# PGNets: Planet mass prediction using convolutional neural networks for radio continuum observations of protoplanetary disks

arXiv: https://arxiv.org/abs/2111.15196 · HTML: https://mlsanity.com/paper/2111.15196/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 5 references that are in the map.
- First posted on arXiv 30 Nov 2021.

## Builds on (most cited first, 1 of 1)

- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)

## Built on by (most cited first, 7 of 7)

- [PPDONet: Deep Operator Networks for Fast Prediction of Steady-State Solutions in Disk-Planet Systems](https://mlsanity.com/paper/2305.11111/) (2023)
- [Using Bayesian Deep Learning to infer Planet Mass from Gaps in Protoplanetary Disks](https://mlsanity.com/paper/2202.11730/) (2022)
- [Denoising Diffusion Probabilistic Models to Predict the Density of Molecular Clouds](https://mlsanity.com/paper/2304.01670/) (2023)
- [Disk2Planet: A Robust and Automated Machine Learning Tool for Parameter Inference in Disk-Planet Systems](https://mlsanity.com/paper/2409.17228/) (2024)
- [Kinematic Evidence of an Embedded Protoplanet in HD 142666 Identified by Machine Learning](https://mlsanity.com/paper/2301.05075/) (2023)
- [Disentangling CO Chemistry in a Protoplanetary Disk Using Explanatory Machine Learning Techniques](https://mlsanity.com/paper/2312.05254/) (2023)
- [VADER: A Variational Autoencoder to Infer Planetary Masses and Gas-Dust Disk Properties Around Young Stars](https://mlsanity.com/paper/2509.12324/) (2025)

## Abstract (arXiv)

We developed Convolutional Neural Networks (CNNs) to rapidly and directly infer the planet mass from radio dust continuum images. Substructures induced by young planets in protoplanetary disks can be used to infer the potential young planets' properties. Hydrodynamical simulations have been used to study the relationships between the planet's properties and these disk features. However, these attempts either fine-tuned numerical simulations to fit one protoplanetary disk at a time, which was time-consuming, or azimuthally averaged simulation results to derive some linear relationships between the gap width/depth and the planet mass, which lost information on asymmetric features in disks. To cope with these disadvantages, we developed Planet Gap neural Networks (PGNets) to infer the planet mass from 2D images. We first fit the gridded data in Zhang et al. (2018) as a classification problem. Then, we quadrupled the data set by running additional simulations with near-randomly sampled parameters, and derived the planet mass and disk viscosity together as a regression problem. The classification approach can reach an accuracy of 92%, whereas the regression approach can reach 1σ as 0.16 dex for planet mass and 0.23 dex for disk viscosity. We can reproduce the degeneracy scaling α propto Mp3 found in the linear fitting method, which means that the CNN method can even be used to find degeneracy relationship. The gradient-weighted class activation mapping effectively confirms that PGNets use proper disk features to constrain the planet mass. We provide programs for PGNets and the traditional fitting method from Zhang et al. (2018), and discuss each method's advantages and disadvantages.