Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAccurate Machine Learning Atmospheric Retrieval via a Neural Network Surrogate Model for Radiative Transfer
107
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Atmospheric retrieval determines the properties of an atmosphere based on its measured spectrum. The low signal-to-noise ratio of exoplanet observations require a Bayesian approach to determine posterior probability distributions of each model parameter, given observed spectra. This inference is computationally expensive, as it requires many executions of a costly radiative transfer (RT) simulation for each set of sampled model parameters. Machine learning (ML) has recently been shown to provide a significant reduction in runtime for retrievals, mainly by training inverse ML models that predict parameter distributions, given observed spectra, albeit with reduced posterior accuracy. Here we present a novel approach to retrieval by training a forward ML surrogate model that predicts spectra given model parameters, providing a fast approximate RT simulation that can be used in a conventional Bayesian retrieval framework without significant loss of accuracy. We demonstrate our method on the emission spectrum of HD 189733 b and find good agreement with a traditional retrieval from the Bayesian Atmospheric Radiative Transfer (BART) code (Bhattacharyya coefficients of 0.9843--0.9972, with a mean of 0.9925, between 1D marginalized posteriors). This accuracy comes while still offering significant speed enhancements over traditional RT, albeit not as much as ML methods with lower posterior accuracy. Our method is ~9x faster per parallel chain than BART when run on an AMD EPYC 7402P central processing unit (CPU). Neural-network computation using an NVIDIA Titan Xp graphics processing unit is 90--180x faster per chain than BART on that CPU.
rate research
Read More
This and companion papers by Harrington et al. and Blecic et al. present the Bayesian Atmospheric Radiative Transfer ({BART}) code, an open-source, open-development package to characterize extrasolar-planet atmospheres. {BART} combines a thermochemical equilibrium abundances ({TEA}), a radiative-transfer ({transit}), and a Bayesian statistical (MC3) module to constrain atmospheric temperatures and molecular abundances for given spectroscopic observations. Here, we describe the {transit} radiative-transfer package, an efficient line-by-line radiative-transfer C code for one-dimensional atmospheres, developed by P. Rojo and further modified by the UCF exoplanet group. This code produces transmission and hemisphere-integrated emission spectra. {transit} handles line-by-line opacities from HITRAN, Partridge & Schwenke ({water}), Schwenke (TiO), and Plez (VO); and collision-induced absorption from Borysow, HITRAN, and ExoMol. {transit} emission-spectra models agree with models from C. Morley (priv. comm.) within a few percent. We applied {BART} to the {Spitzer} and {Hubble} transit observations of the Neptune-sized planet HAT-P-11b. Our results generally agree with those from previous studies, constraining the {water} abundance and finding an atmosphere enhanced in heavy elements. Different conclusions start to emerge when we make different assumptions from other studies. The {BART} source code and documentation are available at https://github.com/exosports/BART.
Over the past decade, the study of extrasolar planets has evolved rapidly from plain detection and identification to comprehensive categorization and characterization of exoplanet systems and their atmospheres. Atmospheric retrieval, the inverse modeling technique used to determine an exoplanetary atmospheres temperature structure and composition from an observed spectrum, is both time-consuming and compute-intensive, requiring complex algorithms that compare thousands to millions of atmospheric models to the observational data to find the most probable values and associated uncertainties for each model parameter. For rocky, terrestrial planets, the retrieved atmospheric composition can give insight into the surface fluxes of gaseous species necessary to maintain the stability of that atmosphere, which may in turn provide insight into the geological and/or biological processes active on the planet. These atmospheres contain many molecules, some of them biosignatures, spectral fingerprints indicative of biological activity, which will become observable with the next generation of telescopes. Runtimes of traditional retrieval models scale with the number of model parameters, so as more molecular species are considered, runtimes can become prohibitively long. Recent advances in machine learning (ML) and computer vision offer new ways to reduce the time to perform a retrieval by orders of magnitude, given a sufficient data set to train with. Here we present an ML-based retrieval framework called Intelligent exoplaNet Atmospheric RetrievAl (INARA) that consists of a Bayesian deep learning model for retrieval and a data set of 3,000,000 synthetic rocky exoplanetary spectra generated using the NASA Planetary Spectrum Generator. Our work represents the first ML retrieval model for rocky, terrestrial exoplanets and the first synthetic data set of terrestrial spectra generated at this scale.
A one-dimensional method for reconstructing the structure of prestellar and protostellar clouds is presented. The method is based on radiative transfer computations and a comparison of theoretical and observed intensity distributions at both millimeter and infrared wavelengths. The radiative transfer of dust emission is modeled for specified parameters of the density distribution, central star, and external background, and the theoretical distribution of the dust temperature inside the cloud is determined. The intensity distributions at millimeter and IR wavelengths are computed and quantitatively compared with observational data. The best-fit model parameters are determined using a genetic minimization algorithm, which makes it possible to reveal the ranges of parameter degeneracy as well. The method is illustrated by modeling the structure of the two infrared dark clouds IRDC-320.27+029 (P2) and IRDC-321.73+005 (P2). The derived density and temperature distributions can be used to model the chemical structure and spectral maps in molecular lines.
Thermal dust emission carries information on physical conditions and dust properties in many astronomical sources. Because observations represent a sum of emission along the line of sight, their interpretation often requires radiative transfer modelling. We describe a new radiative transfer program SOC for computations of dust emission and examine its performance in simulations of interstellar clouds with external and internal heating. SOC implements the Monte Carlo radiative transfer method as a parallel program for shared memory computers. It can be used to study dust extinction, scattering, and emission. We tested SOC with realistic cloud models and examined the convergence and noise of the dust temperature estimates and of the resulting surface brightness maps. SOC has been demonstrated to produces accurate estimates for dust scattering and for thermal dust emission. It performs well with both with CPUs and with GPUs, the latter providing up to an order of magnitude speed-up. In the test cases, ALI improved the convergence rates but also was sensitive to Monte Carlo noise. Run-time refinement of the hierarchical-grid models did not help in reducing the run times required for a given accuracy of solution. The use of a reference field, without ALI, works more robustly. It also allows the run time to be optimised if the number of photon packages is increased only as the iterations progress. The use of GPUs in radiative transfer computations should be investigated further.
We propose a simple, but efficient and accurate machine learning (ML) model for developing high-dimensional potential energy surface. This so-called embedded atom neural network (EANN) approach is inspired by the well-known empirical embedded atom method (EAM) model used in condensed phase. It simply replaces the scalar embedded atom density in EAM with a Gaussian-type orbital based density vector, and represents the complex relationship between the embedded density vector and atomic energy by neural networks. We demonstrate that the EANN approach is equally accurate as several established ML models in representing both big molecular and extended periodic systems, yet with much fewer parameters and configurations. It is highly efficient as it implicitly contains the three-body information without an explicit sum of the conventional costly angular descriptors. With high accuracy and efficiency, EANN potentials can vastly accelerate molecular dynamics and spectroscopic simulations in complex systems at ab initio level.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
