[Big Think -> Nature -> PDF]- Princeton physicist Hong Qin creates an AI algorithm that can predict planetary orbits.
- The scientist partially based his work on the hypothesis which believes reality is a simulation.
- The algorithm is being adapted to predict behavior of plasma and can be used on other natural phenomena
| If this interests you go to Big Think read their synopsis and if you want to dig deeper follow their link to the PDF for the Nature article. |
Qin developed this algorithm to predict the orbits of planets in the solar system, training it on data of Mercury, Venus, Earth, Mars, Ceres, and Jupiter orbits. The data is "similar to what Kepler inherited from Tycho Brahe in 1601," as Qin writes in his newly-published paper on the subject. From this data, a "serving algorithm" can correctly predict other planetary orbits in the solar system, including parabolic and hyperbolic escaping orbits. What's remarkable, it can do so without having to be told about Newton's laws of motion and universal gravitation. It can figure those laws out for itself from the numbers.
Qin is now adapting the algorithm to predict and even control other behaviors, with a current focus on particles of plasma in facilities built for harvesting fusion energy powering the Sun and stars. Along with Eric Palmerduca, a Ph.D. graduate student at PPPL, Qin is using his technique "to learning an effective structure-preserving algorithm with long-term stability to simulate the gyrocenter dynamics in magnetic fusion plasmas," as he elaborated. He also plans to utilize the algorithm to study quantum physics.
|