Detection of Artisanal and Small-Scale Gold Mining Activities and Their Transformation Using Earth Observation, Nighttime Light, and Precipitation Data

Assessing the Applications of Earth Observation Data for Monitoring Artisanal and Small-Scale Gold Mining (ASGM) in Developing Countries

This paper discusses opportunities to use remote sensing (RS) technologies in addressing the persistent global challenges related to the artisanal and small-scale gold mining (ASGM) sector. The paper uses a systematic literature review to identify, analyze, and synthesize various uses of RS on the detection and monitoring of ASGM activities across the globe. The study covers the use of spaceborne sensors and available opportunities for data access and processing and emphasizes the important role that freely-available data has played in understanding ASGM activities. It discusses applications and opportunities offered in assessing the geospatial and temporal characteristics of ASGM and its impacts on the surrounding environment. Furthermore, it examines different indicators for the detection of ASGM in the landscape. Finally, technological capabilities described in the study are illustrated with case studies in the Democratic Republic of Congo and in Colombia using cloud computing with the Open Data Cube. The case studies demonstrate the identification and quantification of impacts of ASGM activities on land degradation and water turbidity in remote areas and results are dissiminated using the MapX platform. This facilitates policy development, implementation, and evaluation in the ASGM context.

Characterizing Time-Series Roving Artisanal and Small-Scale Gold Mining Activities in Indonesia Using Sentinel-1 Data

The rapid growth of roving mining camps has negatively influenced their surrounding environment. Although artisanal and small-scale gold mining (ASGM) is a major source of gold production, the mining activities and their activeness are not well revealed owing to their informal, illegal, and unregulated characteristics. This study characterizes the transformations of roving camp-type ASGM (R-C-ASGM) activities in Central of Katingan Regency, Central Kalimantan Province, Indonesia, from 2015 to 2021 using remotely sensed data, such as the time-series Sentinel-1 dataset. The results show that the growth of active R-C-ASGM sites was identified at the center of the Galangan mining region with expansions to the northwest part along the Kalanaman River, especially in 2021. Hence, these approaches identify the transformations of roving mining activities and their active or nonactive status even in tropical regions experiencing frequent heavy traffic rainstorms. They provide significant information on the socioenvironmental risks possibly caused at local and regional levels. Our results also inform the design of timely interventions suited to local conditions for strengthening environmental governance.

Investigation of Long-Term Roving Artisanal and Small-Scale Gold Mining Activities Using Time-Series Sentinel-1 and Global Surface Water Datasets

Artisanal and small-scale gold mining (ASGM) is a significant source of gold production globally despite the sector being informal and illegal. The rapid increase in the number of roving mining camps has negatively impacted the surrounding environment; however, the formation and transformation of roving mining camps have not been well studied. This study investigated the long-term trends and significant hotspots of roving camp-type ASGM (R-C-ASGM) in Katingain Regency, Central Kalimantan Province, Indonesia, from 1988 to 2020 using remotely sensed data, including Sentinel-1 time-series, global surface water (GSW), and world landcover datasets. Results show that several active R-C-ASGM sites existed in the Galangan and Kalanaman areas in 2017/2018. According to the GSW dataset, the Galangan area was estimated to be formed earlier, whereas the Kalanaman areas were recently formed and were associated with the Kalanaman river expansion. Notably, the center of Galangan was still a significant R-C-ASGM hotspot. The findings of this study broaden our understanding of R-C-ASGM transformation and identify significant R-C-ASGM hotspots over a long period. This study contributes to the development of timely and appropriate interventions for strengthening environmental governance.

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

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.