Do you know what the Earths atmosphere is made of?
Youd probably remember its oxygen, and maybe nitrogen.
As exoplanets are so far away, it has proven extremely difficult to probe their atmospheres.
Now our new paper, published in theAstrophysical Journal, has provided reassuring insight into their mysterious logic.
Earth-sized planets produce 10-100 times lower signals.
Its a bit like spotting the eye color of a cat from an aircraft.
But while scientists are excited about this, thelatest researchsuggests it may be tricky.
40% off TNW Conference!
Scientists have therefore attempted to train AI to predict the abundance of various chemical species in atmospheres.
Current research has established thatAIs are well-suited for this task.
The bad news is that AIs are terrible at explaining their own findings.
Even AI experts have a hard time identifying what causes the internet to provide a given explanation.
This disadvantage has often prevented the adoption of AI techniques in astronomy and other scientific fields.
We developed a method that allows us a glimpse into the decision-making process of AI.
The approach is quite intuitive.
Suppose an AI has to confirm whether an image contains a cat.
It would presumably do this by spotting certain characteristics, such as fur or face shape.
This may come as no surprise, after all, where else can the AI learn it from?
That said, its too early to claim that we fully understand AIs.
The prospect is exciting for AI experts, but even more so for us scientists.
