Saved in:
Bibliographic Details
Main Authors: Levis, Aviad, Luong, Nhan, Teague, Richard, Bouman, Katherine. L., Barraza-Alfaro, Marcelo, Flaherty, Kevin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.03623
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912569467338752
author Levis, Aviad
Luong, Nhan
Teague, Richard
Bouman, Katherine. L.
Barraza-Alfaro, Marcelo
Flaherty, Kevin
author_facet Levis, Aviad
Luong, Nhan
Teague, Richard
Bouman, Katherine. L.
Barraza-Alfaro, Marcelo
Flaherty, Kevin
contents Protoplanetary disks are the birthplaces of planets, and resolving their three-dimensional structure is key to understanding disk evolution. The unprecedented resolution of ALMA demands modeling approaches that capture features beyond the reach of traditional methods. We introduce a computational framework that integrates physics-constrained neural fields with differentiable rendering and present RadJAX, a GPU-accelerated, fully differentiable line radiative transfer solver achieving up to 10,000x speedups over conventional ray tracers, enabling previously intractable, high-dimensional neural reconstructions. Applied to ALMA CO observations of HD 163296, this framework recovers the vertical morphology of the CO-rich layer, revealing a pronounced narrowing and flattening of the emission surface beyond 400 au - a feature missed by existing approaches. Our work establish a new paradigm for extracting complex disk structure and advancing our understanding of protoplanetary evolution.
format Preprint
id arxiv_https___arxiv_org_abs_2509_03623
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Revealing Fine Structure in Protoplanetary Disks with Physics Constrained Neural Fields
Levis, Aviad
Luong, Nhan
Teague, Richard
Bouman, Katherine. L.
Barraza-Alfaro, Marcelo
Flaherty, Kevin
Earth and Planetary Astrophysics
Computer Vision and Pattern Recognition
Protoplanetary disks are the birthplaces of planets, and resolving their three-dimensional structure is key to understanding disk evolution. The unprecedented resolution of ALMA demands modeling approaches that capture features beyond the reach of traditional methods. We introduce a computational framework that integrates physics-constrained neural fields with differentiable rendering and present RadJAX, a GPU-accelerated, fully differentiable line radiative transfer solver achieving up to 10,000x speedups over conventional ray tracers, enabling previously intractable, high-dimensional neural reconstructions. Applied to ALMA CO observations of HD 163296, this framework recovers the vertical morphology of the CO-rich layer, revealing a pronounced narrowing and flattening of the emission surface beyond 400 au - a feature missed by existing approaches. Our work establish a new paradigm for extracting complex disk structure and advancing our understanding of protoplanetary evolution.
title Revealing Fine Structure in Protoplanetary Disks with Physics Constrained Neural Fields
topic Earth and Planetary Astrophysics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.03623