Disk Wind Feedback from High-mass Protostars. V. Application of Multi-Modal Machine Learning to Characterize Outflow Properties

TL;DR

This paper introduces a multi-modal deep learning approach combining spatial and spectral data to accurately characterize protostellar outflows, overcoming traditional projection challenges in high-mass star formation research.

Contribution

It develops a novel Vision Transformer-based framework trained on synthetic data, demonstrating improved robustness and interpretability in inferring outflow properties from complex observations.

Findings

Vision Transformer models outperform CNNs in this task.

The framework provides stable mass and position angle estimates.

Inclination angles are tightly constrained, enhancing understanding of outflow geometry.

Abstract

Characterizing protostellar outflows is fundamental to understanding star formation feedback, yet traditional methods are often hindered by projection effects and complex morphologies. We present a multi-modal deep learning framework that jointly leverages spatial and spectral information from CO observations to infer protostellar mass, inclination, and position angle ($PA$). Our model, trained on synthetic ALMA observations generated from 3D magnetohydrodynamic simulations, utilizes a cross-attention fusion mechanism to integrate morphological and kinematic features with probabilistic uncertainty estimation. Our results demonstrate that Vision Transformer architectures significantly outperform convolutional networks, showing remarkable robustness to reduced spatial resolution. Interpretability analysis reveals a physically consistent hierarchy: spatial features dominate across all parameters, whereas spectral profiles provide secondary constraints for mass and inclination. Applied to observational ALMA data, the framework delivers stable mass and $PA$ estimates with exceptionally tightly constrained inclination angles. This study establishes multi-modal deep learning as a powerful, interpretable tool for overcoming projection biases in high-mass star formation studies.