Deep Generative model that uses physical quantities to generate and retrieve solar magnetic active regions

2025-02-07

AI Summary

Deep generative models in solar physics suffer from limited physical interpretability and a disconnect between latent representations and scientifically meaningful quantities. Method: This paper proposes a physically interpretable deep generative framework: a GAN trained on SHARPs magnetograms, augmented with an SVM to establish directed mappings from the latent space to key physical parameters (e.g., magnetic flux, shear angle), and enhanced via self-supervised learning to align synthetic images with observed solar data. Contribution/Results: The framework enables continuous, controllable modulation of solar physical quantities; generated magnetograms evolve smoothly with specified parameters; and physics-guided reverse retrieval successfully identifies matching real active regions. For the first time, it transforms generative models from black-box synthesizers into interpretable scientific probes—enhancing their credibility and utility in space weather modeling and data-driven solar research.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Deep generative models have shown immense potential in generating unseen data that has properties of real data. These models learn complex data-generating distributions starting from a smaller set of latent dimensions. However, generative models have encountered great skepticism in scientific domains due to the disconnection between generative latent vectors and scientifically relevant quantities. In this study, we integrate three types of machine learning models to generate solar magnetic patches in a physically interpretable manner and use those as a query to find matching patches in real observations. We use the magnetic field measurements from Space-weather HMI Active Region Patches (SHARPs) to train a Generative Adversarial Network (GAN). We connect the physical properties of GAN-generated images with their latent vectors to train Support Vector Machines (SVMs) that do mapping between physical and latent spaces. These produce directions in the GAN latent space along which known physical parameters of the SHARPs change. We train a self-supervised learner (SSL) to make queries with generated images and find matches from real data. We find that the GAN-SVM combination enables users to produce high-quality patches that change smoothly only with a prescribed physical quantity, making generative models physically interpretable. We also show that GAN outputs can be used to retrieve real data that shares the same physical properties as the generated query. This elevates Generative Artificial Intelligence (AI) from a means-to-produce artificial data to a novel tool for scientific data interrogation, supporting its applicability beyond the domain of heliophysics.

Problem

• Interpretable generative models for solar magnetic regions.
• Mapping physical properties to generative model latent vectors.
• Using generative AI to retrieve real scientific data.

Innovation

• Generative Adversarial Network for solar data
• Support Vector Machines mapping physical-latent spaces
• Self-supervised learner for data retrieval