AI for contrail reduction

[rationalfunctions]

Google have marketed an interesting pilot they are running, using AI data to predict conditions that create contrails and provide advisory on how to avoid.

There's a nice glossy youtube video https://www.youtube.com/watch?v=xBkK7olwjx0.

Whilst it's easy to be dubious/sceptical about some of the data and claims, curious to get some perspectives on the actual benefits/viability of this...

[Klauss]

Hi, I like the post. Also, like that something is done ....but I don´t see research into the overall picture.
Is it worth flying higher, lower or whatever , deviating from the ´´optimum´´ flight plan ?
That costs fuel, increases CO2. CO2 stays for decades, contrails are gone after hours.
?

[rationalfunctions]

Valid point. From background research the general consensus is that impact of contrails is problematic, although the scale is debatable.

Google do have a website with some further info/Q&A at https://sites.research.google/contrails/ which includes the following claim

Is there a risk that you cause more harm than good? You’re burning additional fuel - how do you know the additional fuel you’re burning isn’t worse than the contrails you’re mitigating?
Our teams spend a lot of time making sure we are having a net beneficial impact on the climate. When scaled up across an airline’s fleet, our results suggest that the additional fuel burn would be about 0.3%. Using numbers from the IPCC, the reduction in contrail warming is 20x greater than the additional CO2 from fuel burn