Cluster-Weighted Training of Deep Surrogate Models for Subgrid Turbulent Transport

Abstract

Turbulence in the solar interior and atmosphere plays a crucial role in energy transport, yet modeling its subgrid-scale effects remains a major challenge. This study leverages machine learning (ML) models to predict components of the Reynolds stress tensor using high-resolution StellarBox simulations of the quiet Sun. Previously, we have compared a Multi-Layer Perceptron (MLP) and a 3D Convolutional Neural Network (CNN) against physics-based baselines to achieve a lower Mean Squared Error (MSE) and better generalization across various heights and depths in the solar atmosphere. To enhance learning, in this work, we investigate cluster-weighted training using K-Means and Hierarchical Agglomerative Clustering (HAC). By weighing the loss function based on cluster-specific prediction errors, we direct the model's attention to high-error regions. It significantly improves CNN performance, achieving 34% lower MSE and a significantly higher R2 score indicating that integrating deterministic clustering with ML is a promising technique for modeling subgrid turbulence, in particular, and regression in diverse environments, in general.

arXiv comment9 pages, 8 figures, 2 tables, SABID workshop at 2025 IEEE International Conference on Data Mining

References in corpus (4)

• Small-scale dynamo simulations: Magnetic field amplification in exploding granules and the role of deep and shallow recirculation
• Using Realistic MHD Simulations for Modeling and Interpretation of Quiet-Sun Observations with the Solar Dynamics Observatory Helioseismic and Magnetic Imager
• Physics-Informed Machine Learning for Modeling Turbulence in Supernovae
• Non-zero phase-shifts of acoustic waves in the lower solar atmosphere measured from realistic simulations and their role in local helioseismology