN, and RF are used to predict sphalerite samples with uncertain origins. All the models give similar classification results for deposit types, which are consistent with the ore-forming geological setting. The multivariate and ML models, including discrimination diagrams of PCA and PLS-DA, can be used as the first screening for the type of Pb-Zn mineralization in mineral exploration. [ABSTRACT FROM AUTHOR]

[Display omitted] • Ge is mainly coupled with Cu in sphalerite, locally associated with Pb, Ag, and Mn. • The substitution mechanism of Ge will vary with textures and color of sphalerite. • Crystal structure or planes, texture, and temperature affect Ge, Ga, In contents. • Ge, Ga, and In behave differently during sphalerite precipitation. The low-medium temperature Zn-Pb deposits in the Sichuan-Yunnan-Guizhou (SYG) metallogenic region contain not only Pb and Zn but also abundant critical metals such as Ge, Ga, and In. The majority of previous studies focus on the genesis of Pb and Zn metals, and the research on Ge, Ga and In in the SYG region has become a topic in recent years due to economic importance of these metals. In this review, the distribution, occurrence, and enrichment mechanism of Ge, Ga, and In in Zn-Pb deposits in the SYG region is summarized. Sphalerite is the main host mineral of Ge, Ga, and In, with contents of up to ∼1300 ppm, ∼600 ppm, and ∼1191 ppm, respectively. Pyrite from the Fule Zn-Pb deposit is also rich in Ge (up to 340 ppm), which may be due to involvement of magmatic components in the ore-forming fluids. Germanium, Ga, and In mainly appear in the form of isomorphism in sphalerite. Independent minerals of Ge such as ruizhongite (Ag 2 □)Pb 3 Ge 2 S 8), are only found in the Wusihe Zn-Pb deposit. Copper is the main coupling ions for substitution of Ge, Ga, and In in sphalerite. However, the positive correlation of Ge with Pb, Mn and Ag in the sphalerite of Huodehong, Shaojiwan, Shanshulin, and Qingshan Zn-Pb deposits may indicate other means of substitution or existence of nanometer Ge minerals with similar composition to the ruizhongite. The substitution mechanisms of Ge and Ga vary with layers in the zoned sphalerite from the Nayongzhi Zn-Pb deposit, possibly indicating that physical or chemical variations in fluids will affect the substitution ways of Ge and Ga in sphalerite. The growth direction and crystal structure of ZnS also exert control over the contents of Ge, Ga, and In. The enrichment degree of Ge, Ga, and In changes between (1 1 0) and (1 1 1) crystal planes, and the wurtzite structure is beneficial to the infiltration of large ions (Ge, Ga, and In). Compared to sphalerite with euhedral texture, colloform sphalerite is conducive to the enrichment of Ge. For zoned sphalerite such as the rhythmic banding and the conventional zone, the former lacks zoning of Ge, Ga and In but the latter shows elemental zonation and Ge is enriched in the black domains. The correlation between the contents of Ge, Ga, and possible In in sphalerite and Pb or Zn isotopes of sulfides indicates the significant contribution of basement rocks for the enrichment of these metals. During the mineralization process, Ge tends to be enriched in dark or early sphalerite, including the Daliangzi, Tianbaoshan, Huize, Nayongzhi, Fule, Fuli, Wusihe, and Maoping deposits, which may be due to the variations in temperature or fluid evolution. The opposite variation trend of Ge and Ga with sphalerite color or stage in the Daliangzi, Nayongzhi, Maoping, Shaojiwan, and Wusihe Zn-Pb deposits indicates that Ge and Ga may behave differently during precipitation of sphalerite. [ABSTRACT FROM AUTHOR]