Exoplanet atmosphere evolution: emulation with random forests

• URL: http://arxiv.org/abs/2110.15162v1
• Date: Thu, 28 Oct 2021 14:39:19 GMT
• Title: Exoplanet atmosphere evolution: emulation with random forests
• Authors: James G. Rogers, Cl\`audia Jan\'o Mu\~noz, James E. Owen and Richard A. Booth
• Abstract summary: 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.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Atmospheric mass-loss is known to play a leading role in sculpting the demographics of small, close-in exoplanets. Understanding the impact of such mass-loss driven evolution requires modelling large populations of planets to compare with the observed exoplanet distributions. As the quality of planet observations increases, so should the accuracy of the models used to understand them. However, to date, only simple semi-analytic models have been used in such comparisons since modelling populations of planets with high accuracy demands a high computational cost. To address this, we turn to machine learning. We implement random forests trained on atmospheric evolution models, including XUV photoevaporation, to predict a given planet's final radius and atmospheric mass. This evolution emulator is found to have an RMS fractional radius error of 1$\%$ from the original models and is $\sim 400$ times faster to evaluate. As a test case, we use the emulator to infer the initial properties of Kepler-36b and c, confirming that their architecture is consistent with atmospheric mass loss. Our new approach opens the door to highly sophisticated models of atmospheric evolution being used in demographic analysis, which will yield further insight into planet formation and evolution.

Related papers

• The Application of Machine Learning in Tidal Evolution Simulation of Star-Planet Systems [13.080151140004276]
  The speed at which we generate evolutionary curves exceeds that of model-generated curves by more than four orders of magnitude. Our work provides an efficient method to save significant computational resources and time with minimal loss in accuracy.
  arXiv  Detail & Related papers  (2024-08-29T02:09:19Z)
• Accelerating Giant Impact Simulations with Machine Learning [0.8325032895114773]
  Constraining planet formation models based on the observed exoplanet population requires generating large samples of synthetic planetary systems. A significant bottleneck is simulating the giant impact phase, during which planetary embryos evolve gravitationally and combine to form planets. We present a machine learning (ML) approach to predicting collisional outcomes in multiplanet systems.
  arXiv  Detail & Related papers  (2024-08-16T17:59:46Z)
• Aurora: A Foundation Model of the Atmosphere [56.97266186291677]
  We introduce Aurora, a large-scale foundation model of the atmosphere trained on over a million hours of diverse weather and climate data. In under a minute, Aurora produces 5-day global air pollution predictions and 10-day high-resolution weather forecasts.
  arXiv  Detail & Related papers  (2024-05-20T14:45:18Z)
• OXYGENERATOR: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning [50.365198230613956]
  Existing expert-dominated numerical simulations fail to catch up with the dynamic variation caused by global warming and human activities. We propose OxyGenerator, the first deep learning based model, to reconstruct the global ocean deoxygenation from 1920 to 2023.
  arXiv  Detail & Related papers  (2024-05-12T09:32:40Z)
• A Comparative Study on Generative Models for High Resolution Solar Observation Imaging [59.372588316558826]
  This work investigates capabilities of current state-of-the-art generative models to accurately capture the data distribution behind observed solar activity states. Using distributed training on supercomputers, we are able to train generative models for up to 1024x1024 resolution that produce high quality samples indistinguishable to human experts.
  arXiv  Detail & Related papers  (2023-04-14T14:40:32Z)
• 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)
• Spatiotemporal modeling of European paleoclimate using doubly sparse Gaussian processes [61.31361524229248]
  We build on recent scale sparsetemporal GPs to reduce the computational burden. We successfully employ such a doubly sparse GP to construct a probabilistic model of paleoclimate.
  arXiv  Detail & Related papers  (2022-11-15T14:15:04Z)
• Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator [57.57321628587564]
  We introduce Hybrid Graph Network Simulator (HGNS) for learning reservoir simulations of 3D subsurface fluid flows. HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure. Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators.
  arXiv  Detail & Related papers  (2022-06-15T17:29:57Z)
• Comparing Classification Models on Kepler Data [0.0]
  Even though the original Kepler mission ended due to mechanical failures, the Kepler satellite continues to collect data. Using classification models, we can understand the features exoplanets possess and then use those features to investigate further.
  arXiv  Detail & Related papers  (2021-01-06T07:48:52Z)

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.