Quantifying Three Decades of Artisanal and Small-scale Gold Mining Frontiers in the Guiana Shield (1995–2024)

2025 · doi:10.32942/x2bs92
preprint OA: closed
Full text JSON View at publisher
⚙ AI-generated summary by claude@2026-07, 2026-07-14 ⓘ

This study mapped three decades of artisanal gold mining in the Guiana Shield using deep learning, revealing a 1,411% increase in mined area and significant carbon losses impacting biodiversity and protected areas.

One-sentence paraphrase of the abstract; not a substitute for reading it. No clinical advice. How this works

⚙ AI-generated deep summary by claude@2026-07, 2026-07-14 · read from full text ⓘ

This preprint studies the spatial and temporal expansion of artisanal and small-scale gold mining (ASGM) across the Guiana Shield rainforests in Guyana, Suriname, and French Guiana from 1995 to 2024, using Landsat imagery and a deep learning semantic segmentation model to map mining activity annually. The authors report a 995% increase in mine count and a 1,411% increase in total mined area (from ~13,200 ha in 1995 to ~199,489 ha in 2024), along with a 38% increase in mean mine polygon size and substantial estimated aboveground carbon losses (30,933 Gg C). A key limitation noted is that the work is a preprint and not peer reviewed, and the underlying data and code are not yet publicly available. The paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Abstract

Artisanal and Small-scale Gold Mining (ASGM) is a leading driver of tropical deforestation and forest degradation, yet its spatial and temporal dynamics remain largely underexplored. Here, we present a pan-regional, annual time-series analysis of ASGM expansion across rainforests of the Guiana Shield (Guyana, Suriname, and French Guiana) from 1995 to 2024. Using Landsat imagery, we trained a deep learning model to detect gold mining patterns, and we used this to map nearly three decades of ASGM activity. Our results reveal a 995% increase in mine count and a 1,411% increase in total mined area, from ~13,200 ha in 1995 to ~199,489 ha in 2024. Mean mine polygon size increased by 38%, with especially sharp rises in Suriname, suggesting a shift toward more intensive operations. We estimate ASGM-driven aboveground carbon losses of 30,933 Gg C across the region, highlighting its growing climate implications. Mining disproportionately impacted key ecosystems, overlapping with protected areas and Key Biodiversity Areas, particularly in French Guiana. These trends signal escalating pressure on one of the world’s most intact tropical forest frontiers and underscore the need for coordinated regional responses to mitigate ASGM’s environmental footprint. Our findings also demonstrate the power of deep learning for scalable, long-term monitoring of extractive pressures across biodiverse landscapes.
Full text 2,779 characters · extracted from oa-doi-fallback · click to expand
This is a Preprint and has not been peer reviewed. This is version 1 of this Preprint. You must log in to post a comment. There are no comments or no comments have been made public for this article. This is a Preprint and has not been peer reviewed. This is version 1 of this Preprint. Add a Comment You must log in to post a comment. Comments There are no comments or no comments have been made public for this article. Artisanal and Small-scale Gold Mining (ASGM) is a leading driver of tropical deforestation and forest degradation, yet its spatial and temporal dynamics remain largely underexplored. Here, we present a pan-regional, annual time-series analysis of ASGM expansion across rainforests of the Guiana Shield (Guyana, Suriname, and French Guiana) from 1995 to 2024. Using Landsat imagery, we trained a deep learning model to detect gold mining patterns, and we used this to map nearly three decades of ASGM activity. Our results reveal a 995% increase in mine count and a 1,411% increase in total mined area, from ~13,200 ha in 1995 to ~199,489 ha in 2024. Mean mine polygon size increased by 38%, with especially sharp rises in Suriname, suggesting a shift toward more intensive operations. We estimate ASGM-driven aboveground carbon losses of 30,933 Gg C across the region, highlighting its growing climate implications. Mining disproportionately impacted key ecosystems, overlapping with protected areas and Key Biodiversity Areas, particularly in French Guiana. These trends signal escalating pressure on one of the world’s most intact tropical forest frontiers and underscore the need for coordinated regional responses to mitigate ASGM’s environmental footprint. Our findings also demonstrate the power of deep learning for scalable, long-term monitoring of extractive pressures across biodiverse landscapes. https://doi.org/10.32942/X2BS92 Artificial Intelligence and Robotics, Biodiversity, Earth Sciences, Ecology and Evolutionary Biology, Environmental Monitoring, Environmental Sciences, Geography, Life Sciences, Natural Resources and Conservation, Remote Sensing, Sustainability, Terrestrial and Aquatic Ecology Deep learning, semantic segmentation, Landsat time series, U-Net, remote sensing, Aboveground carbon loss, tropical forest degradation, Biodiversity loss, Guiana Shield, amazonía, land-use change, Protected areas, tropical ecology, Gold Mining, deforestation, mineral extraction Published: 2025-12-09 08:00 Last Updated: 2025-12-09 08:00 CC BY Attribution 4.0 International Conflict of interest statement: None Data and Code Availability Statement: The data and analytical code used in this study are not yet publicly available but will be released upon journal publication or in a future updated version of this preprint. Language: English

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

⚙ Ask this paper AI returns verbatim quotes from the full text · source: oa-doi-fallback ⓘ

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00