Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines

V Rodriguez-Galiano, M Sanchez-Castillo… - Ore Geology …, 2015 - Elsevier
Abstract Machine learning algorithms (MLAs) such us artificial neural networks (ANNs),
regression trees (RTs), random forest (RF) and support vector machines (SVMs) are …

Deep learning and its application in geochemical map**

R Zuo, Y ** using machine learning methods: A case study from Tongling ore district, eastern China
T Sun, F Chen, L Zhong, W Liu, Y Wang - Ore Geology Reviews, 2019 - Elsevier
Predictive modelling of mineral prospectivity using GIS is a valid and progressively more
accepted tool for delineating reproducible mineral exploration targets. In this study, machine …

[HTML][HTML] Ensemble learning models with a Bayesian optimization algorithm for mineral prospectivity map**

J Yin, N Li - Ore geology reviews, 2022 - Elsevier
Abstract Machine learning algorithms have been widely applied in mineral prospectivity
map** (MPM). In this study, we implemented ensemble learning of extreme gradient …

[BUCH][B] Geochemical anomaly and mineral prospectivity map** in GIS

EJM Carranza - 2008 - books.google.com
Geochemical Anomaly and Mineral Prospectivity Map** in GIS documents and explains,
in three parts, geochemical anomaly and mineral prospectivity map** by using a …

Prediction–area (P–A) plot and C–A fractal analysis to classify and evaluate evidential maps for mineral prospectivity modeling

M Yousefi, EJM Carranza - Computers & Geosciences, 2015 - Elsevier
There are methods of mineral prospectivity map** whereby, besides assignment of
weights to classes of evidence in an evidential map, every evidential map is also given a …

A data augmentation approach to XGboost-based mineral potential map**: an example of carbonate-hosted ZnPb mineral systems of Western Iran

M Parsa - Journal of Geochemical Exploration, 2021 - Elsevier
This study intends to showcase the application of Extreme Gradient boosting (XGboost), a
state-of-the-art ensemble-learning technique, for district-scale mineral potential map** …

Data analysis methods for prospectivity modelling as applied to mineral exploration targeting: State-of-the-art and outlook

M Yousefi, EJM Carranza, OP Kreuzer… - Journal of Geochemical …, 2021 - Elsevier
Mineral exploration targeting is a highly complex decision-making task. Two key risk factors,
the quality of exploration data and robustness of the underlying conceptual targeting model …

Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines)

EJM Carranza, AG Laborte - Computers & Geosciences, 2015 - Elsevier
Abstract Machine learning methods that have been used in data-driven predictive modeling
of mineral prospectivity (eg, artificial neural networks) invariably require large number of …

Support vector machine: A tool for map** mineral prospectivity

R Zuo, EJM Carranza - Computers & Geosciences, 2011 - Elsevier
In this contribution, we describe an application of support vector machine (SVM), a
supervised learning algorithm, to mineral prospectivity map**. The free R package e1071 …