In this age of neural network “AI,” even the most ardent Butler skeptics have to agree that these machine learning models can be very good at pattern recognition if nothing else. NASA is in the same vein, and to take advantage of pattern recognition, they built a machine learning module called COFFIES, which stands for Consequences of fields and fluxes in and out of the SunBecause everything at NASA is an acronym, or at least a back name. Like most such names, this one is at least vaguely descriptive: the model tries to predict what’s going on in the material flows and magnetic fields deep inside our local star, and using these inferences it’s able to predict active regions — which are sunspots to us chickens — up to 12 hours before they visibly form.
The measurements used here are indirect – we cannot directly map the magneto-hydrodynamic roar deep within the star, but we can measure the magnetic field and sound waves at and above the surface. You could say that the model “hears” sunspot formation. Like all these models, it’s a bit of a black box, but heliophysicists may be able to use its predictions to help them better understand their organic understanding of the big ball of plasma to which we all owe our lives.
So this model is one of the best things to come out of the AI revolution, and no one will do it Give up their thinking to the machine And stop trying to understand the sun, COFFIES will probably give you a few hours of extra warning before Carrington’s next event class A geomagnetic storm can be invaluable, especially since The storm wall that blocks the glow It remains a theoretical exercise at best. If you’re interested in the sun, COFFIES has an interesting YouTube channel, and as you can see in a recent video, They are doing a lot with artificial intelligence.
