Orogenic gold prospectivity mapping using machine learning

Predictive mapping of prospectivity for orogenic gold, Giyani greenstone belt (South Africa)

The exploration of buried mineral deposits is required to generate innovative approaches and the integration of multi-source geoscientific datasets. Mining geochemistry methods have been generated based on the theory of multi-formational geochemical dispersion haloes. Satellite remote sensing data is a form of surficial geoscience datasets and can be considered as big data in terms of veracity and volume. The different alteration zones extracted using remote sensing methods have not been yet categorized based on the mineralogical and geochemical types (MGT) of anomalies and cannot discriminate blind mineralization (BM) from zone dispersed mineralization (ZDM). In this research, an innovative approach was developed to optimize remote sensing-based evidential variables using some constructed mining geochemistry models for a machine learning (ML)-based copper prospectivity mapping. Accordingly, several main steps were implemented and analyzed. Initially, the MGT model was executed by studying the distribution of indicator elements of lithogeochemical data extracted from 50 copper deposits from Commonwealth of Independent States (CIS) countries to identify the MGT of geochemical anomalies associated with copper mineralization. Then, the geochemical zonality model was constructed using the database of the porphyry copper deposits of Iran and Kazakhstan to evaluate the geochemical anomalies related to porphyry copper mineralization (e.g., the Saghari deposit located around the Chah-Musa deposit, Toroud-Chah Shirin belt, central north Iran). Subsequently, the results of mining geochemistry models were used to produce the geochemical evidential variable by vertical geochemical zonality (Vz) (Pb × Zn/Cu × Mo) and to optimize the remote sensing-based evidential variables. Finally, a random forest algorithm was applied to integrate the evidential variables for generating a provincial-scale prospectivity mapping of porphyry copper deposits in the Toroud-Chah Shirin belt. The results of this investigation substantiated that the machine learning (ML)-based integration of multi-source geoscientific datasets, such as mining geochemistry techniques and satellite remote sensing data, is an innovative and applicable approach for copper mineralization prospectivity mapping in metallogenic provinces.

Lithological mapping is a critical aspect of geological mapping that can be useful in studying the mineralization potential of a region and has implications for mineral prospectivity mapping. This is a challenging task if performed manually, particularly in highly remote areas that require a large number of participants and resources. The combination of machine learning (ML) methods and remote sensing data can provide a quick, low-cost, and accurate approach for mapping lithological units. This study used deep learning via convolutional neural networks and conventional ML methods involving support vector machines and multilayer perceptron to map lithological units of a mineral-rich area in the southeast of Iran. Moreover, we used and compared the efficiency of three different types of multispectral remote-sensing data, including Landsat 8 operational land imager (OLI), advanced spaceborne thermal emission and reflection radiometer (ASTER), and Sentinel-2. The results show that CNNs and conventional ML methods effectively use the respective remote-sensing data in generating an accurate lithological map of the study area. However, the combination of CNNs and ASTER data provides the best performance and the highest accuracy and adaptability with field observations and laboratory analysis results so that almost all the test data are predicted correctly. The framework proposed in this study can be helpful for exploration geologists to create accurate lithological maps in other regions by using various remote-sensing data at a low cost.

The Hatu region in the Western Junggar, Xinjiang, is one of the most significant gold metallogenic concentration areas in China. Gold mineralization is primarily controlled by several parallel NE-trending strike-slip faults and Late Paleozoic granitic plutons, accompanied by multiple stages of hydrothermal activity. To enhance the objectivity and accuracy of mineral prospecting prediction, this study develops an integrated forecasting framework that combines multi-source remote sensing datasets with machine learning techniques. Alteration anomalies related to iron staining and hydroxyl-bearing minerals are extracted from ASTER data, alteration mineral mapping is performed using GF-5 hyperspectral imagery, and Landsat-9 data is used for structural interpretation to refine the regional metallogenic framework. On this basis, these multi-source remote sensing products are then integrated to delineate five prospective metallogenic areas (T1–T5). Subsequently, a Random Forest (RF) model optimized by the Grey Wolf Optimizer (GWO) algorithm is employed to quantitatively integrate key evidence layers, including alteration, structure, and geochemistry, for estimating mineralization probability. The results show that the GWO-RF model effectively concentrates anomalous areas and identifies two high-confidence targets, Y1 and Y2, both with mineralization probabilities exceeding 0.8. Among them, the Y1 target is associated with the Bieluagaxi pluton and exhibits strong montmorillonitization, chloritization, and iron-staining alteration, typical for magmatic–hydrothermal controlled mineralization. In contrast, the Y2 target is strictly controlled by the Anqi Fault and its subsidiary faults, primarily characterized by linear chloritization and iron-staining anomalies indicative of structure–hydrothermal mineralization. Field verification confirms the significant metallogenic potential of both Y1 and Y2, demonstrating the effectiveness of integrating multi-source remote sensing and machine learning for predicting orogenic gold systems. This approach not only deepens the understanding of the diverse gold mineralization processes in the Western Junggar but also provides a transferable methodology and case study for improving regional mineral exploration accuracy.

In recent years, machine learning (ML) has been extensively used for the quantitative prediction of mineral resources. However, the accuracy of prediction models is often influenced by data quality, feature selection, and algorithm limitations. This research investigates the benefits of data-driven feature optimization techniques in enhancing model accuracy. Using the Lhasa region in Tibet as the study area, this research applies ensemble learning methods, such as random forest and gradient boosting tree techniques, to optimize 43 feature variables encompassing geology, geochemistry, and geophysics. The optimized feature variables are then input into a support vector machine (SVM) model to generate a prospectivity map. The performance characteristics of the SVM, RF_SVM, and GBDT_SVM models are evaluated using ROC curves. The results indicate that the feature-optimized GBDT_SVM model achieves superior classification accuracy and prediction effectiveness, demonstrating that feature optimization is a necessary step for mineral prospectivity mapping, as it can significantly improve the performance of mineral prospectivity prediction.

GIS-based mineral prospectivity mapping using machine learning methods: A case study from Tongling ore district, eastern China

Major mineral discoveries have declined in recent decades, and the natural resource industry is in the process of adapting and incorporating novel technologies such as machine learning and artificial intelligence to help guide the next generation of exploration. One such development is an artificial intelligence architecture called VNet that uses deep learning and convolutional neural networks. This method is designed specifically for use with geoscience data and is suitable for a multitude of exploration applications. One such application is mineral prospectivity in which the machine is tasked with identifying the complex pattern between many layers of geoscience data and a particular commodity of interest, such as gold. The VNet algorithm is designed to recognize patterns at different spatial scales, which lends itself well to the mineral prospectivity problem of there often being local and regional trends that affect where mineralization occurs. We test this approach on an orogenic gold greenstone belt setting in the Canadian Arctic where the algorithm uses gold values from sparse drill holes for training purposes to predict gold mineralization elsewhere in the region. The prospectivity results highlight new target areas, and one such target was followed up with a direct-current induced polarization survey. A chargeability anomaly was discovered wherein the VNet had predicted gold mineralization, and subsequent drilling encountered a 6 g/t Au intercept within 10 m of drilling that averaged more than 1.0 g/t Au. Although most of the prospectivity targets generated from VNet were not drill tested, this first intercept helps validate the approach. We believe this method can help maximize the use of existing geoscience data for successful and efficient exploration programs in the future.

One of the key objectives for mineral exploration is to map the most prospective areas for the selected deposit type at a regional scale, subsequently narrowing these down to camp size target areas and finally to individual prospects that can be developed into economic mines. Exploration targeting, at all scales, is constrained by conceptual mineral system models and requires the integration and interpretation of a variety of geophysical, geological and geochemical data. Geographic information system (GIS) applications are commonly used to integrate spatially referenced data sets to produce mineral prospectivity maps in support of the mineral exploration targeting process. A knowledge-driven fuzzy logic method is used in this work for data integration and prospectivity modelling for orogenic gold deposits in northern Finland. The modelling workflow is done in a stepwise manner at three scales. Each step simulates the successive stage used in mineral exploration from selecting the most prospective belt scale domain to the camp size target area and individual prospects. New, higher resolution data sets are added at each stage as is typically the case in mineral exploration. Northern Finland was selected as the test area due to the regional scale coverage of publicly available geoscientific data and its proven orogenic gold potential. The regional scale prospectivity map outlines the central part of the Paleoproterozoic Central Lapland Greenstone belt (CLGB) as the most prospective area for orogenic gold in northern Finland. The belt scale model of the CLGB improves the resolution mapping of several camp sized high prospectivity target areas. The camp scale model of one of these, a past producing mining camp, further narrows down the high prospectivity zones into prospect size targets. Three models have score Area Under Curve (AUC) values between 0.839 and 0.930 from the Receiver Operating Characteristic (ROC) method validation technique, indicating that the models are robust. The stepwise approach presented confirms that prospectivity mapping using the knowledge-driven fuzzy logic method is a scalable, flexible and relatively fast method which can be used for decision making at different stages of the exploration targeting process. Adding new data and rerunning the prospectivity model with the new data is fast and easy. The most important conclusion from the study is that remodelling individual regional and camp scale domains separately is highly recommended for mapping the most prospective target areas even if the data sets used are the same.

Approximately one-in-ten reproductive age adults in the USA follow a plant-based diet, yet there is limited information on the influence of vegan and vegetarian diets on the mineral composition of breast milk. This study explored the major and trace mineral composition in breast milk and associations with maternal diet patterns. We used a cross-sectional design to collect a single sample of breast milk from individuals following vegan (n 23), vegetarian (n 19) and omnivore (n 21) diet patterns. Plant-based diet (n 42) was defined as following either vegan or vegetarian diets. Sixteen minerals were assessed using inductively coupled plasma mass spectrometry and inductively coupled plasma optical emission spectrometry. Data were evaluated using traditional statistical techniques and five different machine learning approaches. The distribution of Se (median; quartile 1 and 3) was significantly different between groups (vegetarians 21, 18–26 µg/l; vegans 19, 18–25 µg/l and omnivores 17, 14–20 µg/l; P = 0·007) using a Kruskal–Wallis test. Machine learning techniques also identified Se as a potential biomarker for differentiating breast milk by maternal diet pattern. Individuals following a plant-based diet generally had a lower BMI, higher breast milk Se and lower breast milk I and Fe concentrations compared with those following omnivore diets. This suggests that maternal dietary pattern (plant-based v. omnivore) may be helpful clinical information to consider when caring for the breast-feeding dyad, with the strongest evidence related to differences in Se concentration.

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.

Predictive modelling of mineral prospectivity using satellite remote sensing and machine learning algorithms

A review on hyperspectral imagery application for lithological mapping and mineral prospecting: Machine learning techniques and future prospects

Regional till and weathered bedrock geochemical datasets provide a basis for data analysis and modelling in glaciated terrains. These large-scale surface geochemical datasets have great potential in mineral exploration, especially when machine learning and clustering methods are used to reduce the dimensionality of multivariate datasets. Here, self-organizing maps (SOMs) followed by k-means clustering were used to create SOMs of the target areas for initial modelling and prospectivity mapping of gold (Au) prospecting in central Lapland, northern Finland. Because the till and weathered bedrock datasets are legacy data, an effort was made to level the data between the map sheets. The targeting till geochemical dataset did not contain the typical indicator elements for Au. Instead, elements associated with the Au deposits, within the study area, were used. Indicator associations in this study were Ni–Co with possible Cu. Resulting elemental clusters from the SOMs were assigned as interesting clusters according to their distribution of elements. For the till, two potential clusters were identified: Ni–Co–Cr and Cu–V–Co. For the weathered bedrock, three clusters were specified: Ni–Co–Cr, V–Cu and Cu–Co. This study shows the potential of using legacy datasets for early targeting stages of mineral exploration, potentially reducing the footprint of mineral exploration.

Three-dimensional mineral prospectivity mapping Considering structural restoration in the Dayingezhuang gold Deposit, eastern china

Prospectivity Mapping of Minerals Based on PRISMA Shortwave Infrared Imaging Sensor and Machine Learning in the Bhilwara District, India