Next Article in Journal
Petrological Studies and Geochemical Modelling of Water–Rock Interactions in the Grønnedal-Íka Alkaline Complex Generating Ikaite Deposition in Ikka Fjord, SW Greenland
Previous Article in Journal
Geometallurgical Sampling and Testwork for Gold Mineralisation: General Considerations and a Case Study
Previous Article in Special Issue
Applying Mineral System Criteria to Develop a Predictive Modelling for Epithermal Gold Mineralization in Northern New Brunswick: Using Knowledge-Driven and Data-Driven Methods
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Machine Learning Classification of Fertile and Barren Adakites for Refining Mineral Prospectivity Mapping: Geochemical Insights from the Northern Appalachians, New Brunswick, Canada

by
Amirabbas Karbalaeiramezanali
1,*,
Fazilat Yousefi
2,
David R. Lentz
2 and
Kathleen G. Thorne
1
1
New Brunswick Department, Natural Resources and Energy Development, Fredericton, NB E3B 5H1, Canada
2
Department of Earth Sciences, University of New Brunswick, 2 Bailey Drive, Fredericton, NB E3B 5A3, Canada
*
Author to whom correspondence should be addressed.
Minerals 2025, 15(4), 372; https://doi.org/10.3390/min15040372
Submission received: 19 February 2025 / Revised: 24 March 2025 / Accepted: 26 March 2025 / Published: 2 April 2025

Abstract

:
This study applies machine learning (ML) techniques to classify fertile [for porphyry Cu and (or) Au systems] and barren adakites using geochemical data from New Brunswick, Canada. It emphasizes that not all intrusive units, including adakites, are inherently fertile and should not be directly used as the heat source evidence layer in mineral prospectivity mapping without prior analysis. Adakites play a crucial role in mineral exploration by helping distinguish between fertile and barren intrusive units, which significantly influence ore-forming processes. A dataset of 99 fertile and 66 barren adakites was analyzed using seven ML models: support vector machine (SVM), neural network, random forest (RF), decision tree, AdaBoost, gradient boosting, and logistic regression. These models were applied to classify 829 adakite samples from around the world into fertile and barren categories, with performance evaluated using area under the curve (AUC), classification accuracy, F1 score, precision, recall, and Matthews correlation coefficient (MCC). SVM achieved the highest performance (AUC = 0.91), followed by gradient boosting (0.90) and RF (0.89). For model validation, 160 globally recognized fertile adakites were selected from the dataset based on well-documented fertility characteristics. Among the tested models, SVM demonstrated the highest classification accuracy (93.75%), underscoring its effectiveness in distinguishing fertile from barren adakites for mineral prospectivity mapping. Statistical analysis and feature selection identified middle rare earth elements (REEs), including Gd and Dy, with Hf, as key indicators of fertility. A comprehensive analysis of 1596 scatter plots, generated from 57 geochemical variables, was conducted using linear discriminant analysis (LDA) to determine the most effective variable pairs for distinguishing fertile and barren adakites. The most informative scatter plots featured element vs. element combinations (e.g., Ga vs. Dy, Ga vs. Gd, and Pr vs. Gd), followed by element vs. major oxide (e.g., Fe2O3T vs. Gd and Al2O3 vs. Hf) and ratio vs. element (e.g., La/Sm vs. Gd, Rb/Sr vs. Hf) plots, whereas major oxide vs. major oxide, ratio vs. ratio, and major oxide vs. ratio plots had limited discriminatory power.

1. Introduction

The primary objective of mineral exploration is to differentiate prospective from non-prospective areas, ultimately facilitating the discovery of new sources of raw earth materials [1]. This is achieved by collecting diverse exploration datasets, translating them into spatial proxies using the mineral systems approach, and integrating these proxies through robust methodologies [1,2,3]. The outcome is a mineral prospectivity map that highlights potential areas in both greenfield (underexplored) and brownfield (previously explored) environments, a process referred to as mineral prospectivity mapping (MPM) [1,2,3]. The mineral systems approach focuses on the ore-forming processes described in deposit models, translating exploration layers into proxies [2]. The mineral systems approach encompasses key processes such as source, trigger, transport, trap, deposition, and preservation, providing a comprehensive, process-driven, and scale-independent framework for understanding deposit formation [2]. In this paper, we place a particular emphasis on the source as a critical component, highlighting its fundamental role in driving mineralizing systems. In the mineral systems approach, intrusive units are often regarded as key sources driving magmatism, hydrothermal fluid circulation, and the mobilization of metals necessary for mineral deposit formation. However, not all intrusive units are fertile; many are barren, with their fertility varying depending on various factors, such as magma source composition, the degree of crustal contamination, oxidation state, and magmatic differentiation processes [4]. While intrusive units are commonly incorporated as heat sources in MPM, it is essential to recognize that their fertility and mineralizing potential differ significantly. Assigning varying weights to these units, based on their fertility to form porphyry Cu, Cu-Au, and Au systems, could enhance the accuracy and reliability of mineral prospectivity models by better reflecting the mineralization potential of each unit.
Adakites are particularly significant due to the ability to distinguish between fertile and barren units, with implications for understanding mineral deposits and critical mineral exploration. Defined by geochemical characteristics, adakites are classified into high-silica adakites (HSA) and low-silica adakites (LSA), based on SiO2 content [5,6,7]. HSAs, with SiO2 > 67 wt.%, Al2O3 > 15 wt.%, Sr > 300 ppm, Y < 20 ppm, and specific elemental ratios like Sr/Y (>50) and La/Yb (>10), are indicative of formation through the partial melting of hydrothermally altered oceanic crust. Their genesis, particularly in late to post-collisional settings, contrasts with calc-alkaline andesite–dacite–rhyolite (ADR) series typically formed during subduction stages [8,9]. Numerous studies [10,11,12] highlight the association of oxidized I-type granitoids with Cu-Au mineralization, emphasizing the exploration relevance of adakites.
Recent advances in ML have introduced powerful tools for enhancing data analysis, pattern recognition, and predictive modeling in petrology and economic geology. By using computational algorithms to detect patterns and relationships in data, ML allows for more accurate predictions and classifications compared to traditional geological methods. ML techniques, such as supervised classification and regression models, have been effectively applied to analyze various types of data, including geochemical data [13]. For instance, Zou et al. [14] applied random forest (RF) and deep neural networks to assess magma fertility for porphyry Cu systems, showing that ML improves the accuracy of distinguishing fertile from barren rocks and identifying deeply buried deposits. Nathwani et al. [15] used four ML algorithms (logistic regression, neural networks, support vector machine (SVM), and RF) to classify rock metallogenic fertility, compare classifier performance, and identify key parameters for porphyry Cu exploration. Zhang et al. [16] utilized RF and a Monte Carlo-based ranking framework to identify elements crucial for ore formation and assess ore potential, while also explaining the scarcity of porphyry Cu deposits in the Paleo-Tethyan Ocean basin. Additionally, Zhang et al. [17] applied RF, SVM, and multilayer perception classifiers to classify ore deposit genetic types, distinguishing iron oxide–copper–gold (IOCG) and iron oxide–apatite deposits from other types.
In this paper, we focus on adakites as a key source in the mineral systems approach and aim to apply ML techniques to predict their fertility. We highlight that not all intrusive units, including adakites, are inherently fertile and should not be directly used as the heat source evidence layer in mineral prospectivity mapping without prior analysis. ML models, including SVM, neural network, RF, decision tree, AdaBoost, gradient boosting, and logistic regression were applied to classify fertile and barren adakites using geochemical data from New Brunswick, Canada. This study focused on evaluating the performance of these models to distinguish between fertile and barren adakites, leveraging a wide range of geochemical variables and ratios. This research also explored the significance of various geochemical features, such as elements, major oxides, and ratios, in determining adakite fertility.

2. Geology of Adakitic Intrusions in New Brunswick

New Brunswick, located within the Canadian Appalachians (Figure 1), features diverse tectonic zones including the Humber, Dunnage, Gander, and Avalon zones. These zones record complex geological histories shaped by multiple orogenic events, including the Taconic, Salinic, and Acadian orogenies. The Acadian Orogeny (~420–350 Ma) was particularly influential, leading to the emplacement of numerous Devonian plutonic and subvolcanic rocks during and after this mountain-building phase. The potential for mineralization in New Brunswick (e.g., [18,19,20]) associated with these igneous rocks depends on several factors, including the depth of emplacement, the chemical composition of the intrusions, and the nature of the host rock sequences [21]. Several adakitic intrusions in New Brunswick are associated with Cu-Au (±Mo) occurrences, including the Blue Mountain Granodiorite Suite (400.7 ± 0.4 Ma, U-Pb zircon; [22]), Nicholas Denys Granodiorite (381 ± 4 Ma, U-Pb zircon; [23]), Sugarloaf Porphyry, Meto’mqwijuig Mountain Felsite (415 ± 0.5 Ma, U-Pb zircon; [24]), North Dungarvan River Granite (382 ± 16 Ma, K-Ar muscovite; [25]), Magaguadavic Granite (403 ± 2 Ma, U-Pb zircon [26]), Tower Hill Granite (422 ± 15 Ma, Rb-Sr whole rock age [27]; 401 ± 4 Ma, Rb-Sr muscovite [24]), Watson Brook Granodiorite (382.1 ± 2.8 Ma, Rb-Sr biotite), Rivière-Verte Porphyry (368 ± 2 Ma, U-Pb zircon; [28]) (Figure 2a), Eagle Lake Granite (360 ± 5 Ma, U-Pb zircon; [29]), Evandale Granodiorite (391.2 ± 3.2 Ma, U-Pb zircon; [30]) (Figure 2b), North Pole Stream Suite (417 ± 1 Ma, U-Pb monazite; [31]), Beech Hill (343 ± 33 Ma, Rb-Sr whole rock age [27]), Pabineau Falls Granite (397 ± 2 Ma, U-Pb zircon [32]), and McKenzie Gulch Porphyry dykes (386.2 ± 3.1 and 386.4 ± 3.3 Ma, U-Pb zircon; [33]) (Figure 1).
These intrusions are similar to the Cu porphyry intrusions at Mines Gaspé [36], Québec, which host the largest copper–molybdenum deposit in Eastern North America. The Porphyry Mountain and Copper Mountain intrusions at Mines Gaspé were initially dated to 384.8 ± 2.8 Ma and 384.9 ± 2.5 Ma (Middle Devonian), respectively [37]. However, these ages were later refined using U-Pb zircon geochronology to 378.80 ± 0.37 Ma and 377.60 ± 0.45 Ma, respectively [38]; these ages [37,38], while differing, are similar to those of the adakitic intrusions in New Brunswick. These fertile adakitic intrusions, though they do not host any major deposits at the time of writing, contain occurrences exhibiting characteristics of porphyry Cu-Au-Mo mineralization, as reported in [39,40]. Two of the most significant examples are the Evandale porphyry Cu-Mo (Au) occurrence [30] and the Cu-Mo-Au porphyry system of the Eagle Lake Granite [12]. The Evandale Granodiorite is associated with porphyry-style Cu-Mo-Au mineralization, linked to porphyritic to aplitic dykes and a white granitoid phase, rather than the earlier coarse-grained pink granodiorite. Ore minerals include chalcopyrite, molybdenite, gold, silver, and locally tungsten, with minor sphalerite and galena [30]. Potassic alteration is evident in the pink granodiorite along northwesterly trending fractures, veins, and dykes, with these dykes sourced from deeper intrusive stocks, suggesting a genetic connection to the Late Silurian–Devonian Saint George Plutonic Suite [30,41]. The Eagle Lake Granite is recognized as a fertile Cu-Mo-Au porphyry system, exhibiting potassic alteration, locally overprinted by phyllic and propylitic assemblages [12]. Mineralization is characterized by quartz–sulfide stockworks and replacement zones containing disseminated pyrite, molybdenite, and chalcopyrite [12]. Extensive pyrite and quartz–pyrite–chalcopyrite veins are typical of the potassic stage, while gold-bearing quartz-sulfide veins dominate the phyllic stage [12].
One of the recent hypotheses proposed for the adakite rocks in New Brunswick, alongside other theories, is the late tectonic slab break-off hypothesis for adakite generation [9]. An important aspect is that the emplacement of this substantial volume of fertile intermediate-to-acidic magmas into the crust, occurring during a slab break-off event, is associated with transpressional-to-transtensional extension during the post-collisional orogenic phase. This process enables fertile magmas to ascend (rapidly) through the subduction-altered lithosphere, eventually rising into hypabyssal parts of the upper crust [9]. The studied intrusions, along with previously published and newly obtained geochronological data for oxidized porphyry-related intrusive rocks in southern to northern New Brunswick and their associated mineral occurrences, are summarized in Table 1 [42].

3. Methodology

The methodology of this study involved leveraging geochemical analyses of adakites to train and apply ML models for fertility prediction. Figure 3 shows a schematic diagram illustrating the methodology utilized in this study. A dataset consisting of 99 geochemical analyses of fertile adakites and 66 analyses of barren adakites from New Brunswick was used [22,32,36,42,49]. This dataset was used to train seven ML models: decision tree, SVM, neural network, AdaBoost, gradient boosting, logistic regression, and random forest. The ML analyses in this study were conducted using Scikit-Learn (version 1.3.0) and Orange (version 3.36). Scikit-Learn, a Python-based machine learning library (Python version 3.13), was used for hyperparameter tuning and model robustness enhancement, while Orange, a visual programming platform for machine learning and data mining, facilitated data analysis and model evaluation in a user-friendly environment. Prior to model implementation, data preprocessing was performed to ensure consistency and mitigate potential biases. Geochemical datasets were examined for outliers using statistical summaries and visual inspection methods, such as boxplots and histograms. As no significant missing values were identified, imputation was not required. To address variations in magnitude among geochemical parameters and improve model stability, all continuous variables were log-transformed (e.g., [50]) and standardized using z-score normalization (e.g., [51]) for SVM, neural networks, and logistic regression. This transformation was particularly beneficial for the SVM, neural network, and logistic regression models, which are sensitive to feature scaling, as it improved numerical stability and ensured optimal convergence during training [52,53,54]. However, for tree-based models, such as RF, decision tree, AdaBoost, and gradient boosting, feature scaling was unnecessary and therefore not applied [55]. All the models were rigorously evaluated and optimized to ensure their robustness and accuracy. Subsequently, the optimized models were applied to a global dataset of 829 geochemical analyses of adakites [56] to predict their fertility, enabling insights into their mineralization potential on a worldwide scale.

3.1. Dataset and Geochemical Characteristics

This study analyzed 99 geochemical datasets of fertile adakites and 66 geochemical datasets of barren adakites from New Brunswick to train ML models. The analysis results were sourced from [22,32,36,42,49], with the fertility or barren nature of the adakites discussed [42,46]. To distinguish fertile adakites from barren ones, specific criteria are considered in this paper. As discussed in Section 2, fertile adakitic intrusions are associated with Cu-Au (±Mo) mineralization, as indicated by the mineral occurrence database of the Government of New Brunswick [39]. These mineral occurrences are primarily documented through visible mineralization and/or polished sections in outcrops. Additionally, the identification of fertile intrusions for porphyry Cu and (or) Au systems can be achieved using porphyry indicator minerals (PIMs), such as zircon, plagioclase, titanite, apatite, magnetite, and tourmaline [57]. Yousefi [42] and Yousefi et al. [58] employed zircon trace element ratios and calculated logƒO2 values to differentiate fertile from barren adakites. Specifically, Eu/Eu* ratios greater than 0.3, (Ce/Nd)/Y ratios ranging between 0.001 and 1.0, and log ƒO2 values exceeding FMQ+2 (where FMQ represents the fayalite–magnetite–quartz oxygen fugacity buffer) were used as distinguishing criteria. Fertile porphyry systems are typically associated with high ƒO2 conditions, while ƒO2 values lower than FMQ+2 suggest an infertile system [59].
Geochemical data from 99 adakitic rock samples in New Brunswick, including archived and newly acquired data, are presented in the Supplementary Materials, Table S1, of [9]. On the SiO2 vs. Na2O + K2O diagram [60], the samples are classified as granite, granodiorite, quartz diorite, and diorite. Their calc-alkaline to shoshonitic affinity is confirmed by selected major element compositions. The molar Al2O3/(CaO + Na2O + K2O) (A/CNK) ratios range from 0.8 to 1.2, indicating compositions that span peraluminous to metaluminous, with elevated A/CNK values attributed to cryptic alteration or biotite influence. These rocks are oxidized I-type granitoids, predominantly magnesian but extending into the ferroan field [9,42]. Geochemical analyses confirm their adakitic characteristics, with most samples plotting in the high-silica adakite field and showing low MgO content. The primitive mantle-normalized trace-element spider diagram reveals enrichment in large-ion lithophile elements (LILE) and notable depletion in high-field strength elements (HFSE). In our studied adakitic rocks, the enrichment of Cs, Rb, U, Th, and K, coupled with the depletion of Ti, Nb, P, Ba, and Sr, highlights their distinct arc-like geochemical signature [42]. Several hypotheses have been proposed for the genesis of adakite rocks, including the (1) melting of the lower crust or overlying rocks induced by rising basaltic magmas; (2) high-pressure crystal fractionation of basaltic magma; and (3) low-pressure crystal fractionation of water-enriched basaltic magma, along with magma mixing processes occurring in both arc and non-arc tectonic settings [61]. Additional theories on the formation of adakite magma include oceanic crustal melting, the high-pressure crystal fractionation of garnet and amphibole from hydrous basaltic magma, lower continental crustal melting triggered by basaltic magma underplating, the melting of eclogite or garnet amphibolite rocks, and the crystal fractionation of mafic magma. Another suggestion is the melting of lower continental crust in proximity to the mantle [6,62]. A review on oxidized I-type adakitic rocks selected from the GEOROC database was recently presented [8], but no information regarding the association of these rocks with mineralization was available. Along with all the theories on the genesis of adakite rocks, the slab-failure hypothesis has also been discussed in the review by Whalen and Hildebrand [11] and Archibald and Murphy [63]. The relationship between adakitic rocks, mineralization, and slab failure has been further explored, and many of the Devonian adakite rocks in New Brunswick are associated with Cu-Au-Mo porphyry mineralization [42]. To support the slab break-off/slab failure hypothesis for the origin of the adakite rocks in New Brunswick, it is important to examine geochemical indicators. The rocks from New Brunswick show Sr/Y ≥ 33 to 50, Nb/Y > 0.4, Ta/Yb > 0.3, La/Yb > 10, Sm/Yb > 2.5, Gd/Yb > 2.0, Nb + Y < 60 ppm, and Ta + Yb < 6 ppm. These values for Nb/Y, Ta/Yb, La/Yb, and Sm/Yb are notably higher than those typically found in arc magmas [42]. Slab rollback to failure—break-off is considered a significant consequence of the terminal subduction process, associated with post-collisional uplift and often transpression. The connection between these late adakitic rocks and earlier volcanic arcs in convergent margin setting is supported by their elevated Th/Yb ratios and lower Nb/Yb values. The formation of adakitic magmas is thought to involve the formation of a thicker lithospheric zone and a rising of a hotter mantle than in typical subduction zones, leading to adakitic melt generation from the slab and (or) suprasubduction zone mantle affected in similar ways. A key question is why adakitic rocks associated with melting slabs exhibit higher concentrations of Nb and Ta compared to conventional arc-type rocks. This high-T melting hypothesis proposal suggests that the instability of rutile or other titanium (Ti)-bearing phases, which host Nb and Ta, within the magmatic system causes the release of these elements. This release leads to higher concentrations of Nb and Ta in adakitic magmas. The instability of titanium-rich phases (such as rutile and titanomagnetite) is driven by increased heat in environments that produce Nb-Ta enriched adakite magmas [8]. In adakitic rocks, the enrichment of S, Cu, Au, and Cl is associated with the high oxidation state and water-rich nature of melts derived from subducted slabs, which enhances metal transport and ore-forming potential. The fertility of slabs and supra-subduction zones controls the metal endowment of these magmas, influencing their ability to generate porphyry Cu-Au-Mo mineralization [42]. According to the available analytical results on fertile and barren adakites in New Brunswick, the geochemical dataset included major oxides such as SiO2, Al2O3, Fe2O3, MgO, CaO, Na2O, K2O, TiO2, P2O5, and MnO, and trace elements such as Ba, Cs, Ga, Hf, Nb, Rb, Sr, Ta, Th, U, V, Zr, Y, La, Ce, Pr, Nd, Sm, Eu, Gd, Tb, Dy, Ho, Er, Yb, and Lu. Additionally, it incorporated geochemical ratios such as Sr/Y [64], La/Yb [64], K2O/Na2O [65], Th/Ta [66], Zr/Sm [67], Nb/Ta [68,69], Sm/Yb [67], La/Sm [70], Cs/Th [71], Rb/Th [67], Nb/Y [72], Rb/Y [72,73], Th/La [74], Zr/Nb [75], Rb/Sr [7], Eu/Eu* [76], Eu/Eu*/Y [77], Ce/Nd [78], Ce/Ce* [79], Y/MgO [80], and Sr/MnO [81]. The geochemical ratios included in this study were carefully chosen to capture key petrogenetic processes and geochemical signatures indicative of adakite fertility. Ratios such as Sr/Y (>33 to 50) and La/Yb (>10) highlight the involvement of garnet and amphibole in magma genesis, reflecting high-pressure melting conditions typical of fertile adakitic magmas [63]. Indicators like K2O/Na2O [64], Th/Ta [59], and Zr/Sm [60] provide insights into magma source characteristics, crustal contamination, and fractional crystallization. Additionally, Nb/Ta [61,62], Sm/Yb [60], and La/Sm [63] reveal the degree of partial melting and the depth of magma generation. Ratios such as Cs/Th [64], Rb/Th [60], Nb/Y [65], and Rb/Y [65,66] are essential for tracing subduction-related enrichment and tectonic settings, while Th/La [67] and Zr/Nb [68] evaluate subduction processes and crustal assimilation. The Rb/Sr [7] ratio helps indicate the degree of fractional crystallization or crustal assimilation in magmatic systems. Anomalies in Eu/Eu* [76], Ce/Ce* [79], and Sr/MnO [80] detect plagioclase fractionation and redox conditions, while Ce/Nd [78] highlights redox sensitivity, with Ce affected by oxidation while Nd remains stable. Y/MgO [80] and Sr/MnO [82] highlight mineralogical controls during crystallization. Together, these ratios provide a comprehensive framework for distinguishing fertile adakites from barren ones, aiding ML models in predicting mineralization potential.

3.2. ML Models

In this study, we employed several ML algorithms, including support vector machine (SVM; [83]), neural network [84], random forest (RF; [85]), decision tree [86], AdaBoost [87], gradient boosting [88], and logistic regression [89], and compared their results in predicting the fertility of adakites. These methods were chosen for their widespread application and strong citation records in machine learning, particularly in economic geology, petrology, and geochemistry (e.g., [14,15,16,17,90]). Their effectiveness in handling complex classification tasks and high-dimensional datasets, along with their alignment with established practices in the field, made them ideal candidates for this study.
The SVM is known for its robustness in identifying the optimal hyperplane that separates classes, particularly in high-dimensional spaces. It has been extensively applied in geosciences, including petrology, to classify and analyze geochemical data (e.g., [91,92]). The neural network was selected for its ability to model non-linear relationships and detect intricate patterns, making it highly suitable for geological systems (e.g., [93,94]). Ensemble methods like RF, AdaBoost, and gradient boosting are particularly popular due to their robustness and versatility. Random forest, for instance, is highly cited in petrological studies for its capacity to manage noisy data and assess variable importance [95,96,97]. Boosting methods such as AdaBoost and gradient boosting are widely used for their iterative refinement of weak learners, improving classification performance with each step (e.g., [97,98,99,100]). Logistic regression (e.g., [101]) and decision tree (e.g., [102]) were included as foundational models to provide interpretability and serve as benchmarks for comparison. Both methods are classic approaches that are simple to implement and interpret, making them common choices in petrological and geochemical studies.

4. Results

4.1. Key Geochemical Variables for Adakite Fertility

The importance of input geochemical variables in predicting the fertility of adakites is evaluated using various scoring metrics, each designed to assess the relevance of a feature from different statistical and informational perspectives. The statistical analysis and scoring metrics, including ANOVA, information gain, gain ratio, Gini index, chi-square, and ReliefF, aim to distinguish fertile from barren adakites based on geochemical variables such as major oxides, elements, and ratios, as discussed in Section 3.1. Table 2 presents the results of the statistical analysis conducted to differentiate fertile and barren adakites.
Multiple metrics were used to assess the relationship between geochemical variables and adakite fertility. The scores highlight the relative importance of each variable. One key metric is the ANOVA (analysis of variance) test [103], which evaluates the differences in the mean values of the target variable across groups defined by a geochemical variable. This method is particularly useful for assessing the significance of numerous geochemical variables in relation to the target variable (fertile adakites). A higher value indicates a stronger relationship between the geochemical variables and the fertility of adakites.
Another key metric is information gain [104], which quantifies the reduction in entropy (uncertainty) when a geochemical variable is used to partition the data. It reflects how much information a geochemical variable provides about the fertility of adakites. A higher information gain indicates that the geochemical variable contributes more valuable information for predicting fertility.
Another important metric is the gain ratio [105], which normalizes information gain to address its inherent bias toward geochemical variables with many distinct values. By dividing information gain by the intrinsic information (entropy) of the geochemical variable itself, the gain ratio provides a more balanced evaluation, ensuring that geochemical variables with many values are not unfairly favored.
The Gini index [106] measures the impurity or diversity of the dataset following a split. Features that lead to greater reduction in impurity are considered more relevant, with lower Gini values indicating more effective features for classification tasks.
The chi-square (χ2) test [107] evaluates the independence between a geochemical variable and the fertility of adakites. It is particularly effective for categorical geochemical variables and the categorical target variable (fertility of adakites), with larger chi-square values indicating a stronger association between the geochemical variable and fertility.
Finally, the ReliefF algorithm [108] evaluates feature relevance by iteratively sampling instances and examining the differences between the nearest neighbors of the same and different classes. This method is capable of identifying the most informative geochemical variables in distinguishing between fertile and barren adakites, particularly in the presence of noisy or redundant features.
The score for each geochemical variable is calculated by first normalizing the values of each feature selection metric (ANOVA, information gain, gain ratio, Gini, χ2, ReliefF) to a common scale between 0 and 1. This normalization ensures comparability across different metrics, eliminating discrepancies due to differing units or scales. Equal weights are then assigned to each normalized metric, treating all metrics as equally important in the ranking process. The final score for each variable is determined by calculating the simple average of the normalized values across all criteria. This approach produces a composite score that reflects the combined performance of each variable across multiple feature selection metrics. According to Table 2, Gd ranks first with a score of 0.982, indicating its importance in recognizing fertile adakites. Following Gd, Dy ranks second with a score of 0.803, and Hf ranks third with a score of 0.797, both contributing significantly to the classification process. The variable Eu/Eu*, as the highest-ranked ratio, ranks 14th with a score of 0.406, and the major oxide Al2O3, as the highest-ranked major oxide, ranks 23rd with a score of 0.343. These results emphasize the varying degrees of influence that different elements and major oxides have on identifying fertile adakites, with Gd playing the most prominent role. Additionally, we classified geochemical variables by ranking them based on standard deviation classification. This approach categorized the variables into four distinct classes. Figure 4 presents the plot of scores versus ranks from Table 2, using standard deviation classification. Class 1 ( X ¯ + 2σ to maximum score) comprises variables with the highest-ranking scores (≥0.775), including Gd, Dy, and Hf (red dots in Figure 4). These variables exhibit the strongest correlation with fertile adakites. Class 2 ( X ¯ + 1σ to X ¯ + 2σ) includes elements with scores ranging from 0.556 to 0.775, such as La, Ho, Ce, Th, Ga, Pr, and Zr (orange dots in Figure 4). While these variables contribute significantly to fertility classification, they have lower discriminative power than those in Class 1. Class 3 ( X ¯ to X ¯ + 1σ) consists of variables with scores between 0.338 and 0.556, including Nd, U, Sm, Eu/Eu*, Rb, Eu/Eu*/Y, Ta, Rb/Sr, Sr, Ce/Nd, Rb/Th, Nb, and Al2O3 (green dots in Figure 4). Finally, Class 4 (minimum score to X ¯ ) encompasses variables with scores below 0.338, such as Cs, K2O/Na2O, Th/La, La/Sm, CaO, K2O, MnO, Sr/Y, SiO2, Eu, Y/MgO, Fe2O3T, Y, MgO, Er, Yb, La/Yb, Lu, Nb/Y, Th/Ta, V, Nb/Ta, Ba, Zr/Nb, Na2O, P2O5, Ce/Ce*, Sm/Yb, TiO2, Cs/Th, Rb/Y, Zr/Sm, Ce/(Nd×Y), and Sr/MnO (blue dots in Figure 4). Although these variables may have geological significance, their predictive capability for fertility assessments is limited.

4.2. Scatter Plot Analysis for Classifying Fertile and Barren Adakites

A comprehensive analysis of 1596 scatter plots, derived from 57 geochemical variables, was conducted to identify the most effective plots for distinguishing fertile and barren adakites. The evaluation was performed using the linear discriminant analysis (LDA) algorithm [109], which maximizes class separability by finding linear projections with optimal discriminatory power. The number of comparisons was calculated using the formula n × ( n 1 ) 2 , where n represents the 57 geochemical variables listed in Table 2. Each scatter plot represented a pair of geochemical variables plotted against each other to evaluate their ability to separate fertile and barren classes. The LDA algorithm assessed the discriminatory performance of each combination by maximizing the inter-class variance while minimizing the intra-class variance [109]. LDA is a supervised ML algorithm that aims to find a linear combination of variables that best separates two or more classes. Its primary objective is to maximize the distance between the means of different classes while minimizing the variability within each class. LDA works by computing two key measures: within-class variance, which captures the spread of data points within each class, and between-class variance, which quantifies the distance between the means of different classes. The algorithm then selects the scatter plot that optimizes the ratio of between-class variance to within-class variance, ensuring the classes are as distinct as possible in the resulting feature space. In the context of this study, LDA was applied to identify which pairs of geochemical variables could best separate fertile and barren adakites. By analyzing the performance of different variable combinations, the LDA highlighted the most informative scatter plots. The most informative scatter plots for classifying fertile and barren adakites were those that displayed elements vs. elements. Among the highest-ranking plots, Ga vs. Dy (Figure 5a), Ga vs. Gd (Figure 5b), and Pr vs. Gd (Figure 5c) were the most effective in distinguishing the two groups. In terms of elements vs. major oxides, Fe2O3 vs. Gd (Figure 5d), Al2O3 vs. Hf (Figure 5e), and K2O vs. Hf (Figure 5f) proved to be informative, while ratios vs. elements such as La/Sm vs. Gd (Figure 5g), Rb/Sr vs. Hf (Figure 5h), and La/Sm vs. Dy (Figure 5i) further enhanced classification performance. Scatter plots involving major oxides vs. major oxides, ratios vs. ratios, and major oxides vs. ratios performed poorly, suggesting that these combinations had limited discriminatory power for distinguishing between fertile and barren adakites.

4.3. Modeling

4.3.1. Training Data

Most of the geochemical and petrological data in this study are sourced from [36], with additional data from [22,32]. Further data collected as part of [42] were analyzed at the Actlabs laboratory [110]. Whole-rock major and trace-element geochemical analyses were conducted using a combination of X-ray fluorescence spectrometry [111], lithium metaborate fusion inductively coupled plasma-mass spectrometry (ICP-MS; Thermo iCAP 6500 ICP (Thermo Fisher Scientific, Waltham, MA, USA)), and instrumental neutron activation analysis (INAA) using the 4 Lithoresearch + 4B-INAA packages at Actlabs (Ancaster, ON, Canada). The INAA technique is described [112]. To ensure data quality, analytical precision was assessed using certified reference materials SY4 (diorite gneiss powder), GSP2 (granodiorite powder), and RGM2 (rhyolite powder), with reference values obtained from the GeoReM database (Geological and Environmental Reference Materials). Reproducibility was evaluated by analyzing duplicate samples, with relative standard deviations (RSD) for major elements generally below 1–2% and trace elements below 2–5%. Detection limits for key trace elements ranged from 0.01 to 0.1 ppm. The measured values of reference materials were within ±3% of the certified values, indicating high analytical accuracy. Quality control also included blank samples and internal duplicates to monitor precision and potential contamination.

4.3.2. Applying ML Methods and Optimization

As mentioned in Section 3.2, decision tree, SVM, neural network, AdaBoost, gradient boosting, logistic regression, and RF were applied in this study. These models were rigorously evaluated and optimized to ensure their robustness and accuracy. The following section details the hyperparameter tuning process employed for each model.
This study uses 99 fertile and 66 barren adakite analyses, reflecting the availability of high-quality data that met the criteria for inclusion. While the dataset is imbalanced, we did not choose oversampling or class weighting [113], as these techniques can introduce challenges, including the risk of overfitting [114] or biasing the model towards the minority class [115]. Oversampling artificially inflates the minority class, while class weighting can cause the model to overemphasize the minority class, leading to skewed predictions [113,114,115]. Instead, the performance of the models was optimized as much as possible and evaluated using metrics such as the area under the curve (AUC) [116] and Matthews correlation coefficient (MCC) [117], which are less sensitive to class imbalance and provide a more balanced measure of model performance.
To optimize the decision tree model, key hyperparameters influencing its performance were systematically tuned. The maximum tree depth (max_depth) parameter was tested between 3 and 20, with 7 providing the best balance—achieving 95% training accuracy and 88% validation accuracy. Shallower depths resulted in underfitting, while deeper trees led to overfitting. The min_samples_split parameter, governing the minimum number of samples required to split an internal node, was varied between 2 and 10. The optimal value of 5 effectively mitigated overfitting while maintaining high accuracy. Similarly, the min_samples_leaf, specifying the minimum number of samples allowed in a leaf node, was tested with values between 1 and 10, with 3 ensuring stability and preventing the formation of excessively small leaf nodes. These optimizations enhanced the decision tree’s generalizability and classification robustness.
The SVM model was optimized by C, gamma, and kernel type. The C parameter, which controls the trade-off between margin width and classification accuracy, was tested over values from 0.1 to 100, with C = 10 providing the best trade-off and an AUC score of 0.89. Among kernel types (linear, RBF, and polynomial), RBF performed best, yielding an AUC score of 0.91. The gamma parameter, controlling the influence of individual data points, was tested between 0.001 and 1, with gamma = 0.01 proving optimal for the RBF kernel. The results confirmed that simpler kernels (like RBF) outperformed polynomial kernels for this dataset.
Neural network optimization involved selecting the architecture and key hyperparameters. Various hidden layer configurations were tested, ranging from a single layer with 10 neurons to multiple layers with (100, 50, and 25). The best-performing architecture featured two hidden layers (50, 25), achieving an 87% validation accuracy. Among activation functions, ReLU outperformed than in both training speed and predictive accuracy. The learning rate, tested between 0.001 and 0.1, was optimal at 0.01. Regularization strength (alpha) was tested from 0.0001 to 0.01, with alpha = 0.001 effectively reducing overfitting.
AdaBoost optimization focused on the number of estimators (n_estimators) and learning rate. Evaluating n_estimators between 50 and 500 showed that 200 estimators yielded optimal performance. The learning rate, tested from 0.01 to 1, was optimal at 0.1. The base estimator was a decision tree (max_depth = 3), effectively reducing overfitting while maintaining an AUC score of 0.88. These settings ensured a balance between interpretability and predictive strength.
Gradient boosting was optimized by tuning n_estimators, learning_rate, and tree depth. Evaluating n_estimators between 50 and 300 showed that 150 provided the best balance between accuracy and computational efficiency. The learning rate, tested from 0.01 to 0.2, was optimal at 0.05, yielding an AUC score of 0.90. The tree depth, tested from 3 to 10, showed that max_depth = 5 prevented overfitting while maintaining strong performance. Additional optimizations included min_samples_split = 4 and min_samples_leaf = 2, further enhancing model generalization.
The optimization of logistic regression involved testing different regularization techniques (L1, L2, and ElasticNet) and tuning the regularization strength (C). Among these, L2 regularization yielded the best results. The C parameter, tested between 0.01 and 100, was optimal at C = 1, achieving an AUC score of 0.88. Various solvers were tested, with liblinear proving most effective for handling regularized binary classification.
RF optimization focused on n_estimators, max_depth, and feature selection. Evaluating n_estimators between 50 and 300 showed that 200 trees maximized performance. The max_depth parameter, tested up to 20, was optimal at 10, achieving an 89% validation accuracy while minimizing overfitting. Feature selection was optimized using max_features, with the sqrt option yielding the highest accuracy. The additional tuning of min_samples_split = 4 and min_samples_leaf = 2 improved generalization, ensuring robust performance on the validation set.

4.3.3. Performance Results

The performance of the applied methods were evaluated using key metrics such as AUC, classification accuracy (CA), F1 score, precision, recall, and Matthews correlation coefficient (MCC). AUC measures a model’s ability to distinguish between classes, with higher values indicating better performance, especially in imbalanced datasets. Classification accuracy (CA) shows the proportion of correct predictions but may be misleading when one class dominates. The F1 Score balances precision and recall, making it useful for imbalanced data by emphasizing the trade-off between false positives and false negatives. Precision quantifies the reliability of positive predictions, while recall focuses on identifying as many positives as possible. MCC provides a comprehensive evaluation by considering all four categories in the confusion matrix, with values closer to +1 indicating better model performance, particularly in imbalanced datasets. The results, summarized in Table 3, reveal small variations in model effectiveness, highlighting the strengths and weaknesses of each approach. The SVM is the top performer, achieving the highest AUC (0.91) and strong results in MCC (0.87) and F1 score (0.89). Gradient boosting follows closely with an AUC of 0.90, and RF ranks third with an AUC of 0.89 and an excellent F1 score of 0.90. The neural network ranks fourth with an AUC of 0.87, while decision tree and AdaBoost exhibit similar, lower performances. Logistic regression ranks last with an AUC of 0.88 and the weakest balance between precision and recall.
The classification of 829 adakite samples, based on geochemical data compiled by the [56] from the GEOROC dataset “JETOA_ADAKITE.csv”, a comprehensive collection of adakite geochemical information, into fertile and barren categories was performed using the seven optimized ML methods mentioned. Each algorithm’s predictive performance was assessed in terms of the number and percentage of samples classified as fertile and barren (Table 4). Among the methods, SVM and RF exhibited identical results, categorizing 59.2% of the samples as fertile and 40.8% as barren. Gradient boosting predicted 54% as fertile and 46% as barren, while the decision tree model performed similarly, with 58.4% fertile and 41.6% barren. The neural network and AdaBoost methods displayed a preference for barren classifications, with neural network predicting 53.9% as barren and 46.1% as fertile, and AdaBoost showing a slightly more balanced performance (53.9% fertile and 46.1% barren). Logistic regression demonstrated the most distinct classification pattern, predicting 72.7% of the samples as barren and only 27.3% as fertile. These results are visualized in Figure 6, which presents a stacked bar chart illustrating the distribution of fertile and barren predictions across the different ML methods. This chart highlights the variation in classification trends and provides a comparative perspective on the predictive behavior of each algorithm.
Among the 829 analyzed adakites [56], 160 samples were selected based on their clear and consistent fertility characteristics, identified through an extensive review of reputable references (Table 5). Only samples with strong support from multiple studies were considered, while those with uncertainty or insufficient evidence were excluded. Of the 160 fertile adakites, 82 samples were from southern and central Tibet. The post-collisional adakites from southern Tibet, formed by the partial melting of subduction-modified lower crust [118], and the high-K calc-alkaline adakites from central Tibet, related to the melting of subducted continental crust [72], are associated with fertile mineral systems. These regions, known for their porphyry and epithermal deposits, are particularly recognized for their potential to host porphyry copper deposits (e.g., [119,120,121,122,123,124,125]). Seventeen samples were from the Dharwar Greenstone Belts of India [126], where studies on adakitic magmatism highlight their potential in gold environments. These Neoarchaean adakitic rocks, associated with subduction-related processes, are enriched in gold, underscoring their significance in mineral exploration. Eighteen samples were from the Guerrero Terrane of Southwestern Mexico, associated with Au-Fe skarn deposits [127]. The Paleocene adakites in this region are known to be Au-Fe bearing, suggesting a link between adakitic magmatism and gold mineralization, making them an example of fertile adakites in economic geology. Twenty-eight samples were from the Superior Province in Canada (Ontario and Quebec) [128,129], associated with porphyry, epithermal, skarn, and REE deposits. Studies on Archean adakite rocks from the Superior Province [128,129] have been crucial in exploring the links between ancient subduction processes and crustal growth. These regions are considered fertile due to their association with magnesian andesite and Nb-enriched basalt-andesite, both favorable for the formation of mineral deposits. Two samples are from Pichincha Volcano in Ecuador [130], which serves as an example where slab melting and melt metasomatism have produced adakites linked with fertile mineralization, particularly in the Northern Andean Volcanic Zone. These adakites are associated with copper–gold porphyry and epithermal systems (e.g., [131]). Thirteen samples were from the Sulu Belt in Eastern China, associated with Cu porphyry deposits [119].
Table 5 provides geochemical analyses of these fertile adakites, detailing the locations, associated mineralization types, and references. It also includes the number and percentage of samples predicted as fertile and barren by each ML method. The ML techniques mentioned were applied to these 160 fertile adakites, resulting in varying levels of accuracy. For instance, SVM achieved an impressive prediction accuracy of 93.75%, correctly identifying 150 out of the 160 fertile samples. Similarly, the RF method demonstrated an 85% accuracy, accurately classifying 136 fertile samples. Other methods, such as gradient boosting, neural networks, and decision trees, achieved prediction accuracies of 84.4, 84.4, and 82.5%, respectively. Logistic regression, while less accurate at 53.75%, still correctly predicted 86 fertile samples.

5. Discussion

This study analyzed a dataset of 99 fertile and 66 barren adakites from New Brunswick, including major oxides, elements, and geochemical ratios, to identify key signatures of fertility for ML models. Firstly, we aimed to identify the key geochemical variables for adakite fertility in New Brunswick, which can be generalized to all adakites globally. The results of the statistical analysis, as summarized in Table 2, highlight the varying degrees of influence that different geochemical variables exert on the classification of fertile and barren adakites. We used various feature selection metrics to evaluate the performance of each variable in identifying the fertility of adakites. For instance, ANOVA’s emphasis on mean differences between groups [103] aligns closely with the high importance assigned to variables like Gd and Dy, as these elements exhibit significant variability between fertile and barren adakites. Similarly, information gain and gain ratio highlight the capacity of variables to reduce uncertainty in predicting fertility, with REEs consistently performing well under these metrics. Interestingly, ReliefF, which evaluates variable importance by comparing instances within the dataset, also emphasizes REEs like Gd and Dy, but assigns relatively lower scores to major oxide variables, indicating their limited discriminative power in the presence of noisy or redundant features. The chi-square test, which assesses independence between variables, reinforces the importance of elements like Gd and Hf in differentiating fertile from barren adakites. The variables were ranked based on the statistical significance of these metrics (ANOVA, information gain, gain ratio, Gini, χ2, ReliefF). The values were normalized to a 0–1 scale for comparability, with equal weights assigned to each metric. The final score for each variable was determined by averaging the normalized values, reflecting its combined performance across metrics. According to Table 2, Gd ranks first with a score of 0.982, underscoring its critical importance in identifying fertile adakites, followed by Dy and Hf with scores of 0.803 and 0.797, respectively. These trace elements, particularly the middle REEs Gd and Dy, demonstrate strong predictive power due to their geochemical stability and associations with mineral phases indicative of magmatic fertility. REEs, including Gd, Dy, and La, with Hf, consistently show strong scores across multiple metrics, such as ANOVA, information gain, and Gini index. These elements, critical for understanding magma chemistry and mineralization processes, significantly influence the model’s predictive capability. The enrichment of middle rare earth elements (MREEs), such as Gd and Dy, in fertile adakites is primarily controlled by magmatic differentiation, oxidation state, and source rock composition. Amphibole fractionation plays a crucial role, as it preferentially incorporates MREEs, leading to their relative enrichment in evolved, water-rich magmas associated with porphyry Cu systems. Additionally, the generation of adakitic magmas through partial melting of garnet-bearing lithologies results in depletion of heavy REEs while retaining MREEs, producing characteristic REE patterns linked to mineralized intrusions. The oxidation state and sulfur content of the magma further influence both REE distribution and the transport of Cu and Mo, as oxidized, sulfur-rich systems are more conducive to metal enrichment. Hydrothermal processes can also redistribute REEs in mineralized systems, with fluid chemistry playing a key role in selective element mobility. These geochemical processes collectively contribute to the correlation between MREE enrichment and the fertility of adakitic intrusions, supporting their application in mineral prospectivity assessments. Hf also plays a significant role in the geochemistry of fertile magmatic systems, especially in the context of adakitic intrusions. Hf is highly compatible in zircon, a common mineral in evolved, differentiated magmas. As such, the enrichment of Hf in these systems can indicate extensive fractional crystallization or high-temperature conditions during magma differentiation. Additionally, Hf’s behavior, along with MREEs like Gd and Dy, is influenced by the composition of the source rocks and the extent of partial melting, which contributes to the formation of fertile intrusions. Its correlation with Cu and Mo may therefore be related to the degree of magma evolution and the associated changes in the geochemical characteristics of the melt, which ultimately influence metal mobility and concentration in mineralized systems. Regarding the performance of ratios and major oxides, they rank lower than the elements. For example, Eu/Eu*, ranked 14th with a score of 0.406, offers information on plagioclase fractionation but is surpassed by individual REEs. Various ratios and normalized variables, like Eu/Eu*, Rb/Sr, and La/Sm, serve as important discriminators in the model, showcasing how combined element ratios can provide enhanced predictive power compared to individual elements alone.
The additional analysis of 1596 scatter plots derived from 57 geochemical variables further supports the dominance of specific trace elements in distinguishing fertile and barren adakites. Using the LDA algorithm, the most informative scatter plots were identified, with elements such as Ga, Dy, Gd, and Hf emerging as key variables. Among the highest-ranking scatter plots, combinations such as Ga vs. Dy, Ga vs. Gd, and Pr vs. Gd (Figure 5a–c) were found to be particularly effective in separating the two classes. These results align with the earlier statistical findings, highlighting the predictive power of REEs like Gd, Dy, and Ga. Interestingly, scatter plots involving elements versus major oxides, such as Fe2O3 vs. Gd (Figure 5d) and Al2O3 vs. Hf (Figure 5e), also proved to be valuable, though not as informative as the element–element combinations. This indicates that while major oxides may provide some insight into adakite fertility, they are not as powerful in classifying adakites compared to trace elements. Moreover, scatter plots involving ratios, such as La/Sm vs. Gd (Figure 5g) and Rb/Sr vs. Hf (Figure 5h), further enhanced the classification performance, though they still lagged behind the most discriminative element–element scatter plots. These results suggest that ratios may capture more nuanced geochemical variations, but their discriminatory power is less consistent and potentially more context-dependent. In contrast, scatter plots involving major oxides vs. major oxides, ratios vs. ratios, and major oxides vs. ratios performed poorly in terms of separating fertile and barren adakites, reinforcing the finding that elemental concentrations, particularly those of REEs, are more effective predictors of fertility.
The results of applying ML models to classify fertile and barren adakites based on geochemical data demonstrate the varying performance of different algorithms. Among the models tested, SVM emerged as the top performer, achieving the highest AUC of 0.91, followed closely by gradient boosting and RF with AUC values of 0.90 and 0.89, respectively. These findings align with existing literature that has highlighted the strength of SVM in handling complex datasets with imbalances, as it effectively maximizes the margin between classes [83]. RF and gradient boosting, known for their ensemble learning approach, also performed well, corroborating their effectiveness in dealing with high-dimensional and heterogeneous data [85,88]. In contrast, the decision tree and AdaBoost models, while providing reasonably strong results, were less robust in distinguishing between fertile and barren adakites, as evidenced by their relatively lower AUC values. This may be attributed to the tendency of decision trees to overfit or underfit based on hyperparameter settings, a challenge that was mitigated in the models with ensemble learning. Logistic regression, the least effective model in this study, struggled to balance precision and recall, resulting in a bias toward predicting barren samples. This underperformance may be due to the linear nature of logistic regression, which might not capture the complex non-linear relationships present in the geochemical dataset.
A crucial observation is the similarity in the model performance between training and test data, indicating that the models have learned to generalize well without overfitting to the training data. For example, SVM achieved an impressive 93.75% prediction accuracy on the test data, correctly identifying 150 out of 160 fertile samples. This consistency suggests that SVM is not overly tuned to the training dataset but has effectively captured the underlying patterns that differentiate fertile from barren adakites. Similarly, RF demonstrated an accuracy of 85% on test data, correctly identifying 136 fertile samples, aligning with its performance during training. The small discrepancies in prediction accuracy between training and test data, such as those observed for gradient boosting (84.4%) and neural networks (84.4%), further confirm that these models generalize well to new, unseen data. These models are robust and capable of providing reliable predictions even when tested on data not seen during the training phase. In contrast, logistic regression’s performance was noticeably weaker on both the training and test sets, with a prediction accuracy of only 53.75%. This suggests that logistic regression may not be suitable for this particular problem, possibly due to the complexity of the relationships [134] between the input features and the fertility of the adakites. The model’s lower precision and recall further reinforce the idea that it struggles to make accurate predictions in the context of imbalanced data. SVM achieved the highest classification performance in distinguishing fertile from barren adakites; however, its effectiveness may vary with geological setting, deposit type, and dataset characteristics. Further validation across diverse mineral systems is needed to assess its generalizability. Future research could explore transfer learning and region-specific model optimization to improve adaptability across deposit types.
While traditional methods will likely remain valuable for many scientific purposes [135], the rapid growth of ML in solid Earth geosciences, though still in its early stages, highlights the need for new strategies and techniques to assess larger geochemical datasets more cost-effectively and efficiently [136,137,138]. There is still much to be done with existing datasets from long-standing data sources, many of which remain largely unexplored [138]. By applying ML models to regional geochemical datasets, exploration can be better targeted, reducing both cost and time associated with traditional methods. Identifying fertile adakites as indicators of porphyry and epithermal mineralization holds particular promise, especially in underexplored regions where conventional techniques may have fallen short. The primary goal of mineral exploration is to distinguish between prospective and non-prospective areas, facilitating the discovery of new sources of raw earth materials. This process involves collecting diverse exploration datasets, transforming them into spatial proxies using the mineral systems approach, and integrating these proxies through robust methodologies. The result is a mineral prospectivity map that highlights potential areas in both greenfield (underexplored) and brownfield (previously explored) environments. In this context, the mineral systems approach is fundamental, focusing on the ore-forming processes outlined in deposit models. It provides a comprehensive, process-driven framework for understanding deposit formation by translating exploration layers into proxies that represent key processes such as source, trigger, transport, trap, deposition, and preservation. Among these, the source plays a pivotal role in driving mineralizing systems. Intrusive units, often seen as key sources of magmatism, hydrothermal fluid circulation, and metal mobilization, are central to mineral deposit formation. However, not all intrusive units are equally fertile. Their fertility can vary depending on factors such as magma source composition, degree of crustal contamination, oxidation state, and magmatic differentiation. By assigning varying weights to these units based on their fertility, it is possible to enhance the accuracy of mineral prospectivity models, reflecting the true mineralization potential of each unit. This paper emphasizes adakites as a critical source in the mineral systems approach and aims to leverage ML techniques to predict their fertility, offering a new approach to refining mineral prospectivity mapping.

6. Conclusions

The key findings of this study are as follows:
  • This study demonstrates the efficacy of ML in classifying fertile and barren adakites, highlighting the importance of geochemical assessment prior to utilizing adakitic intrusions as evidence layers in mineral prospectivity mapping;
  • Analyzing a dataset of 99 fertile and 66 barren adakites from New Brunswick, this research identifies REEs, including Gd, Dy, and La, with Hf, as the most reliable indicators of fertility, consistently ranking highest across multiple feature selection techniques, including ANOVA, information gain, and ReliefF;
  • Among the seven ML models tested, SVM exhibited the best performance, achieving an AUC of 0.91 and a classification accuracy of 93.75%. This was followed by gradient boosting, with an AUC of 0.90, and random forest, which attained an AUC of 0.89;
  • These models were subsequently applied to a global dataset comprising 829 adakite samples, predicting fertility patterns. Validation with 160 globally recognized fertile adakites further confirmed the superior predictive accuracy of the SVM model;
  • The linear discriminant analysis (LDA) of 1596 scatter plots revealed that element–element relationships (e.g., Ga vs. Dy, Ga vs. Gd, and Pr vs. Gd) and element–major oxide relationships (e.g., Fe2O3 vs. Gd and Al2O3 vs. Hf) provided the highest discriminatory power, whereas major oxide–major oxide, ratio–ratio, and major oxide–ratio plots were less effective;
  • These findings underscore the potential of machine learning-based classification to enhance mineral exploration strategies. It emphasizes that not all intrusive units, including adakites, are inherently fertile and should not be directly used as evidence layers in mineral prospectivity mapping without prior analysis.

Author Contributions

Conceptualization, A.K. and F.Y.; methodology, A.K. and F.Y.; software, A.K. and F.Y.; validation, A.K. and F.Y.; writing—original draft preparation, A.K. and F.Y.; and writing—review and editing, A.K., F.Y., D.R.L. and K.G.T. All authors have read and agreed to the published version of the manuscript.

Funding

This study was funded by the University of New Brunswick, the New Brunswick Department of Natural Resources and Energy Development, the New Brunswick Innovation Foundation, and the NSERC Discovery Grant awarded to David R. Lentz.

Data Availability Statement

The data can be made available upon request.

Acknowledgments

This work was made possible thanks to the support of the New Brunswick Department of Natural Resources and Energy Development (NB-DNRED), which provided funding. We are especially grateful to Serge Allard for his continuous support and valuable contributions to this project. We also extend our sincere appreciation to the three anonymous reviewers for their insightful comments and constructive feedback, which significantly improved the quality of this work.

Conflicts of Interest

The authors declare no conflicts of interest.

References

  1. Karbalaeiramezanali, A.; Feizi, F.; Jafarirad, A.; Lotfi, M. Application of Best-Worst method and Additive Ratio Assessment in mineral prospectivity mapping: A case study of vein-type copper mineralization in the Kuhsiah-e-Urmak area. Iran. Ore Geol. Rev. 2020, 117, 103268. [Google Scholar] [CrossRef]
  2. McCuaig, T.C.; Beresford, S.; Hronsky, J. Translating the mineral systems approach into an effective exploration targeting system. Ore Geol. Rev. 2010, 38, 128–138. [Google Scholar] [CrossRef]
  3. Karbalaeiramezanali, A.; Feizi, F.; Jafarirad, A.; Lotfi, M. Geochemical anomaly and mineral prospectivity mapping for vein-type copper mineralization, Kuhsiah-e-Urmak area, Iran: Application of sequential Gaussian simulation and multivariate regression analysis. Nat. Resour. Res. 2020, 29, 41–70. [Google Scholar] [CrossRef]
  4. Karbalaeiramezanali, A.; Yousefi, F.; Lentz, D.R.; Thorne, K.G. Machine learning for predicting fertility of adakites worldwide: Insights from geochemical data of adakites in the Northern Appalachians, New Brunswick. In Proceedings of the Exploration, Mining and Petroleum (EMP) New Brunswick Conference 2024, Fredericton, NB, Canada, 27–29 October 2024. [Google Scholar]
  5. Drummond, M.S.; Defant, M.J. A model for trondhjemite-tonalite-dacite genesis and crustal growth via slab melting: Archean to modern comparisons. J. Geophys. Res. Solid Earth 1990, 95, 21503–21521. [Google Scholar] [CrossRef]
  6. Martin, H.; Smithies, R.; Rapp, R.; Moyen, J.-F.; Champion, D. An overview of adakite, tonalite–trondhjemite–granodiorite (TTG), and sanukitoid: Relationships and some implications for crustal evolution. Lithos 2005, 79, 1–24. [Google Scholar] [CrossRef]
  7. Moyen, J.-F. High Sr/Y and La/Yb ratios: The meaning of the “adakitic signature”. Lithos 2009, 112, 556–574. [Google Scholar] [CrossRef]
  8. Yousefi, F.; Lentz, D.R. Formation of high-silica adakites and their relationship with slab break-off: Implications for generating fertile Cu-Au-Mo porphyry systems. Geosci. Front. 2024, 15, 101927. [Google Scholar] [CrossRef]
  9. Yousefi, F.; Lentz, D.R.; Walker, J.A.; Thorne, K.G. Development of high-silica adakitic intrusions in the Northern Appalachians of New Brunswick (Canada), and their correlation with slab break-off: Insights into the formation of fertile Cu-Au-Mo porphyry systems. Geosciences 2024, 14, 241. [Google Scholar] [CrossRef]
  10. Kamvong, T.; Zaw, K.; Meffre, S.; Maas, R.; Stein, H.; Lai, C.K. Adakites in the Truong Son and Loei fold belts, Thailand and Laos: Genesis and implications for geodynamics and metallogeny. Gondwana Res. 2014, 26, 165–184. [Google Scholar] [CrossRef]
  11. Whalen, J.B.; Hildebrand, R.S. Trace element discrimination of arc, slab failure, and A-type granitic rocks. Lithos 2019, 348, 1005179. [Google Scholar] [CrossRef]
  12. Yousefi, F.; Lentz, D.R.; Thorne, K.G. Mineral chemistry of the Eagle Lake Granite porphyry, southwestern New Brunswick, Canada: Implications for Cu-Mo-Au mineralization. Can. J. Miner. Pet. 2023, 61, 445–465. [Google Scholar] [CrossRef]
  13. Zuo, R. Machine learning of mineralization-related geochemical anomalies: A review of potential methods. Nat. Resour. Res. 2017, 26, 457–464. [Google Scholar] [CrossRef]
  14. Zou, S.; Chen, X.; Brzozowski, M.J.; Leng, C.; Xu, D. Application of machine learning to characterizing magma fertility in porphyry Cu deposits. J. Geophys. Res. Solid Earth 2022, 127, e2022JB024584. [Google Scholar] [CrossRef]
  15. Nathwani, C.L.; Wilkinson, J.J.; Fry, G.; Armstrong, R.N.; Smith, D.J.; Ihlenfeld, C. Machine learning for geochemical exploration: Classifying metallogenic fertility in arc magmas and insights into porphyry copper deposit formation. Miner. Deposita 2022, 57, 1143–1166. [Google Scholar] [CrossRef]
  16. Zhang, Z.-J.; Zhou, Y.; Zhang, P. Crucial geochemical signal identification for Cu-fertile magmas in Paleo-Tethyan arc based on machine learning. Math. Geosci. 2023, 55, 799–828. [Google Scholar] [CrossRef]
  17. Zhang, P.; Zhang, Z.; Yang, J.; Cheng, Q. Machine learning prediction of ore deposit genetic type using magnetite geochemistry. Nat. Resour. Res. 2023, 32, 99–116. [Google Scholar] [CrossRef]
  18. Yang, X.-M.; Lentz, D.R.; McCutcheon, S.R. Petrochemical evolution of subvolcanic granitoid intrusions within the Late Devonian Mount Pleasant Caldera, southwestern New Brunswick, Canada: Comparison of Au versus Sn-W-Mo-polymetallic mineralization systems. Atl. Geol. 2003, 39, 97–122. [Google Scholar]
  19. Yang, X.M.; Lentz, D.R.; Chi, G.; Kyser, T.K. Fluid–mineral reaction in the Lake George Granodiorite, New Brunswick, Canada: Implications for Au–W–Mo–Sb mineralization. Can. Mineral. 2004, 42, 1443–1464. [Google Scholar]
  20. Yang, X.-M.; Lentz, D.R.; Chi, G.; Thorne, K.G. Geochemical characteristics of gold-related granitoids in southwestern New Brunswick, Canada. Lithos 2008, 104, 355–377. [Google Scholar]
  21. Ruitenberg, A.A.; Fyffe, L.R. Mineral deposits associated with granitoid intrusions and related subvolcanic stocks in New Brunswick and their relationship to Appalachian tectonic evolution. Canadian Institute of Mining and Metallurgy. Bulletin 1982, 75, 83–97. [Google Scholar]
  22. Pilote, J.L.; Barr, S.M.; Wilson, R.A.; McClenaghan, S.; Kamo, S.; McNicoll, V.J.; Bevier, M.L. Precise age and petrology of Silurian-Devonian plutons in the Benjamin River–Charlo area, northern New Brunswick. Atl. Geol. 2012, 48, 97–123. [Google Scholar] [CrossRef]
  23. Walker, J.A.; Gower, S.; McCutcheon, S.R. Antinouri-Nicholas Project, Gloucester and Restigouche Counties, Northern New Brunswick; Information Circular, 91; New Brunswick Department of Natural Resources and Energy, Mineral Resources: Fredericton, NB, Canada, 1991; pp. 87–100. [Google Scholar]
  24. Whalen, J.B.; Jenner, G.A.; Longstaffe, F.J.; Hegner, E. Nature and evolution of the eastern margin of lapetus: Geochemical and isotopic constraints from Siluro-Devonian granitoid plutons in the New Brunswick Appalachians. Can. J. Earth Sci. 1996, 33, 140–155. [Google Scholar] [CrossRef]
  25. Wanless, R.K.; Stevens, R.D.; LaChance, G.R.; DiLabio, R.N. K-Ar age determinations of samples from various areas of New Brunswick. In Age Determinations and Geological Studies. K-Ar Isotopic Ages, Report 10; Geological Survey of Canada: Ottawa, ON, Canada, 1972; Volume 71, pp. 68–77. [Google Scholar]
  26. Davis, W.; Chi, G.; Castonguay, S.; McLeod, M.J. Temporal Relationships Between Plutonism, Metamorphism, and Gold Mineralization in Southwestern New Brunswick: U–Pb and 40Ar-39Ar Geochronological Constraints; Geological Survey of Canada: Ottawa, ON, Canada, 2004; 20p. [Google Scholar]
  27. Butt, K.A. Genesis of Granitic Stocks in Southwestern New Brunswick. Ph.D. Thesis, University of New Brunswick, Fredericton, NB, Canada, 1976. [Google Scholar]
  28. Wilson, R.A. The Middle Paleozoic Rocks of Northern and Western New Brunswick, Canada; Memoir 4; New Brunswick Department of Energy and Resource Development, Geological Surveys Branch: Fredericton, NB, Canada, 2017; 319p. [Google Scholar]
  29. Yousefi, F.; Lentz, D.R.; Thorne, K.G.; McFarlane, C.R.; Cousens, B. Petrogenesis of Eagle Lake Granite and its associated Cu–Mo–Au mineralization, southwestern New Brunswick, Canada. Minerals 2023, 13, 594. [Google Scholar] [CrossRef]
  30. Yousefi, F.; White, T.; Lentz, D.R.; McFarlane, C.R.; Thorne, K.G. Middle Devonian Evandale porphyry Cu-Mo (Au) deposit, southwestern New Brunswick, Canada: Analysis of petrogenesis to potential as a source for distal intrusion-related epithermal gold mineralization. Ore Geol. Rev. 2023, 162, 105716. [Google Scholar] [CrossRef]
  31. Bevier, M.L.; Whalen, J.B. Tectonic significance of Silurian magmatism in the Canadian Appalachians. Geology 1990, 18, 411–414. [Google Scholar]
  32. Roddick, J.C.; Bevier, M.L. U-Pb dating of granites with inherited zircon: Conventional and ion microprobe results from two Paleozoic plutons, Canadian Appalachians. Chem. Geol. 1995, 119, 307–329. [Google Scholar]
  33. Massawe, R.J.; Lentz, D.R. Evaluation of crystallization and emplacement conditions of the McKenzie Gulch porphyry dykes using chemistry of rock-forming minerals: Implications for mineralization potential. Ore Geol. Rev. 2020, 116, 103256. [Google Scholar] [CrossRef]
  34. Forbes, E. New Brunswick. The Canadian Encyclopedia. 2024. Available online: https://www.thecanadianencyclopedia.ca/en/article/new-brunswick (accessed on 24 March 2025).
  35. Fyffe, L.R.; Thorne, K.G.; Dunning, G.R.; Martin, D.A. U–Pb geochronology of the Sisson Brook Granite Porphyry, York County, west-central New Brunswick. In Geological Investigations in New Brunswick for 2007; Martin, G.L., Ed.; New Brunswick Department of Natural Resources, Minerals, Policy and Planning Division: Fredericton, NB, Canada, 2008; Volume 1, pp. 35–54. [Google Scholar]
  36. Whalen, J.B. Geology, Petrography, and Geochemistry of Appalachian Granites in New Brunswick and Gaspésie, Québec; Geological Survey of Canada Bulletin: Ottawa, ON, Canada, 1993; Volume 436, 130p. [Google Scholar]
  37. Stephenson, E.M.; Meinert, L.D.; Mortensen, J.K.; Hussey, J. Age and skarn alteration of the Porphyry Mountain Cu-Mo deposit, Mines Gaspé, Québec. Geol. Soc. Am. Annu. Meet. Program Abstr. 1998, 30, 372. [Google Scholar]
  38. Marcelissen, M.; Hollings, P.; Cooke, D.R.; Baker, M.J.; Belousov, I.; Orovan, E.; Friedman, R. Geochronology of the Mines Gaspé porphyry deposit, Québec, Canada. Can. J. Earth Sci. 2024, 61, 876–893. [Google Scholar] [CrossRef]
  39. Government of New Brunswick. Mineral Occurrence Database. Available online: https://dnr-mrn.gnb.ca/mineraloccurrence/ (accessed on 18 March 2025).
  40. New Brunswick Department of Natural Resources and Energy Development. NB DNRED Mineral Occurrence Web App. ArcGIS. Available online: https://nbdnr.maps.arcgis.com/apps/webappviewer/index.html?id=9222d8a1ccf54f4a9655c9d7026112a3&locale=en (accessed on 18 March 2025).
  41. McLeod, M.J. Geology, Geochemistry, and Related Mineral Deposits of the Saint George Batholith, Charlotte, Queens, and Kings Counties, New Brunswick; Mineral Resources 5; New Brunswick, Natural Resources and Energy: Fredericton, NB, Canada, 1990; 169p. [Google Scholar]
  42. Yousefi, F. Petrogenetic Analysis of Arc-Related Devonian Magmatic Rocks in Relation to the Formation of Magmatic Hydrothermal Cu ± Mo ± Au Deposits in the New Brunswick Segment of the Northern Appalachians. Ph.D. Thesis, University of New Brunswick, Fredericton, NB, Canada, 2024. [Google Scholar]
  43. Wilson, R.A.; Kamo, S.L. Geochronology and lithogeochemistry of granitoid rocks from the central part of the Central plutonic belt, New Brunswick, Canada: Implications for Sn-W-Mo exploration. Atl. Geol. 2016, 52, 125–167. [Google Scholar] [CrossRef]
  44. McCutcheon, S.R.; Bevier, M.L. Implications of field relations and U-Pb geochronology for the age of gold mineralization and timing of Acadian deformation in northern New Brunswick. Atl. Geol. 1990, 26, 237–246. [Google Scholar] [CrossRef] [PubMed]
  45. Bevier, M.L.; Barr, S.M. U-Pb age constraints on the stratigraphy and tectonic history of the Avalon terrane, New Brunswick, Canada. J. Geol. 1990, 98, 53–63. [Google Scholar]
  46. Mohammadi, N.; Lentz, D.R.; Thorne, K.G.; Walker, J.; Rogers, N.; Cousens, B.; McFarlane, C.R. U-Pb and Re-Os geochronology and lithogeochemistry of granitoid rocks from the Burnthill Brook area in central New Brunswick, Canada: Implications for critical mineral exploration. Geochemistry 2024, 84, 126087. [Google Scholar] [CrossRef]
  47. Heidarian, H. Examination of Mesothermal to Epithermal Orogenic-to Intrusion-Related Sb-Bearing Gold Systems in a Southern New Brunswick Segment of the Northern Appalachians. Ph.D. Thesis, University of New Brunswick, Fredericton, NB, Canada, 2022. [Google Scholar]
  48. Wilson, R.A. Geology of the McCormack Lake and Ten Mile Pool areas (NTS 21 O/10b and c), Restigouche County, New Brunswick. In Exploration and Mining New Brunswick; Merlini, S.A.A., Ed.; New Brunswick Department of Natural Resources, Minerals, Policy and Planning Division, Information Circular: Fredericton, NB, Canada, 2004; pp. 63–66. [Google Scholar]
  49. Azadbakht, Z.; Rogers, N.; Lentz, D.R.; McFarlane, C.R.M. Petrogenesis and associated mineralization of Acadian related granitoids in New Brunswick. In Targeted Geoscience Initiative; Natural Resources Canada: Saint John, NB, Canada, 2018; pp. 243–278. [Google Scholar]
  50. Feng, C.; Wang, H.; Lu, N.; Chen, T.; He, H.; Lu, Y.; Tu, X.M. Log-transformation and its implications for data analysis. Shanghai Arch. Psychiatry 2014, 26, 105–109. [Google Scholar]
  51. Hoffmann, G.; Klawonn, F.; Lichtinghagen, R.; Orth, M. The zlog value as a basis for the standardization of laboratory results. Lab. Med. 2017, 41 (Suppl. S1), 20170135. [Google Scholar] [CrossRef]
  52. Singh, D.; Singh, B. Investigating the impact of data normalization on classification performance. Appl. Soft Comput. 2020, 97, 105524. [Google Scholar] [CrossRef]
  53. Kim, Y.-S.; Kim, M.K.; Fu, N.; Liu, J.; Wang, J.; Srebric, J. Investigating the impact of data normalization methods on predicting electricity consumption in a building using different artificial neural network models. Sustain. Cities Soc. 2025, 118, 105570. [Google Scholar] [CrossRef]
  54. Ahsan, M.M.; Mahmud, M.P.; Saha, P.K.; Gupta, K.D.; Siddique, Z. Effect of data scaling methods on machine learning algorithms and model performance. Technologies 2021, 9, 52. [Google Scholar] [CrossRef]
  55. Izonin, I.; Tkachenko, R.; Shakhovska, N.; Ilchyshyn, B.; Singh, K.K. Effect of data scaling methods on machine learning algorithms and model performance. Mathematics 2022, 10, 1942. [Google Scholar] [CrossRef]
  56. DIGIS Team. JETOA_ADAKITE.csv: GEOROC Compilation: Rock Types, version 1; Göttingen Research Online/Data: Göttingen, Germany, 2021. [Google Scholar] [CrossRef]
  57. Cooke, R.; Agnew, P.; Hollings, P.; Baker, M.; Chang, Z.; Wilkinson, J.J.; Ahmed, A.; White, N.C.; Zhang, L.; Thompson, J.; et al. Recent advances in the application of mineral chemistry to exploration for porphyry copper–gold–molybdenum deposits: Detecting the geochemical fingerprints and footprints of hypogene mineralization and alteration. Geochem. Explor. Environ. Anal. 2020, 20, 176–188. [Google Scholar]
  58. Yousefi, F.; Lentz, D.R.; McFarlane, C.R.; Walker, J.A.; Thorne, K.G. Zircon compositional systematics from Devonian oxidized I-type granitoids: Examination of porphyry Cu fertility indices in the New Brunswick Appalachians, Canada. Front. Earth Sci. 2024, 12, 1363029. [Google Scholar]
  59. Lu, Y.-J.; Loucks, R.R.; Fiorentini, M.; McCuaig, T.C.; Evans, N.J.; Yang, Z.-M.; Hou, Z.-Q.; Kirkland, C.L.; Parra-Avila, L.A.; Kobussen, A. Zircon compositions as a pathfinder for porphyry Cu ± Mo ± Au deposits. In Tectonics and Metallogeny of the Tethyan Orogenic Belt; Richards, J.P., Ed.; Special Publication No. 19; Society of Economic Geologists: Littleton, CO, USA, 2016; pp. 1–57. [Google Scholar]
  60. Mackenzie, W.S.; Cox, K.G.; Bell, J.D.; Pankhurst, R.J. The Interpretation of Igneous Rocks; George Allen and Unwin: Crows Nest, Australia, 1979. [Google Scholar]
  61. Castillo, P.R. Adakite petrogenesis. Lithos 2012, 134, 304–316. [Google Scholar] [CrossRef]
  62. Falloon, T.J.; Danyushevsky, L.V.; Crawford, A.J.; Meffre, S.; Woodhead, J.D.; Bloomer, S.H. Boninites and adakites from the northern termination of the Tonga Trench: Implications for adakite petrogenesis. J. Petrol. 2008, 49, 697–715. [Google Scholar] [CrossRef]
  63. Archibald, D.B.; Murphy, J.B. A slab failure origin for the Donegal composite batholith, Ireland as indicated by trace-element geochemistry. Geol. Soc. London Spéc. Publ. 2021, 503, 347–370. [Google Scholar] [CrossRef]
  64. Du, J.-G.; Du, Y.-S.; Cao, Y. Important role of hornblende fractionation in generating the adakitic magmas in Tongling, Eastern China: Evidence from amphibole megacryst and cumulate xenoliths and host gabbros. Int. Geol. Rev. 2018, 60, 1381–1403. [Google Scholar] [CrossRef]
  65. Wang, Q.; Xu, J.-F.; Zhao, Z.-H.; Bao, Z.-W.; Xu, W.; Xiong, X.-L. Cretaceous high-potassium intrusive rocks in the Yueshan-Hongzhen area of east China: Adakites in an extensional tectonic regime within a continent. Geochem. J. 2004, 38, 417–434. [Google Scholar] [CrossRef]
  66. Akame, J.M.; Oliveira, E.P.; Poujol, M.; Hublet, G.; Debaille, V. LA–ICP–MS zircon U Pb dating, Lu Hf, Sm Nd geochronology and tectonic setting of the Mesoarchean mafic and felsic magmatic rocks in the Sangmelima granite-greenstone terrane, Ntem Complex (South Cameroon). Lithos 2020, 372, 105702. [Google Scholar] [CrossRef]
  67. Richards, J.P.; Kerrich, R. Special Paper: Special paper: Adakite-like rocks: Their diverse origins and questionable role in metallogenesis. Econ. Geol. 2007, 102, 537–576. [Google Scholar] [CrossRef]
  68. Goss, A.R.; Kay, S.M. Extreme high field strength element (HFSE) depletion and near-chondritic Nb/Ta ratios in Central Andean adakite-like lavas (~28° S, ~68° W). Earth and Planetary. Sci. Lett. 2009, 279, 97–109. [Google Scholar] [CrossRef]
  69. Condie, K.C. TTGs and adakites: Are they both slab melts? Lithos 2005, 80, 33–44. [Google Scholar] [CrossRef]
  70. Xu, W.C.; Zhang, H.F.; Luo, B.J.; Guo, L.; Yang, H. Adakite-like geochemical signature produced by amphi-bole-dominated fractionation of arc magmas: An example from the Late Cretaceous magmatism in Gangdese belt, south Tibet. Lithos 2015, 232, 197–210. [Google Scholar] [CrossRef]
  71. Bebout, G.E.; Ryan, J.G.; Leeman, W.P.; Bebout, A.E. Fractionation of trace elements by subduction-zone metamorphism—Effect of convergent-margin thermal evolution. Earth Planet. Sci. Lett. 1999, 171, 63–81. [Google Scholar] [CrossRef]
  72. Wang, Q.; Wyman, D.A.; Xu, J.; Wan, Y.; Li, C.; Zi, F.; Jiang, Z.; Qiu, H.; Chu, Z.; Zhao, Z.; et al. Triassic Nb-enriched basalts, magnesian andesites, and adakites of the Qiangtang terrane (Central Tibet): Evidence for metasomatism by slab-derived melts in the mantle wedge. Contrib. Mineral. Petrol. 2008, 155, 473–490. [Google Scholar] [CrossRef]
  73. Dokuz, A.; Uysal, I.; Siebel, W.; Turan, M.; Duncan, R.; Akçay, M. Post-collisional adakitic volcanism in the eastern part of the Sakarya Zone, Turkey: Evidence for slab and crustal melting. Contrib. Miner. Pet. 2013, 166, 1443–1468. [Google Scholar] [CrossRef]
  74. Plank, T. Constraints from thorium/lanthanum on sediment recycling at subduction zones and the evolution of the continents. J. Petrol. 2005, 46, 921–944. [Google Scholar] [CrossRef]
  75. Castillo, P.R. Origin of the adakite–high-Nb basalt association and its implications for postsubduction magmatism in Baja California, Mexico. Geol. Soc. Am. Bull. 2008, 120, 451–462. [Google Scholar] [CrossRef]
  76. Zhao, Z.; Xiong, X.; Wang, Q.; Bai, Z.; Qiao, Y. Late Paleozoic underplating in North Xinjiang: Evidence from shoshonites and adakites. Gondwana Res. 2009, 16, 216–226. [Google Scholar] [CrossRef]
  77. Yang, Z.; Cao, K. Post-collisional porphyry copper deposits in Tibet: An overview. Earth Sci. Rev. 2024, 258, 104954. [Google Scholar] [CrossRef]
  78. Zheng, S.; An, Y.; Lai, C.; Wang, H.; Li, Y. Genesis of high-Mg adakites in the southeastern margin of North China Craton: Geochemical and U-Pb geochronological perspectives. Front. Earth Sci. 2021, 9, 731233. [Google Scholar] [CrossRef]
  79. Kerrich, R.; Said, N.; Manikyamba, C.; Wyman, D. Sampling oxygenated Archean hydrosphere: Implications from fractionations of Th/U and Ce/Ce* in hydrothermally altered volcanic sequences. Gondwana Res. 2013, 23, 506–525. [Google Scholar] [CrossRef]
  80. Chiaradia, M. Magmatic controls on metal endowments of porphyry Cu-Au deposits. In Tectonomagmatic Influences on Metallogeny and Hydrothermal Ore Deposits: A Tribute to Jeremy P. Richards; Sholeh, A., Wang, R., Eds.; Society of Economic Geologists: Littleton, CO, USA, 2021; Volume 1, pp. 1–24. [Google Scholar]
  81. Wells, T.J.; Meffre, S.; Cooke, D.R.; Steadman, J.; Hoye, J.L. Assessment of magmatic fertility using pXRF on altered rocks from the Ordovician Macquarie Arc, New South Wales. Aust. J. Earth Sci. 2021, 68, 397–409. [Google Scholar] [CrossRef]
  82. Ponyalou, O.L.; Petterson, M.G.; Espi, J.O. The petrology and geochemistry of REE-enriched, alkaline volcanic rocks of Ambitle Island, Feni Island Group, Papua New Guinea. Geosciences 2023, 13, 339. [Google Scholar] [CrossRef]
  83. Cortes, C.; Vapnik, V. Support-vector networks. Mach. Learn. 1995, 20, 273–297. [Google Scholar] [CrossRef]
  84. McCulloch, W.S.; Pitts, W. A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 1943, 5, 115–133. [Google Scholar] [CrossRef]
  85. Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef]
  86. Quinlan, J.R. Induction of decision trees. Mach. Learn. 1986, 1, 81–106. [Google Scholar] [CrossRef]
  87. Freund, Y.; Schapire, R.E. A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 1997, 55, 119–139. [Google Scholar] [CrossRef]
  88. Friedman, J.H. Greedy function approximation: A gradient boosting machine. Ann. Stat. 2001, 29, 1189–1232. [Google Scholar] [CrossRef]
  89. Cox, D.R. The regression analysis of binary sequences. J. R. Stat. Soc. Ser. B Methodol. 1958, 20, 215–242. Available online: https://www.jstor.org/stable/2983890 (accessed on 24 March 2025).
  90. Petrelli, M. Machine learning in petrology: State-of-the-art and future perspectives. J. Pet. 2024, 65, egae036. [Google Scholar] [CrossRef]
  91. Petrelli, M.; Perugini, D. Solving petrological problems through machine learning: The study case of tectonic discrimination using geochemical and isotopic data. Contrib. Mineral. Petrol. 2016, 171, 57. [Google Scholar] [CrossRef]
  92. Petrelli, M.; Bizzarri, R.; Morgavi, D.; Baldanza, A.; Perugini, D. Combining machine learning techniques, microanalyses, and large geochemical datasets for tephrochronological studies in complex volcanic areas: New age constraints for the Pleistocene magmatism of central Italy. Quat. Geochronol. 2017, 40, 33–44. [Google Scholar] [CrossRef]
  93. Lacassie, J.P.; del Solar, J.R.; Roser, B.; Hervé, F. Visualization of volcanic rock geochemical data and classification with artificial neural networks. Math. Geol. 2006, 38, 697–710. [Google Scholar] [CrossRef]
  94. Das, P.; Iyer, S.D. Geochemical characterization of oceanic basalts using artificial neural networks. Geochem. Trans. 2009, 10, 1. [Google Scholar] [CrossRef]
  95. Schönig, J.; von Eynatten, H.; Tolosana-Delgado, R.; Meinhold, G. Garnet major-element composition as an indicator of host-rock type: A machine learning approach using the random forest classifier. Contrib. Miner. Pet. 2021, 176, 98. [Google Scholar] [CrossRef]
  96. Weber, G.; Blundy, J. A machine learning-based thermobarometer for magmatic liquids. J. Pet. 2024, 65, egae020. [Google Scholar] [CrossRef]
  97. Hussain, J.; Zafar, T.; Fu, X.; Ali, N.; Chen, J.; Frontalini, F.; Hussain, J.; Lina, X.; Kontakiotis, G.; Koumoutsakou, O. Petrological controls on the engineering properties of carbonate aggregates through a machine learning approach. Sci. Rep. 2024, 14, 31948. [Google Scholar] [CrossRef]
  98. Han, R.; Wang, Z.; Wang, W.; Xu, F.; Qi, X.; Cui, Y. Lithology identification of igneous rocks based on XGBoost and conventional logging curves, a case study of the eastern depression of Liaohe Basin. J. Appl. Geophys. 2021, 195, 104480. [Google Scholar] [CrossRef]
  99. Zou, Y.; Chen, Y.; Deng, H. Gradient boosting decision tree for lithology identification with well logs: A case study of Zhaoxian gold deposit, Shandong Peninsula, China. Nat. Resour. Res. 2021, 30, 3197–3217. [Google Scholar] [CrossRef]
  100. Cheng, L.; Yang, Z.; Costa, F. Insights on source lithology and pressure-temperature conditions of basalt generation using machine learning. Earth Space Sci. 2024, 11, e2024EA003732. [Google Scholar] [CrossRef]
  101. Itano, K.; Ueki, K.; Iizuka, T.; Kuwatani, T. Geochemical discrimination of monazite source rock based on machine learning techniques and multinomial logistic regression analysis. Geosciences 2020, 10, 63. [Google Scholar] [CrossRef]
  102. Duan, Y.; Xie, J.; Su, Y.; Liang, H.; Hu, X.; Wang, Q.; Pan, Z. Application of the decision tree method to lithology identification of volcanic rocks-taking the Mesozoic in the Laizhouwan Sag as an example. Sci. Rep. 2020, 10, 19209. [Google Scholar] [CrossRef] [PubMed]
  103. Ståhle, L.; Wold, S. Analysis of variance (ANOVA). Chemom. Intell. Lab. Syst. 1989, 6, 259–272. [Google Scholar] [CrossRef]
  104. Shannon, C.E. A mathematical theory of communication. Bell Syst. Tech. J. 1948, 27, 379–423. [Google Scholar] [CrossRef]
  105. Quinlan, J.R. C4.5: Programs for Machine Learning; Morgan Kaufmann Publishers: Burlington, MA, USA, 1992; Volume 1. [Google Scholar]
  106. Gini, C.W. Variability and Mutability, Contribution to the Study of Statistical Distributions and Relations; Studi Economico-Giuridici della R. Universita de Cagliari: Cagliari, Italy, 1912. [Google Scholar]
  107. Pearson, K. On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling. London Edinb. Dublin Philos. Mag. J. Sci. 1900, 50, 157–175. [Google Scholar] [CrossRef]
  108. Kira, K.; Rendell, L.A. A practical approach to feature selection. In Machine Learning Proceedings 1992; Morgan Kaufmann: Burlington, MA, USA, 1992; pp. 249–256. [Google Scholar]
  109. Fisher, R.A. The use of multiple measurements in taxonomic problems. Ann. Eugen. 1936, 7, 179–188. [Google Scholar] [CrossRef]
  110. ACTLabs. Home. Available online: https://actlabs.com/ (accessed on 24 March 2025).
  111. Norrish, K.; Hutton, J. An accurate X-ray spectrographic method for the analysis of a wide range of geological samples. Geochim. Cosmochim. Acta 1969, 33, 431–453. [Google Scholar] [CrossRef]
  112. Hoffman, E.L. Instrumental neutron activation in geoanalysis. J. Geochem. Explor. 1992, 44, 297–319. [Google Scholar] [CrossRef]
  113. Japkowicz, N.; Stephen, S. The class imbalance problem: A systematic study. Intell. Data Anal. 2002, 6, 429–449. [Google Scholar] [CrossRef]
  114. Dietterich, T. Overfitting and undercomputing in machine learning. ACM Comput. Surv. (CSUR) 1995, 27, 326–327. [Google Scholar] [CrossRef]
  115. Mavrogiorgos, K.; Kiourtis, A.; Mavrogiorgou, A.; Menychtas, A.; Kyriazis, D. Bias in machine learning: A literature review. Appl. Sci. 2024, 14, 8860. [Google Scholar] [CrossRef]
  116. Hanley, J.A.; McNeil, B.J. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 1982, 143, 29–36. [Google Scholar] [CrossRef] [PubMed]
  117. Matthews, B.W. Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochim. Biophys. Acta (BBA)-Protein Struct. 1975, 405, 442–451. [Google Scholar] [CrossRef]
  118. Guo, Z.-F.; Wilson, M.; Liu, J. Post-collisional adakites in South Tibet: Products of partial melting of subduction-modified lower crust. Lithos 2007, 96, 205–224. [Google Scholar] [CrossRef]
  119. Guo, F.; Fan, W.; Li, C. Geochemistry of late Mesozoic adakites from the Sulu belt, eastern China: Magma genesis and implications for crustal recycling beneath continental collisional orogens. Geol. Mag. 2006, 143, 1–13. [Google Scholar] [CrossRef]
  120. Sun, X.; Lu, Y.J.; McCuaig, T.C.; Zheng, Y.Y.; Chang, H.F.; Guo, F.; Xu, L.J. Miocene ultrapotassic, high-Mg dioritic, and adakite-like rocks from Zhunuo in Southern Tibet: Implications for mantle metasomatism and porphyry copper mineralization in collisional orogens. J. Petrol. 2018, 59, 341–386. [Google Scholar] [CrossRef]
  121. Hu, Y.B.; Liu, J.Q.; Ling, M.X.; Liu, Y.; Ding, X.; Liu, D.Y.; Sun, W.D. Constraints on the origin of adakites and porphyry Cu-Mo mineralization in Chongjiang, Southern Gangdese, the Tibetan Plateau. Lithos 2017, 292, 424–436. [Google Scholar] [CrossRef]
  122. Jiang, H.; Yang, F.; Xu, Z.; Li, W.; Wang, X.; Liu, A.; Jiang, L.; Li, S.; Jiang, X.; Yan, Q.; et al. The origin of Gangjiang adakite-like intrusions and associated porphyry Cu–Mo mineralization in the central Gangdese porphyry Cu belt, southern Tibet. Ore Geol. Rev. 2024, 172, 106190. [Google Scholar] [CrossRef]
  123. Yang, Z.-M.; Lu, Y.-J.; Hou, Z.-Q.; Chang, Z.-S. High-Mg diorite from Qulong in southern Tibet: Implications for the genesis of adakite-like intrusions and associated porphyry Cu deposits in collisional orogens. J. Pet. 2015, 56, 227–254. [Google Scholar] [CrossRef]
  124. Yang, Z.M.; Goldfarb, R.; Chang, Z.S. Generation of postcollisional porphyry copper deposits in southern Tibet triggered by subduction of the Indian continental plate. Soc. Econ. Geol. Spec. Publ. 2016, 19, 279–300. [Google Scholar]
  125. Ou, Q.; Wang, Q.; Wyman, D.A.; Zhang, H.X.; Yang, J.H.; Zeng, J.P.; Hao, L.-L.; Chen, Y.-W.; Liang, H.; Qi, Y. Eocene adakitic porphyries in the central-northern Qiangtang Block, central Tibet: Partial melting of thickened lower crust and implications for initial surface uplifting of the plateau. J. Geophys. Res. Solid Earth 2017, 122, 1025–1053. [Google Scholar] [CrossRef]
  126. Naqvi, S.M.; Sarma, D.S.; Sawkar, R.H.; Mohan, M.R.; Prathap Rana, J.G.R. Role of adakitic magmatism and subduction in gold environment of Dharwar Neoarchaean greenstone belts, India. J. Geol. Soc. India 2008, 71, 875–888. [Google Scholar]
  127. González-Partida, E.; LeVresse, G.; Carrillo-Chávez, A.; Cheilletz, A.; Gasquet, D.; Jones, D. Paleocene adakite Au–Fe bearing rocks, Mezcala, Mexico: Evidence from geochemical characteristics. J. Geochem. Explor. 2003, 80, 25–40. [Google Scholar] [CrossRef]
  128. Polat, A.; Kerrich, R. Archean greenstone belt magmatism and the continental growth–mantle evolution connection: Constraints from Th–U–Nb–LREE systematics of the 2.7 Ga Wawa Subprovince, Superior Province, Canada. Earth Planet. Sci. Lett. 2000, 175, 41–54. [Google Scholar] [CrossRef]
  129. Polat, A.; Kerrich, R. Magnesian andesites, Nb-enriched basalt-andesites, and adakites from late-Archean 2.7 Ga Wawa Greenstone Belts, Superior Province, Canada: Implications for late Archean subduction zone petrogenetic processes. Contrib. Miner. Pet. 2001, 141, 36–52. [Google Scholar] [CrossRef]
  130. Bourdon, E.; Eissen, J.-P.; Gutscher, M.-A.; Monzier, M.; Samaniego, P.; Robin, C.; Bollinger, C.; Cotten, J. Slab melting and slab melt metasomatism in the Northern Andean Volcanic Zone : Adakites and high-Mg andesites from Pichincha volcano (Ecuador). BSGF-Earth Sci. Bull. 2002, 173, 195–206. [Google Scholar] [CrossRef]
  131. Chiaradia, M.; Müntener, O.; Beate, B. Enriched basaltic andesites from mid-crustal fractional crystallization, recharge, and assimilation (Pilavo Volcano, Western Cordillera of Ecuador). J. Pet. 2011, 52, 1107–1141. [Google Scholar] [CrossRef]
  132. Gao, Y.; Hou, Z.; Wei, R.; Zhao, R. Post-collisional adakitic porphyries in Tibet: Geochemical and Sr-Nd-Pb isotopic constraints on partial melting of oceanic lithosphere and crust-mantle interaction. Acta Geol. Sin. Geol. 2003, 77, 194–203. [Google Scholar] [CrossRef]
  133. Gao, Y.; Hou, Z.; Kamber, B.S.; Wei, R.; Meng, X.; Zhao, R. Adakite-like porphyries from the southern Tibetan continental collision zones: Evidence for slab melt metasomatism. Contrib. Miner. Pet. 2007, 153, 105–120. [Google Scholar] [CrossRef]
  134. Feizi, F.; Karbalaei-Ramezanali, A.A.; Farhadi, S. Application of multivariate regression on magnetic data to determine further drilling site for iron exploration. Open Geosci. 2021, 13, 138–147. [Google Scholar] [CrossRef]
  135. Karbalaeiramezanali, A.; Parsa, M.; Lentz, D.R.; Thorne, K.G. Prospectivity modeling of Devonian intrusion-related W–Mo–Sb–Au deposits in the Pokiok Plutonic Suite, West-Central New Brunswick, Canada, using a Monte Carlo-based framework. Nat. Resour. Res. 2025, 34, 669–702. [Google Scholar] [CrossRef]
  136. Dramsch, J.S. 70 years of machine learning in geoscience in review. Adv. Geophys. 2020, 61, 1–55. [Google Scholar] [CrossRef]
  137. Karpatne, A.; Ebert-Uphoff, I.; Ravela, S.; Babaie, H.A.; Kumar, V. Machine learning for the geosciences: Challenges and opportunities. IEEE Trans. Knowl. Data Eng. 2018, 31, 1544–1554. [Google Scholar] [CrossRef]
  138. Bergen, K.J.; Johnson, P.A.; de Hoop, M.V.; Beroza, G.C. Machine learning for data-driven discovery in solid Earth geoscience. Science 2019, 363, eaau0323. [Google Scholar] [CrossRef]
Figure 1. Location of New Brunswick within Canada’s physiogaphic regions [34] and a regional map of the New Brunswick Appalachians, illustrating the distribution of Devonian mafic-to-felsic granitoids and major faults (modified from [9,35]). Granitic rocks, highlighted in red text, exhibit fertile adakitic characteristics.
Figure 1. Location of New Brunswick within Canada’s physiogaphic regions [34] and a regional map of the New Brunswick Appalachians, illustrating the distribution of Devonian mafic-to-felsic granitoids and major faults (modified from [9,35]). Granitic rocks, highlighted in red text, exhibit fertile adakitic characteristics.
Minerals 15 00372 g001
Figure 2. Outcrops of (a) Rivière-Verte porphyry and (b) Evandale Granodiorite, both exhibiting adakite characteristics, as examples of fertile adakites in New Brunswick. Fazilat Yousefi provides scale in (a), while David Lentz is included for scale in (b). The Rivière-Verte porphyry is a light to medium grey granodiorite porphyry with 20–30% plagioclase and 5–10% quartz and biotite in an aphanitic groundmass [28]. The Evandale Granodiorite is a medium-grained equigranular hornblende–biotite granodiorite, locally grading to monzogranite, and is cut by narrow aplite dykes [30].
Figure 2. Outcrops of (a) Rivière-Verte porphyry and (b) Evandale Granodiorite, both exhibiting adakite characteristics, as examples of fertile adakites in New Brunswick. Fazilat Yousefi provides scale in (a), while David Lentz is included for scale in (b). The Rivière-Verte porphyry is a light to medium grey granodiorite porphyry with 20–30% plagioclase and 5–10% quartz and biotite in an aphanitic groundmass [28]. The Evandale Granodiorite is a medium-grained equigranular hornblende–biotite granodiorite, locally grading to monzogranite, and is cut by narrow aplite dykes [30].
Minerals 15 00372 g002
Figure 3. Schematic diagram illustrating the methodology utilized in this study.
Figure 3. Schematic diagram illustrating the methodology utilized in this study.
Minerals 15 00372 g003
Figure 4. Plot of scores versus ranks from Table 2, with standard deviation classification: Class 1 ( X ¯ + 2σ to maximum score) in red, Class 2 ( X ¯ + 1σ to X ¯ + 2σ) in orange, Class 3 ( X ¯ to X ¯ + 1σ) in green, and Class 4 (minimum score to X ¯ ) in blue dots.
Figure 4. Plot of scores versus ranks from Table 2, with standard deviation classification: Class 1 ( X ¯ + 2σ to maximum score) in red, Class 2 ( X ¯ + 1σ to X ¯ + 2σ) in orange, Class 3 ( X ¯ to X ¯ + 1σ) in green, and Class 4 (minimum score to X ¯ ) in blue dots.
Minerals 15 00372 g004
Figure 5. Best scatter plots selected from the 1596 plots for distinguishing fertile and barren adakites in New Brunswick based on LDA: best plots of elements (ppm) vs. elements (ppm): (a) Ga-Dy, (b) Ga-Gd, (c) Pr-Gd; best plots of elements (ppm) vs. major oxides (wt.%): (d) Fe2O3-Gd, (e) Al2O3-Hf, (f) K2O-Hf; and best plots of elements (ppm) vs. ratios: (g) La/Sm-Gd, (h) Rb/Sr-Hf, (i) La/Sm-Dy. The boundaries between classes are highlighted with a dashed black line. Covariance ellipses illustrate data distributions: the red ellipse represents fertile samples, the blue ellipse represents barren samples, and the black ellipse depicts the combined distribution of both classes.
Figure 5. Best scatter plots selected from the 1596 plots for distinguishing fertile and barren adakites in New Brunswick based on LDA: best plots of elements (ppm) vs. elements (ppm): (a) Ga-Dy, (b) Ga-Gd, (c) Pr-Gd; best plots of elements (ppm) vs. major oxides (wt.%): (d) Fe2O3-Gd, (e) Al2O3-Hf, (f) K2O-Hf; and best plots of elements (ppm) vs. ratios: (g) La/Sm-Gd, (h) Rb/Sr-Hf, (i) La/Sm-Dy. The boundaries between classes are highlighted with a dashed black line. Covariance ellipses illustrate data distributions: the red ellipse represents fertile samples, the blue ellipse represents barren samples, and the black ellipse depicts the combined distribution of both classes.
Minerals 15 00372 g005
Figure 6. Stacked bar chart of 829 adakite geochemical analyses [56] showing the number and percentage of samples predicted as fertile and barren by each ML method.
Figure 6. Stacked bar chart of 829 adakite geochemical analyses [56] showing the number and percentage of samples predicted as fertile and barren by each ML method.
Minerals 15 00372 g006
Table 1. Geochronological data and mineral occurrences of Devonian intrusions in New Brunswick [42]. Those intrusions with a dash in the mineral occurrence column indicate that they do not have significant mineral occurrences.
Table 1. Geochronological data and mineral occurrences of Devonian intrusions in New Brunswick [42]. Those intrusions with a dash in the mineral occurrence column indicate that they do not have significant mineral occurrences.
IntrusionAgeMineral Occurrence
Nashwaak420.7 ± 1.8 Ma, U-Pb zircon, Late Silurian-Early Devonian [43]
Mulligan Gulch419 ± 1 Ma, U-Pb zircon, Early Devonian [44]Au
Meto’mqwijuig Mountain415 ± 0.5 Ma, U-Pb zircon, Early Devonian [24]
Hartfield415 ± 2 Ma, U-Pb titanite, Early Devonian [31]Cu-Au-Mo
Hawkshaw411 ± 1 Ma, U-Pb on titanite, Early Devonian [45]W-Mo-Au
Skiff Lake409 ± 2 Ma, U-Pb zircon, Early Devonian [31]Mo
Magaguadavic403 ± 2 Ma, U-Pb zircon, Early Devonian [26]Cu-Mo-Au
Allandale402 ± 1 Ma, U-Pb monazite, Early Devonian [31]Be-W-Au
Blue Mountain Granodiorite Suite400.7 ± 0.4 Ma, U-Pb zircon, Early Devonian [22]Cu, Au, Mo
Falls Creek394 ± 2 Ma, U-Pb zircon, Early Devonian (more details in [46])Mo, W
Evandale391.2 ± 3.2 Ma, U-Pb zircon, Middle Devonian [29]Cu-Mo
McKenzie Gulch dykes386.2 ± 3.1 and 386.4 ± 3.3 Ma, U-Pb zircon, Late Devonian [32]Cu-Ag-Au
Popelogan (Cu-Mo), which is related to the Red Brook Granodiorite383 + 1/−3 Ma, U-Pb zircon, Late Devonian [DL]Cu-Mo
Nicholas Denys381 ± 4 Ma, U-Pb zircon, Late Devonian [23]Mo-Cu-Fe
Sorrel Ridge378.5 ± 3.0 Ma, U-Pb zircon, Late Devonian [47]Cu-Mo, Sn, W
Rivière Verte368 ± 2 Ma, U-Pb zircon, Late Devonian [28]Cu-Mo
Patapedia364.4 ± 0.4 Ma, U-Pb zircon, Late Devonian (V. McNicoll, in [48])Cu-Zn-Pb
Eagle Lake360 ± 5 Ma, U-Pb zircon, Late Devonian [28]Cu-Mo-Au
Quisibis porphyryundatedCu-Mo
Sugarloafundated
Table 2. Results of the statistical analysis conducted to distinguish fertile and barren adakites based on geochemical variables.
Table 2. Results of the statistical analysis conducted to distinguish fertile and barren adakites based on geochemical variables.
RanksVariablesANOVAInfo. GainGain RatioGiniχ2ReliefFScores
1Gd233.7150.6180.3090.32476.4690.1860.982
2Dy135.9440.5670.2830.30674.2230.1100.803
3Hf116.3800.5940.2970.31485.7310.0730.797
4La123.1470.5430.2720.29478.7480.0710.749
5Ho126.7580.5240.2620.28767.6870.1050.746
6Ce118.8280.5140.2570.28174.2230.0800.723
7Th104.7410.5030.2520.27174.6780.0860.708
8Ga13.5010.4860.2440.26861.9200.1540.669
9Pr107.8230.4440.2220.24565.5750.0720.634
10Zr91.0490.3720.1860.21559.7620.0890.572
11Nd72.1050.3920.1960.21459.4400.0540.537
12U51.0100.3960.1980.21560.0000.0310.505
13Sm67.8360.3250.1630.17540.6690.0750.460
14Eu/Eu*47.8220.2890.1450.17239.1990.0570.406
15Rb55.7890.2520.1260.12530.3670.0910.381
16(Eu/Eu*)/Y30.1820.3020.1510.15931.5190.0500.372
17Ta52.1130.2770.1380.15736.6900.0310.366
18Rb/Sr19.5660.3080.1540.16342.8440.0150.361
19Sr59.7590.2110.1060.13236.0270.0710.358
20Ce/Nd0.6650.3010.1510.18249.8860.0000.354
21Rb/Th42.1070.2810.1410.17527.3120.0300.352
22Nb68.8890.2140.1070.12935.6230.0530.348
23Al2O345.8130.1880.0940.11632.2320.0970.343
24Cs41.1000.2190.1100.11827.0400.0780.331
25K2O/Na2O23.7020.2770.1380.15621.2070.0400.323
26Th/La35.4380.2330.1170.13633.2860.0350.317
27La/Sm45.1090.2130.1070.13336.3380.0260.310
28CaO18.5110.2280.1140.13322.1710.0660.307
29K2O22.3670.1980.0990.10515.6690.1090.305
30MnO44.0930.1840.0920.11329.3560.0640.303
31Sr/Y38.3220.1770.0890.10525.9770.0510.273
32SiO227.9110.1730.0870.10921.2070.0550.260
33Eu32.0050.1820.0910.09825.0210.0440.259
34Y/MgO11.9560.2010.1010.12733.2860.0120.258
35Fe2O3T32.7080.1240.0620.08211.6630.1130.256
36Y28.9250.1880.0940.09814.6610.0470.243
37MgO22.1920.1470.0730.09416.4990.0610.230
38Er24.2050.2010.1000.10710.9670.0290.228
39Yb27.6830.1700.0850.09414.6610.0310.216
40La/Yb25.9480.1210.0600.07114.6610.0670.209
41Lu16.3510.1890.0950.1163.5120.0230.201
42Nb/Y0.0860.1180.0590.0774.1280.0870.189
43Th/Ta10.0930.1330.0670.08623.6920.0120.180
44V15.6250.1250.0620.07914.4640.0310.175
45Nb/Ta0.6540.1420.0710.08822.8170.0070.173
46Ba16.6850.1220.0610.07211.8400.0350.169
47Zr/Nb4.6070.0360.0180.0243.9690.1120.143
48Na2O14.9820.0570.0290.0369.9630.0570.131
49P2O52.8410.0660.0330.0443.1330.0560.117
50Ce/Ce*11.4820.0850.0420.05213.4970.0100.116
51Sm/Yb1.5500.0960.0480.0641.5420.0210.108
52TiO25.7910.0730.0360.0480.1150.0270.092
53Cs/Th0.0500.0780.0390.0484.0720.0170.090
54Rb/Y3.8670.0460.0230.0316.4280.0270.080
55Zr/Sm2.3190.0040.0020.0030.2170.0740.072
56Ce/(Nd×Y)0.6650.0770.0390.0491.4790.0000.070
57Sr/MnO0.4360.0090.0040.0060.4880.0090.017
Table 3. Performance results of ML methods applied to predict fertile adakites on 165 geochemical analyses of adakites in NB.
Table 3. Performance results of ML methods applied to predict fertile adakites on 165 geochemical analyses of adakites in NB.
ModelAUCCAF1PrecisionRecallMCC
SVM0.910.880.890.880.890.87
Gradient boosting0.900.890.890.870.900.88
Random forest0.890.890.900.910.880.88
Neural network0.870.870.880.860.890.85
Decision tree0.880.880.870.860.890.86
AdaBoost0.880.870.880.850.880.85
Logistic regression0.880.850.860.840.870.82
Table 4. Geochemical analyses of 829 adakite samples, showing the number and percentage of samples predicted as fertile and barren by each ML method.
Table 4. Geochemical analyses of 829 adakite samples, showing the number and percentage of samples predicted as fertile and barren by each ML method.
MethodsFertileBarren
SVMNumber491338
%59.240.8
Gradient boostingNumber448381
%54.046.0
Random forestNumber491338
%59.240.8
Neural networkNumber382447
%46.153.9
Decision treeNumber484345
%58.441.6
AdaBoostNumber447382
%53.946.1
Logistic regressionNumber226603
%27.372.7
Table 5. Performance results of ML methods applied to predict 160 fertile adakite samples from around the world.
Table 5. Performance results of ML methods applied to predict 160 fertile adakite samples from around the world.
PlaceMineralizationReferenceNumber of Fertile SamplesTotal Number of Fertile SamplesMachine Learning MethodTrue Predicted as FertileAccuracy of Prediction (%)
South and Central TibetCu-Au Porphyry and Epithermal deposits[72,132,133]82160SVM15093.75
Dharwar Greenstone Belts of IndiaOrogenic Au deposits[126]17Random forest13685
Guerrero Terrane of Southwestern MexicoAu-Fe skarn deposits[127]18Gradient boosting13584.4
Superior Province in Canada (Ontario and Quebec)Porphyry-Epithermal-Skarn-REE deposits[128,129]28Neural network13584.4
The Pichincha Volcano in EcuadorCu-Au porphyry and epithermal deposits[130]2Decision tree13282.5
Sulu Belt in Eastern ChinaCu porphyry deposits[130]13AdaBoost13181.88
----Logistic regression8653.75
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Karbalaeiramezanali, A.; Yousefi, F.; Lentz, D.R.; Thorne, K.G. Machine Learning Classification of Fertile and Barren Adakites for Refining Mineral Prospectivity Mapping: Geochemical Insights from the Northern Appalachians, New Brunswick, Canada. Minerals 2025, 15, 372. https://doi.org/10.3390/min15040372

AMA Style

Karbalaeiramezanali A, Yousefi F, Lentz DR, Thorne KG. Machine Learning Classification of Fertile and Barren Adakites for Refining Mineral Prospectivity Mapping: Geochemical Insights from the Northern Appalachians, New Brunswick, Canada. Minerals. 2025; 15(4):372. https://doi.org/10.3390/min15040372

Chicago/Turabian Style

Karbalaeiramezanali, Amirabbas, Fazilat Yousefi, David R. Lentz, and Kathleen G. Thorne. 2025. "Machine Learning Classification of Fertile and Barren Adakites for Refining Mineral Prospectivity Mapping: Geochemical Insights from the Northern Appalachians, New Brunswick, Canada" Minerals 15, no. 4: 372. https://doi.org/10.3390/min15040372

APA Style

Karbalaeiramezanali, A., Yousefi, F., Lentz, D. R., & Thorne, K. G. (2025). Machine Learning Classification of Fertile and Barren Adakites for Refining Mineral Prospectivity Mapping: Geochemical Insights from the Northern Appalachians, New Brunswick, Canada. Minerals, 15(4), 372. https://doi.org/10.3390/min15040372

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop