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

Elmontaserbellah Ammar , Sean J Glynn, Kerry Anne Kansinally, William Clemens, Emilius Richter, Matthew J Struebig, Jake E Bicknell

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.