A prospecting cost-benefit strategy for mineral potential mapping based on ROC curve analysis

Yongliang, Chen; Wu, Wei

doi:10.1016/j.oregeorev.2015.11.011

Cited by 72 publications

(29 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…i.e., the stronger the spatial association is between the discovered polymetallic deposits and the buffered linear features (Chen, 2015;Chen and Wu;.…”

Section: Geological Map Patternmentioning

confidence: 99%

“…Among these classified results, the optimally classified multivariate geochemical anomalies have the strongest spatial association with the discovered polymetallic deposits. According to Chen (2015) and Chen and Wu (2016), the Youden index can be applied to express spatial association…”

Section: Accepted Manuscriptmentioning

confidence: 99%

“…According to Chen (2015) and Chen and Wu (2016), the Youden index can be used to measure spatial association between a binary map pattern and the discovered polymetallic deposits. A map pattern, which is significant for mapping polymetallic prospectivity, should have a positive Youden index.…”

Section: Map Pattern Selectionmentioning

confidence: 99%

“…Both ROC curves and AUCs can be applied to measure the performance of mineral prospectivity mapping models by replacing the sensitivity and false alarm rate used in ROC curve analysis with the benefit and cost used in mapping mineral prospectivity (Chen, 2015;Chen and Wu, 2016). In this study, ROC curves and AUCs were applied to evaluate the performance of the ELM-regression-based and logistic-regression-based models in mapping polymetallic prospectivity.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…The polymetallic prospectivity mapping results and the 1,000 thresholds defined in Sections 3.9 were also used to estimate the overall performances of AUCs, S AUC s, and Z AUC s. For methods to estimate AUC, S AUC , and Z AUC , please see Chen (2015) and Chen and Wu (2016). Based on the polymetallic prospectivities predicted by the ELM-regression-based and logistic-regression-based models, AUCs, S AUC s, and Z AUC s were estimated and listed in Table 5.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

See 4 more Smart Citations

Mapping mineral prospectivity using an extreme learning machine regression

Yongliang

2017

Ore Geology Reviews

Self Cite

128

View full text Add to dashboard Cite

“…i.e., the stronger the spatial association is between the discovered polymetallic deposits and the buffered linear features (Chen, 2015;Chen and Wu;.…”

Section: Geological Map Patternmentioning

confidence: 99%

Section: Accepted Manuscriptmentioning

confidence: 99%

Section: Map Pattern Selectionmentioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

Section: Accepted Manuscriptmentioning

confidence: 99%

See 3 more Smart Citations

Mapping mineral prospectivity using an extreme learning machine regression

Yongliang

2017

Ore Geology Reviews

Self Cite

128

View full text Add to dashboard Cite

Mineral prospectivity mapping of tungsten polymetallic deposits using machine learning algorithms and comparison of their performance in the Gannan region, China

Liu

Yonghang

2022

Preprint

View full text Add to dashboard Cite

The current study aimed at assessing the capabilities of five machine learning models in term of mapping tungsten polymetallic prospectivity in the Gannan region of China. The five models include logistic regression (LR), support vector machine (SVM), random forest (RF), convolutional neural network (CNN), and light gradient boosting machine (LGBM) models. Geochemical, lithostratigraphic, and structural datasets were used to generate 16 evidential maps, which were integrated into the machine learning models. Tungsten polymetallic deposits were randomly separated into two parts: 80% for training and 20% for validating. Performances of the models were evaluated through receiver operating characteristic (ROC) and K-fold cross validation, with an emphasis on the variable influence within different machine learning methods. The results show that the models are especially sensitive to the chemical elements: Be, Bi, Pb and Cd, implying that these are closely related to tungsten polymetallic mineralization. Compared to other models, the LGBM and CNN models performed best, while the LR model was the most stable. The results also indicated that the CNN model can predict maximum known deposits within a minimum area, based on the prediction-area plot analysis of the five models, while the RF model can capture the most well-known deposits within the smallest study area. Finally, eighteen prospective areas were delineated according to the predicting results of the machine learning models, which will provide important guidance for further tungsten polymetallic exploration and associated studies.

show abstract