Deep-Learning-Based Zero-Sample Gradient Guidance Spatial Resolution Enhancement for Microwave Radiometer in Fengyun-3D

Minghao Feng, Weidong Hu, Yuming Bai*, Zhiyu Yao, Vahid Rastinasab, Jian Shang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

For satellite brightness temperature images, researchers are constantly pursuing higher resolutions to obtain more detailed meteorological information. In this article, a novel deep-learning-based modeling approach, named zero-sample gradient guidance spatial resolution enhancement (ZSGRE), is developed explicitly for microwave radiometers. The detailed model, including mathematical derivation and key parameters, is presented. Subsequently, the proposed approach is applied in four scenarios: synthetic scene, simulated geographical brightness temperature, practical measurement of microwave radiometer in Fengyun-3D (FY-3D), and a cyclone analysis on the Atlantic. Compared with other methods, the proposed ZSGRE method improves 2.51% of structural similarity (SSIM), enhances 2.3 dB of peak signal-to-noise ratio (PSNR), and decreases 15.8% of instantaneous field of view (IFOV). Such applications demonstrate ZSGRE’s significant performance: zero-sample preparation and spatial resolution enhancement.

Original languageEnglish
Article number5301311
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume63
DOIs
Publication statusPublished - 2025

Keywords

  • Fengyun-3D (FY-3D)
  • microwave radiometer
  • spatial resolution enhancement
  • zero sample

Fingerprint

Dive into the research topics of 'Deep-Learning-Based Zero-Sample Gradient Guidance Spatial Resolution Enhancement for Microwave Radiometer in Fengyun-3D'. Together they form a unique fingerprint.

Cite this