A Multimodal Tiered Magnetic Polarity Inversion Features Dataset for Space Weather Forecasting

TL;DR

This paper introduces a comprehensive, multimodal dataset of magnetic polarity inversion lines from solar observations, designed to enhance space weather forecasting through detailed, tiered feature extraction and metadata.

Contribution

It provides a novel, publicly available tiered MPIL dataset with multiple thresholds and detailed metadata, facilitating tailored analysis for space weather research.

Findings

Dataset includes 6,695 HARP series with 12-minute cadence.

Four tiers capture different sensitivities to polarity changes.

Includes six binary MPIL masks for diverse analysis objectives.

Abstract

This article presents a publicly available, multimodal, tiered magnetic polarity inversion lines (MPILs) dataset extracted from the Solar Dynamics Observatory's (SDO) Helioseismic and Magnetic Imager (HMI) Active Region Patches (SDO/HMI HARP) between May 2010 and April 2025. The dataset comprises four distinct tiers, each generated by running our detection methodology with four different magnetic field strength thresholds to capture nuanced variations in MPIL features at multiple levels of detail. In total, we provide 6,695 HARP series mapped using the Lambert Cylindrical Equal Area (CEA) projection at a 12-minute cadence. This tiered approach ensures that each tier captures specific sensitivities to polarity changes, enabling researchers to tailor their analyses to a range of scientific and operational objectives. In each threshold tier, we offer six binary MPIL masks associated with heliophysics and space weather forecasting, including MPIL, Region of Polarity Inversion (RoPI), positive and negative polarity regions, unsigned polarity regions, and MPIL convex hulls. Furthermore, structured metadata in the form of multivariate time series is included, allowing users to track and analyze MPIL properties over time.