State-of-the-Art Capability of Convolutional Neural Networks to Distinguish the Signal in the Ionosphere

Abstract

Recovering and distinguishing different ionospheric layers and signals usually requires slow and complicated procedures. In this work, we construct and train five convolutional neural network (CNN) models: DeepLab, fully convolutional DenseNet24 (FC-DenseNet24), deep watershed transform (DWT), Mask R-CNN, and spatial attention-UNet (SA-UNet) for the recovery of ionograms. The performance of the models is evaluated by intersection over union (IoU). We collect and manually label 6131 ionograms, which are acquired from a low-latitude ionosonde in Taiwan. These ionograms are contaminated by strong quasi-static noise, with an average signal-to-noise ratio (SNR) equal to 1.4. Applying the five models to these noisy ionograms, we show that the models can recover useful signals with IoU > 0.6. The highest accuracy is achieved by SA-UNet. For signals with less than 15% of samples in the data set, they can be recovered by Mask R-CNN to some degree (IoU > 0.2). In addition to the number of samples, we identify and examine the effects of three factors: (1) SNR, (2) shape of signal, (3) overlapping of signals on the recovery accuracy of different models. Our results indicate that FC-DenseNet24, DWT, Mask R-CNN and SA-UNet are capable of identifying signals from very noisy ionograms (SNR < 1.4), overlapping signals can be well identified by DWT, Mask R-CNN and SA-UNet, and that more elongated signals are better identified by all models.

Multi‐Scale Attention‐Enhanced Deep Learning Model for Ionogram Automatic Scaling

“…Chang et al. (2022), its mean IoU of F2 layer can be up to 74.5% for SA‐UNet. This big discrepancy between its and our mIoU may be attributed to the different ionogram data used and the different formulas applied for calculating their respective mIoUs.…”

“…Among developed amounts of deep‐learning methods, a deep‐learning method for ionogram automatic scaling (DIAS) was developed to first apply feature pyramid network (FPN) architecture for recovery of useful signals in ionograms (Xiao et al., 2020). Additionally, different convolutional neural network models have been constructed to recover and distinguish different ionospheric layers and signals in terms of low signal‐to‐noise ratio (SNR) characteristics of ionograms (Chang et al., 2022). Among a large number of deep‐learning networks, the well‐known UNet is a convolutional neural network based on U‐shaped encoder‐decoder architecture (Ronneberger et al., 2015).…”