Automatic classification of mesoscale auroral forms using convolutional neural networks
Automatic classification of mesoscale auroral forms using convolutional neural networks
复制标题
DOI：
10.1016/j.jastp.2022.105906
复制
发表时间：
2022
影响因子：
1.9
通讯作者：
Z. Guo;J. Yang;M. Dunlop;J.‐B. Cao;L. Li;Y.-D. Ma;K.-F. Ji;C. Xiong;J. Li;W.-T. Ding
中科院分区：
文献类型：
--
作者：
Z. Guo;J. Yang;M. Dunlop;J.‐B. Cao;L. Li;Y.-D. Ma;K.-F. Ji;C. Xiong;J. Li;W.-T. Ding
深度学习中的卷积神经网络（CNN）可以提取图像数据中的特征。通过卷积神经网络的多层叠加，我们可以更好地捕捉不同极光子类的本质特征，并进一步对极光图像进行详细分类。由于极光形态特征往往呈现抽象特征，因此我们的研究比较了不同的CNN架构和不同的分层，以测试用于中尺度极光分类的最佳神经网络模型。虽然我们使用的分类模型和子类都比较复杂，但测试集的极光分类最高F1得分达到99.6%（ResNet-50），与以往的工作相比表现最好。我们的分类模型也很好地适用于一个独立的极光图像序列时，声明我们的方法可以自动选择各种中尺度极光形式的图像使用CNN，并允许极光演变的时间序列自动通过中尺度极光特征识别。
Convolutional neural networks (CNNs) in deep learning enable the extraction of features in image data. Through the multi-layer superposition of a convolutional neural network, we can better capture the essential characteristics of different auroral subclasses and further classify auroral images in detail. Because the auroral morphological features often present abstract characteristics, our study compares different CNN architectures and different layering in order to test the best neural network model for mesoscale aurora classification. Although the classification models and subclasses used by us are both more complex, the highest F1 score of aurora classification of the test set reaches 99.6% (ResNet-50), which performs best comparing with previous works. Our classification models work also quite well when applied to an independent auroral image sequence, declaring our approach can automatically select images of various mesoscale auroral forms using CNNs, and allow the time sequence of auroral evolution to be seen automatically through the mesoscale auroral feature recognitions.