A large-scale trial involving thousands of flights between the United States and Europe has demonstrated that aircraft can produce considerably fewer contrails when following flight paths recommended by artificial intelligence. This AI-driven approach aims to mitigate the global warming impact associated with these condensation trails.
Contrails, which are streaks of condensed water vapor formed by soot particles emitted from aircraft engines, are believed to contribute more to global warming than the carbon dioxide released by planes. Research indicates that certain ice-rich regions in the upper atmosphere are particularly prone to contrail formation when aircraft pass through them. Advanced AI models can now predict the location of these areas by analyzing detailed weather forecasts.
Previous smaller trials have shown that rerouting aircraft through these less conducive areas can result in fewer contrails. However, implementing this practice on a commercial scale has remained a challenge.
In a recent randomized controlled trial, a team led by Dinesh Sanekommu at Google utilized an AI contrail-forecasting tool to provide routing recommendations for over 2,400 actual American Airlines flights. This experiment specifically examined eastbound flights from the US to Europe, spanning approximately 17 weeks from January to May 2025. The one-way focus was chosen because contrails exhibit a more pronounced warming effect at night. During daylight, contrails can have a cooling influence by reflecting sunlight back into space.
Each flight route between its origin and destination was randomly assigned to one of two experimental groups. For the first group, air traffic dispatchers were provided with an option in their flight-planning software to select an AI-optimized, low-contrail route. The second group, serving as a control, received no such alternative suggestions.
Despite the availability of the low-contrail route option, dispatchers in the first group ultimately chose the alternative path in only 112 out of 1,232 flights. This limited adoption was attributed to operational considerations, including cost and safety concerns, as noted by Sanekommu.
An AI analysis of satellite imagery tracking flight paths revealed a 62% reduction in visible contrails for flights that followed the contrail-optimized routes suggested to dispatchers. Considering all flights that had the option of taking such a route, the overall effective reduction in contrail formation reached 11.6% when compared to the control group.
“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,” Sanekommu stated.
The research team estimates that the overall warming effect of the flights was reduced by 13.7% within the group that received route suggestions. For the flights that actually followed the optimized routes, this reduction was a substantial 69.3%. Notably, there was no statistically significant difference in fuel consumption between the two groups.
“This is probably the best you can do, at least with the tools we have at the moment,” commented Edward Gryspeerdt from Imperial College London. “It does indicate that this is possible. The 62 per cent reduction in satellite-observed contrails that they see is unlikely to have happened by chance.”
However, Gryspeerdt cautioned that due to the complexities of flight planning, the achievable reduction in real-world operations might differ from the observed results. “You can’t necessarily just scale this up to be a 60 per cent reduction in contrails from every flight everywhere, but even a 10 per cent reduction in contrails is still a non-negligible effect,” he added.