EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Validation-Controlled Label-Efficient Framework for Coastal Wetland Habitat Mapping Using Multi-Season Sentinel-1 and Sentinel-2 Data

Marwa Zerrouk, Siham Fellahi, Asmaa Moussaoui, Imane Sebari, Kenza Aitelkadi

Earth · 15.08.2026 · 7 (4) · 137

DOI: 10.3390/earth7040137 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Earth, online erschienen am 15.08.2026. Verfasst von Marwa Zerrouk und 4 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CNRST-UM6P.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable coastal wetland habitat mapping is often constrained by the scarcity and the cost of reliable reference data, especially in data-limited coastal environments. We propose a validation-controlled, label-efficient framework pairing multi-season Sentinel-1 and Sentinel-2 predictors with a CatBoost teacher and a lightweight MLP student. A candidate is pseudo-labeled only when both separately calibrated models agree and exceed class-specific thresholds; accepted labels are class-balanced and down-weighted. The framework was evaluated at the Sidi Moussa–Oualidia wetland complex and Merja Zerga lagoon in Morocco. At Sidi Moussa–Oualidia, 62 configurations were compared through nested polygon-grouped validation and then frozen before a five-seed held-out evaluation. The supervised MLP and Agreement-augmented MLP achieved mean Macro-F1 values of 0.9518±0.0044 and 0.9509±0.0062, indicating that augmentation did not materially change the already strong full-data baseline. Under a stricter budget of 30 training and 20 validation observations per class, Agreement yielded a mean Macro-F1 of 0.9092±0.0102 compared with 0.9023±0.0093 for the supervised baseline and produced pseudo-labels in all five seeds. A spatial-range sensitivity analysis further showed that both models retained Macro-F1 values of 0.9391 and 0.9403 for test observations located beyond the largest estimated within-class autocorrelation range. At Merja Zerga, the native six-class supervised MLP achieved 0.9456±0.0050, compared with 0.9401±0.0047 after Agreement augmentation. Spatially blocked four-class experiments nevertheless showed that 20 to 30 local training labels per class recovered approximately 96–98% of the corresponding full-data performance. The framework therefore supplies an operational criterion for using unlabeled observations: augmentation is adopted only where calibrated filtering yields adequate class coverage, and validation confirms a downstream effect; otherwise the supervised model is retained. For the strict Sidi Moussa–Oualidia reduced-label experiment, the reported development budgets count every site-specific label used for fitting, early stopping, and calibration. The Merja Zerga blocked experiments separately quantify training-label sensitivity while retaining their blocked validation resources.

Förderung

  • CNRST-UM6P

Zitieren

APA

Zerrouk, M., Fellahi, S., Moussaoui, A., Sebari, I., & Aitelkadi, K. (2026). A Validation-Controlled Label-Efficient Framework for Coastal Wetland Habitat Mapping Using Multi-Season Sentinel-1 and Sentinel-2 Data. Earth, 7(4), 137. https://doi.org/10.3390/earth7040137

Vancouver

Zerrouk M, Fellahi S, Moussaoui A, Sebari I, Aitelkadi K. A Validation-Controlled Label-Efficient Framework for Coastal Wetland Habitat Mapping Using Multi-Season Sentinel-1 and Sentinel-2 Data. Earth. 2026;7(4):137. doi:10.3390/earth7040137

BibTeX
@article{Zerrouk2026,
  author = {Zerrouk, Marwa and Fellahi, Siham and Moussaoui, Asmaa and Sebari, Imane and Aitelkadi, Kenza},
  title = {A Validation-Controlled Label-Efficient Framework for Coastal Wetland Habitat Mapping Using Multi-Season Sentinel-1 and Sentinel-2 Data},
  journal = {Earth},
  year = {2026},
  volume = {7},
  number = {4},
  pages = {137},
  doi = {10.3390/earth7040137}
}
Kostenlos starten →