Revealing Fine Structure in Protoplanetary Disks with Physics Constrained Neural Fields
This work addresses the challenge of modeling high-resolution ALMA data for protoplanetary disks, advancing understanding of disk evolution and planet formation, though it is incremental in applying neural methods to a specific domain.
The authors tackled the problem of resolving the three-dimensional structure of protoplanetary disks by developing a computational framework integrating physics-constrained neural fields with differentiable rendering, resulting in RadJAX, a solver that achieves up to 10,000x speedups and reveals a narrowing and flattening of the CO emission surface beyond 400 au in HD 163296.
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.