A large-scale trial involving thousands of flights between the US and Europe has demonstrated that airplanes can generate fewer contrails by adhering to flight paths recommended by artificial intelligence (AI). This approach aims to mitigate their global warming impact.
Contrails, those condensation trails formed by soot particles from aircraft engines, are believed to contribute more to warming than the carbon dioxide planes emit. Research indicates that certain ice-rich areas in the upper atmosphere are particularly prone to contrail formation when aircraft pass through them. AI has shown potential in predicting the location of these sensitive regions by analyzing detailed weather forecasts.
Previous smaller trials have suggested that rerouting planes through these specific atmospheric zones can lead to a reduction in contrails. However, this practice has not yet been widely implemented in commercial aviation at scale.
Developing and Deploying AI for Contrail Avoidance
The recent study, led by Dinesh Sanekommu at Google and his collaborators, utilized an AI contrail-forecasting tool. This tool provided routing recommendations during a randomized controlled trial involving over 2400 actual American Airlines flights.
The trial specifically focused on flights traveling eastward from the US to Europe. It spanned approximately 17 weeks, from January to May 2025. The unidirectional nature of the flights was chosen because they occurred at night, a time when contrails are known to have a more pronounced warming effect. In contrast, contrails can exhibit a cooling effect during the day by reflecting sunlight back into space.
Trial Methodology and Findings
Each flight route between two designated cities was randomly assigned to one of two groups. For the first group, air traffic dispatchers were equipped with flight-planning software that offered an option to select an AI-optimized, low-contrail route. The second group did not receive any alternative route suggestions.
While dispatchers in the first group had the option to choose a low-contrail path, operational considerations such as cost or safety led to only 112 out of 1232 flights in this group actually adopting the alternative route, according to Sanekommu.
An AI analysis of satellite imagery of flight paths revealed a substantial reduction. Flights that followed the contrail-optimized route suggested to dispatchers exhibited a 62 percent lower amount of visible contrails. When considering all flights that had the option to take the optimized route, the overall effective reduction in contrail formation reached 11.6 percent when compared to the control group.
Implications and Expert Commentary
Sanekommu stated, “It validated the thesis of, if we could figure out how to safely and correctly integrate into the flight planning process, then this is a scalable route to consider contrail avoidance across many flights.”
The research team estimates that the flights’ warming impact was reduced by 13.7 percent for the entire group that received route suggestions. For the flights that actually took the optimized route, the reduction was a significant 69.3 percent. Importantly, no statistically significant difference in fuel consumption was observed between the two groups.
Edward Gryspeerdt at Imperial College London commented, “This is probably the best you can do, at least with the tools we have at the moment. It does indicate that this is possible. The 62 percent reduction in satellite-observed contrails that they see is unlikely to have happened by chance.”
However, Gryspeerdt noted that it remains unclear how much the 11.6 percent figure can be improved in real-world operations due to the complexities of flight planning. “You can’t necessarily just scale this up to be a 60 percent reduction in contrails from every flight everywhere, but even a 10 percent reduction in contrails is still a non-negligible effect,” he added.