Revealing Fine Structure in Protoplanetary Disks with Physics Constrained Neural Fields

2025-09-03

AI Summary

ALMA observations suffer from insufficient vertical resolution, hindering detailed 3D characterization of planet-forming regions in protoplanetary disks. Method: We propose a novel paradigm integrating physics-constrained neural fields with differentiable rendering, coupled with RadJAX—a GPU-accelerated, fully differentiable line radiative transfer solver—to enable high-dimensional neural reconstruction of CO emission layers. Contribution/Results: Our approach achieves up to a 10⁴-fold speedup over conventional ray-tracing methods. Applied to the HD 163296 disk, it accurately recovers the vertical morphology and reveals, for the first time, significant narrowing and flattening of the CO emission surface beyond 400 au. This provides a high-fidelity 3D structural benchmark for disk evolution modeling and diagnostics of planetary formation environments.

Technology Category

• Computer Vision: 3D Computer Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Feature Construction/Reformulation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

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.

Problem

• Revealing 3D structure in protoplanetary disks
• Modeling high-resolution ALMA observations beyond traditional methods
• Recovering vertical morphology of CO-rich disk layers

Innovation

• Physics-constrained neural fields integration
• Differentiable radiative transfer solver RadJAX
• GPU-accelerated 10000x speedup rendering