Imperial College London
Portrait Picture

ProfessorJamieWilkinson

Faculty of Engineering, Department of Earth Science & Engineering

Professor of Geology
 
 
 
//

Contact

 

j.wilkinson Website

 
 
//

Location

 

PA418Natural History MuseumNatural History Museum

//

Summary

 

Publications

Citation

BibTex format

@article{Nathwani:2023:10.1029/2022jb025933,
author = {Nathwani, CL and Wilkinson, JJ and Brownscombe, W and John, CM},
doi = {10.1029/2022jb025933},
journal = {Journal of Geophysical Research: Solid Earth},
pages = {1--19},
title = {Mineral texture classification using deep convolutional neural networks: An application to zircons from porphyry copper deposits},
url = {http://dx.doi.org/10.1029/2022jb025933},
volume = {128},
year = {2023}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - The texture and morphology of igneous zircon indicates magmatic conditions during zircon crystallization and can be used to constrain provenance. Zircons from porphyry copper deposits are typically prismatic, euhedral, and strongly oscillatory zoned which may differentiate them from zircons associated with unmineralized igneous systems. Here, cathodoluminescence images of zircons from the Quellaveco porphyry copper district, Southern Peru, were collected to compare zircon textures between the premineralization Yarabamba Batholith and the Quellaveco porphyry copper deposit. Quellaveco porphyry zircons are prismatic, euhedral, and strongly oscillatory zoned, whereas the batholith zircons are subhedral-anhedral with weaker zoning. We adopt a deep convolutional neural network (CNN) approach to demonstrate that a CNN can classify Quellaveco porphyry zircons with high success. We trial several CNN architectures to classify zircon images: LeNet-5, AlexNet and VGG, including a transfer learning approach where we used the weights of a VGG model pretrained on the ImageNet data set. The VGG model with transfer learning is the most effective approach, with accuracy and receiver operating characteristic-area under curve (ROC-AUC) scores of 0.86 and 0.93, indicating that a Quellaveco porphyry zircon CL image can be ranked higher than a batholith zircon with 93% probability. Visualizing model layer outputs demonstrates that the CNN models can recognize crystal edges, zoning, and mineral inclusions. We trial implementing trained CNN models as unsupervised feature extractors, which can empirically quantify crystal textures and morphology. Therefore, deep learning provides a tool for the extraction of information from large, imaged-based petrographic data sets which can facilitate petrologic and provenance studies.
AU  - Nathwani,CL
AU  - Wilkinson,JJ
AU  - Brownscombe,W
AU  - John,CM
DO  - 10.1029/2022jb025933
EP  - 19
PY  - 2023///
SN  - 2169-9313
SP  - 1
TI  - Mineral texture classification using deep convolutional neural networks: An application to zircons from porphyry copper deposits
T2  - Journal of Geophysical Research: Solid Earth
UR  - http://dx.doi.org/10.1029/2022jb025933
UR  - https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2022JB025933
UR  - http://hdl.handle.net/10044/1/101752
VL  - 128
ER  -
Download