New AI Calculates Distant Planet Orbits 100,000 Times Faster
We live in a solar system of eight planets, none of which collide with each other, which is nice for us. How often do planets in other solar systems smash into each other, though? A new AI designed by Princeton researchers can crunch the numbers with record speed to determine which potential orbits are stable and which will result in catastrophe. This could help astronomers nail down the orbits of distant solar systems we can’t examine in sufficient detail.
Our current exoplanet detection technology can’t provide accurate orbital information, but we can get a general idea of the mechanics by analyzing what we do know and modeling the various options. Unfortunately, there are a lot of potential orbits, and modeling a billion or so of them can take many hours even with powerful supercomputers. Daniel Tamayo, a NASA Hubble Fellowship Program Sagan Fellow in astrophysical sciences at Princeton, devised the algorithm as an alternative to the “brute force” computing that researchers currently use.
According to Tamayo, separating potentially stable from unstable orbits is computationally expensive, even with current supercomputers because there are so many orbits to explore. Tamayo’s SPOCK (Stability of Planetary Orbital Configurations Klassifier) system simplifies the process by combining a pared down model of planetary interactions with machine learning techniques. This allows SPOCK to quickly rule out the most unstable options, giving you a few thousand plausible orbits in a fraction of a second instead of hours.
At a basic level, the algorithm separates systems that will fly apart or smash together “soon” from stable ones. In this case, “soon” means in the space of a few million years. Given the average lifespan of a solar system, it’s unlikely astronomers are seeing any of these doomed configurations. The AI starts by simulating 10,000 orbits. SPOCK creates 10 summary metrics from that data to capture the system’s resonant dynamics, and then the algorithm predicts based on these metrics whether the configurations would remain stable for a billion orbits. This works out to be about 100,000 times faster than traditional methods.
SPOCK can’t tell you exactly what an alien solar system looks like, but it can rule out configurations that are definitely unstable. This could help astronomers narrow their observations as they attempt to study distant exoplanets. Maybe someday we’ll have instruments powerful enough to get an accurate picture of exoplanet orbits, but for now, we’ll have to leave it to the AI.
- Astronomers Find Two Super-Earths Orbiting Nearby Red Dwarf
- This Yellow Swirl Could Be the Birth of a New Planet
- The Hottest Known Planet Continuously Melts its Own Atmosphere