Next Article in Journal
Machine Learning for Defining the Probability of Sentinel-1 Based Deformation Trend Changes Occurrence
Previous Article in Journal
Satellite Observations of Fire Activity in Relation to Biophysical Forcing Effect of Land Surface Temperature in Mediterranean Climate
Article

Change Detection of Amazonian Alluvial Gold Mining Using Deep Learning and Sentinel-2 Imagery

1
Department of Computer Science, Wake Forest University, Winston-Salem, NC 27109, USA
2
Department of Mathematics, City University of Hong Kong, 83 Tat Chee Ave., Kawloon, Hong Kong
3
Department of Biology, Wake Forest University, Winston-Salem, NC 27109, USA
4
Center for Energy, Environment and Sustainability, Wake Forest University, Winston-Salem, NC 27109, USA
5
Environmental Studies Department, Dartmouth College, Hanover, NH 03755, USA
6
Centro de Innovación Científica Amazónica, (CINCIA), Jr. Cajamarca Cdra. 1, Puerto Maldonado 17001, Madre de Dios, Peru
*
Author to whom correspondence should be addressed.
Academic Editor: Alex Lechner
Remote Sens. 2022, 14(7), 1746; https://doi.org/10.3390/rs14071746
Received: 2 March 2022 / Revised: 31 March 2022 / Accepted: 1 April 2022 / Published: 5 April 2022
Monitoring changes within the land surface and open water bodies is critical for natural resource management, conservation, and environmental policy. While the use of satellite imagery for these purposes is common, fine-scale change detection can be a technical challenge. Difficulties arise from variable atmospheric conditions and the problem of assigning pixels to individual objects. We examined the degree to which two machine learning approaches can better characterize change detection in the context of a current conservation challenge, artisanal small-scale gold mining (ASGM). We obtained Sentinel-2 imagery and consulted with domain experts to construct an open-source labeled land-cover change dataset. The focus of this dataset is the Madre de Dios (MDD) region in Peru, a hotspot of ASGM activity. We also generated datasets of active ASGM areas in other countries (Venezuela, Indonesia, and Myanmar) for out-of-sample testing. With these labeled data, we utilized a supervised (E-ReCNN) and semi-supervised (SVM-STV) approach to study binary and multi-class change within mining ponds in the MDD region. Additionally, we tested how the inclusion of multiple channels, histogram matching, and La*b* color metrics improved the performance of the models and reduced the influence of atmospheric effects. Empirical results show that the supervised E-ReCNN method on 6-Channel histogram-matched images generated the most accurate detection of change not only in the focal region (Kappa: 0.92 (± 0.04), Jaccard: 0.88 (± 0.07), F1: 0.88 (± 0.05)) but also in the out-of-sample prediction regions (Kappa: 0.90 (± 0.03), Jaccard: 0.84 (± 0.04), and F1: 0.77 (± 0.04)). While semi-supervised methods did not perform as accurately on 6- or 10-channel imagery, histogram matching and the inclusion of La*b* metrics generated accurate results with low memory and resource costs. These results show that E-ReCNN is capable of accurately detecting specific and object-oriented environmental changes related to ASGM. E-ReCNN is scalable to areas outside the focal area and is a method of change detection that can be extended to other forms of land-use modification. View Full-Text
Keywords: change detection; small water bodies; ASGM; Sentinal-2 imagery; ReCNN; CNN; LSTM; smoothed total variation; SVM; semi-supervised change detection; small water bodies; ASGM; Sentinal-2 imagery; ReCNN; CNN; LSTM; smoothed total variation; SVM; semi-supervised
Show Figures

Figure 1

MDPI and ACS Style

Camalan, S.; Cui, K.; Pauca, V.P.; Alqahtani, S.; Silman, M.; Chan, R.; Plemmons, R.J.; Dethier, E.N.; Fernandez, L.E.; Lutz, D.A. Change Detection of Amazonian Alluvial Gold Mining Using Deep Learning and Sentinel-2 Imagery. Remote Sens. 2022, 14, 1746. https://doi.org/10.3390/rs14071746

AMA Style

Camalan S, Cui K, Pauca VP, Alqahtani S, Silman M, Chan R, Plemmons RJ, Dethier EN, Fernandez LE, Lutz DA. Change Detection of Amazonian Alluvial Gold Mining Using Deep Learning and Sentinel-2 Imagery. Remote Sensing. 2022; 14(7):1746. https://doi.org/10.3390/rs14071746

Chicago/Turabian Style

Camalan, Seda, Kangning Cui, Victor P. Pauca, Sarra Alqahtani, Miles Silman, Raymond Chan, Robert J. Plemmons, Evan N. Dethier, Luis E. Fernandez, and David A. Lutz. 2022. "Change Detection of Amazonian Alluvial Gold Mining Using Deep Learning and Sentinel-2 Imagery" Remote Sensing 14, no. 7: 1746. https://doi.org/10.3390/rs14071746

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop