MAAP #212: Using Machine Learning to Detect Mining Deforestation Across the Amazon

June 11, 2024

Gold Mining is one of the major deforestation drivers across the Amazon, often targeting remote areas such as protected areas and indigenous territories. Given the vastness of the Amazon, accurately monitoring mining deforestation in the most real-time, up-to-date format has been a challenge.

To help better analyze deforestation patterns, our latest MAAP report, MAAP #212, gathers results from a new machine learning-based tool known as Amazon Mining Watch, which analyzes satellite imagery archives to detect mining deforestation across the entire Amazon. Machine learning, a subset of artificial intelligence (AI), focuses on the development of algorithms and statistical models that allow computers to learn from and make predictions or decisions based on data. In this case, the use of machine learning in MAAP helps provide a more prompt and accurate analysis of mining deforestation across the entire biome by producing 10-meter resolution mining deforestation alerts based on the European Space Agency’s Sentinel-2 satellite imagery. The alerts currently cover each year annually from 2018 to 2023.

This data collected from Amazon Mining Watch reveals that gold mining is actively causing deforestation in all nine countries of the Amazon Biome.

We estimate that as of 2018, there was a historical mining deforestation footprint of over 963,000 hectares across the Amazon. Between 2019 and 2023, we estimate the mining deforestation footprint grew by over 944,000 hectares (2.3 million acres).

Thus, of the total accumulated mining deforestation footprint of over 1.9 million hectares (4.7 million acres), about half has occurred in just the past five years.

The countries with the most overall mining deforestation are 1) Brazil 55%, 2) Guyana (15%), 3) Suriname (12%), 4) Venezuela (7%), and 5) Peru (7%).

We also present five case studies that highlight the power of the data to see recent trends in mining deforestation.

A. Southern Peruvian Amazon. In one of the most emblematic mining sites in the Amazon, we recorded over 135,000 hectares of mining deforestation, of which 38% (51,000 ha) has occurred in just the past five years. We also highlight that 41% (55,000 hectares) is likely illegal.

B. Brazilian Amazon – Yanomami Indigenous Territory. The data shows a major escalation and expansion of gold mining deforestation since 2018, especially along the Uraricoera and Mucajai Rivers. Specifically, we documented the total mining deforestation of over 19,000 hectares, of which the vast majority (93%) has occurred in just the past five years.

C. Brazilian Amazon – Kayapó Indigenous Territory. We documented the mining deforestation of nearly 50,000 hectares, of which 60% (30,000 has) has occurred in just the past five years.

D. Venezuelan Amazon – Yapacana National Park. We documented the mining deforestation of over 6,000 hectares in the southern part of the park, of which just over half (52%) has occurred in just the past five years.

E. Ecuadorian Amazon – Punino zone. We documented the mining deforestation of over 500 hectares in the Punino River area, of which 100% is new (starting in 2023).

 

Read the full report here.