Skip to content

Machine Learning-Based Characterization of Solar p-Mode Frequency Shifts during Solar Cycle 25

Home / Papers / Machine Learning-Based Characterization of Solar p-Mode Frequency Shifts during Solar Cycle 25

Machine Learning-Based Characterization of Solar p-Mode Frequency Shifts during Solar Cycle 25

Authors: Rekha Jain, Akash Kumar, Sushanta C. Tripathy Date: 2026-04-22 Paper ID: openalex:2604.20802

Summary

This paper explores the temporal relationship between solar p-mode frequency shifts and established solar activity proxies, such as sunspot numbers and 10.7 cm radio flux. The authors employ time-series and machine learning methods to characterize these shifts for the remainder of solar cycle 25. By modeling these shifts, the work aims to enhance the understanding of energy transport from the solar interior to the heliosphere and improve long-term space weather forecasting capabilities.

Key Contributions

  • Demonstrates the application of standard time-series analysis and machine learning to characterize p-mode solar frequency shifts.
  • Identifies p-mode frequency shifts as a potential indicator for solar cycle phases to improve space weather forecasting.
  • Establishes a quantitative methodology for bridging solar interior oscillation data with heliospheric activity proxies.

Open Questions & Future Work

Archivist Review

I have approved one open question concerning the data limitations in helioseismic forecasting. No other concepts or datasets met the strict bar for inclusion, as the techniques used are standard applications rather than novel, reusable architectural or methodological contributions. The title of the open question was adjusted for clarity and alignment with existing vault terminology.

Approved Open Questions

  • Helioseismic Forecasting Data Bottleneck: The lack of long-term, high-resolution helioseismic data prevents the full validation of machine learning models for solar cycle prediction, which is essential for bridging the gap between solar interior dynamics and space weather forecasting.

Metadata & Links

url
https://arxiv.org/abs/2604.20802
paper_id
2604.20802
paper_source
openalex
domain
time-series
tags
architectures
datasets
concept_slugs
dataset_slugs
skill
TimeSeriesSkill
created_at
2026-04-25T05:37:56Z