Semi-supervised Change Detection of Small Water Bodies Using RGB and Multispectral Images in Peruvian Rainforests

TL;DR

This study develops semi-supervised SVM classifiers to detect water body changes in Peruvian rainforests using multispectral satellite images, aiding in identifying artisanal gold mining activities with limited labeled data.

Contribution

It introduces semi-supervised SVM-based methods for change detection in multispectral images, demonstrating effective performance with minimal annotations in a challenging environmental context.

Findings

SVM models achieved Cohen's κ of 0.49 with RGB images.

Cohen's κ increased to 0.71 with 6-channel images.

Incorporating Lab color space improves change detection accuracy.

Abstract

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 $\kappa$ 0.49) and 6-channel images (using Cohen's $\kappa$ 0.71) with very limited annotations. The efficacy of incorporating Lab color space for change detection is analyzed as well.