Posted in | News | Drones and UAVs

USP Researchers Launch AI-Driven Drones to Track Wildfires and Greenhouse Gas Emissions in Real Time

Researchers at the University of São Paulo (USP) are developing AI-powered drones equipped with gas sensors to detect forest fires and monitor greenhouse gases (GHGs) in real time.

To validate the use of drones for collecting GHG data, the researchers conducted tests around the USP campus in São Carlos (photos: Antonio Daud)
To validate the use of drones for collecting GHG data, the researchers conducted tests around the USP campus in São Carlos. Image Credit: Antonio Daud

This new approach offers a faster, more flexible, and more affordable alternative to traditional satellite and aircraft-based systems—and could eventually support large-scale monitoring efforts in critical regions like the Amazon.

A Smarter Way to Monitor the Environment

Conventional tools for tracking wildfires and GHG emissions—such as satellites, aircraft, and fixed observation towers—often come with high costs and slow response times.

To overcome those challenges, a team at USP’s São Carlos Engineering School is combining low-cost gas sensors with onboard artificial intelligence in drones capable of collecting volumetric gas data during flight. Unlike satellites, which typically provide surface-level data with delays, these drones can zero in on emission sources quickly and generate three-dimensional maps in near real time.

The project, presented during FAPESP Week France, builds on research supported by the Research Center for Greenhouse Gas Innovation (RCGI). Initial field trials in São Carlos have demonstrated the system’s potential for early fire detection and precise GHG mapping. The next step is extending flight range and endurance to enable use in larger and more remote areas, such as the Amazon rainforest.

How it Works

Each drone is outfitted with sensors that measure carbon dioxide, methane, temperature, and humidity—essentially creating an airborne “electronic nose.” As the drones fly over target areas, they collect data on gas concentrations and environmental conditions. Onboard AI processes this information in real time, identifying emission patterns and pinpointing their sources.

This capability allows the system to detect fires before they escalate, offering a critical advantage over traditional monitoring methods. Satellites might take days to pass over the same location, but drones can be launched on demand, delivering immediate data that can help first responders act quickly. This responsiveness has already proven to be valuable in early tests conducted in coordination with São Carlos’ Civil Defense and Environmental Department.

Versatility Beyond Fire Detection

Beyond spotting fires, these drones are also effective tools for greenhouse gas monitoring. Compared to towers or aircraft, both limited in scope and costly to operate, drones provide flexible, repeatable measurements at various altitudes. This enables more detailed tracking of CO2 and methane levels, particularly in ecologically sensitive or hard-to-reach areas.

Trials conducted in São Carlos, a region straddling both the Atlantic Forest and the Cerrado, have validated the system’s precision. Researchers are now focused on enhancing drone aerodynamics and battery life to extend flight times beyond the current 15–30 minute window. That upgrade is essential for broader deployment, especially in vast regions like the Amazon.

Looking Ahead

With their ability to gather high-resolution, real-time emissions data, USP’s drones offer a practical solution to key challenges in environmental monitoring. They complement existing tools by filling gaps in speed, accessibility, and depth of data, without the steep costs of satellite or aircraft systems.

As flight capabilities improve, these drones could become an essential part of Brazil’s environmental toolkit, particularly for fire prevention and climate research in the Amazon.

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.

Source:

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Nandi, Soham. (2025, June 25). USP Researchers Launch AI-Driven Drones to Track Wildfires and Greenhouse Gas Emissions in Real Time. AZoRobotics. Retrieved on July 08, 2025 from https://www.azorobotics.com/News.aspx?newsID=16064.

  • MLA

    Nandi, Soham. "USP Researchers Launch AI-Driven Drones to Track Wildfires and Greenhouse Gas Emissions in Real Time". AZoRobotics. 08 July 2025. <https://www.azorobotics.com/News.aspx?newsID=16064>.

  • Chicago

    Nandi, Soham. "USP Researchers Launch AI-Driven Drones to Track Wildfires and Greenhouse Gas Emissions in Real Time". AZoRobotics. https://www.azorobotics.com/News.aspx?newsID=16064. (accessed July 08, 2025).

  • Harvard

    Nandi, Soham. 2025. USP Researchers Launch AI-Driven Drones to Track Wildfires and Greenhouse Gas Emissions in Real Time. AZoRobotics, viewed 08 July 2025, https://www.azorobotics.com/News.aspx?newsID=16064.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.