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

To increase the accuracy of ionogram automatic scaling, a deep learning model—multi-scale attention-enhanced UNet (MSAE-UNet) is proposed. Correspondingly, a multi-scale attention-enhanced (MSAE) sub-network is developed which involves a spatial attention nearest up-sampling (SNU) module and several residual channel attention modules with multi-scale skip connections. They contribute to multi-scale feature fusion and augmentation of the learning ability for enhancing faint and elongated profile traces of ionograms. The MSAE sub-network input consists of multi-scale feature maps which could be optimally employed to make the network effectively utilize useful information from the encoders and decoders. Incidentally, a dual channel spatial attention (DCSA) block is embedded between the encoder and the decoder for deeper detail extraction. When the proposed model is applied to scale different electron density profiles of ionograms based on an open dataset, the experimental results show the segmentation performance evaluation indexes: the precision and the recall rate can be improved by 6.9% and 26.1%, respectively, compared to ARTIST routine. Another set of indexes: the mIoU and the F-score are superior to that of other several contrasted deep learning models, which can be improved by 3% and 1.6%, respectively, compared to the original UNet model.