AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
PDF (8.9 MB)
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access

Detecting Patched Anomaly Regions in Spatial Electric Field Power Spectrum Images

Xingsu Li1,2, Zhong Li2,3( ), Jianping Huang2,4( ), Ying Han2,5, Junjie Song2,5, Yumeng Huo2,5, Bo Hao2,3
College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130000, China
Institute of Intelligent Emergency Information Processing, Institute of Disaster Prevention, Langfang 065201, China
School of Emergency Management, Institute of Disaster Prevention, Langfang 065201, China
National Institute of Natural Hazards, Ministry of Emergency Management of China, Beijing 100085, China
School of Information Engineering, Institute of Disaster Prevention, Langfang 065201, China
Show Author Information

Abstract

Research has found patched anomaly regions in the power spectrum images of ionospheric electric fields in space, which are widely distributed. To effectively detect these patched abnormal regions, this paper proposes a new patched abnormal region detection method, KANs-Unet, based on Kolmogorov–Arnold networks (KANs) and U-net networks. The model embeds the KAN-Conv convolution module based on KANs in the encoder section, implements learnable activation functions at the network edge, reduces model parameters, and improves the network’s generalization ability. A feature pyramid attention module is introduced at the junction of the encoder and decoder to enhance the model’s ability to capture features of different scales. The convolutional block attention module is introduced in the decoder section, effectively enhancing the network’s attention to valuable features and improving the feature expression ability. The experimental results of patched anomaly detection show that the KANs-Unet algorithm has better detection performance than the currently popular semantic segmentation algorithms. To further study the characteristics of patched anomaly areas and the differences during major geomagnetic storms, in this research work, we analyzed the patched anomaly areas from November 2021 to October 2022 and from 2024 May 1 to 2024 May 13 during major geomagnetic storms. It was found that the majority of the central frequency points in the patched anomaly area are distributed between 3 and 12.5 kHz, and the number of orbits in the patched anomaly area during the 3 seasons of spring, summer, and autumn is higher than that of the descending orbit, except in winter, where the opposite is true. During a major geomagnetic storm, the overall distribution of patched anomaly areas shows a parallel trend with a band-like distribution. The spatial distribution of magnetic latitudes is relatively scattered, especially in the southern hemisphere, where the magnetic latitudes are wider. Additionally, the number of orbits with patched anomaly areas during ascending increases, especially during peak periods of major geomagnetic storms. In addition, the phenomenon of dual events in patched anomaly areas was also discovered, where 2 consecutive patched anomaly areas appear in the same hemisphere.

References

【1】
【1】
 
 
Space: Science & Technology
Article number: 0329

{{item.num}}

Comments on this article

Go to comment

< Back to all reports

Review Status: {{reviewData.commendedNum}} Commended , {{reviewData.revisionRequiredNum}} Revision Required , {{reviewData.notCommendedNum}} Not Commended Under Peer Review

Review Comment

Close
Close
Cite this article:
Li X, Li Z, Huang J, et al. Detecting Patched Anomaly Regions in Spatial Electric Field Power Spectrum Images. Space: Science & Technology, 2026, 6: 0329. https://doi.org/10.34133/space.0329

2

Views

0

Downloads

0

Crossref

0

Web of Science

0

Scopus

Received: 15 September 2024
Revised: 31 December 2024
Accepted: 11 May 2025
Published: 14 April 2026
© 2026 Xingsu Li et al. Exclusive licensee Beijing Institute of Technology Press. No claim to original U.S. Government Works.

Distributed under a Creative Commons Attribution License (CC BY 4.0).