Remote sensing capabilities of detecting spatio-temporal dynamics in unregulated extractivism hotspots in Ecuador

Degradation of the Amazon rainforest is increasing by expanding human activities, especially unregulated extractivism. Particularly gold mining is a major driver of environmental change, causing large-scale deforestation, river fragmentation and increased sediment loads. These pressures have intensified over the past decade due to rising global gold prices and policy shifts, most notably the 2016 decision by the Ecuadorian government to open approximately 13% of the national territory to mining exploration, including areas that were previously under protection ^{[1, 2]}.

This study assesses the suitability of different remote sensing datasets for detecting unregulated mining and investigates the spatio-temporal dynamics of mining expansion in the Ecuadorian Amazon. The analysis focuses on three mining hotspots in eastern Ecuador (further called Punino, Napo, and Shaime) where unregulated activities have been widely reported. Given the sensitivity of the topic and the need for transparent and reproducible information, the study relies exclusively on remote sensing data, including Sentinel-1 synthetic aperture radar (SAR) data and PlanetScope optical imagery, as well as the Satellite Embedding Datatset V1 (SED). All datasets are processed mainly in Google Earth Engine (GEE) with dataset-specific methodologies applied. Supervised classification approaches were used, employing a k-NN classifier for the SED dataset and a random forest classifier for PlanetScope imagery, covering the period from 2017 to 2024. For Sentinel-1 data, a Sequential Change Detection (SCD) approach was implemented, evaluating multi-temporal polarimetric SAR time series to detect statistically significant changes throughout the specified observation period, with a revisit interval of approximately 12 days.

Results show a pronounced increase in mining extent and associated deforestation across all study areas, with particularly strong expansion during 2023 and 2024. In the Punino region, several sub-areas exhibited mining coverage approaching 10 % of the total AOI in 2024, while one sub-AOI exceeded 20 %, corresponding to approximately 13.2 km² of mining area. Comparison of classification results indicates that persistent cloud cover and temporal inconsistencies limit the effectiveness of optical PlanetScope data, whereas the SED dataset provides a reliable and efficient alternative for annual assessments with minimal preprocessing requirements. The SCD analysis revealed detailed expansion dynamics, demonstrating that mining typically initiates along major rivers and progressively expands toward tributaries and surrounding forest areas. The multi-method approach further enables cross-validation of results, which are consistent with independent reports documenting similar spatial patterns and trends.

The severe environmental consequences of unregulated mining, including deforestation, water pollution, and threats to indigenous communities, emphasize the importance of systematic and transferable remote sensing-based monitoring frameworks to support environmental protection in the Ecuadorian Amazon and enable timely, accessible reporting for environmental governance and decision-making.

 

[1] Albert, J. S., Carnaval, A. C., Flantua, S. G., Lohmann, L. G., Ribas, C. C., Riff, D., ... & Nobre, C. A. (2023). Human impacts outpace natural processes in the Amazon. Science, 379(6630), eabo5003.

[2] Roy, B. A., Zorrilla, M., Endara, L., Thomas, D. C., Vandegrift, R., Rubenstein, J. M., ... & Read, M. (2018). New mining concessions could severely decrease biodiversity and ecosystem services in Ecuador. Tropical Conservation Science, 11, 1940082918780427.