Exoplanet Formation Inference Using Conditional Invertible Neural Networks

The interpretation of the origin of observed exoplanets is usually done only qualitatively due to uncertainties of key parameters in planet formation models.

To allow a quantitative methodology which traces back in time to the planet birth locations, we train recently developed conditional invertible neural networks (cINN) on synthetic data from a global planet formation model which tracks growth from dust grains to evolved final giant planets.

In addition to deterministic single planet formation runs, we also include gravitationally interacting planets in multiplanetary systems, which include some measure of chaos. For the latter case, we treat them as individual planets or choose the two or three planets most likely to be discovered by telescopes.

We find that training on multiplanetary data, each planet treated as individual point, is promising. The single-planet data only covers a small range of planets and does not extrapolate well to planet properties not included in the training data. Extension to planetary systems will require more training data due to the higher dimensionality of the problem.

Remo Burn, Victor F. Ksoll, Hubert Klahr, Thomas Henning

Comments: 10 pages, accepted poster for the Machine Learning and the Physical Sciences Workshop at the 39th conference on Neural Information Processing Systems (NeurIPS 2025)
Subjects: Earth and Planetary Astrophysics (astro-ph.EP); Neural and Evolutionary Computing (cs.NE); Data Analysis, Statistics and Probability (physics.data-an)
Cite as: arXiv:2512.05751 [astro-ph.EP] (or arXiv:2512.05751v1 [astro-ph.EP] for this version)
https://doi.org/10.48550/arXiv.2512.05751
Focus to learn more
Journal reference: Machine Learning and the Physical Sciences Workshop, 39th conference on Neural Information Processing Systems (NeurIPS 2025)
Submission history
From: Remo Burn
[v1] Fri, 5 Dec 2025 14:38:34 UTC (5,701 KB)
https://arxiv.org/abs/2512.05751

Astrobiology,