Detection of quasi-periodic pulsations in solar flares based on a ResNet-Transformer hybrid model — E8 Intelligence Research

Quasi-Periodic Pulsations (QPPs) in solar and stellar flares are key phenomena reflecting magnetic reconnection processes. However, their non-stationary nature, low signal-to-noise ratio, and other characteristics make reliable detection highly challenging. Traditional detection methods (such as Fourier transform and wavelet analysis) rely on manual parameter setting, making it difficult to achieve high-precision automated detection. This study proposes a deep learning method based on a ResNet-Transformer hybrid model to achieve automated detection of quasi-periodic pulsations in solar flares. This model combines the local feature extraction capability of Residual Networks (ResNet) with the advantage of Transformer structures in modeling long-range dependencies and introduces Fast Fourier Transform to enhance the recognition of periodic features. The detection accuracy on the synthetic dataset achieves 90.1%, which is higher than that of the Fully Convolutional Network (FCN), demonstra Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-21
DOI
https://doi.org/10.5281/zenodo.24418767
Primary Topic
Solar and Space Plasma Dynamics
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Detection of quasi-periodic pulsations in solar flares based on a ResNet-Transformer hybrid model — E8 Intelligence Research

Andrew Stewart Caldin
Zenodo (CERN European Organization for Nuclear Research)
Solar and Space Plasma Dynamics
preprint

Detection of quasi-periodic pulsations in solar flares based on a ResNet-Transformer hybrid model — E8 Intelligence Research

Andrew Stewart Caldin
preprint en

Abstract

Quasi-Periodic Pulsations (QPPs) in solar and stellar flares are key phenomena reflecting magnetic reconnection processes. However, their non-stationary nature, low signal-to-noise ratio, and other characteristics make reliable detection highly challenging. Traditional detection methods (such as Fourier transform and wavelet analysis) rely on manual parameter setting, making it difficult to achieve high-precision automated detection. This study proposes a deep learning method based on a ResNet-Transformer hybrid model to achieve automated detection of quasi-periodic pulsations in solar flares. This model combines the local feature extraction capability of Residual Networks (ResNet) with the advantage of Transformer structures in modeling long-range dependencies and introduces Fast Fourier Transform to enhance the recognition of periodic features. The detection accuracy on the synthetic dataset achieves 90.1%, which is higher than that of the Fully Convolutional Network (FCN), demonstra Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com

Zenodo (CERN European Organization for Nuclear Research)
Solar and Space Plasma Dynamics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon