Researchers at the University of São Paulo’s São Carlos Engineering School are developing drones equipped with gas sensors and artificial intelligence to detect forest fires quickly and monitor greenhouse gas emissions.
This technology aims to help environmental and civil defense agencies in São Carlos, in the state of São Paulo, Brazil, detect fire hotspots early and prevent wildfires from spreading uncontrollably.
The drones are fitted with small, low-cost sensors that can detect gases such as carbon dioxide and methane – key indicators of forest fires – as well as temperature and humidity. AI systems then analyse the data to identify and locate emissions. This method allows for faster fire detection than satellite systems, enabling quicker response by authorities.
According to project coordinator Professor Glauco Caurin, the drones are already being considered for use by local agencies: ‘We’re already working with the Civil Defense, the city government, and the São Carlos Department of the Environment, and we’ve submitted a proposal to evaluate using the drones we’re developing to identify fire hotspots in the municipality.’
Beyond fire detection, the drones are also being tested for monitoring greenhouse gas emissions. Tests have established that drones are both more cost-effective and flexible than traditional methods like satellites, observation towers, or research aircraft. Drones can fly at variable altitudes and gather more detailed, volumetric data on gas concentrations, which satellites currently cannot provide.
Caurin said: ‘By collecting greenhouse gas data with drones, instead of an average of carbon dioxide or methane on a surface, it’s possible to obtain the volume of distribution of these gases in a given region.
‘Today, even with the best satellites, we’re unable to obtain this volumetric information. With drones, greenhouse gas data collection is no longer a surface or map of the region, but rather volumetric information.’
A key limitation is that commercial drones typically have a limited flight time of around 15 to 30 minutes, limiting their range. To address this, the team is working on improving drone efficiency through aerodynamic research. Initial tests have been conducted around the USP campus, with hopes to eventually deploy the technology in larger regions, including the Amazon.
Photo: Antonio Daud
Leave a Reply