Department of Space Science and Engineering, National Central University, Taoyuan City 320317, Taiwan.
Skobeltsyn Institute of Nuclear Physics, Lomonosov Moscow State University, 119899 Moscow, Russia.
Sensors (Basel). 2021 Sep 28;21(19):6482. doi: 10.3390/s21196482.
The technique of active ionospheric sounding by ionosondes requires sophisticated methods for the recovery of experimental data on ionograms. In this work, we applied an advanced algorithm of deep learning for the identification and classification of signals from different ionospheric layers. We collected a dataset of 6131 manually labeled ionograms acquired from low-latitude ionosondes in Taiwan. In the ionograms, we distinguished 11 different classes of the signals according to their ionospheric layers. We developed an artificial neural network, FC-DenseNet24, based on the FC-DenseNet convolutional neural network. We also developed a double-filtering algorithm to reduce incorrectly classified signals. That made it possible to successfully recover the sporadic E layer and the F2 layer from highly noise-contaminated ionograms whose mean signal-to-noise ratio was low, SNR = 1.43. The Intersection over Union (IoU) of the recovery of these two signal classes was greater than 0.6, which was higher than the previous models reported. We also identified three factors that can lower the recovery accuracy: (1) smaller statistics of samples; (2) mixing and overlapping of different signals; (3) the compact shape of signals.
利用电离层探测仪进行主动电离层探测技术需要复杂的方法来恢复关于电离图的实验数据。在这项工作中，我们应用了深度学习的先进算法来识别和分类来自不同电离层的信号。我们收集了来自台湾低纬度电离层探测仪的 6131 个手动标记的电离图数据集。在这些电离图中，我们根据它们的电离层区分了 11 种不同类别的信号。我们基于 FC-DenseNet 卷积神经网络开发了一个名为 FC-DenseNet24 的人工神经网络。我们还开发了一种双滤波算法来减少错误分类的信号。这使得我们能够成功地从高度噪声污染的电离图中恢复出不规则 E 层和 F2 层，这些电离图的平均信噪比 SNR = 1.43 很低。这两种信号类别的恢复的交集（IoU）大于 0.6，高于之前报道的模型。我们还确定了三个可能降低恢复准确性的因素：（1）样本统计量较小；（2）不同信号的混合和重叠；（3）信号的紧凑形状。
