Self-supervised Synthetic Pretraining for Inference of Stellar Mass Embedded in Dense Gas
This addresses the problem of expensive labeled data for astronomers by enabling better stellar mass inference with limited simulations, though it is incremental as it builds on existing self-supervised methods.
The paper tackled the challenge of estimating stellar mass in obscured star-forming regions by pretraining a vision transformer on synthetic fractal images with DINOv2, then applying it to limited MHD simulations, resulting in slightly improved predictions over supervised models on the same data.
Stellar mass is a fundamental quantity that determines the properties and evolution of stars. However, estimating stellar masses in star-forming regions is challenging because young stars are obscured by dense gas and the regions are highly inhomogeneous, making spherical dynamical estimates unreliable. Supervised machine learning could link such complex structures to stellar mass, but it requires large, high-quality labeled datasets from high-resolution magneto-hydrodynamical (MHD) simulations, which are computationally expensive. We address this by pretraining a vision transformer on one million synthetic fractal images using the self-supervised framework DINOv2, and then applying the frozen model to limited high-resolution MHD simulations. Our results demonstrate that synthetic pretraining improves frozen-feature regression stellar mass predictions, with the pretrained model performing slightly better than a supervised model trained on the same limited simulations. Principal component analysis of the extracted features further reveals semantically meaningful structures, suggesting that the model enables unsupervised segmentation of star-forming regions without the need for labeled data or fine-tuning.