EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TLE-FEDformer: A Frequency-Domain Transformer Framework for Multi-Sensor Multi-Temporal Flood Inundation Mapping

Pouya Ahmadi, Mohammad Javad Valadan Zoej, Mehdi Mokhtarzade, Nazila Kardan, Parya Ahmadi, Ebrahim Ghaderpour

Remote Sensing · 14.03.2026 · 18 (6) · 895

DOI: 10.3390/rs18060895 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 14.03.2026. Verfasst von Pouya Ahmadi und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Space It Up, the Italian Space Agency and the Ministry of University, Progetti Piccoli di Ateneo 2025, Sapienza University of Rome, Italy.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Floods are among the most devastating natural hazards, intensified by climate change and rapid urbanization. This study introduces a novel deep learning framework, Transfer Learning-Enhanced FEDformer (TLE-FEDformer), designed for accurate and temporally consistent flood inundation mapping. The framework integrates pre-trained Xception backbones for robust multi-sensor feature extraction from Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 optical imagery, a cross-modal fusion module to align heterogeneous modalities, and the Frequency Enhanced Decomposed Transformer (FEDformer) for efficient frequency-domain temporal modeling. This architecture effectively captures long-range dependencies and flood dynamics including onset, peak, duration, and recession, while addressing challenges such as cloud contamination, speckle noise, and limited labeled data. Comprehensive experiments demonstrate superior performance, achieving an overall accuracy of 98.12%, an F1-score of 98.55%, and an Intersection over Union (IoU) of 97.38%, outperforming baselines including Convolutional Neural Networks, Capsule Networks, and transfer learning alone. Ablation studies validate the contributions of each component, while sensitivity analyses confirm robustness across hyperparameters. Uncertainty quantification via Monte Carlo dropout highlights high confidence in core flooded regions. Preliminary generalization tests on independent events yield IoU > 94%, indicating strong transferability. TLE-FEDformer advances operational flood monitoring by providing reliable, scalable, and temporally consistent mapping from multi-sensor remote sensing data. This approach offers significant potential for real-time disaster response, early warning systems, and damage assessment in flood-prone regions worldwide.

Förderung

  • Space It Up
  • the Italian Space Agency and the Ministry of University
  • Progetti Piccoli di Ateneo 2025, Sapienza University of Rome, Italy

Zitieren

APA

Ahmadi, P., Zoej, M. J. V., Mokhtarzade, M., Kardan, N., Ahmadi, P., & Ghaderpour, E. (2026). TLE-FEDformer: A Frequency-Domain Transformer Framework for Multi-Sensor Multi-Temporal Flood Inundation Mapping. Remote Sensing, 18(6), 895. https://doi.org/10.3390/rs18060895

Vancouver

Ahmadi P, Zoej MJV, Mokhtarzade M, Kardan N, Ahmadi P, Ghaderpour E. TLE-FEDformer: A Frequency-Domain Transformer Framework for Multi-Sensor Multi-Temporal Flood Inundation Mapping. Remote Sensing. 2026;18(6):895. doi:10.3390/rs18060895

BibTeX
@article{Ahmadi2026,
  author = {Ahmadi, Pouya and Zoej, Mohammad Javad Valadan and Mokhtarzade, Mehdi and Kardan, Nazila and Ahmadi, Parya and Ghaderpour, Ebrahim},
  title = {TLE-FEDformer: A Frequency-Domain Transformer Framework for Multi-Sensor Multi-Temporal Flood Inundation Mapping},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {6},
  pages = {895},
  doi = {10.3390/rs18060895}
}
Kostenlos starten →