A Sentinel-2 based multispectral convolutional neural network for detecting artisanal small-scale mining in Ghana: Applying deep learning to shallow mining
- Submitting institution
-
University of Exeter
- Unit of assessment
- 12 - Engineering
- Output identifier
- 5168
- Type
- D - Journal article
- DOI
-
10.1016/j.rse.2020.111970
- Title of journal
- Remote Sensing of Environment
- Article number
- 111970
- First page
- -
- Volume
- 248
- Issue
- -
- ISSN
- 0034-4257
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
https://ars.els-cdn.com/content/image/1-s2.0-S0034425720303400-mmc1.xlsx
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
H - CSM
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper presents the first published multispectral convolutional neural network (CNN) model to distinguish between mined and built areas. The work led to an invited talk at the Satellite Applications Catapult online webinar 'Satellite Technology Addressing Social Challenges in Mining' (conradgillespie@gmail.com). The Head of Sibanye-Stillwater Digital Mining Laboratory (DigiMine) has stated that the methodology provides the basis for governments, NGOs and licensing authorities to control, and then mitigate, negative effects of artisanal and illegal mining activity. This potential is also recognised by the international development organisation PACT and the work informed the €4.1M ERDF-funded Deep Digital Cornwall project.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -