Africa Mining Watch trains journalists to spot illegal mines from space
New CapabilitiesA Pulitzer Center, Code for Africa and Earth Genome tool brings satellite AI to extractives reporting across the Congo Basin
July 2026: Planned public launchNew here? Follow stories to track developments over time. Create a free account to get updates when stories you care about change.
Overview
Updated May 24Spotting a fresh mining pit in the Congo Basin used to take months of ground reporting and a small fortune in plane tickets. On April 22, about 25 African journalists logged into an online mapathon and learned to find one in minutes, using Sentinel-2 satellite imagery and a machine-learning model trained to recognize the bare-earth scar of an open pit.
The training is the soft launch of Africa Mining Watch, a tool built by the Pulitzer Center, Code for Africa and Earth Genome. A public release is planned for July. The platform copies the playbook of Amazon Mining Watch, which has already sparked investigations into illegal gold mining in Brazil, Spain, Venezuela and the United States.
Why it matters
Reporters covering Congo Basin mining can now see new pits the week they appear, not months later when communities finally complain.
Questions about this story
Free account needed to ask — your question is kept and asked for you right after sign-up. Answers are public.
No questions yet — be the first to ask.
Key Indicators
Voices
Curated perspectives — historical figures and your fellow readers.
Play
Exploring all sides of a story is often best achieved with Play.
Higher or Lower
A number from this story, against one from elsewhere in the news — guess which is bigger, then keep the chain going. 5 rounds, 3 strikes; a miss costs a strike and resets your streak.
Keyboard: ↓/L lower · ↑/H higher
0 points — sign up to put that on the leaderboard.
Connections
Sixteen names from the news. Find the four hidden groups of four. Four mistakes max.
Sign up to keep a daily streak — a new puzzle lands every day.
Exit debate?
Your progress in this debate will be lost.
- 1 Two AI personas square off on this story.
- 2 You predict who'll win each round — correct picks earn XP.
- 3 One crossfire question is yours to fire. Pick it carefully.
Couldn't generate a topic
Select Your Champions
Choose one persona for each side of the debate
DEBATE TOPIC
Choose personas with different perspectives for a more dynamic debate.
Select debater for this side:
No debate personas available right now.
Select debater for this side:
No debate personas available right now.
Who's Got This Round?
Make your prediction before the referee scores
The referee scores both sides on
Round Results
Set the Crossfire
Pick the question both personas must answer in the final round
Debate Oracle! You called every round!
Sharp Instincts! You know your debaters!
The Coin Flip Strategist! Perfectly balanced!
The Contrarian! Bold predictions!
Inverse Genius! Try betting the opposite next time!
XP Breakdown
Prediction History
Organizations Involved
A Washington-based nonprofit that funds and trains journalists on under-covered international stories.
The continent's largest network of civic-tech and data-journalism teams, with labs in more than 20 African countries.
A nonprofit that builds machine-learning pipelines on satellite imagery for environmental monitoring.
Timeline
October 2022 July 2026
-
Planned public launch
Latest MilestonePartners say africaminingwatch.org will open to the public, with detection layers and an open data download.
-
Earth Day mapathon trains 25 African journalists
TrainingReporters from across the continent join an online mapathon. Earth Genome staff walk them through reading satellite tiles and flagging suspected mines.
-
Africa Mining Watch partnership announced
AnnouncementCode for Africa publishes the partnership announcement with the Pulitzer Center and Earth Genome on Medium.
-
Amazon platform moves to quarterly updates
CapabilityAmazon Mining Watch begins near-real-time quarterly detection of new gold-mining fronts, proving the model can run at production cadence.
-
Amazon Mining Watch launches
PrecedentEarth Genome, Amazon Conservation and the Pulitzer Center release the first AI-driven public map of gold-mining deforestation across all nine Amazonian countries.
Historical Context
3 moments from history that rhyme with this story — and how they unfolded.
Global Forest Watch launch (2014)
The World Resources Institute launched Global Forest Watch with Google, the University of Maryland and about 40 other partners. It put near-real-time deforestation alerts on a public web map, built on Landsat imagery and the Hansen forest-loss dataset.
Within a year, governments in Indonesia and Peru and NGOs in the Congo Basin used the alerts to direct enforcement and reporting. Newsrooms cited the data in dozens of investigations.
Global Forest Watch became permanent reference infrastructure for environmental reporting and accountability, with more than three million users by 2024.
It is the closest analog for what Africa Mining Watch is trying to be: a public, satellite-driven dataset that both watchdogs and reporters can plug into. Adoption was rapid once the data was free and clickable.
Bellingcat and the rise of open-source satellite reporting (2014 onward)
Eliot Higgins founded Bellingcat in 2014. The team used commercial satellite imagery and social-media geolocation to reconstruct the downing of Malaysia Airlines Flight 17 and later mapped Russian forces in eastern Ukraine and Syria.
Bellingcat investigations were cited by the Dutch Safety Board and the Joint Investigation Team that indicted suspects in the MH17 case.
Open-source intelligence using satellite data became a standard method in investigative journalism, with units at the New York Times, BBC and Reuters.
Africa Mining Watch tries to do for environmental reporters what Bellingcat did for conflict reporters: turn satellite imagery from a specialist resource into an everyday newsroom tool.
Amazon Mining Watch launch (2022)
Earth Genome, Amazon Conservation and the Pulitzer Center's Rainforest Investigations Network released the first AI-driven public map of gold-mining deforestation across all nine Amazonian countries. The site used a convolutional neural network on Sentinel-2 imagery to flag suspected pits at ten-meter resolution.
Within two years, reporters used the data to publish investigations in Brazil, Spain, Venezuela and the United States, several focused on mining inside Indigenous reserves.
The platform moved to quarterly updates in 2025 and became a standard reference for Amazon environmental coverage, including by Mongabay and MAAP.
Africa Mining Watch is a direct port of this project with the same lead engineering team. The Amazon timeline is the best guide to what the Africa version is likely to produce and when.
