Using Bayesian Deep Learning to infer Planet Mass from Gaps in Protoplanetary Disks

Abstract

Planet induced sub-structures, like annular gaps, observed in dust emission from protoplanetary disks provide a unique probe to characterize unseen young planets. While deep learning based model has an edge in characterizing the planet's properties over traditional methods, like customized simulations and empirical relations, it lacks in its ability to quantify the uncertainty associated with its predictions. In this paper, we introduce a Bayesian deep learning network "DPNNet-Bayesian" that can predict planet mass from disk gaps and provides uncertainties associated with the prediction. A unique feature of our approach is that it can distinguish between the uncertainty associated with the deep learning architecture and uncertainty inherent in the input data due to measurement noise. The model is trained on a data set generated from disk-planet simulations using the \textsc{fargo3d} hydrodynamics code with a newly implemented fixed grain size module and improved initial conditions. The Bayesian framework enables estimating a gauge/confidence interval over the validity of the prediction when applied to unknown observations. As a proof-of-concept, we apply DPNNet-Bayesian to dust gaps observed in HL Tau. The network predicts masses of $ 86.0 \pm 5.5 M_{\Earth} $, $ 43.8 \pm 3.3 M_{\Earth} $, and $ 92.2 \pm 5.1 M_{\Earth} $ respectively, which are comparable to other studies based on specialized simulations.

14 pages, 6 figures, submitted to ApJ

References in corpus (15)

• Two accreting protoplanets around the young star PDS 70
• A comparative study of disc-planet interaction
• Mass Estimates of a Giant Planet in a Protoplanetary Disk from the Gap Structures
• The Disk Substructures at High Angular Resolution Project (DSHARP): III. Spiral Structures in the Millimeter Continuum of the Elias 27, IM Lup, and WaOph 6 Disks
• Nine localised deviations from Keplerian rotation in the DSHARP circumstellar disks: Kinematic evidence for protoplanets carving the gaps
• CO and dust properties in the TW Hya disk from high-resolution ALMA observations
• Formation of a disc gap induced by a planet: Effect of the deviation from Keplerian disc rotation
• The newborn planet population emerging from ring-like structures in discs
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• On the width and shape of the corotation region for low-mass planets
• Observing protoplanetary discs with the Square Kilometre Array -- I. Characterising pebble substructure caused by forming planets
• Quantifying Uncertainty in Deep Learning Approaches to Radio Galaxy Classification
• PGNets: Planet mass prediction using convolutional neural networks for radio continuum observations of protoplanetary disks
• A Machine Learning model to infer planet masses from gaps observed in protoplanetary disks
• DPNNet-2.0 Part I: Finding hidden planets from simulated images of protoplanetary disk gaps

Cited by in corpus (6)

• ExoMDN: Rapid characterization of exoplanet interior structures with Mixture Density Networks
• Locating Hidden Exoplanets in ALMA Data Using Machine Learning
• DBNets2.0: simulation-based inference for planet-induced dust substructures in protoplanetary discs
• Predicting Stellar Mass Accretion: An Optimized Echo State Network Approach in Time Series Modeling
• Dynamics of small, constant size particles in a protoplanetary disk with an embedded protoplanet
• exoALMA XXIII. Estimating Disk and Planet Properties from Dust Morphologies with DBNets2.0