Out-of-Sample Validation of MagNet

TL;DR

This paper validates the MagNet machine learning model for solar magnetic field prediction using out-of-sample data, demonstrating its reliability and potential for broader application in solar physics research.

Contribution

It provides the first out-of-sample validation of MagNet, confirming its effectiveness on new data not used during training.

Findings

Good correlation between AI-generated and observed magnetograms.

Strengthens confidence in applying MagNet to the entire SOHO/MDI archive.

Supports future scientific analysis using AI-generated data.

Abstract

Machine learning is starting to be used in almost every industry and academic research, and solar physics is no exception. A newly developed machine learning model named MagNet helps us to tackle some of the most serious challenges in data mining by generating transverse fields of solar active regions. Being trained on line-of-sight magnetograms from Michelson Doppler Imager at Solar and Heliospheric Observatory (SOHO/MDI), H{\alpha} maps from Big Bear Solar Observatory and Kanzelhohe Solar Observatory and vector magnetograms from Helioseismic and Magnetic Imager at Solar Dynamic Observatory (SDO/HMI), this model provides vector magnetograms in active regions for SOHO/MDI data covering the strong solar cycle 23. In this study, we performed out-of-sample validation of the MagNet model with data from Imaging Vector Magnetograph (IVM) at Mees Solar Observatory, which was not included in the training process. Our results show good correlation between the AI generated data and the observed vector magnetograms and therefore strengthen the confidence of implementing MagNet to the entire SOHO/MDI archive and future scientific analysis of the AI generated data.