Hajar Hamdaoui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hajar Hamdaoui has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Hanae Al Kaddouri
Mohammed First University, ENSAO, SmartICT
7 shared publications - Yassine Zarrouk
Mohammed First University
5 shared publications Khalid Hachami
3 shared publicationsMohammed Bourhaleb
3 shared publicationsMohammed Rahmoune
3 shared publications- Nour-Eddine Kouddane
Mohammed First University
2 shared publications
Latest Publications
- Open Access
- 13 November 2026
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 17, 1989847
A unified YOLOv11 framework for multi-crop detection of diseases, pests and nutrient deficiencies, with preliminary field validation and mobile decision support
Diseases, insect pests and nutrient deficiencies account for substantial annual crop losses worldwide, yet field diagnosis remains largely dependent on expert visual inspection. Although deep learning has shown considerable promise, most existing studies focus on a single crop or stress category under controlled conditions, with limited attention to nutrient deficiencies and few progressing to real-world deployment. This study presents a unified crop-stress detection framework covering 53 classes (41 biotic stresses, five nutrient deficiencies and seven healthy classes) across seven economically important crops of the Oriental region of Morocco. A dual-device dataset of 159,000 images was assembled, 90.4% acquired in the field with a DSLR camera and a smartphone and 9.6% from open-access sources used for training only. A lightweight YOLOv11n detector was trained at 832 × 832 resolution, with all settings selected on a separate field-acquired validation partition. On an independent test partition not used for model selection, it achieved Precision = 0.977, Recall = 0.972, F1-score = 0.974, mAP@50 = 0.975 (95% CI 0.973–0.977) and mAP@50–95 = 0.953, outperforming YOLOv8n trained under the same protocol on every metric (mAP@50–95 = 0.934) whilst being lighter. In the complete 53-class confusion matrix, all residual misclassifications (3.2%) occurred between visually similar classes of the same stress category, a pattern requiring confirmation on externally acquired data. Performance did not depend on crop recognition alone, as multi-host classes reached a mean mAP@50 comparable to that of single-crop classes (0.968 vs 0.976). Preliminary independent validation on 150 farmer-captured field images covering five stress classes yielded an overall accuracy of 98.7% (148/150; 95% CI 95.3–99.6%). The exported ONNX model reproduced all class predictions of the original PyTorch model on these 150 images. The model was integrated into a multilingual, offline-capable mobile application developed with Flutter and ONNX Runtime Mobile. A preliminary usability assessment with the System Usability Scale, completed by the same 50 farmers, gave a mean score of 93.7 (SD 3.2), a very high value that probably also reflects social desirability and a ceiling effect. This work represents a step towards translating AI-based crop-stress detection from experimental research to practical decision support for farmers.
- 13 November 2026
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 17, 1989847
Open AccessA unified YOLOv11 framework for multi-crop detection of diseases, pests and nutrient deficiencies, with preliminary field validation and mobile decision support
Diseases, insect pests and nutrient deficiencies account for substantial annual crop losses worldwide, yet field diagnosis remains largely dependent on expert visual inspection. Although deep learning has shown considerable promise, most existing studies focus on a single crop or stress category under controlled conditions, with limited attention to nutrient deficiencies and few progressing to real-world deployment. This study presents a unified crop-stress detection framework covering 53 classes (41 biotic stresses, five nutrient deficiencies and seven healthy classes) across seven economically important crops of the Oriental region of Morocco. A dual-device dataset of 159,000 images was assembled, 90.4% acquired in the field with a DSLR camera and a smartphone and 9.6% from open-access sources used for training only. A lightweight YOLOv11n detector was trained at 832 × 832 resolution, with all settings selected on a separate field-acquired validation partition. On an independent test partition not used for model selection, it achieved Precision = 0.977, Recall = 0.972, F1-score = 0.974, mAP@50 = 0.975 (95% CI 0.973–0.977) and mAP@50–95 = 0.953, outperforming YOLOv8n trained under the same protocol on every metric (mAP@50–95 = 0.934) whilst being lighter. In the complete 53-class confusion matrix, all residual misclassifications (3.2%) occurred between visually similar classes of the same stress category, a pattern requiring confirmation on externally acquired data. Performance did not depend on crop recognition alone, as multi-host classes reached a mean mAP@50 comparable to that of single-crop classes (0.968 vs 0.976). Preliminary independent validation on 150 farmer-captured field images covering five stress classes yielded an overall accuracy of 98.7% (148/150; 95% CI 95.3–99.6%). The exported ONNX model reproduced all class predictions of the original PyTorch model on these 150 images. The model was integrated into a multilingual, offline-capable mobile application developed with Flutter and ONNX Runtime Mobile. A preliminary usability assessment with the System Usability Scale, completed by the same 50 farmers, gave a mean score of 93.7 (SD 3.2), a very high value that probably also reflects social desirability and a ceiling effect. This work represents a step towards translating AI-based crop-stress detection from experimental research to practical decision support for farmers.
- 8 January 2026
- Published by Springer Nature
- p. 303-314
Enhancing Room Prediction for Autonomous Indoor Navigation via Object Differentiation and Semantic Mapping
- 8 January 2026
- Published by Springer Nature
- p. 303-314
Enhancing Room Prediction for Autonomous Indoor Navigation via Object Differentiation and Semantic Mapping
- Open Access
- 31 December 2025
- Published by Basrah Journal of Agricultural Sciences, College of Agriculture, University of Basrah in Basrah Journal of Agricultural Sciences
- Vol. 38 (2) , 527-569
Toward Sustainable Farming: Artificial Intelligence Applications in the Detection and Management of Crop Diseases and Pests: A Systematic Review
Crop production faces increasing threats from pests and diseases, which significantly reduce yields and compromise food security, a challenge further intensified by climate change. Conventional pest and disease management approaches are often labor-intensive, time-consuming, and environmentally unsustainable. In this context, Artificial Intelligence (AI), particularly Convolutional Neural Networks (CNNs), has emerged as a powerful tool for accurate and timely detection of crop pests and diseases. This study presents a systematic review of recent advances in CNN-based approaches for pest and disease detection in agricultural systems. A comprehensive literature search was conducted across Scopus, IEEE Xplore, PubMed, Springer, and ScienceDirect for English-language studies published between 2019 and 2025, using predefined keywords related to AI, CNNs, crop diseases, and pest monitoring. Eligible studies were selected based on inclusion and exclusion criteria derived from the PICo framework. Extracted data included crop types, targeted pests and diseases, CNN architectures, dataset characteristics, and performance metrics such as accuracy, precision, and recall. A total of 100 studies were included and synthesized narratively. The findings indicate that CNN-based models consistently achieve high detection performance across a wide range of crops and agro-climatic conditions, with many studies reporting accuracy rates exceeding 95%. These AI-based approaches outperform traditional visual and manual inspection methods in terms of speed, precision, and scalability. Moreover, the integration of CNN models with IoT and edge computing platforms shows strong potential for real-time, field-deployable applications. However, challenges remain, particularly regarding data availability, computational requirements, and deployment in resource-constrained environments. Overall, CNN-based AI technologies represent a promising pathway toward sustainable crop protection, improved agricultural productivity, and enhanced food security.
- 31 December 2025
- Published by Basrah Journal of Agricultural Sciences, College of Agriculture, University of Basrah in Basrah Journal of Agricultural Sciences
- Vol. 38 (2) , 527-569
Open AccessToward Sustainable Farming: Artificial Intelligence Applications in the Detection and Management of Crop Diseases and Pests: A Systematic Review
Crop production faces increasing threats from pests and diseases, which significantly reduce yields and compromise food security, a challenge further intensified by climate change. Conventional pest and disease management approaches are often labor-intensive, time-consuming, and environmentally unsustainable. In this context, Artificial Intelligence (AI), particularly Convolutional Neural Networks (CNNs), has emerged as a powerful tool for accurate and timely detection of crop pests and diseases. This study presents a systematic review of recent advances in CNN-based approaches for pest and disease detection in agricultural systems. A comprehensive literature search was conducted across Scopus, IEEE Xplore, PubMed, Springer, and ScienceDirect for English-language studies published between 2019 and 2025, using predefined keywords related to AI, CNNs, crop diseases, and pest monitoring. Eligible studies were selected based on inclusion and exclusion criteria derived from the PICo framework. Extracted data included crop types, targeted pests and diseases, CNN architectures, dataset characteristics, and performance metrics such as accuracy, precision, and recall. A total of 100 studies were included and synthesized narratively. The findings indicate that CNN-based models consistently achieve high detection performance across a wide range of crops and agro-climatic conditions, with many studies reporting accuracy rates exceeding 95%. These AI-based approaches outperform traditional visual and manual inspection methods in terms of speed, precision, and scalability. Moreover, the integration of CNN models with IoT and edge computing platforms shows strong potential for real-time, field-deployable applications. However, challenges remain, particularly regarding data availability, computational requirements, and deployment in resource-constrained environments. Overall, CNN-based AI technologies represent a promising pathway toward sustainable crop protection, improved agricultural productivity, and enhanced food security.
- 20 March 2025
- Published by Springer Nature
- p. 477-487
A Deep Learning-Based Model for Efficient Olive Leaf Disease Classification
- 20 March 2025
- Published by Springer Nature
- p. 477-487
A Deep Learning-Based Model for Efficient Olive Leaf Disease Classification
- Open Access
- 31 December 2024
- Published by Basrah Journal of Agricultural Sciences, College of Agriculture, University of Basrah in Basrah Journal of Agricultural Sciences
- Vol. 37 (2) , 354-380
Revolutionizing Agriculture: A Comprehensive Review of AI-Enabled Precision Irrigation and Water Quality Forecasting
Climate change poses significant challenges to the agricultural sector, exacerbating water scarcity and intensifying the irrational utilization of water reserves. In response to these pressing issues, Artificial Intelligence (AI) optimizes irrigation, predicting water quantity and quality to ensure optimal crop yields. AI-driven approaches mitigate the challenges of water scarcity, enhancing precision in irrigation management. This review explores recent AI applications in irrigation, focusing on three areas: AI-powered estimation of Crop Evapotranspiration (ETo), integration of AI with Interet of Things (IoT) for Smart Irrigation Systems (Smart-IS), and AI's role in forecasting water quality for irrigation. AI algorithms optimize water usage by quantifying water needs, enabling real-time monitoring, autonomous decision-making, and mitigating risks associated with poor water quality, thus enhancing crop productivity while minimizing environmental impacts. This review emphasizes AI's role in addressing water scarcity and optimizing irrigation in agriculture by utilizing different technologies to ensure sustainable water management and food security. Future researchers will find this review valuable for understanding AI's current impact on irrigation and identifying avenues for further innovation.
- 31 December 2024
- Published by Basrah Journal of Agricultural Sciences, College of Agriculture, University of Basrah in Basrah Journal of Agricultural Sciences
- Vol. 37 (2) , 354-380
Open AccessRevolutionizing Agriculture: A Comprehensive Review of AI-Enabled Precision Irrigation and Water Quality Forecasting
Climate change poses significant challenges to the agricultural sector, exacerbating water scarcity and intensifying the irrational utilization of water reserves. In response to these pressing issues, Artificial Intelligence (AI) optimizes irrigation, predicting water quantity and quality to ensure optimal crop yields. AI-driven approaches mitigate the challenges of water scarcity, enhancing precision in irrigation management. This review explores recent AI applications in irrigation, focusing on three areas: AI-powered estimation of Crop Evapotranspiration (ETo), integration of AI with Interet of Things (IoT) for Smart Irrigation Systems (Smart-IS), and AI's role in forecasting water quality for irrigation. AI algorithms optimize water usage by quantifying water needs, enabling real-time monitoring, autonomous decision-making, and mitigating risks associated with poor water quality, thus enhancing crop productivity while minimizing environmental impacts. This review emphasizes AI's role in addressing water scarcity and optimizing irrigation in agriculture by utilizing different technologies to ensure sustainable water management and food security. Future researchers will find this review valuable for understanding AI's current impact on irrigation and identifying avenues for further innovation.