Peri-urbanization is one of the most complex and rapidly territorial phenomena in African metropolitan areas, including Morocco. This dynamic, characterized by unplanned urban growth, presents significant challenges in terms of land management and sustainable territorial planning. In this context, this work proposes a methodology for detecting and analyzing peri-urban areas using a deep learning model based on the Global Human Settlement Layer and Global Land Analysis and Discovery Land Cover data. The Multi-Layer Perceptron model was trained on a manually annotated dataset covering the Casablanca metropolitan region and then used to classify the area into four categories: urban, peri-urban, rural, and water. Model interpretability was ensured through the Shapley Additive Explanations method, and a diachronic analysis was conducted from 2005 to 2025. The model achieved high accuracy (90.6%), with strong performance in identifying urban (F1 ≈ 0.996) and rural (F1 ≈ 0.94) areas. However, peri-urban areas represent some challenges, which result in a lower F1-score of about 0.63 due to transitional land patterns. The results reveal a significant expansion of peri-urban areas (+28,000 ha) at the expense of rural lands. These findings offer valuable insights for policymakers to develop sustainable land-use planning strategies and to anticipate urban sprawl dynamics.

Urbanization is one of the most important challenges contributing to the trend of replacing agricultural land with high-value land uses, such as housing, as well as industrial and commercial activities, as a result of significant population growth. To face these challenges and improve urban sustainability, integrating an embedded concept of spatial planning, taking into account urban and peri-urban agriculture, will contribute to mitigating food security issues and the negative impact of climate change, while improving social and economic development. This project aims to analyze land use/cover changes in the Casablanca metropolitan area and its surrounding cities, which are undergoing rapid urban growth. To achieve this, time series of remote sensing data were analyzed in order to investigate the spatio-temporal changes in LU/LC and to evaluate the dynamics and spatial pattern of the city’s expansion over the past three decades, which has come at the expense of agricultural land. The study will also examine the relationship between urbanization and agricultural land use change over time. The results of this study show that Casablanca and its outskirts experience significant urban expansion and a decline in arable lands, with rates of 45% and 42%, respectively. The analysis of SDG indicator 11.3.1 has also shown that land consumption in the provinces of Mediouna, Mohammadia, and Nouaceur has exceeded population growth, due to rapid, uncontrolled urbanization at the expense of agricultural land, which highlights the need to develop a new conceptual framework for regenerating land systems based on the implementation of urban and peri-urban agriculture in vacant sites within urban and peri-urban areas. This will offer valuable insights for policymakers to investigate measures that can ensure sustainable land use planning strategies that effectively integrate agriculture into urban development.

Urbanization represents a major challenge, driving the conversion of agricultural land into high-value uses such as residential, industrial, and commercial developments, largely due to rapid population growth. To address these challenges and enhance urban sustainability, it is essential to incorporate spatial planning strategies that integrate urban and peri-urban agriculture. We consider urban and peri-urban agriculture to be of vital importance in ensuring food security and meeting citizens' needs. Thus, our proposal is based on integrating agriculture into open spaces in urban and peri urban areas, such as community gardens, rooftops and greenhouses. In this way, we will be able to exploit these spaces for the cultivation of agricultural commodities common in the region, such as cereals and market garden crops. This project aims to extract those vacant spaces and rooftops using various methods. For vacant space extraction, three classifiers were used: Support Vector Machine (SVM), Minimum Distance, and Random Forest. With a 75% precision, the SVM classifier had the highest accuracy. For rooftop extraction, three methods were tested, including object-based classification using SVM, the pre-trained and optimized deep learning model Footprint Building Extraction-USA, and Mapflow's building model. According to our analysis, the last two approaches achieved the highest accuracy with F-Factor values above 77%.

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.