Semi-supervised Change Detection of Small Water Bodies Using RGB and Multispectral Images in Peruvian Rainforests
This work addresses environmental monitoring for ASGM in rainforests, but it is incremental as it applies existing SVM-based methods to a specific domain with new data.
The paper tackled the problem of detecting Artisanal and Small-scale Gold Mining (ASGM) activities in Peruvian rainforests by recognizing changes in small water bodies using semi-supervised classifiers on Sentinel-2 images from 2019 to 2021, achieving Cohen's κ scores of 0.49 for RGB and 0.71 for 6-channel images with limited annotations.
Artisanal and Small-scale Gold Mining (ASGM) is an important source of income for many households, but it can have large social and environmental effects, especially in rainforests of developing countries. The Sentinel-2 satellites collect multispectral images that can be used for the purpose of detecting changes in water extent and quality which indicates the locations of mining sites. This work focuses on the recognition of ASGM activities in Peruvian Amazon rainforests. We tested several semi-supervised classifiers based on Support Vector Machines (SVMs) to detect the changes of water bodies from 2019 to 2021 in the Madre de Dios region, which is one of the global hotspots of ASGM activities. Experiments show that SVM-based models can achieve reasonable performance for both RGB (using Cohen's $κ$ 0.49) and 6-channel images (using Cohen's $κ$ 0.71) with very limited annotations. The efficacy of incorporating Lab color space for change detection is analyzed as well.