The Use of C-Band and X-Band SAR with Machine Learning for Detecting Small-Scale Mining

Gabrielle Janse Van Rensburg,Jaco Kemp

doi:10.3390/rs14040977

Gabrielle Janse Van Rensburg, Jaco Kemp

Open Access

https://doi.org/10.3390/rs14040977

Copy DOI

Journal: Remote sensing	Publication Date: Feb 17, 2022
Citations: 6	License type: CC BY 4.0

Affiliation: Council for Geoscience, Stellenbosch University

Abstract

Illicit small-scale mining occurs in many tropical regions and is both environmentally and socially hazardous. The aim of this study was to determine whether the classification of Synthetic Aperture Radar (SAR) imagery could detect and map small-scale mining in Ghana by analyzing multi-temporal filtering applied to three SAR datasets and testing five machine-learning classifiers. Using an object-based image analysis approach, we were successful in classifying water bodies associated with small-scale mining. The multi-temporally filtered Sentinel-1 dataset was the most reliable, with kappa coefficients at 0.65 and 0.82 for the multi-class classification scheme and binary-water classification scheme, respectively. The single-date Sentinel-1 dataset has the highest overall accuracy, at 90.93% for the binary water classification scheme. The KompSAT-5 dataset achieved the lowest accuracy at an overall accuracy of 80.61% and a kappa coefficient of 0.61 for a binary-water classification scheme. The experimental results demonstrated that it is possible to classify water as a proxy to identify illegal mining activities and that SAR is a potentially accurate and reliable solution for the detection of SSM in tropical regions such as Ghana. Therefore, using SAR can assist local governments in regulating small-scale mining activities by providing specific spatial information on the whereabouts of small-scale mining locations.

Highlights

We evaluated how different Synthetic Aperture Radar (SAR) sensors compare regarding the mapping of Small-scale mining (SSM) when applying classification
The Sentinel-1 multi-temporally filtered image (S1-MT) dataset has the highest overall accuracy at 73.60% for the multi-class classification scheme and S1 has the highest overall accuracy at 90.93% for the binary water classification scheme (Figure 4)
The results from the classification conducted in this study showed that Random forest (RF) outperformed support vector machine (SVM)

Summary

Introduction

SSM is a low-cost, labor-intensive method of mining [1] in areas where gold is accessible, such as on the river banks where alluvial gold deposits can be found. Land degradation is a consequence of such mining activities and remains an important global issue, as the global demand for precious minerals will continue to increase [2]. Around two-thirds of the total supply of these minerals comes from countries in South America, South Asia, and. In Ghana, “galamsey” is a term commonly used to describe illegal mining activity in. Mantey et al [4] and Owusu-Nimo et al [5] suggest that galamsey operations are an illegal or unregulated form of SSM and processing of gold that lies at or below soil and water surfaces in Ghana. Galamseyers do not pay tax, many mines are in delicate or prohibited areas, and often, human safety is put at risk [5,10,11,12]

Objectives

Methods

Results

Conclusion