Asset Details
Do you wish to reserve the book?
Determination of Predictive Variables in Mineral Prospectivity Mapping Using Supervised and Unsupervised Methods
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
Determination of Predictive Variables in Mineral Prospectivity Mapping Using Supervised and Unsupervised Methods
Do you wish to request the book?
Determination of Predictive Variables in Mineral Prospectivity Mapping Using Supervised and Unsupervised Methods
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
Determination of Predictive Variables in Mineral Prospectivity Mapping Using Supervised and Unsupervised Methods
2022
Overview
Machine learning methods have recently been used widely for mineral prospectivity mapping. However, few studies have focused on the determination of variables for mineral prospectivity prediction using such methods. Here, we present a comparative study using supervised and unsupervised methods to determine predictive variables (PVs). First, based on a mineral deposit model, 12 variables were created including information about granite, fault and strata, and information from geochemical and geophysical surveys. Second, recursive feature elimination (RFE) and sparse principal components analysis (SPCA) were used to determine the PVs for mineral prospectivity prediction. Third, the weights-of-evidence and Random Forest methods were used to integrate the PVs to generate a probability map of mineral prospectivity. Finally, the receiver operating characteristic curve was used to evaluate the performance of the PVs for indicating mineral prospectivity. The variable strata buffer, granite buffer, stratigraphic entropy, derivative norm of magnetic data, and fault buffer were selected as PVs by SPCA, whereas the derivative norm of magnetic data, fault buffer, geochemical anomalies, and strata number were selected as PVs by the RFE method. The results demonstrate that PV determination is a necessary step for mineral prospectivity mapping because it can improve the performance of mineral prospectivity prediction.
Publisher
Springer US,Springer Nature B.V
