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

no code implementations • 23 Feb 2022 • Sayantan Auddy, Ramit Dey, Min-Kai Lin, Daniel Carrera, Jacob B. Simon

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.

DPNNet-2.0 Part I: Finding hidden planets from simulated images of protoplanetary disk gaps

1 code implementation • 19 Jul 2021 • Sayantan Auddy, Ramit Dey, Min-Kai Lin, Cassandra Hall

The observed sub-structures, like annular gaps, in dust emissions from protoplanetary disk, are often interpreted as signatures of embedded planets.

Stratified and vertically-shearing streaming instabilities in protoplanetary disks

1 code implementation • 24 Nov 2020 • Min-Kai Lin

Under the right conditions, the streaming instability between imperfectly coupled dust and gas is a powerful mechanism for planetesimal formation as it can concentrate dust grains to the point of gravitational collapse.

Earth and Planetary Astrophysics

A Machine Learning model to infer planet masses from gaps observed in protoplanetary disks

no code implementations • 27 Jul 2020 • Sayantan Auddy, Min-Kai Lin

To this end, we introduce DPNNet (Disk Planet Neural Network), an efficient model of planetary gaps by exploiting the power of machine learning.

Earth and Planetary Astrophysics