This repository contains the notebooks and supplementary files required to reproduce the results presented in the paper (under review): Heidari, E., Farahbakhsh, E., Müller, R. D., Machine learning framework for prospectivity mapping of porphyry mineralisation in New South Wales, Australia. The notebook enables users to create a prospectivity map for porphyry mineralisation in New South Wales, particularly the Lachlan Orogen.
The input files include geological and geophysical data, which will be available to be downloaded soon! Geological data are provided as polyline and polygon files, while geophysical data are available as raster layers. The polyline files contain information on intrusion boundaries, metamorphic boundaries and isograds, rock unit boundaries, and faults. The polygon files represent intrusions, metamorphic facies, and rock units. The raster layers include magnetic, gravity, seismic, radiometric, remote sensing, and elevation grids.
To set up the necessary environment to run the notebooks, use the env.yml file available in this repository. This file configures a Conda environment with all the dependencies required to run the notebooks.
The final output is a GeoTIFF file that shows the probability of the targeted mineralisation in NSW or a specific area within it, like the Lachlan Orogen.
@article{Heidari202?,
title = {Machine learning framework for prospectivity mapping of porphyry mineralisation in New South Wales, Australia},
author = {Heidari, Elnaz and Farahbakhsh, Ehsan and Shirmard, Hojat and Kohlman, Fabian and Blevin, Phillip and M{\"u}ller, R. Dietmar},
year = {202?},
journal = {?},
volume = {?},
number = {?},
pages = {?},
doi = {?},
}