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.

Original languageEnglish
Article number771
JournalRemote Sensing
Issue number7
Publication statusPublished - 2019
Externally publishedYes

    Research areas

  • Convolutional neural network (CNN), Fengyun-3C (FY-3C), Microwave radiation imager (MWRI), Microwave radiometer, Spatial resolution enhancement

ID: 53336455