Search Results (10)

Here, we present holistic targeting models for lithium–cesium–tantalum (LCT) pegmatites in Western Australia, the world’s largest supplier of hardrock lithium ores, and Ontario, an emerging hardrock lithium mining jurisdiction. In this study, the LCT pegmatite targeting models, informed by a review of this deposit type and framed in the context of a mineral system approach, served to identify a set of targeting criteria that are mappable in the publicly available exploration data for Western Australia and Ontario. This approach, which formed the basis for artificial intelligence (AI)-powered mineral potential modeling (MPM), using multiple, complimentary modeling techniques, not only delivered the first published regional-scale views of lithium potential across the Archean to Proterozoic terrains of Western Australia and Ontario, but it also delivered an effective framework for exploration and revealed hidden trends. For example, we identified a statistically verifiable proximity relationship between lithium, gold, and nickel occurrences and confirmed a significant size differential between LCT pegmatites in Western Australia and Ontario, with the former typically containing much larger resources than the latter. Overall, this regional-scale targeting study served to demonstrate the power of precompetitive, high-quality geoscience data, not only for regional-scale targeting but also for the development of camp-scale targets that have the resolution to be investigated using conventional prospecting techniques. Importantly, MPM does not generate ‘treasure maps’. Rather, MPM provides another tool in the ‘exploration toolbox’, and its output should be taken as the starting point for further investigations. Full article

Using mineral prospectivity mapping (MPM), the mineral systems approach enables the identification of geological indicators linked to ore formation. This approach streamlines exploration by minimizing the time and cost required to identify areas with the highest mineral potential. With its extensive till cover and dense forests limiting bedrock exposure, New Brunswick provides an ideal environment to test this approach. The New Brunswick portion of the Canadian Appalachians hosts a diverse range of gold deposits and occurrences that formed during various stages of the Appalachian orogeny. In northern New Brunswick and the adjacent Gaspé Peninsula, the Tobique–Chaleur Zone contains several orogenic and epithermal gold systems that are closely associated with a large-scale crustal fault and its offshoots, i.e., the long-lived trans-crustal Rocky Brook–Millstream Fault system. To identify favorable zones for epithermal gold mineralization in northwestern New Brunswick, this study employed MPM by translating key mineral system components—such as ore metal sources, fluid pathways, traps, and geological controls—into mappable criteria for regional-scale analysis. The data were modeled through the integration of knowledge-based and data-driven methods, including fuzzy logic, geometric average, and logistic regression approaches. The concentration–area (C–A) fractal model was applied to reclassify the final maps based on prospectivity values obtained from these three approaches, dividing the mineral prospectivity maps into six classes, with threshold values emphasizing high-favorability zones. The fuzzy overlay model had the highest predictive accuracy (AUC 0.97), followed by the geometric average model (AUC 0.93), whereas the logistic regression identified more tightly constrained high-potential zones. In the prospectivity models, known epithermal gold mineralization consistently overlaps with regions of high favorability. This suggests a positive result from the use of MPM, indicating that this approach could be applicable to other regions and types of ore deposits. Full article

The Xiahe-Hezuo area in Gansu Province, China, located in the West Qinling Metallogenic Belt, is characterized by complex regional geological structures and abundant mineral resources. A number of gold-polymetallic deposits have been identified in this region, demonstrating significant potential for gold-polymetallic mineral prospecting within the metallogenic belt. This study focuses on regional Mineral Prospectivity Mapping (MPM) in the Xiahe-Hezuo area. To address the common challenge of small-sample data limitations in geological prediction, we introduce a Wasserstein Generative Adversarial Network with gradient penalty (WGAN-GP) to generate high-fidelity geological feature samples, effectively expanding the training dataset. A Convolutional Neural Network (CNN) was used to train and predict on both pre- and post-augmentation data. The experimental results show that, before augmentation, the CNN model’s Receiver Operating Characteristic (ROC) value was 0.9648. After data augmentation with the WGAN-GP, the CNN model’s ROC value improved to 0.9792. Additionally, the CNN model’s classification performance was significantly enhanced, with the training set accuracy increasing by 5% and the test set accuracy improving by 2%, successfully overcoming the issue of insufficient model generalization caused by small sample sizes. The mineralization prediction results based on data augmentation delineate five prospective mineralization targets, whose spatial distribution exhibits strong correlations with known deposits and fault structural belts, confirming the reliability of the predictions. This study validates the effectiveness of data augmentation techniques in MPM and provides a transferable technical framework for MPM in data-scarce regions. Full article

Random Forest classification was applied to create mineral prospectivity maps (MPM) for orogenic gold in the Rainy River area of Ontario, Canada. Geological and geophysical data were used to create 36 predictive maps as RF algorithm input. Eighty-three (83) orogenic gold prospects/occurrences were used to train the classifier, and 33 occurrences were used to validate the model. The non-Au (negative) points were randomly selected with or without spatial restriction. The prospectivity mapping results show high performance for the training and test data in area-frequency curves. The F1 accuracy is high and moderate when assessed with the training and test data, respectively. The mean decrease accuracy was applied to calculate the variable importance. Density, proximity to lithological contacts, mafic to intermediate volcanics, analytic signal, and proximity to the Cameron-Pipestone deformation zone exhibit the highest variable importance in both models. The main difference between the models is in the uncertainty maps, in which the high-potential areas show lower uncertainty in the maps created with spatial restriction when selecting the negative points. Full article

The development of mineral prospectivity mapping (MPM), which aims to outline and prioritize mineral exploration targets, has been spurred by advances in data-driven machine learning algorithms. Supervised data-driven MPM is a typical few-shot task, suffering from a scarcity of labeled data, the over-fitting of models and an uncertainty of predictions. The main objective of this contribution is to propose a robust framework of few-shot learning (FSL), combining data augmentation and transfer learning to enable the generation of prospectivity models with excellent predictive efficiency and low uncertainty. The mineral systems approach was used to transfer a conceptual mineral system into mappable exploration criteria. Synthetic minority over-sampling technique (SMOTE) was employed to augment and balance the labeled dataset, allowing for model pre-training with the large synthetic training dataset of a source domain. The knowledge derived from pre-trained models was then transferred to the target domain by fine-tuning, and the prospectivity model was generated in light of over-fitting and uncertainty assessments. The proposed FSL framework was applied to tungsten prospectivity mapping in southern Jiangxi Province. The results indicated that the SMOTE-ed balanced dataset boosted the classification accuracy in the training process. The FSL models yielded an arch-shaped prediction point pattern which was favorable for focusing potential targets with high probability and low uncertainty. The FSL models achieved a high predictive performance (test AUC = 0.9172) and the lowest quantitative over-fitting value compared to the models derived from the benchmark algorithms of random forest and support vector machine. Four levels of potential targeting zones, considering both predictive efficiency and uncertainty, were extracted from the resulting FSL prospectivity map. The final high-potential and low-risk exploration targets only cover 4.27% of the area, but capture 41.53% of known tungsten deposits, thus achieving a superior predictive performance. This study highlights the capability of FSL framework to control over-fitting and generate high-confidence exploration targets with low levels of uncertainty. Full article

As the need to discovers new mineral deposits and occurrences has intensified in recent years, it has become increasingly apparent that we need to map potentials via integrated information on the basis of metallogeny. Occurrences of mineralization such as tungsten (W), tin (Sn), columbium (Nb), tantalum (Ta), gold (Au), copper (Cu), lead (Pb), zinc (Zn), manganese (Mn) and monazite (Mnz) have been discovered in Rwanda. The objective of this study was to present a regional quantitative mineral prospectivity mapping (MPM) of W, Sn and Nb-Ta mineralization in Rwanda using the random forest (RF) method on the basis of open source data, such as geological maps, Bouguer gravity anomalies, magnetic anomalies, Landsat 8 images, ASTER GDEM, Globeland30, and OpenStreetMap. In addition, a newly introduced interpolation–density–delineation (IDD) process was applied to deal with the blank (masked) areas in remotely sensed mineral alteration extraction. Additionally, a k²-fold cross-validation method was also proposed to obtain more reasonable test errors. Firstly, the metallogenic regularity of W, Sn and Nb-Ta in Rwanda was summarized with the help of articles online. Secondly, original geological, geophysical, and remote sensing data were utilized to generate secondary data. Specifically, the IDD process was applied subsequent to the directed principal component analysis method (DPCA) to reconstruct the alteration anomaly map, and a relevant dataset was formed by the combination of original and secondary data. Thirdly, specific predictor layers for W, Sn and Nb-Ta were selected from relevant data via spatial correlation with known deposits, respectively, and the predictive models were established. Finally, near 26,000 squares were zoned in Rwanda, and RF was optimized and applied, the k²-fold cross-validation method was utilized to assess test errors, metallogenic belts and prospective areas for W, Sn, and Nb-Ta were delineated on the basis of total mineralization potential map and likelihoods map. Results proved that the open source data online were valid for drawing a preliminary mineralization potential map. Furthermore, it was also shown that the IDD method is suitable for the postprocessing of masked alteration anomaly maps. Belt IV-4 in the northwest and belt IV-2, IV-1 in the middle-east of Rwanda, containing a number of prospective areas, possess considerable likelihoods of deposits, and mining in Rwanda is at its dawn, with potential worth expecting. Full article

The weak classifier ensemble algorithms based on the decision tree model, mainly include bagging (e.g., fandom forest-RF) and boosting (e.g., gradient boosting decision tree, eXtreme gradient boosting), the former reduces the variance for the overall generalization error reduction while the latter focuses on reducing the overall bias to that end. Because of its straightforward idea, it is prevalent in MPM (mineral prospectivity mapping). However, an inevitable problem in the application of such methods is the hyperparameters tuning which is a laborious and time-consuming task. The selection of hyperparameters suitable for a specific task is worth investigating. In this paper, a tree Parzen estimator-based GBDT (gradient boosting decision tree) model (TPE-GBDT) was introduced for hyperparameters tuning (e.g., loss criterion, n_estimators, learning_rate, max_features, subsample, max_depth, min_impurity_decrease). Then, the geological data of the gold deposit in the Xiong ‘ershan area was used to create training data for MPM and to compare the TPE-GBDT and random search-GBDT training results. Results showed that the TPE-GBDT model can obtain higher accuracy than random search-GBDT in a shorter time for the same parameter space, which proves that this algorithm is superior to random search in principle and more suitable for complex hyperparametric tuning. Subsequently, the validation measures, five-fold cross-validation, confusion matrix and success rate curves were employed to evaluate the overall performance of the hyperparameter optimization models. The results showed good scores for the predictive models. Finally, according to the maximum Youden index as the threshold to divide metallogenic potential areas and non-prospective areas, the high metallogenic prospect area (accounts for 10.22% of the total study area) derived by the TPE-GBDT model contained > 90% of the known deposits and provided a preferred range for future exploration work. Full article

The Middle–Lower Yangtze River Metallogenic Belt is an important copper and iron polymetallic metallogenic belt in China. Today’s economic development is inseparable from the support of metal mineral resources. With the continuous exploitation of shallow and easily identifiable mines in China, the prospecting work of deep and hidden mines is very important. Mineral prospectivity modeling (MPM) is an important means to improve the efficiency of mineral exploration. With the increase in resource demands and exploration difficulty, the traditional 2DMPM is often difficult to use to reflect the information of deep mineral deposits. More large-scale deposits are needed to carry out 3DMPM research. With the rise of artificial intelligence, the combination of machine learning and geological big data has become a hot issue in the field of 3DMPM. In this paper, a case study of 3DMPM is carried out based on the Xuancheng–Magushan area’s actual data. Two machine learning methods, the random forest and the logistic regression, are selected for comparison. The results show that the 3DMPM based on random forest method performs better than the logistic regression method. It can better characterize the corresponding relationship between the geological structure combination and the metallogenic distribution, and the accuracy in the test set reaches 96.63%. This means that the random forest model could provide more effective and accurate support for integrating predictive data during 3DMPM. Finally, five prospecting targets with good metallogenic potential are delineated in the deep area of the Xuancheng–Magushan area for future exploration. Full article

Mineral prospectivity mapping (MPM), like other geoscience fields, is subject to a variety of uncertainties. When data about unfavorable sites to find deposits (i.e., drill intersections to barren rocks) is lacking in MPM using machine learning (ML) methods, the synthetic generation of negative datasets is required. As a result, techniques for selecting point locations to represent negative examples must be employed. Several approaches have been proposed in the past; however, one can never be certain that the points chosen are true negatives or, at the very least, optimal for training. As a consequence, methodologies that account for the uncertainty of the generation of negative datasets in MPM are needed. In this paper, we compare two criteria for selecting negative examples and quantify the uncertainty associated with this process by generating 400 potential maps for each of the three ML methods utilized (200 maps for each criterion), which include random forest (RF), support vector machine (SVM), and k-nearest neighbors (KNC). The results showed that applying a geological constraint to the creation of negative datasets reduced prediction uncertainty and improved overall model performance but produced larger areas of very high probability (i.e., >0.9) when compared to using only the spatial distribution of known deposits and occurrences as a constraint. SHAP values were used to find approximations for the importance of features in nonlinear methods, and kernel density estimations were used to examine how they varied depending on the negative dataset used to train the ML models. Prospectivity models for magmatic-hydrothermal gold deposits were generated using data from the shuttle radar terrain mission, gamma-ray, magnetic lineaments, and proximity to dykes. The Juruena Mineral Province, situated in Northern Mato Grosso, Brazil, represented the case study for this work. Full article

Mineral prospectivity mapping (MPM) needs robust predictive techniques so that the target zones of mineral deposits can be accurately delineated at a specific location. Although an individual machine learning algorithm has been successfully applied, it remains a challenge because of the complicated non-linear relations between prospecting factors and deposits. Ensemble learning methods were efficiently applied for their excellent generalization, but their potential has not been fully explored in MPM. In this study, three well-known machine learning models, namely random forest (RF), support vector machine (SVM), and the maximum entropy model (MaxEnt), were fused into ensembles (i.e., RF–SVM, RF–MaxEnt, SVM–MaxEnt, RF–SVM–MaxEnt) to produce a final prediction. The paper aims to investigate the potential application of stacking ensemble learning methods (SELM) for MPM. In this study, 69 hydrothermal gold deposits were split into two parts: 70% for the training model and 30% for testing the model. Then, 11 mineral prospecting factors were selected as a spatial dataset constructed for MPM. Finally, the models’ performance was assessed using the receiver operating characteristic (ROC) curves and five statistical metrics. Compared with other single methods, the SELM framework showed an improved predictive performance in the model evaluation. Therefore, this finding suggests that the SELM framework is promising and should be selected as an alternative technique for MPM. Full article