Exoplanet formation inference using conditional invertible neural networks

• URL: http://arxiv.org/abs/2512.05751v1
• Date: Fri, 05 Dec 2025 14:38:34 GMT
• Title: Exoplanet formation inference using conditional invertible neural networks
• Authors: Remo Burn, Victor F. Ksoll, Hubert Klahr, Thomas Henning,
• Abstract summary: We train conditional invertible neural networks (cINNs) on synthetic data from a global planet formation model.<n>We find that training on multiplanetary data, each planet treated as individual point, is promising.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• A Self-Evolving AI Agent System for Climate Science [59.08800209508371]
  We introduce EarthLink, the first self-evolving AI agent system designed as an interactive "copilot" for Earth scientists.<n>Through natural language interaction, EarthLink automates the entire research workflow by integrating planning, code execution, data analysis, and physical reasoning.<n>It exhibits human-like cross-disciplinary analytical ability and proficiency comparable to a junior researcher in expert evaluations on core large-scale climate tasks.
  arXiv  Detail & Related papers  (2025-07-23T08:29:25Z)
• Towards LLM Agents for Earth Observation [63.163707376462405]
  We introduce datasetnamenospace, a benchmark of 140 yes/no questions from NASA Earth Observatory articles across 13 topics and 17 satellite sensors.<n>Using Google Earth Engine API as a tool, LLM agents can only achieve an accuracy of 33% because the code fails to run over 58% of the time.<n>We improve the failure rate for open models by fine-tuning synthetic data, allowing much smaller models to achieve comparable accuracy to much larger ones.
  arXiv  Detail & Related papers  (2025-04-16T14:19:25Z)
• Exoplanets Prediction in Multi-Planetary Systems and Determining the Correlation Between the Parameters of Planets and Host Stars Using Artificial Intelligence [0.0]
  We search for additional exoplanets in 229 multi-planetary systems that house at least three or more confirmed planets. We employ efficient machine learning approaches to analyze a dataset comprising 762 confirmed exoplanets and eight Solar System planets. For giant planets, we observe a strong correlation between planetary radius and the mass of their host stars, which might provide intriguing insights into the relationship between giant planet formation and stellar characteristics.
  arXiv  Detail & Related papers  (2024-02-27T21:28:08Z)
• DBNets: A publicly available deep learning tool to measure the masses of young planets in dusty protoplanetary discs [49.1574468325115]
  We develop DBNets, a tool to quickly infer the mass of allegedly embedded planets from protoplanetary discs. We extensively tested our tool on out-of-distribution data. DBNets can identify inputs strongly outside its training scope returning an uncertainty above a specific threshold. It can be reliably applied only on discs observed with inclinations below approximately 60deg, in the optically thin regime.
  arXiv  Detail & Related papers  (2024-02-19T19:00:09Z)
• Multiple Random Masking Autoencoder Ensembles for Robust Multimodal Semi-supervised Learning [64.81450582542878]
  There is an increasing number of real-world problems in computer vision and machine learning. In the case of Earth Observations from satellite data, it is important to be able to predict one observation layer.
  arXiv  Detail & Related papers  (2024-02-12T20:08:58Z)
• Real-World Humanoid Locomotion with Reinforcement Learning [92.85934954371099]
  We present a fully learning-based approach for real-world humanoid locomotion. Our controller can walk over various outdoor terrains, is robust to external disturbances, and can adapt in context.
  arXiv  Detail & Related papers  (2023-03-06T18:59:09Z)
• Revisiting mass-radius relationships for exoplanet populations: a machine learning insight [0.0]
  We employ efficient machine learning approaches to analyze a dataset comprising 762 confirmed exoplanets and eight Solar System planets. By applying different unsupervised clustering algorithms, we classify the data into two main classes:'small' and 'giant' planets. Our analysis highlights that planetary mass, orbital period, and stellar mass play crucial roles in predicting exoplanet radius.
  arXiv  Detail & Related papers  (2023-01-17T19:15:06Z)
• Predictive World Models from Real-World Partial Observations [66.80340484148931]
  We present a framework for learning a probabilistic predictive world model for real-world road environments. While prior methods require complete states as ground truth for learning, we present a novel sequential training method to allow HVAEs to learn to predict complete states from partially observed states only.
  arXiv  Detail & Related papers  (2023-01-12T02:07:26Z)
• Locating Hidden Exoplanets in ALMA Data Using Machine Learning [10.316742952272394]
  We demonstrate that machine learning can quickly and accurately detect the presence of planets. We train our model on synthetic images generated from simulations and apply it to real observations to identify forming planets in real systems.
  arXiv  Detail & Related papers  (2022-11-17T14:02:16Z)
• On planetary systems as ordered sequences [7.216830424040808]
  We consider what information belongs to the configuration, or ordering, of 4286 Kepler planets in their 3277 planetary systems. We train a neural network model to predict the radius and period of a planet based on the properties of its host star. We adapt a model used for unsupervised part-of-speech tagging in computational linguistics to investigate whether planets or planetary systems fall into natural categories with physically interpretable "grammatical rules"
  arXiv  Detail & Related papers  (2021-05-20T18:00:29Z)
• Analyzing the Stability of Non-coplanar Circumbinary Planets using Machine Learning [0.0]
  We analyze orbital stability of exoplanets in non-coplanar circumbinary systems using a numerical simulation method. We train a machine learning model that can quickly determine the stability of the circumbinary planetary systems. Our results indicate that larger inclinations of the planet tend to increase the stability of its orbit, but change in the planet's mass range between Earth and Jupiter has little effect on the stability of the system.
  arXiv  Detail & Related papers  (2021-01-07T00:59:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.