Applications of Deep Learning for Correcting Tropospheric Phase Delays in InSAR: A Review
Remote Sensing · 02.11.2026 · 18 (21) · 3767
DOI: 10.3390/rs18213767 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 02.11.2026. Verfasst von Ke Ye und 6 weiteren Autor:innen. Die Arbeit nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, ESA-MOST China Dragon-6 Program, National Natural Science Foundation of China.
Abstract (Originalsprache)
Tropospheric phase delay is a major error source that limits the accuracy of Interferometric Synthetic Aperture Radar (InSAR) deformation measurements, including those from the C- and X-band systems commonly examined in the studies reviewed here. Traditional correction methods, including external atmospheric models, spatiotemporal filtering, and phase–elevation empirical approaches, can partially mitigate atmospheric delays but often suffer from limited resolution, strong assumptions, or difficulties in separating atmospheric signals from complex surface deformation. Recent advances in deep learning provide new opportunities for InSAR tropospheric correction by learning nonlinear spatial and temporal relationships from interferometric observations and auxiliary information. This review provides a focused overview of deep learning-based approaches for correcting tropospheric phase delays in InSAR. Existing studies are organized according to their dominant modeling strategies, including convolutional neural network (CNN)-based spatial modeling, recurrent neural network (RNN)-based temporal modeling, generative adversarial network (GAN)-based generative learning, and other feedforward regression approaches. Key network-design strategies, training-label and dataset construction methods, and representative applications are discussed. Finally, current limitations and future research directions are discussed, emphasizing physical consistency, deformation preservation, cross-region generalization, and independent geodetic validation.
Förderung
- National Key Research and Development Program of China
- ESA-MOST China Dragon-6 Program
- National Natural Science Foundation of China
- President’s International Fellowship Initiative
Zitieren
APA
Ye, K., Fan, J., Sousa, J. J., Zhao, H., Guo, H., Bai, S., & Liu, G. (2026). Applications of Deep Learning for Correcting Tropospheric Phase Delays in InSAR: A Review. Remote Sensing, 18(21), 3767. https://doi.org/10.3390/rs18213767
Vancouver
Ye K, Fan J, Sousa JJ, Zhao H, Guo H, Bai S, et al. Applications of Deep Learning for Correcting Tropospheric Phase Delays in InSAR: A Review. Remote Sensing. 2026;18(21):3767. doi:10.3390/rs18213767
BibTeX
@article{Ye2026,
author = {Ye, Ke and Fan, Jinghui and Sousa, Joaquim Joao and Zhao, Hongli and Guo, Hua and Bai, Shibiao and Liu, Guang},
title = {Applications of Deep Learning for Correcting Tropospheric Phase Delays in InSAR: A Review},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {21},
pages = {3767},
doi = {10.3390/rs18213767}
}
EUVIMED