Using machine learning to estimate a key missing geochemical variable in mining exploration: Application of the Random Forest algorithm to multi-sensor core logging data

Journal of Geochemical Exploration - Tập 205 - Trang 106344 - 2019
N. Schnitzler1, P.-S. Ross1, E. Gloaguen1
1Institut national de la recherche scientifique, 490 de la Couronne, Québec, QC G1K 9A9, Canada

Tài liệu tham khảo

Adair, 2009 Bérubé, 2018, Predicting rock type and detecting hydrothermal alteration using machine learning and petrophysical properties of the Canadian Malartic ore and host rocks, Pontiac Subprovince, Québec, Canada, Ore Geol. Rev., 96, 130, 10.1016/j.oregeorev.2018.04.011 Bourke, 2016, Portable X-ray fluorescence measurements on exploration drill-cores: comparing performance on unprepared cores and powders for ‘whole-rock’ analysis, Geochem. Explor. Environ. Anal., 16, 147, 10.1144/geochem2014-326 Breiman, 2001, v. 45, 5 Carranza, 2015, Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines), Comput. Geosci., 74, 60, 10.1016/j.cageo.2014.10.004 Caté, 2017, Machine learning as a tool for geologists, Lead. Edge, 36, 215, 10.1190/tle36030215.1 Caté, 2018, Classification of lithostratigraphic and alteration units from drillhole lithogeochemical data using machine learning: a case study from the Lalor volcanogenic massive sulphide deposit, Snow Lake, Manitoba, Canada, J. Geochem. Explor., 188, 216, 10.1016/j.gexplo.2018.01.019 Chen, 2018, Identification of sandstones above blind uranium deposits using multivariate statistical assessment of compositional data, Athabasca Basin, Canada, J. Geochem. Explor., 188, 229, 10.1016/j.gexplo.2018.01.026 Debreil, 2018, The Matagami district, Abitibi Greenstone Belt, Canada: volcanic controls on Archean volcanogenic massive sulfide deposits associated with voluminous felsic volcanism, Econ. Geol., 113, 891, 10.5382/econgeo.2018.4575 Fischer, 2014, Deux méthodes d’apprentissage non supervisé: synthèse sur la méthode des centres mobiles et présentation des courbes principales, Journal de la Société Française de Statistique, 155, 2 Franklin, 2005, Volcanogenic massive sulfide deposits, 523 Fresia, 2013 Fresia, 2017, Lithological discrimination based on statistical analysis of multi-sensor drill core logging data in the Matagami VMS district, Quebec, Canada, Ore Geol. Rev., 80, 552, 10.1016/j.oregeorev.2016.07.019 Genna, 2014, The Key Tuffite, Matagami Camp, Abitibi Greenstone Belt, Canada: petrogenesis and implications for VMS formation and exploration, Mineral. Deposita, 49, 489, 10.1007/s00126-013-0499-7 Gifkins, 2005 Heutte, 2008, De la sélection d’arbres de décision dans les forêts aléatoires, 163 Jácomo, 2015, Magnetic susceptibility and gamma-ray spectrometry on drill core: lithotype characterization and 3D ore modelling of the Morro Do Padre niobium deposit, Goiás, Brazil, Revista Brasileira de Geofísica, 33, 15, 10.22564/rbgf.v33i2.719 Large, 2001, v. 96, 957 Martín-Fernández, 2003, v. 35, 253 Mercier-Langevin, 2014, A special issue on Archean magmatism, volcanism, and ore deposits: part 2. Volcanogenic massive sulfide deposits preface, Econ. Geol., 109, 1, 10.2113/econgeo.109.1.1 Mohamadally, 2006 Pedregosa, 2011, Scikit-learn: machine learning in Python, J. Mach. Learn. Res., 12, 2825 Piché, 1991 Rakotomalala, 2005, 33, 163 Raschka, 2017 Rodriguez-Galiano, 2015, Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines, Ore Geol. Rev., 71, 804, 10.1016/j.oregeorev.2015.01.001 Ross, 2017, High-resolution gamma ray attenuation density measurements on mining exploration drill cores, including cut cores, J. Appl. Geophys., 136, 262, 10.1016/j.jappgeo.2016.11.012 Ross, 2013, A multi-sensor logger for rock cores: Methodology and preliminary results from the Matagami mining camp, Canada, Ore Geol. Rev., 53, 93, 10.1016/j.oregeorev.2013.01.002 Ross, 2014, Improving lithological discrimination in exploration drill-cores using portable X-ray fluorescence measurements: (1) testing three Olympus Innov-X analysers on unprepared cores, Geochemistry: Exploration, Environment, Analysis, 14, 171 Ross, 2014, Improving lithological discrimination in exploration drill-cores using portable X-ray fluorescence measurements: (2) applications to the Zn-Cu Matagami mining camp, Canada, Geochemistry: Exploration, Environment, Analysis, 14, 187 Ross, 2016, High-resolution physical properties, geochemistry and alteration mineralogy for the host rocks of the Archean Lemoine auriferous VMS deposit, Canada, Econ. Geol., 111, 561, 10.2113/econgeo.111.7.1561 Ross, 2016 Roy, 2006, 13 Schnitzler, 2017 Sharpe, 1968, Geology and sulfide deposits of the Matagami area, Abitibi-East County Wang, 2017, White mica as a hyperspectral tool in exploration for the Sunrise Dam and Kanowna Belle gold deposits, Western Australia, Econ. Geol., 112, 1153, 10.5382/econgeo.2017.4505