Search

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. [ABSTRACT FROM AUTHOR]

Predictive modelling of mineral prospectivity, a critical, but challenging procedure for delineation of undiscovered prospective targets in mineral exploration, has been spurred by recent advancements of spatial modelling techniques and machine learning algorithms. In this study, a set of machine learning methods, including random forest (RF), support vector machine (SVM), artificial neural network (ANN), and a deep learning convolutional neural network (CNN), were employed to conduct a data-driven W prospectivity modelling of the southern Jiangxi Province, China. A total of 118 known W occurrences derived from long-term exploration of this brownfield area and eight evidential layers of multi-source geoscience information related to W mineralization constituted the input datasets. This provided a data-rich foundation for training machine learning models. The optimal configuration of model parameters was trained by a grid search procedure and validated by 10-fold cross-validation. The resulting predictive models were comprehensively assessed by a confusion matrix, receiver operating characteristic curve, and success-rate curve. The modelling results indicate that the CNN model achieves the best classification performance with an accuracy of 92.38%, followed by the RF model (87.62%). In contrast, the RF model outperforms the rest of ML models in overall predictive performance and predictive efficiency. This is characterized by the highest value of area under the curve and the steepest slope of success-rate curve. The RF model was chosen as the optimal model for mineral prospectivity in this region as it is the best predictor. The prospective zones delineated by the prospectivity map occupy 9% of the study area and capture 66.95% of the known mineral occurrences. The geological interpretation of the model reveals that previously neglected Mn anomalies are significant indicators. This implies that enrichment of ore-forming material in the host rocks may play an important role in the formation process of wolframite and can represent an innovative exploration criterion for further exploration in this area. [ABSTRACT FROM AUTHOR]

Details on processes of the early-middle Paleozoic Wuyi–Yunkai orogeny in South China remain poorly defined. Most Silurian–Devonian granites in South China are S-type or I-type granites, which are suggested to be petrogenetically related to the Wuyi–Yunkai orogeny. This paper firstly reported a systematic study on two Devonian A-type granites in the central Jiangxi Province. LA-ICP-MS zircon U–Pb dating results imply that the Huitong and Epo granites were emplaced at about 415 Ma. Both of the two granites have the petrographic and geochemical characteristics of A-type granites. Interstitial biotites occur along the boundary of euhedral plagioclase and quartz and they formed later than plagioclase and quartz. It implies that the primary magma could have been anhydrous. Biotites from the two granites are Fe-rich and have high Fe 2 + /(Fe 2 + + Mg 2 + ) ratios (0.60–0.74). The magmatic temperatures estimated from zircon saturation thermometer are 802–920 °C for the two granites, higher than common I-type and S-type granites. The two granites show high contents of total alkalis (Na 2 O + K 2 O = 6.96–9.39 wt.%), high field strength elements (e.g. Zr = 181–437 ppm, Y = 22.1–39.7 ppm, Nb = 18.6–30.3 ppm and Zr + Nb + Ce + Y = 324–555 ppm), rare earth elements (total REE = 155–312 ppm) as well as high Ga/Al ratios (10,000 × Ga/Al = 2.50–3.44). These geochemical characteristics are similar to those of A-type granites. The Huitong and Epo granites have relatively low ε Nd (t) values of − 10.4 to − 7.7, and low zircon ε Hf (t) values (peak value of − 8.0). Whole-rock two stage Nd isotopic model ages and zircon Hf isotopic model ages mostly vary from 1.78 Ga to 2.00 Ga. According to these data, we suggest that the two granites might have derived from partial melting of pre-Cambrian sedimentary rocks which had been granulitized during an earlier thermal event. The two granites contain abundant contemporaneous mafic microgranular enclaves (MMEs). The MMEs display igneous textures and contain acicular apatites, suggesting quenching of mafic magmas that have co-mingled with the host granites. The MMEs might have derived from the enriched lithospheric mantle source. This study on the Devonian Huitong and Epo A-type granites, together with previous studies on Paleozoic granites in South China, indicated that the Wuyi–Yunkai orogeny in South China had changed from syn-collisional crustal thickening to post-collisional extension at least from 415 Ma. [ABSTRACT FROM AUTHOR]

This paper presents geochemical analyses of a lamprophyre intruding the Caledonian Doushui granite body in Shangyou County, southern Jiangxi Province. U-Pb dating and Hf-isotope analyses are especially carried out for zircons from it. Petrological and geochemical features show that the lamprophyre belongs to a high-K, weakly alkaline pyroxene-biotite lamprophyre. It is characterized by high Mg# (0.74), Ni (253 μg/g) and Cr (893 μg/g) contents, and also enriched in incompatible elements, such as REE, Rb, Sr, Ba and K. It is suggested that its primitive melt probably derived from enriched mantle metasomatized by non-crust-derived agent. Morphology and LAM-ICPMS dating results of zircons in the lamprophyre indicate that they are xenocrysts captured from deep crustal rocks. Most xenocrystic zircons formed at -.1.86 Ga, and a few in different Phanerozoic periods. The Paleoproterozoic zircons are of magmatic origin and have similar 176Hf/177Hf and 176Lu/177Hf ratios, indicating that they probably are from the same igneous basement rock. The ages and Hf-isotope compositions of zircons from this basement rock are similar to those of Paleoproterozoic Danzhu granite in the southern Zhejiang Province, but extremely distinguished from the Nanhing basement, suggesting that the study area probably is a westward extension part of Paleoproterozoic Wuyishan terrane in the eastern Cathaysia Block. These Paleoproterozoic zircons have low Hf-isotope compositions, characteristic of crustal source. Hf model ages of these zircons and the presence of older inherited cores within them, coupled with available other data reported by previous studies, suggest that the source of Paleoproterozoic magma is Neoarchaean crust, implying the existence of older basement in the Wuyishan terrane. U-Pb ages and Hf isotopes of five Phanerozoic zircons indicate that Paleoproterozoic basement underwent multi-reworking occurring in Caledonian, Indosinian and early Yanshanian, respectively. The Caledonian magmatism also involves reworking of juvenile crust. [ABSTRACT FROM AUTHOR]