)"Solved" is maybe too strong a word for that paper... DNN's are trained to approximate the functions produced by numerical integrators. This leads to a constant-computational cost approximate solution. As far as I can tell anyways...gleem said:
The Three Body Problem is a classical mechanics problem that involves three bodies (usually celestial bodies) interacting with each other through gravitational forces. It is a notoriously difficult problem to solve analytically, and has been a subject of study for centuries.
The Statistical (almost) Solution to the Three Body Problem is a method proposed by physicist Jürgen Kurths and his team in 2015. It involves using statistical mechanics and a computer algorithm to approximate the motion of three bodies over time, taking into account the chaotic nature of the system.
The Statistical (almost) Solution has been shown to be accurate up to 10,000 years in the future, which is a significant improvement compared to previous analytical solutions. However, it should be noted that the accuracy decreases as time goes on, due to the chaotic nature of the system.
The Statistical (almost) Solution has potential applications in various fields, such as astrophysics, celestial mechanics, and climate science. It can also help us better understand the long-term stability of planetary systems and the universe as a whole.
While the Statistical (almost) Solution is a significant breakthrough in solving the Three Body Problem, it is not a perfect solution. It still has limitations, such as the inability to accurately predict the exact positions of the bodies at any given time, and the inability to account for external factors that may affect the system. Further research and improvements are needed to fully understand and solve the Three Body Problem.