ExoMDN: Rapid characterization of exoplanet interior structures with Mixture Density Networks

• URL: http://arxiv.org/abs/2306.09002v1
• Date: Thu, 15 Jun 2023 10:00:03 GMT
• Title: ExoMDN: Rapid characterization of exoplanet interior structures with Mixture Density Networks
• Authors: Philipp Baumeister and Nicola Tosi
• Abstract summary: We present ExoMDN, a machine-learning model for the interior characterization of exoplanets. We show that ExoMDN can deliver a full posterior distribution of mass fractions and thicknesses of each planetary layer in under a second on a standard Intel i5 CPU. We use ExoMDN to characterize the interior of 22 confirmed exoplanets with mass and radius uncertainties below 10% and 5% respectively.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Characterizing the interior structure of exoplanets is essential for understanding their diversity, formation, and evolution. As the interior of exoplanets is inaccessible to observations, an inverse problem must be solved, where numerical structure models need to conform to observable parameters such as mass and radius. This is a highly degenerate problem whose solution often relies on computationally-expensive and time-consuming inference methods such as Markov Chain Monte Carlo. We present ExoMDN, a machine-learning model for the interior characterization of exoplanets based on Mixture Density Networks (MDN). The model is trained on a large dataset of more than 5.6 million synthetic planets below 25 Earth masses consisting of an iron core, a silicate mantle, a water and high-pressure ice layer, and a H/He atmosphere. We employ log-ratio transformations to convert the interior structure data into a form that the MDN can easily handle. Given mass, radius, and equilibrium temperature, we show that ExoMDN can deliver a full posterior distribution of mass fractions and thicknesses of each planetary layer in under a second on a standard Intel i5 CPU. Observational uncertainties can be easily accounted for through repeated predictions from within the uncertainties. We use ExoMDN to characterize the interior of 22 confirmed exoplanets with mass and radius uncertainties below 10% and 5% respectively, including the well studied GJ 1214 b, GJ 486 b, and the TRAPPIST-1 planets. We discuss the inclusion of the fluid Love number $k_2$ as an additional (potential) observable, showing how it can significantly reduce the degeneracy of interior structures. Utilizing the fast predictions of ExoMDN, we show that measuring $k_2$ with an accuracy of 10% can constrain the thickness of core and mantle of an Earth analog to $\approx13\%$ of the true values.

Related papers

• Estimating Exoplanet Mass using Machine Learning on Incomplete Datasets [1.6231541773673115]
  More than 70% of discovered planets have no measured planet mass. We show how machine learning algorithms can be used to estimate missing properties for imputing planet mass.
  arXiv  Detail & Related papers  (2024-10-09T14:19:33Z)
• NeuralCMS: A deep learning approach to study Jupiter's interior [0.0]
  We propose an efficient deep neural network (DNN) model to generate high-precision wide-ranged interior models. We trained a sharing-based DNN with a large set of CMS results for a four-layer interior model of Jupiter. NeuralCMS shows very good performance in predicting the gravity moments, with errors comparable with the uncertainty due to differential rotation, and a very accurate mass prediction.
  arXiv  Detail & Related papers  (2024-05-15T10:55:16Z)
• 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)
• Towards Predicting Equilibrium Distributions for Molecular Systems with Deep Learning [60.02391969049972]
  We introduce a novel deep learning framework, called Distributional Graphormer (DiG), in an attempt to predict the equilibrium distribution of molecular systems. DiG employs deep neural networks to transform a simple distribution towards the equilibrium distribution, conditioned on a descriptor of a molecular system.
  arXiv  Detail & Related papers  (2023-06-08T17:12:08Z)
• 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)
• Exploring Chemical Space with Score-based Out-of-distribution Generation [57.15855198512551]
  We propose a score-based diffusion scheme that incorporates out-of-distribution control in the generative differential equation (SDE) Since some novel molecules may not meet the basic requirements of real-world drugs, MOOD performs conditional generation by utilizing the gradients from a property predictor. We experimentally validate that MOOD is able to explore the chemical space beyond the training distribution, generating molecules that outscore ones found with existing methods, and even the top 0.01% of the original training pool.
  arXiv  Detail & Related papers  (2022-06-06T06:17:11Z)
• Exoplanet Characterization using Conditional Invertible Neural Networks [21.516242058639637]
  Conditional invertible neural networks (cINNs) are a special type of neural network which excel in solving inverse problems. We show that cINNs are a possible alternative to the standard time-consuming sampling methods.
  arXiv  Detail & Related papers  (2022-01-31T19:00:06Z)
• Unsupervised Spectral Unmixing For Telluric Correction Using A Neural Network Autoencoder [58.720142291102135]
  We present a neural network autoencoder approach for extracting a telluric transmission spectrum from a large set of high-precision observed solar spectra from the HARPS-N radial velocity spectrograph.
  arXiv  Detail & Related papers  (2021-11-17T12:54:48Z)
• Exoplanet atmosphere evolution: emulation with random forests [0.0]
  Atmospheric mass-loss plays a leading role in sculpting the demographics of small, close-in exoplanets. We implement random forests trained on atmospheric evolution models to predict a given planet's final radius and atmospheric mass. Our new approach opens the door to highly sophisticated models of atmospheric evolution being used in demographic analysis.
  arXiv  Detail & Related papers  (2021-10-28T14:39:19Z)
• Relativistic aspects of orbital and magnetic anisotropies in the chemical bonding and structure of lanthanide molecules [60.17174832243075]
  We study the electronic and ro-vibrational states of heavy homonuclear lanthanide Er2 and Tm2 molecules by applying state-of-the-art relativistic methods. We were able to obtain reliable spin-orbit and correlation-induced splittings between the 91 Er2 and 36 Tm2 electronic potentials dissociating to two ground-state atoms.
  arXiv  Detail & Related papers  (2021-07-06T15:34:00Z)
• Probing chiral edge dynamics and bulk topology of a synthetic Hall system [52.77024349608834]
  Quantum Hall systems are characterized by the quantization of the Hall conductance -- a bulk property rooted in the topological structure of the underlying quantum states. Here, we realize a quantum Hall system using ultracold dysprosium atoms, in a two-dimensional geometry formed by one spatial dimension. We demonstrate that the large number of magnetic sublevels leads to distinct bulk and edge behaviors.
  arXiv  Detail & Related papers  (2020-01-06T16:59:08Z)

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.