Marwa Zerrouk

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 $0.9518\pm 0.0044$ and $0.9509\pm 0.0062$, 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 $0.9092\pm 0.0102$ compared with $0.9023\pm 0.0093$ 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 $0.9456\pm 0.0050$, compared with $0.9401\pm 0.0047$ 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.

Rurbanization and peri-urbanization are among the most dynamic territorial processes affecting metropolitan regions in Morocco, particularly within the Casablanca–Settat region. These transformations, driven by rapid urban growth, demographic pressure, and socio-economic change, generate complex transitional spaces between rural and urban environments. In this context, the present study proposes a hybrid methodology for detecting, classifying, and analyzing the rural–urban continuum by using remote sensing data and artificial intelligence techniques. The approach integrates Sentinel-2 satellite imagery, spectral indices, Global Human Settlement Layer datasets, and socio-demographic indicators derived from the Moroccan census. Two models, Self-Organizing Maps (SOM) and Graph Neural Networks (GNN), were applied to classify territories into four categories: urban, peri-urban, rurban, and rural. Model outputs were combined with expert-based decision rules to improve classification robustness and interpretability. The SOM model achieved up to $89.3\%$ agreement with expert classifications and a Cohen’s Kappa coefficient of $0.842$, demonstrating strong interpretability and consistency, while the GNN model reached $53\%$ agreement and effectively modeled spatial dependencies and neighborhood interactions. Diachronic analysis between 2014 and 2024 revealed a $54\%$ increase in peri-urban municipalities, a $24\%$ decrease in rurban territories, and a decline in rural municipalities, highlighting intensified urban sprawl and fragmentation of agricultural landscapes. Beyond its scientific contribution, this study provides a valuable decision-support framework for urban planners, environmental agencies, and policy makers involved in territorial governance and sustainable development. It can support land-use planning, monitoring of urban sprawl, protection of agricultural lands, and the implementation of adaptive territorial policies aimed at improving the resilience and sustainability of rurban environments.

Wetlands, among the most productive ecosystems on Earth, shelter a diversity of species and help maintain ecological balance. However, they are witnessing growing anthropogenic and climatic threats, which underscores the need for regular and long-term monitoring. This study presents a systematic review of 121 peer-reviewed articles published between January 2015 and 30 April 2025 that applied machine learning (ML) and deep learning (DL) for wetland mapping and bird-habitat monitoring. Despite rising interest, applications remain fragmented, especially for avian habitats; only 39 studies considered birds, and fewer explicitly framed wetlands as bird habitats. Following PRISMA 2020 and the SPIDER framework, we compare data sources, classification methods, validation practices, geographic focus, and wetland types. ML is predominant overall, with random forest the most common baseline, while DL (e.g., U-Net and Transformer variants) is underused relative to its broader land cover adoption. Where reported, DL shows a modest but consistent accuracy over ML for complex wetland mapping; this accuracy improves when fusing synthetic aperture radar (SAR) and optical data. Validation still relies mainly on overall accuracy (OA) and Kappa coefficient ($\kappa$), with limited class-wise metrics. Salt marshes and mangroves dominate thematically, and China geographically, whereas peatlands, urban marshes, tundra, and many regions (e.g., Africa and South America) remain underrepresented. Multi-source fusion is beneficial yet not routine; The combination of unmanned aerial vehicles (UAVs) and DL is promising for fine-scale avian micro-habitats but constrained by disturbance and labeling costs. We then conclude with actionable recommendations to enable more robust and scalable monitoring. This review can be considered as the first comparative synthesis of ML/DL methods applied to wetland mapping and bird-habitat monitoring, and highlights the need for more diverse, transferable, and ecologically/socially integrated AI applications in wetland and bird-habitat monitoring.