Expected outputs

  • A mineral prospectivity analysis procedure where part of the currently manual processing is done using machine learning
  • Model validation and testing methods for geoscience applications that are handling well with spatially correlated data
  • Deep learning techniques for prospectivity analysis to maximize the amount of information extracted from the data
  • Preprocessing workflow for geochemical data by spatial filtering and compositional data analysis for improving geochemical data efficiency prospectivity analysis
  • Sustainability-enhanced processes for MPM
  • ArcSDM toolbox for ArcGIS Pro
  • The current version will be updated, and new deep-learning tools will be implemented.
  • Updated MPM online map service
  • A mineral prospectivity analysis procedure where part of the currently manual processing is done using machine learning
  • Model validation and testing methods for geoscience applications that are handling well with spatially correlated data
  • Deep learning techniques for prospectivity analysis to maximize the amount of information extracted from the data
  • Preprocessing workflow for geochemical data by spatial filtering and compositional data analysis for improving geochemical data efficiency prospectivity analysis
  • Sustainability-enhanced processes for MPM
  • ArcSDM toolbox for ArcGIS Pro
    • Access to the most recent version of ArcSDM 5 through GitHub
  • The current version will be updated, and new deep-learning tools will be implemented.
  • Updated MPM online map service
  • Aim and objectives using AI in mineral prospectivity mapping

Mineral prospectivity mapping or analysis can be divided into:

1) Definition of the mineral system type

2) Data selection and preprocessing

3) Prospectivity modelling

4) Model testing

Mineral Systems Model