Morphological Identification of Dynamical Regimes in MHD Turbulence with ScaleAware-JEPA
Abstract
The morphology of turbulent interstellar gas reflects the coupled action of turbulence, magnetic fields, and self-gravity, but density amplitude alone does not uniquely specify dynamical state. We use ScaleAware-JEPA to learn multiscale structural coordinates from density alone and test whether these learned coordinates organize dynamical states more clearly than density-based conditioning. Clump-like, filament-like, and diffuse-like latent neighborhoods show an ordered progression in turbulent velocity scaling that is not reproduced by density-selected populations. Velocity and magnetic fields are withheld during training and used afterward as post-training physical diagnostics: MHD states occupy ordered but overlapping regions of the learned representation, and dimensionless dynamical balances vary coherently across the full latent atlas. These results show that a representation learned from density morphology can acquire a geometry that is systematically organized by established MHD diagnostics. Multiscale morphology therefore provides a useful coordinate for dynamical state beyond density amplitude alone.
Related
- Nonlinear Dynamical Regimes of Cosmological Frequency Combs
- Complex dynamical regimes of the Tayler-Spruit dynamo
- Identification of Magnetic Reconnection in Plasma Turbulence Using a Dual-branch Lightweight Hybrid Convolutional Neural Network
- Photometric Identification and Dynamical Purification of Blue Horizontal Branch Stars in DESI MWS DR1
- GIMLI: a toolkit connecting linear and non-linear magnetohydrodynamic regimes
BibTeX
@misc{zhao2026morphological,
title = {{Morphological Identification of Dynamical Regimes in MHD Turbulence with ScaleAware-JEPA}},
author = {Mengke Zhao and Guang-Xing Li and Keping Qiu},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.36833},
eprint = {2609.36833},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.36833},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Morphological Identification of Dynamical Regimes in MHD Turbulence with ScaleAware-JEPA
AU - Mengke Zhao
AU - Guang-Xing Li
AU - Keping Qiu
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.36833
UR - https://arxiv.org/abs/2609.36833
AB - The morphology of turbulent interstellar gas reflects the coupled action of turbulence, magnetic fields, and self-gravity, but density amplitude alone does not uniquely specify dynamical state. We use ScaleAware-JEPA to learn multiscale structural coordinates from density alone and test whether these learned coordinates organize dynamical states more clearly than density-based conditioning. Clump-like, filament-like, and diffuse-like latent neighborhoods show an ordered progression in turbulent velocity scaling that is not reproduced by density-selected populations. Velocity and magnetic fields are withheld during training and used afterward as post-training physical diagnostics: MHD states occupy ordered but overlapping regions of the learned representation, and dimensionless dynamical balances vary coherently across the full latent atlas. These results show that a representation learned from density morphology can acquire a geometry that is systematically organized by established MHD diagnostics. Multiscale morphology therefore provides a useful coordinate for dynamical state beyond density amplitude alone.
ER -