A Deep Learning Approach to the Detection of Gossans in the Canadian Arctic
Gossans are surficial deposits that form in host bedrock by the alteration of sulphides by acidic and oxidizing fluids. These deposits are typically a few meters to kilometers in size and they constitute important vectors to buried ore deposits. Hundreds of gossans have been mapped by field geologis...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2020
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs12193123 https://doaj.org/article/1fad45b1919546f788b748e966a611c1 |
id |
ftdoajarticles:oai:doaj.org/article:1fad45b1919546f788b748e966a611c1 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:1fad45b1919546f788b748e966a611c1 2023-05-15T14:48:11+02:00 A Deep Learning Approach to the Detection of Gossans in the Canadian Arctic Étienne Clabaut Myriam Lemelin Mickaël Germain Marie-Claude Williamson Éloïse Brassard 2020-09-01T00:00:00Z https://doi.org/10.3390/rs12193123 https://doaj.org/article/1fad45b1919546f788b748e966a611c1 EN eng MDPI AG https://www.mdpi.com/2072-4292/12/19/3123 https://doaj.org/toc/2072-4292 doi:10.3390/rs12193123 2072-4292 https://doaj.org/article/1fad45b1919546f788b748e966a611c1 Remote Sensing, Vol 12, Iss 3123, p 3123 (2020) gossan deep learning convolutional neural network geo big data multispectral Landsat Science Q article 2020 ftdoajarticles https://doi.org/10.3390/rs12193123 2022-12-31T12:47:29Z Gossans are surficial deposits that form in host bedrock by the alteration of sulphides by acidic and oxidizing fluids. These deposits are typically a few meters to kilometers in size and they constitute important vectors to buried ore deposits. Hundreds of gossans have been mapped by field geologists in sparsely vegetated areas of the Canadian Arctic. However, due to Canada’s vast northern landmass, it is highly probable that many existing occurrences have been missed. In contrast, a variety of remote sensing data has been acquired in recent years, allowing for a broader survey of gossans from orbit. These include band ratioing or methods based on principal component analysis. Spectrally, the 809 gossans used in this study show no significant difference from randomly placed points on the Landsat 8 imageries. To overcome this major issue, we propose a deep learning method based on convolutional neural networks and relying on geo big data (Landsat-8, Arctic digital elevation model lithological maps) that can be used for the detection of gossans. Its application in different regions in the Canadian Arctic shows great promise, with precisions reaching 77%. This first order approach could provide a useful precursor tool to identify gossans prior to more detailed surveys using hyperspectral imaging. Article in Journal/Newspaper Arctic Directory of Open Access Journals: DOAJ Articles Arctic Remote Sensing 12 19 3123 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
gossan deep learning convolutional neural network geo big data multispectral Landsat Science Q |
spellingShingle |
gossan deep learning convolutional neural network geo big data multispectral Landsat Science Q Étienne Clabaut Myriam Lemelin Mickaël Germain Marie-Claude Williamson Éloïse Brassard A Deep Learning Approach to the Detection of Gossans in the Canadian Arctic |
topic_facet |
gossan deep learning convolutional neural network geo big data multispectral Landsat Science Q |
description |
Gossans are surficial deposits that form in host bedrock by the alteration of sulphides by acidic and oxidizing fluids. These deposits are typically a few meters to kilometers in size and they constitute important vectors to buried ore deposits. Hundreds of gossans have been mapped by field geologists in sparsely vegetated areas of the Canadian Arctic. However, due to Canada’s vast northern landmass, it is highly probable that many existing occurrences have been missed. In contrast, a variety of remote sensing data has been acquired in recent years, allowing for a broader survey of gossans from orbit. These include band ratioing or methods based on principal component analysis. Spectrally, the 809 gossans used in this study show no significant difference from randomly placed points on the Landsat 8 imageries. To overcome this major issue, we propose a deep learning method based on convolutional neural networks and relying on geo big data (Landsat-8, Arctic digital elevation model lithological maps) that can be used for the detection of gossans. Its application in different regions in the Canadian Arctic shows great promise, with precisions reaching 77%. This first order approach could provide a useful precursor tool to identify gossans prior to more detailed surveys using hyperspectral imaging. |
format |
Article in Journal/Newspaper |
author |
Étienne Clabaut Myriam Lemelin Mickaël Germain Marie-Claude Williamson Éloïse Brassard |
author_facet |
Étienne Clabaut Myriam Lemelin Mickaël Germain Marie-Claude Williamson Éloïse Brassard |
author_sort |
Étienne Clabaut |
title |
A Deep Learning Approach to the Detection of Gossans in the Canadian Arctic |
title_short |
A Deep Learning Approach to the Detection of Gossans in the Canadian Arctic |
title_full |
A Deep Learning Approach to the Detection of Gossans in the Canadian Arctic |
title_fullStr |
A Deep Learning Approach to the Detection of Gossans in the Canadian Arctic |
title_full_unstemmed |
A Deep Learning Approach to the Detection of Gossans in the Canadian Arctic |
title_sort |
deep learning approach to the detection of gossans in the canadian arctic |
publisher |
MDPI AG |
publishDate |
2020 |
url |
https://doi.org/10.3390/rs12193123 https://doaj.org/article/1fad45b1919546f788b748e966a611c1 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_source |
Remote Sensing, Vol 12, Iss 3123, p 3123 (2020) |
op_relation |
https://www.mdpi.com/2072-4292/12/19/3123 https://doaj.org/toc/2072-4292 doi:10.3390/rs12193123 2072-4292 https://doaj.org/article/1fad45b1919546f788b748e966a611c1 |
op_doi |
https://doi.org/10.3390/rs12193123 |
container_title |
Remote Sensing |
container_volume |
12 |
container_issue |
19 |
container_start_page |
3123 |
_version_ |
1766319279530049536 |