Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Defining geologic domains using cluster analysis and indicator correlograms: a phosphate-titanium case study

Defining geologic domains using cluster analysis and indicator correlograms: a phosphate-titanium... One of the first decisions to be made when building a mineral resource model is the definition of geological/geostatistical domains. Cluster analysis is a set of techniques in machine learning that can be especially suited for this matter. In order to compare different approaches, two clustering algorithms were investigated in this study: k-means and the dual-space clustering algorithm. Choosing the most appropriate method and the number of clusters can be challenging and some metrics are needed to support these decisions, including the validation of the spatial distribution of the clusters, which is not always appropriately discussed in the literature. We introduce the use of correlograms of the indicators for that matter. Although clustering techniques can be robust for an application in resource modelling, expert knowledge is still necessary when applying cluster analysis to resource modeling, since final decisions should not be based solely on statistical indexes, but also on experience. In this paper, the proposed methodology was tested in a three-dimensional dataset related to a phosphate/titanium deposit. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Applied Earth Science Taylor & Francis

Defining geologic domains using cluster analysis and indicator correlograms: a phosphate-titanium case study

Download PDF

Defining geologic domains using cluster analysis and indicator correlograms: a phosphate-titanium case study

Abstract

One of the first decisions to be made when building a mineral resource model is the definition of geological/geostatistical domains. Cluster analysis is a set of techniques in machine learning that can be especially suited for this matter. In order to compare different approaches, two clustering algorithms were investigated in this study: k-means and the dual-space clustering algorithm. Choosing the most appropriate method and the number of clusters can be challenging and some metrics are...
Loading next page...
 
/lp/taylor-francis/defining-geologic-domains-using-cluster-analysis-and-indicator-iU4BHPcuP7
Publisher
Taylor & Francis
Copyright
© 2020 Institute of Materials, Minerals and Mining and The AusIMM
ISSN
2572-6838
eISSN
2572-6846
DOI
10.1080/25726838.2020.1814483
Publisher site
See Article on Publisher Site

Abstract

One of the first decisions to be made when building a mineral resource model is the definition of geological/geostatistical domains. Cluster analysis is a set of techniques in machine learning that can be especially suited for this matter. In order to compare different approaches, two clustering algorithms were investigated in this study: k-means and the dual-space clustering algorithm. Choosing the most appropriate method and the number of clusters can be challenging and some metrics are needed to support these decisions, including the validation of the spatial distribution of the clusters, which is not always appropriately discussed in the literature. We introduce the use of correlograms of the indicators for that matter. Although clustering techniques can be robust for an application in resource modelling, expert knowledge is still necessary when applying cluster analysis to resource modeling, since final decisions should not be based solely on statistical indexes, but also on experience. In this paper, the proposed methodology was tested in a three-dimensional dataset related to a phosphate/titanium deposit.

Journal

Applied Earth Science – Taylor & Francis

Published: Oct 1, 2020

Keywords: Cluster analysis; Estimation domains; Stationarity; Geostatistics; Mining; Geology; Machine learning; Data science

References

  • Clustering of spatial data by the EM algorithm
  • K-means++: the advantages of careful seeding
  • Random forests
  • A dendrite method for cluster analysis
  • Maximum likelihood from incomplete data via the EM algorithm
  • A robust hierarchical clustering for georeferenced data
  • A hierarchical clustering method for multivariate geostatistical data
  • Discovering spatially contiguous clusters in multivariate geostatistical data through spectral clustering
  • A spectral clustering approach for multivariate geostatistical data
  • A spectral clustering method for large-scale geostatistical datasets
  • Clustering of multivariate geostatistical data
  • Geostatistical clustering as an aid for ore body domaining: case study at the Rocklea Dome channel iron ore deposit, Western Australia
  • The analysis of spatial association by use of distance statistics
  • Some methods for classification and analysis of multivariate observations
  • Geostatistical clustering, potential modeling and traditional geostatistics: a new coherent workflow
  • Towards justifying unsupervised stationary decisions for geostatistical modeling: ensemble spatial and multivariate clustering with geomodeling specific clustering metrics
  • Avaliação de técnicas de agrupamento para definição de domínios estacionários com o auxílio de geoestatística
  • A geostatistical basis for spatial weighting in multivariate classification
  • Local spatial autocorrelation statistics: distributional issues and an application
  • Scikit-learn: Machine learning in Python
  • Unsupervised classification of multivariate geostatistical data: two algorithms
  • Domaining by clustering multivariate geostatistical data
  • Silhouettes: a graphical aid to the interpretation and validation of cluster analysis
  • Clustering multivariate spatial data based on local measures of spatial autocorrelation
  • Principles of numerical taxonomy
  • Cluster ensembles – a knowledge reuse framework for combining multiple partitions