Back-propagation neural network and support vector machines for gold mineral prospectivity mapping in the Hatu region, Xinjiang, China

Abstract

Machine Learning technologies have the potential to deliver new nonlinear mineral prospectivity mapping (MPM) models. In this study, Back Propagation (BP) neural network Support Vector Machine (SVM) methods were applied to MPM in the Hatu region of Xinjiang, northwestern China. First, a conceptual model of mineral prospectivity for Au deposits was constructed by analysis of geological background. Evidential layers were selected and transformed into a binary data format. Then, the processes of selecting samples and parameters were described. For the BP model, the parameters of the network were 9-10 − 1; for the SVM model, a radial basis function was selected as the kernel function with best C = 1 and γ = 0.25. MPM models using these parameters were constructed, and threshold values of prediction results were determined by the concentration-area (C-A) method. Finally, prediction results from the BP neural network and SVM model were compared with that of a conventional method that is the weight-of-evidence (W-of-E). The prospectivity efficacy was evaluated by traditional statistical analysis, prediction-area (P-A) plots, and the receiver operating characteristic (ROC) technique. Given the higher intersection position (74% of the known deposits were within 26% of the total area) and the larger AUC values (0.825), the result shows that the model built by the BP neural network algorithm has a relatively better prediction capability for MPM. The BP neural network algorithm applied in MPM can elucidate the next investigative steps in the study area.

Systematic Review of Machine Learning Applications in Mining: Exploration, Exploitation, and Reclamation

“…A mineral analysis [25][26][27][28][29][30][31] was conducted using drilling data or samples. A mineral prospectivity modeling and mapping [32][33][34][35][36][37][38][39][40][41][42] study was performed to evaluate the potential of minerals using the exploration data.…”

Predicting the emplacement of Cordilleran porphyry copper systems using a spatio-temporal machine learning model

“…Support vector machines have also been used with the same purpose which includes; prospection of turbidite-hosted gold deposits in Nova Scotia (Canada) (Zuo & Carranza, 2011), prospecting for copper mineralisation in Iran (Abedi et al, 2012;Shabankareh & Hezarkhani, 2017;Zandiyyeh et al, 2016), lead and zinc deposits in north-western India (Porwal & Yu, 2010) and porphyry Cu systems in central British Columbia (Canada) (Granek & Haber, 2015). Additionally, neural networks have been used to predict the location of gold mineralization in north-western China (N. Zhang et al, 2018), New South Wales (Australia) (Brown et al, 2000); and decision trees have been used to generate evidence maps for potential skarn iron mineralisation in China (Chen et al, 2014).…”

Data-Driven Predictive Modelling of Mineral Prospectivity Using Machine Learning and Deep Learning Methods: A Case Study from Southern Jiangxi Province, China

“…where w and b are the weight vector and the bias term of the hyperplane; and ξ i is the positive slack variable. According to the optimization theory, the problem of finding the optimal hyperplane is transformed into the problem of solving the following convex quadratic equation [26,56]:…”

“…Some of the most commonly used machine learning methods include artificial neural network (ANN), support vector machine (SVM), and random forest (RF). Many previous studies demonstrate that these ML methods outperform the traditional statistical techniques and empirical explorative models in predictive performance, especially when the input evidential features are complexly distributed and their associations with mineralization are expected to be nonlinear [5,[26][27][28]. More recently, deep learning methods, an important branch of machine learning algorithms, have achieved great success in many domains of science [29][30][31].…”