Spatial Resolution Enhancement of Satellite Microwave Radiometer Data with Deep Residual Convolutional Neural Network

Abstract

Satellite microwave radiometer data is affected by many degradation factors during the imaging process, such as the sampling interval, antenna pattern and scan mode, etc., leading to spatial resolution reduction. In this paper, a deep residual convolutional neural network (CNN) is proposed to solve these degradation problems by learning the end-to-end mapping between low-and high-resolution images. Unlike traditional methods that handle each degradation factor separately, our network jointly learns both the sampling interval limitation and the comprehensive degeneration factors, including the antenna pattern, receiver sensitivity and scan mode, during the training process. Moreover, due to the powerful mapping capability of the deep residual CNN, our method achieves better resolution enhancement results both quantitatively and qualitatively than the methods in literature. The microwave radiation imager (MWRI) data from the Fengyun-3C (FY-3C) satellite has been used to demonstrate the validity and the effectiveness of the method.

Comparison of the Remapping Algorithms for the Advanced Technology Microwave Sounder (ATMS)

“…Some filter-based deconvolution algorithms similar to the AFA have already incorporated the along-scan deformation of FOVs using space-variant PSFs [17,[30][31][32]. In these algorithms, filtering is completed along each column of the image with a PSF at that specific scan position, since the relative geometry changes of the data in the along-track direction almost stay the same.…”

“…Figure 1 illustrates that the relative geometries of the samples change significantly along the scan. Because the remapping algorithms are highly dependent on the overlaps between the raw antenna pattern and the expected one, the geometric deformation of the FOVs over the scan has a very important effect on the remapping algorithms [17,[30][31][32].…”

“…Recently, many deep-learning-based super-resolution technologies have been proposed to improve the image quality of the natural environment [24][25][26][27][28][29]. Since the development by Hu et al [30] of a deconvolution algorithm based on a convolutional neural network, the deep learning technique has been applied to microwave radiometer data to enhance their resolution [31][32][33]. However, among these algorithms, only a few manage to match the intrinsic antenna…”

Spatial Resolution Matching of Microwave Radiometer Data with Convolutional Neural Network

“…In order to enhance the spatial resolution of the microwave radiometer data, several degradation factors should be reduced, including the antenna pattern, the integration time, the scan geometry, and the receiver sensitivity. Specifically, due to the limited size and long working distance of the satellite antenna, the observed data are smoothed by the wide beam width of the antenna pattern, leading to the low spatial resolution [6][7][8][9][10][11]. Secondly, considering the integration time of the radiometer, the equivalent antenna pattern is further broadened [12].…”

“…Secondly, considering the integration time of the radiometer, the equivalent antenna pattern is further broadened [12]. Moreover, the relative geometry of the observation changes along with the conical scan, which makes the resolution spatial variable [8][9][10][11]. Lastly, the receiver sensitivity of the radiometer leads to the noise of the observation [3,10,11].…”