Channel estimation for underwater acoustic OFDM based on super-resolution network

Abstract

In this letter, we propose a method for underwater acoustic channel estimation that combines image super-resolution (SR) and is named FCDnNet. FCDnNet consists of two parts: Fast Super Resolution Convolutional Neural Network (FSRCNN) and Complex Denoising Convolutional Neural Network (C-DnCNN). FSRCNN extracts effective features of pilot channels, uses deconvolution to achieve SR reconstruction, and generates a pre-estimation channel matrix. C-DnCNN preserves the relative positions of the real and imaginary parts of the channel, fully utilizing amplitude and phase information, and can more effectively recover the channel matrix from the pre-estimation matrix. Experimental results show that the normalized mean square error (NMSE) of FCDnNet is at least 13.1$\%$–65.2$\%$ lower than other channel estimation methods based on deep learning.