EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Deep Neural Networks for Refining Vertical Modeling of Global Tropospheric Delay

Peng Yuan, Kyriakos Balidakis, Jungang Wang, Pengfei Xia, Jian Wang, Mingyuan Zhang, Weiping Jiang, Harald Schuh, Jens Wickert, Zhiguo Deng

Geophysical Research Letters · 28.01.2025 · 52 (2)

DOI: 10.1029/2024gl111404 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Geophysical Research Letters, online erschienen am 25.01.2025. Verfasst von Peng Yuan und 9 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, State Key Laboratory of Geo-Information Engineering, Bundesministerium für Umwelt, Naturschutz, nukleare Sicherheit und Verbraucherschutz.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kinematic airborne platforms are becoming increasingly vital for Earth observation. They highlight the critical need for accurate tropospheric delay corrections across varying altitudes, especially as most existing models are limited to Earth's surface. Although analytical functions have been used to model vertical reductions in tropospheric delays, they struggle to capture the intricate vertical variations of atmospheric state. In response, we introduce a novel approach that utilizes deep neural networks (DNN) to reconstruct global three‐dimensional zenith hydrostatic delay (ZHD) and zenith wet delays (ZWD) derived from numerical weather models (NWM). Our method reconstructs NWM‐derived ZHD and ZWD globally up to 14 km above the Earth's surface, with average precision levels of 0.4 and 0.8 mm, respectively. Compared to the analytical third‐order exponential model, the DNN approach demonstrates substantial improvement with global average root‐mean‐square reductions of 63% for ZHD and 36% for ZWD.

Förderung

  • Deutsche Forschungsgemeinschaft
  • State Key Laboratory of Geo-Information Engineering
  • Bundesministerium für Umwelt, Naturschutz, nukleare Sicherheit und Verbraucherschutz

Zitieren

APA

Yuan, P., Balidakis, K., Wang, J., Xia, P., Wang, J., Zhang, M., Jiang, W., Schuh, H., Wickert, J., & Deng, Z. (2025). Deep Neural Networks for Refining Vertical Modeling of Global Tropospheric Delay. Geophysical Research Letters, 52(2). https://doi.org/10.1029/2024gl111404

Vancouver

Yuan P, Balidakis K, Wang J, Xia P, Wang J, Zhang M, et al. Deep Neural Networks for Refining Vertical Modeling of Global Tropospheric Delay. Geophysical Research Letters. 2025;52(2). doi:10.1029/2024gl111404

BibTeX
@article{Yuan2025,
  author = {Yuan, Peng and Balidakis, Kyriakos and Wang, Jungang and Xia, Pengfei and Wang, Jian and Zhang, Mingyuan and Jiang, Weiping and Schuh, Harald and Wickert, Jens and Deng, Zhiguo},
  title = {Deep Neural Networks for Refining Vertical Modeling of Global Tropospheric Delay},
  journal = {Geophysical Research Letters},
  year = {2025},
  volume = {52},
  number = {2},
  doi = {10.1029/2024gl111404}
}
Kostenlos starten →