Regionalized Classification of Geochemical Data with Filtering of Measurement Noises for Predictive Lithological Mapping
- PDF / 4,495,161 Bytes
- 20 Pages / 595.276 x 790.866 pts Page_size
- 17 Downloads / 176 Views
Original Paper
Regionalized Classification of Geochemical Data with Filtering of Measurement Noises for Predictive Lithological Mapping Jose´ A. Guarta´n1,2,3 and Xavier Emery
1,2,4
Received 24 May 2020; accepted 31 October 2020
A method for predictive lithological mapping is proposed, which combines geostatistical simulation of geochemical concentrations with coregionalization analysis and decision-tree classification algorithm. The method consists of classifying each target point based on simulated values of the geochemical concentrations, filtered from the short-scale spatial components corresponding to noise and measurement errors. The procedure is repeated over many simulations to give finally as a result the most probable lithology at each target point. An application to a set of geochemical samples of soils and surface rocks is presented, in which lithology is recorded from an interpretive geological field map. It shows significant classification improvement when pre-processing the sampling data through geostatistical simulation with filtering of the nugget effect, with rates of correctly classified data increased by 3.5 to 11 percentage points depending on whether training or testing data subset is considered. The lithological prediction allows generating geological maps as complementary activities to exploration of mineral resources to be able to forecast and/or to validate the geology mapped at each point of explored areas. KEY WORDS: Geochemistry, Geostatistical simulation, Coregionalization analysis, Nugget effect, Decision trees.
INTRODUCTION A geological map is the result of the characterization of rocks. The different types of lithology can be studied based on their mineralogy or based on geochemical prospecting, which analyzes the composition of surface or soil sediments (Jenny 1941). Surface chemistry research at a regional scale 1
Department of Mining Engineering, University of Chile, Santiago, Chile. 2 Advanced Mining Technology Center, University of Chile, Santiago, Chile. 3 Department of Mines, Geology and Civil Engineering, Particular Technical University of Loja, Loja, Ecuador. 4 To whom correspondence should be addressed; e-mail: [email protected]
is often directed to determine the geochemical background or baseline of simple elements (Stanley and Sinclair 1989). Surficial geochemical concentrations vary from one location in space to another with a more or less pronounced continuity, and they can be used to describe local natural conditions such as geology or anthropogenic activities. Multi-element geochemistry therefore provides useful information on the lithology as an essential parameter for the geology of prospective areas (Grunsky et al. 2012). The application of machine learning provides a systematic framework for identification of geochemical/geological processes, and such a framework could be, among others, the use of classification techniques for mineral prospectivity modeling and lithological mapping (Carranza 2009;
Ó 2020 International Association for Mathematical Geosci
Data Loading...
