Journal
COMPUTERS & GEOSCIENCES
Volume 80, Issue -, Pages 9-25Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.cageo.2015.03.013
Keywords
Geophysics; Geochemistry; Geological mapping; Classification; Random Forests
Funding
- Geological Survey of Canada under the Remote Predictive Mapping Project (RPM)
- Geo-mapping for minerals and energy (GEMS) program
Ask authors/readers for more resources
A recent method for mapping lithology which involves the Random Forest (RF) machine classification algorithm is evaluated. Random Forests, a supervised classifier, requires training data representative of each lithology to produce a predictive or classified map. We use two training strategies, one based on the location of lake sediment geochemical samples where the rock type is recorded from a legacy geology map at each sample station and the second strategy is based on lithology recorded from field stations derived from reconnaissance field mapping. We apply the classification to interpolated major and minor lake sediment geochemical data as well as airborne total field magnetic and gamma ray spectrometer data.. Using this method we produce predictions of the lithology of a large section of the Hearne Archean - Paleoproterozoic tectonic domain, in northern Canada. The results indicate that meaningful predictive lithologic maps can be produced using RF classification for both training strategies. The best results were achieved when all data were used; however, the geochemical and gamma ray data were the strongest predictors of the various lithologies. The maps generated from this research can be used to compliment field mapping activities by focusing field work on areas where the predicted geology and legacy geology do not match and as first order geological maps in poorly mapped areas. Crown Copyright (C) 2015 Published by Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available