Three Argentine teenagers built a wildfire AI. Now it is beating NASA on detection speed
Franco Rodriguez Viau was 16 when his hometown in Córdoba burned. At 22, his wildfire detection AI is alerting firefighters 35 minutes before NASA does.

Franco Rodriguez Viau was 16 when his hometown in Córdoba burned. At 22, his wildfire detection AI is alerting firefighters 35 minutes before NASA does.

image from grok
Satellites on Fire, a wildfire detection startup founded by three Argentine teenagers, aggregates imagery from 8+ satellites (NASA, NOAA, ESA) to achieve fire detection averaging 35 minutes ahead of NASA's FIRMS service—documented cases show up to 7-hour lead times. Their architectural edge stems from higher temporal resolution (5-minute updates) filling revisit gaps in NASA's constellation, particularly over Latin America. The company has closed a $2.7M seed round and is running pilots with US nonprofit Watch Duty, monitoring over 200 million hectares across 19 countries.
When Franco Rodriguez Viau was 16, he watched his hometown burn. Wildfires tore through Córdoba, Argentina in 2020, killing two people and scorching 60,000 hectares, according to Newsweek. His family friends lost their homes. He was a sophomore at ORT Buenos Aires with no formal engineering training and no budget. Three years later, his company is alerting firefighters to blazes seven hours before NASA's systems notice them.
Satellites on Fire, the wildfire detection startup Rodriguez Viau co-founded as a school project in 2020 with fellow teenagers Ulises López Pacholczak and Joaquín Chamo, has closed a $2.7 million seed round led by Dalus Capital, with participation from Draper Associates, Draper Cygnus, and nine other investors, The Next Web reported. The company monitors more than 200 million hectares across 19 countries and says its AI detects fires an average of 35 minutes ahead of NASA's FIRMS service.
The edge is architectural. NASA FIRMS relies on a relatively small constellation with multi-hour revisit gaps over Latin America, where satellite coverage is thinner. Satellites on Fire aggregates imagery from more than eight satellites operated by NASA, NOAA, and the European Space Agency, updated as frequently as every five minutes, then runs its own AI models against that aggregated feed. The company says this density of coverage is what closes the detection gap.
A documented case from Argentina, reported by Newsweek, illustrates the difference: the system flagged a fire at 1:40 a.m.; NASA's alert arrived seven hours later. In Mexico, brigades using the platform went an entire fire season with zero fatalities, Newsweek reported. The company says it has supported responses to more than 600 wildfires in 2025 and over 400 in just the last three months, The Next Web reported, though these figures are self-reported and haven't been independently audited.
John Mills, CEO of Watch Duty, the nonprofit wildfire tracking platform, is an advisor to the company. He told The Next Web the platform's results with existing satellite data had genuinely astounded his team. Watch Duty is running pilots with Satellites on Fire in the United States, where the 2025 Los Angeles fires sharpened commercial and political attention on detection gaps.
The commercial model is a software-as-a-service subscription, with pricing from $0.02 to $10 per hectare annually depending on service tier, according to The Next Web. Clients include forestry companies, agricultural operations, energy utilities, carbon credit projects, insurers, and government agencies. Aon has integrated the platform into its forestry insurance policies across Latin America for risk calculation and premium pricing.
The road to this point was not smooth. When the founders first showed their system to firefighters and national park managers, the response was blunt. "They told us that what we did was useless," Rodriguez Viau told Newsweek. The team went back to work, interviewed more than 80 firefighters and emergency responders, and rebuilt the system from scratch. The final version integrates satellite imagery, tower cameras, fire propagation modeling, and real-time alerts delivered to first responders via WhatsApp, showing predicted spread trajectories based on climate data and fuel load.
MIT Technology Review's Spanish edition named Rodriguez Viau among its 35 Innovators Under 35 for Latin America in 2025, The Next Web reported. The other co-founders hold the CTO and CPO titles. The team previously won a spot representing Argentina at the International Olympiad in Informatics, Draper Cygnus noted, and received early support from MIT, Cornell University, and the United Nations. The company has also received backing from Tim Draper and Adam Draper after appearing on Meet the Drapers Season 9.
The new capital will fund U.S. expansion, AI model optimization, and a parametric wildfire insurance product developed with Aon. Rodriguez Viau has also said the company eventually plans to move into suppression technology using drones, though no product exists yet and no timeline has been set.
There are open questions. The 35-minute detection advantage is a company-claimed figure based on internal metrics; independent verification across different geographies and conditions has not been published. The operational data comes from the company's own reporting. The $20 billion annual wildfire problem and 300,000 deaths per year cited by Draper Cygnus draw on global health and economic estimates that are difficult to attribute to any single detection platform. Whether Satellites on Fire can replicate its Latin American performance in the United States, where fire ecology and agency infrastructure differ significantly, is the test that matters next.
Story entered the newsroom
Assigned to reporter
Research completed — 3 sources registered. Three Argentine teenagers (Franco Rodriguez Viau, Ulises Lopez Pacholczak, Joaquin Chamo) founded Satellites on Fire in 2020 as a school project at OR
Draft (718 words)
Reporter revised draft (731 words)
Reporter revised draft (734 words)
Reporter revised draft based on fact-check feedback
Reporter revised draft based on fact-check feedback (736 words)
Approved for publication
Published (728 words)
Get the best frontier systems analysis delivered weekly. No spam, no fluff.
Artificial Intelligence · 3h 21m ago · 4 min read
Artificial Intelligence · 5h 20m ago · 3 min read