A machine learning approach to understand how accessibility influences alluvial gold mining expansion in the Peruvian Amazon

Larrea‐Gallegos, Gustavo; Kahhat, Ramzy; Vázquez‐Rowe, Ian; Parodi, Eduardo

doi:10.1016/j.cscee.2023.100353

Cited by 3 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, the most prominent in terms of its ecological impact has been artisanal and small‐scale gold mining (ASGM), which has been occurring in the area since the 1970s via mostly informal and illegal operations (Asner & Tupayachi, 2016; Brack Egg et al., 2011; Diringer et al., 2020; Swenson et al., 2011). ASGM operations in the Amazon involve deforestation, soil excavation, and the use of large amounts of liquid mercury, among other processes, that negatively impact the environment (Caballero Espejo et al., 2018; Cheng et al., 2023; Gerson et al., 2020; Kahhat et al., 2019; Larrea‐Gallegos et al., 2023; Martins et al., 2022). As a result, between 1984 and 2021, nearly 120,000 ha (1200 km 2 ) of forests were lost due to ASGM in Madre de Dios (Caballero Espejo et al., 2018; Dethier, Silman, Leiva, et al., 2023).…”

Section: Introductionmentioning

confidence: 99%

“…ASGM operations in the Amazon involve deforestation, soil excavation, and the use of large amounts of liquid mercury, among other processes, that negatively impact the environment (Caballero Espejo et al, 2018;Cheng et al, 2023;Gerson et al, 2020;Kahhat et al, 2019;Larrea-Gallegos et al, 2023;Martins et al, 2022). As a result, between 1984 and 2021, nearly 120,000 ha (1200 km 2 ) of forests were lost due to ASGM in Madre de Dios (Caballero Espejo et al, 2018;Dethier, Silman, Leiva, et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Assessing fish diversity in abandoned mining ponds in Madre de Dios, Peru, using environmental DNA

Timana‐Mendoza,

Reyes‐Calderon,

Venail

et al. 2024

Environmental DNA

View full text Add to dashboard Cite

The Peruvian region of Madre de Dios is a biodiversity hotspot located in the Andean‐Amazon region. Since the 1970s, it has experienced the harsh effects of artisanal and small‐scale gold mining (ASGM), which has transformed the primary forests into numerous small mining ponds left abandoned after extraction. Preliminary surveys indicate that these ponds are being recolonized by surrounding biodiversity. These assessments are typically carried out using traditional methods that are costly, difficult to deploy at multiple locations, and have raised safety concerns. In this context, environmental DNA (eDNA) becomes a useful tool for biodiversity monitoring due to its simplicity for sample collection and performance to identify taxonomic groups. In this study, we evaluated fish biodiversity in two mining ponds created by ASGM along with two nearby pristine lakes, unimpacted by mining operations but also influenced by seasonal flooding. We compared two alternative eDNA processing methods and contrasted our results with historic data from traditional biodiversity monitoring. Both eDNA‐based methods yielded comparable results, varying only in logistic requirements and costs. In total, we detected 85 fish MOTUs (22 at the species level) from 5 orders, 22 families, and 41 genera. Some of the species identified with eDNA were rarely registered by traditional monitoring, and we could identify 6 genera associated with ASGM mining ponds only. A major restriction of the eDNA approach in this location was the insufficient local taxa registered in genomic databases which limited our taxonomic resolution. Despite this limitation, our results indicate that eDNA could be a powerful tool for biodiversity estimations in the Western Amazon, identifying more taxa, with much less time and money invested than traditional monitoring. Our results also confirm that abandoned mining ponds are being recolonized by surrounding ichthyofauna, reaching richness levels above nearby unmined oxbow lakes used as reference.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Assessing fish diversity in abandoned mining ponds in Madre de Dios, Peru, using environmental DNA

Timana‐Mendoza,

Reyes‐Calderon,

Venail

et al. 2024

Environmental DNA

View full text Add to dashboard Cite

show abstract

Spatio-temporal trends of mercury levels in alluvial gold mining spoils areas monitored between rainy and dry seasons in the Peruvian Amazon

Becerra-Lira,

Rodriguez-Achata,

Muñoz Ushñahua

et al. 2024

Environmental Research

View full text Add to dashboard Cite

Machine Learning in Geosciences: A Review of Complex Environmental Monitoring Applications

Binetti,

Massarelli,

Uricchio

2024

MAKE

View full text Add to dashboard Cite

This is a systematic literature review of the application of machine learning (ML) algorithms in geosciences, with a focus on environmental monitoring applications. ML algorithms, with their ability to analyze vast quantities of data, decipher complex relationships, and predict future events, and they offer promising capabilities to implement technologies based on more precise and reliable data processing. This review considers several vulnerable and particularly at-risk themes as landfills, mining activities, the protection of coastal dunes, illegal discharges into water bodies, and the pollution and degradation of soil and water matrices in large industrial complexes. These case studies about environmental monitoring provide an opportunity to better examine the impact of human activities on the environment, with a specific focus on water and soil matrices. The recent literature underscores the increasing importance of ML in these contexts, highlighting a preference for adapted classic models: random forest (RF) (the most widely used), decision trees (DTs), support vector machines (SVMs), artificial neural networks (ANNs), convolutional neural networks (CNNs), principal component analysis (PCA), and much more. In the field of environmental management, the following methodologies offer invaluable insights that can steer strategic planning and decision-making based on more accurate image classification, prediction models, object detection and recognition, map classification, data classification, and environmental variable predictions.

show abstract

A machine learning approach to understand how accessibility influences alluvial gold mining expansion in the Peruvian Amazon

Cited by 3 publications

References 41 publications

Assessing fish diversity in abandoned mining ponds in Madre de Dios, Peru, using environmental DNA

Assessing fish diversity in abandoned mining ponds in Madre de Dios, Peru, using environmental DNA

Spatio-temporal trends of mercury levels in alluvial gold mining spoils areas monitored between rainy and dry seasons in the Peruvian Amazon

Machine Learning in Geosciences: A Review of Complex Environmental Monitoring Applications

Contact Info

Product

Resources

About