About this document

Machine Learning for Alteration Classification by Edilber is a document available to read on EtoBox.

The document discusses using machine learning to classify alteration using short-wave infrared (SWIR), X-ray fluorescence (XRF), and photographic textural data from samples. The author examines applying data-driven methods to improve on traditional visual classification of alteration. Preliminary results suggest alteration can be well constrained in a semi-automated way integrating mineralogical, compositional, and textural data from field instruments.

Author

Edilber

Language

EN