Workshop: 2nd ICML Workshop on Machine Learning for Astrophysics

PPDONet: Deep Operator Networks for Fast Prediction of Steady-State Solutions in Disk-Planet Systems

Shunyuan Mao · Ruobing Dong · Lu Lu · Kwang Moo Yi · Sifan Wang · Paris Perdikaris

Abstract: We have created a tool called the Protoplanetary Disk Operator Network (PPDONet) that quickly predicts disk-planet interactions in protoplanetary disks. Our tool uses Deep Operator Networks (DeepONets), a type of neural network that learns non-linear operators to accurately represent both deterministic and stochastic differential equations. PPDONet maps three key parameters in a disk-planet system -- the Shakura \& Sunyaev viscosity $\alpha$, the disk aspect ratio $h_\mathrm{0}$, and the planet-star mass ratio $q$ -- to the steady-state solutions for disk surface density, radial velocity, and azimuthal velocity. We've validated the accuracy of PPDONet's solutions with an extensive array of tests. Our tool can calculate the result of a disk-planet interaction for a given system in under a second using a standard laptop. PPDONet is publicly accessible for use.

Chat is not available.