Saad Farah

Saad Farah


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 July 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
HSHachem Saadaoui
Hachem Saadaoui
SFSaad Farah
Saad Farah
HLHatim Lechgar
Hatim Lechgar
AGAbdellatif Ghennioui
Abdellatif Ghennioui
HRHassan Rhinane
Hassan Rhinane
Urban roof segmentation plays a pivotal role in applications such as urban planning, infrastructure management, and renewable energy deployment. This study explores the evolution of deep learning techniques from traditional Convolutional Neural Networks (CNNs) to cutting-edge Transformer-based models in the context of roof segmentation from satellite imagery. We highlight the limitations of conventional methods when applied to urban environments, including resolution constraints and the complexity of roof structures. To address these challenges, we evaluate two advanced deep learning models: Mask R-CNN and MaskFormer, which have shown significant promise in accurately segmenting roofs, even in dense urban settings with diverse roof geometries. These models, especially the one based on transformers, offer improved segmentation accuracy by capturing both global and local image features, enhancing their performance in tasks where fine detail and contextual awareness are critical. A case study on Ben Guerir City in Morocco, an urban area experiencing rapid development, serves as the foundation for testing these models. Using high-resolution satellite imagery, the segmentation results offer a deeper understanding of the accuracy and effectiveness of these models, particularly in optimizing urban planning and renewable energy assessments. Quantitative metrics such as Intersection over Union (IoU), precision, recall, and F1-score are used to benchmark model performance. Mask R-CNN achieved a mean IoU of 74.6%, precision of 81.3%, recall of 78.9%, and F1-score of 80.1%. MaskFormer outperformed Mask R-CNN, reaching a mean IoU of 79.8%, precision of 85.6%, recall of 82.7%, and F1-score of 84.1%, highlighting the transformative potential of transformer-based architectures for scalable and precise urban imaging. The study also outlines future work in 3D modelling and height estimation, positioning these advancements as critical tools for sustainable urban development.

2 February 2026 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Verified
Journal Article
Open access
SFSaad Farah
Saad Farah
NNNora Nait
Nora Nait
HSHachem Saadaoui
Hachem Saadaoui
HLHatim Lechgar
Hatim Lechgar
MMMehdi Maanan
Mehdi Maanan
HRHassan Rhinane
Hassan Rhinane
Solar energy has become a major contributor to global renewable energy strategies, offering a sustainable alternative to fossil fuels. Photovoltaic (PV) systems, which convert sunlight into electricity, play a central role in this transition. As the demand for large-scale solar energy projects grows, Geographic Information Systems (GIS) and advanced deep learning models have become critical for accurately detecting and mapping PV installations, particularly from satellite imagery. However, challenges remain, especially in regions with suboptimal satellite data quality. This study focuses on the Marrakesh-Safi region of Morocco, where the potential for solar energy is high but hindered by limitations in available satellite imagery. We employ advanced transformer-based models, including Mask2Former, SegFormer, and DeepLabV3+, to enhance the semantic segmentation of PV systems from high-resolution satellite images. By integrating GIS with these deep learning models, we aim to improve the accuracy and scalability of PV detection, even in complex and diverse geographical settings. Our methodology involves training and testing these models on annotated satellite imagery, with performance evaluated using key metrics such as Intersection over Union (IoU), precision, recall, and F1 score. Mask2Former achieved notable results with a recall of 0.95 and an F1 score of 0.936, excelling in the detection of smaller and more complex PV layouts. DeepLabV3+ demonstrated strong overall performance, with an IoU of 0.89 and precision of 0.93, while also being the most computationally efficient model, processing 28 samples per second. This research highlights the effectiveness of integrating GIS with deep learning, particularly transformer-based architectures, for the accurate detection and mapping of PV systems. The results contribute to the broader efforts in renewable energy optimization, supporting more efficient solar energy deployment, especially in regions like Morocco where data quality poses significant challenges.

2 February 2026 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Verified
Journal Article
Open access
SFSaad Farah
Saad Farah
AEAbderrazzak Elbidouri
Abderrazzak Elbidouri
ABAchraf Boutejdir
Achraf Boutejdir
NDNadia Dagdague
Nadia Dagdague
ARAmine Rouhi
Amine Rouhi
HRHassan Rhinane
Hassan Rhinane
Leishmaniasis remains a persistent global public health challenge, particularly in regions where ecological and socioeconomic conditions favor vector proliferation and disease transmission. In Morocco, the provinces of Beni Mellal and Khenifra are among the most severely affected, necessitating the use of advanced spatial prediction tools to guide effective disease control strategies. This study integrated machine learning techniques and Geographic Information System (GIS) technologies to develop a predictive framework for cutaneous leishmaniasis risk mapping. A spatial database was constructed by combining reported case data from 2011 to 2018 with key environmental and climatic variables including temperature, precipitation, normalized difference vegetation index (NDVI), altitude, slope, and wind speed. Three machine learning algorithms, Support Vector Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost), were evaluated for their predictive performance, while the CORrelation ALignment (CORAL) method was applied as a domain adaptation strategy to address distributional differences between training and target regions. The results demonstrated that XGBoost achieved the highest predictive accuracy (R2 = 0.91, MSE = 0.1229, MAE = 0.2587), followed by SVR (R2 = 0.89, MSE = 0.1434, MAE = 0.2765), and RF (R2 = 0.85, MSE = 0.1925, MAE = 0.3120). Incorporating CORAL significantly improved the model generalizability and stability across ecologically diverse zones. The final risk map identified high-risk clusters in central and northern Beni Mellal and Khenifra, offering actionable insights into spatially targeted interventions. This study presents a scalable GIS-integrated machine learning framework with strong potential for application in other data-scarce high-risk regions. Future research should incorporate real-time data and advanced deep learning techniques to further enhance the predictive power.