Case Studies - Amazon Mining Watch
This work grew out of a series of collaborations with journalists and with activists seeking to expose illegal gold-mining activity and document its impacts on the environment and on local Indigenous communities.
The team of developers began identifying mines by sight in satellite imagery. Later, some high school classes helped Earthrise Media in the image sleuthing. Finally, it made sense to try to automate the identification of mine sites. The training datasets for the machine-learned models followed those painstaking human surveys.
Reports using the automated detections:
- “The pollution of illegal gold mining in the Tapajós River,” InfoAmazonia, 2021. The story is part of the series Murky Waters, on pollution in the Amazon River system and links to sargassum seaweed blooms in the Caribbean.
- “Las pistas illegales que bullen en la selva Venezolana,” El País and ArmandoInfo, 2022. First in the series Corredor Furtivo. Produced in conjunction with the Pulitzer Center's Rainforest Investigations Network (in English, translated).
- “Amazon gold rush: The threatened tribe,” Reuters, 2019, on illegal mining in protected Yanomami Indigenous Territory.
- “Illegal mining sparks malaria outbreak in Indigenous territories in Brazil,” InfoAmazonia and Mongabay, 2020.
- “Serious risk of attack by miners on uncontacted Yanomami in Brazil,” Survival International, 2021.
- “Gana por ouro,” The Intercept, 2021. Report on an industrial gold mine operating without proper environmental permits. Two weeks after the story appeared, the mine was shut down and fined.
- “Garimpo destruidor,” The Intercept, 2021.
Many thanks to our collaborators, whose skill and resourceful reporting brought these important stories to light. If you are a journalist and want to investigate some of the areas of mining identified by this tool, we recommend you check on the geographical coordinates of the mines as provided in our interactive map. The location data will help you to cross-reference the information with other databases, such as deforestation or mining concessions. By correlating these datasets, you might be able to find the corporate actors responsible for the mining sites and determine the legality of the operations.