A comparative study of auroral morphology distribution between the Northern and Southern Hemisphere based on automatic classification

Yang, Qiuju; Hu, Zejun

doi:10.5194/gi-7-113-2018

Cited by 2 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The statistical aurora distribution is consistent with the observation law of Hu et al (2009) at the YRS. This shows that auroras occur periodically and repeatedly, and there are dominant morphological characteristics in the different regions (Hu et al, 2009; Q. Yang & Hu, 2018).…”

Section: Discussionmentioning

confidence: 95%

Automatic Aurora Image Classification Framework Based on Deep Learning for Occurrence Distribution Analysis: A Case Study of All‐Sky Image Data Sets From the Yellow River Station

Zhong

Liu

et al. 2020

JGR Space Physics

Self Cite

View full text Add to dashboard Cite

Developing a computational model for aurora image classification is an important task for polar research. However, the design of the handcrafted features in the traditional methods has insufficient descriptive ability for auroral morphology and is dependent on expert knowledge. In this paper, an automatic aurora image classification framework based on deep learning is proposed to solve the problem. In this framework, three basic deep learning networks-AlexNet, VGG, and ResNet-are used to automatically classify all-sky aurora images via convolution and pooling processes and a back-propagation mechanism, without requiring manual intervention. As shown in the class activation mapping (CAM), the proposed framework can extract the complex auroral feature representations automatically and discriminatively. The results obtained with all-sky aurora images from the Yellow River Station demonstrate that the proposed framework has effective transfer ability and can achieve real-time classification. It is also shown that the proposed method can achieve higher average classification accuracy than the AI-MFLDA method. The statistical auroral occurrence distribution can be obtained based on the classification results. There are dominant morphological characteristics in the four magnetic local time (MLT) regions of the dayside aurora oval, which confirms the effectiveness of the proposed method.

show abstract

Section: Discussionmentioning

confidence: 95%

Automatic Aurora Image Classification Framework Based on Deep Learning for Occurrence Distribution Analysis: A Case Study of All‐Sky Image Data Sets From the Yellow River Station

Zhong

Liu

et al. 2020

JGR Space Physics

Self Cite

View full text Add to dashboard Cite

show abstract

Classification and Distribution of the Dayside Ion Upflows Associated with Auroral Particle Precipitation

Cai

et al. 2023

Universe

View full text Add to dashboard Cite

Two important phenomena of the solar wind–magnetosphere–ionosphere coupling are auroral particle precipitation and the formation of ions flowing upward from the ionosphere. They have opposite transport directions of energy and substance. Based on the observations of particle precipitation and ion drift from the DMSP F13 satellite in January and July 2005, the ionospheric ion upflows in dayside auroral oval (0600–1800 MLT) can be divided into five types according to the velocity of ion upflows and the spectrum characteristics of auroral particle precipitation, and the distribution for different types of ion upflows is studied. The results show that the ion upflows mainly occur in the geomagnetic latitude (MLAT) range of 70–80°.The main magnetospheric source region of ion upflows (type A and D) caused by the accelerated electron (mainly the soft electron) corresponds to Low Latitude Boundary Layer (LLBL) and Cusp, and ion upflows of type B and C (related to the process of ambipolar diffusion caused by electron acceleration) mainly occur in LLBL and Boundary Plasma Sheet (BPS), while ion upflows of type E without electron acceleration mainly occur in the central plasma sheet (CPS).The dawn–dusk asymmetry is obvious in the winter season, with the ion upflows mainly occurring on the dawn/dusk side ionosphere. However, the ion upflows in summer mainly occur at the magnetic noon, with a symmetric distribution centered at the magnetic noon. The occurrence of ion upflow in winter is significantly higher than that in summer, and it is significantly enhanced during the period of moderate geomagnetic activity. The upward region expands to the lower latitude when the geomagnetic activity is enhanced. The effect of interplanetary magnetic field (IMF) components has also been studied in this paper. When IMF Bx is negative, the upflow occurrence increases in the region of 1500–1800 MLT and 0600–0900 MLT, with the MLAT range below 70°. The direction of IMF By may lead to the high-incidence area reverse at the prenoon or postnoon region. The occurrence of ion upflows with the MLAT range below 75° increases significantly when IMF is southward. Type A ion upflow has the highest velocity of ion upflows, followed by type E, and type D has the lowest. The average velocity of ion upflows in winter is significantly higher than that in summer.

show abstract

A comparative study of auroral morphology distribution between the Northern and Southern Hemisphere based on automatic classification

Cited by 2 publications

References 34 publications

Automatic Aurora Image Classification Framework Based on Deep Learning for Occurrence Distribution Analysis: A Case Study of All‐Sky Image Data Sets From the Yellow River Station

Automatic Aurora Image Classification Framework Based on Deep Learning for Occurrence Distribution Analysis: A Case Study of All‐Sky Image Data Sets From the Yellow River Station

Classification and Distribution of the Dayside Ion Upflows Associated with Auroral Particle Precipitation

Contact Info

Product

Resources

About