Feature‐Enhanced Inversion Algorithms for Accurate Ground Object Radiation Detection With Fully Polarized Microwave Radiometers
International Journal of Numerical Modelling: Electronic Networks, Devices and Fields · 2026-11 · 39 (6)
DOI: 10.1002/jnm.70224 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Numerical Modelling: Electronic Networks, Devices and Fields, online erschienen am 06.11.2026. Verfasst von Jie Liu und 4 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Gefördert von: Natural Science Foundation of Beijing Municipality.
Abstract (Originalsprache)
Microwave radiation detection technology is extensively utilized for identifying targets across diverse terrains, with significant applications in remote sensing and security inspection. However, existing microwave radiometer measurement systems struggle to differentiate subtle brightness temperature variations across similar ground objects (e.g., turf or cement with varying roughness) that exhibit extremely close physical emissivities. To address this gap, this study proposes a feature‐enhanced inversion algorithm based on a fully polarized passive microwave radiometer. Six selected features from and are combined with the mean, maximum and standard deviation of each of and , giving 12 model inputs. Furthermore, a hybrid neural network combining Particle Swarm Optimization and Levenberg–Marquardt Backpropagation (PSO‐LM‐BP) integrates global initialization and local refinement to map these polarimetric features to reference brightness temperature. Comparative analyses employing multiple feature sets and optimization algorithms confirm the superior inversion accuracy of the proposed method, achieving a mean squared prediction error of 0.3243 K 2 relative to the reference labels under a record‐level split. In conclusion, this work provides an effective algorithmic framework and feature extraction approach for high‐precision microwave target identification under complex ground object backgrounds.
Förderung
- Natural Science Foundation of Beijing Municipality
Zitieren
APA
Liu, J., Li, J., Tan, G., Zhao, S., & Tong, D. (2026). Feature‐Enhanced Inversion Algorithms for Accurate Ground Object Radiation Detection With Fully Polarized Microwave Radiometers. International Journal of Numerical Modelling: Electronic Networks, Devices and Fields, 39(6). https://doi.org/10.1002/jnm.70224
Vancouver
Liu J, Li J, Tan G, Zhao S, Tong D. Feature‐Enhanced Inversion Algorithms for Accurate Ground Object Radiation Detection With Fully Polarized Microwave Radiometers. International Journal of Numerical Modelling: Electronic Networks, Devices and Fields. 2026;39(6). doi:10.1002/jnm.70224
BibTeX
@article{Liu2026,
author = {Liu, Jie and Li, Jiachen and Tan, Guoxiang and Zhao, Shaojie and Tong, Dewang},
title = {Feature‐Enhanced Inversion Algorithms for Accurate Ground Object Radiation Detection With Fully Polarized Microwave Radiometers},
journal = {International Journal of Numerical Modelling: Electronic Networks, Devices and Fields},
year = {2026},
volume = {39},
number = {6},
doi = {10.1002/jnm.70224}
}
EUVIMED