{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:44:49Z","timestamp":1760060689785,"version":"build-2065373602"},"reference-count":43,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Bourgogne-Franche-Comt\u00e9 Region","award":["ANR-17-EURE-0002"],"award-info":[{"award-number":["ANR-17-EURE-0002"]}]},{"name":"EIPHI Graduate School","award":["ANR-17-EURE-0002"],"award-info":[{"award-number":["ANR-17-EURE-0002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>The reliable operation of photovoltaic (PV) systems is often compromised by surface soiling and structural damage, which reduce energy efficiency and complicate large-scale monitoring. To address this challenge, we propose a two-tiered image-classification framework that combines Vision Transformer (ViT) models, lightweight convolutional neural networks (CNNs), and knowledge distillation (KD). In Tier 1, a DINOv2 ViT-Base model is fine-tuned to provide robust high-level categorization of solar-panel images into three classes: Normal, Soiled, and Damaged. In Tier 2, two enhanced EfficientNetB0 models are introduced: (i) a KD-based student model distilled from a DINOv2 ViT-S\/14 teacher, which improves accuracy from 96.7% to 98.67% for damage classification and from 90.7% to 92.38% for soiling classification, and (ii) an EfficientNetB0 augmented with Multi-Head Self-Attention (MHSA), which achieves 98.73% accuracy for damage and 93.33% accuracy for soiling. These results demonstrate that integrating transformer-based representations with compact CNN architectures yields a scalable and efficient solution for automated monitoring of the condition of PV systems, offering high accuracy and real-time applicability in inspections on solar farms.<\/jats:p>","DOI":"10.3390\/fi17100433","type":"journal-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T13:48:37Z","timestamp":1758635317000},"page":"433","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Learning-Based Approach to Automated Monitoring of Defects and Soiling on Solar Panels"],"prefix":"10.3390","volume":"17","author":[{"given":"Ahmed","family":"Hamdi","sequence":"first","affiliation":[{"name":"FEMTO-ST Institute, University Marie et Louis Pasteur, F-90000 Belfort, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2589-5053","authenticated-orcid":false,"given":"Hassan N.","family":"Noura","sequence":"additional","affiliation":[{"name":"FEMTO-ST Institute, University Marie et Louis Pasteur, F-90000 Belfort, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4068-2996","authenticated-orcid":false,"given":"Joseph","family":"Azar","sequence":"additional","affiliation":[{"name":"FEMTO-ST Institute, University Marie et Louis Pasteur, F-90000 Belfort, France"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,23]]},"reference":[{"key":"ref_1","unstructured":"U.S. Department of Energy (2025, April 24). Solar Photovoltaic Cell Basics, Available online: https:\/\/www.energy.gov\/eere\/solar\/solar-photovoltaic-cell-basics."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"100094","DOI":"10.1016\/j.cles.2023.100094","article-title":"Soiling loss in solar systems: A review of its effect on solar energy efficiency and mitigation techniques","volume":"7","author":"Adekanbi","year":"2024","journal-title":"Clean. Energy Syst."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Bassil, J., Noura, H., Salman, O., Chahine, K., and Guizani, M. (2024, January 27\u201331). Deep Learning Image Classification Models for Solar Panels Dust Detection. Proceedings of the 2024 International Wireless Communications and Mobile Computing (IWCMC), Ayia Napa, Cyprus.","DOI":"10.1109\/IWCMC61514.2024.10592387"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ozturk, O., Hangun, B., and Eyecioglu, O. (2021, January 26\u201329). Detecting snow layer on solar panels using deep learning. Proceedings of the 2021 10th International Conference on Renewable Energy Research and Application (ICRERA), Istanbul, Turkey.","DOI":"10.1109\/ICRERA52334.2021.9598700"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"31119","DOI":"10.1007\/s11356-019-06100-2","article-title":"Impact of bird dropping deposition on solar photovoltaic module performance: A systematic study in Western Rajasthan","volume":"26","author":"Sisodia","year":"2019","journal-title":"Environ. Sci. Pollut. Res."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1186\/s40807-017-0043-y","article-title":"An experimental study on effect of dust on power loss in solar photovoltaic module","volume":"4","author":"Hussain","year":"2017","journal-title":"Renew. Wind Water Sol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"118822","DOI":"10.1016\/j.apenergy.2022.118822","article-title":"Failures of Photovoltaic modules and their Detection: A Review","volume":"313","author":"Akram","year":"2022","journal-title":"Appl. Energy"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hasan, A.A., Ahmed Alkahtani, A., Shahahmadi, S.A., Nur E. Alam, M., Islam, M.A., and Amin, N. (2021). Delamination-and electromigration-related failures in solar panels\u2014A review. Sustainability, 13.","DOI":"10.3390\/su13126882"},{"key":"ref_9","unstructured":"Renewable Energy Magazine (2025, April 22). Above Partners with Leading Universities to Develop Next-Generation Drone Technology for Intelligent Solar Plant Inspections. Available online: https:\/\/www.renewableenergymagazine.com\/pv_solar\/above-partners-with-leading-universities-to-develop-20210611."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Bounabi, M., Azmi, R., Chenal, J., Diop, E.B., Ebnou Abdem, S.A., Adraoui, M., Hlal, M., and Serbouti, I. (2024). Smart PV Monitoring and Maintenance: A Vision Transformer Approach within Urban 4.0. Technologies, 12.","DOI":"10.3390\/technologies12100192"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Amiri, A.F., Kichou, S., Oudira, H., Chouder, A., and Silvestre, S. (2024). Fault detection and diagnosis of a photovoltaic system based on deep learning using the combination of a convolutional neural network (cnn) and bidirectional gated recurrent unit (Bi-GRU). Sustainability, 16.","DOI":"10.3390\/su16031012"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.esd.2021.12.003","article-title":"Investigation into the impacts of design, installation, operation and maintenance issues on performance and degradation of installed solar photovoltaic (PV) systems","volume":"66","author":"Aboagye","year":"2022","journal-title":"Energy Sustain. Dev."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ansari, S., Ayob, A., Lipu, M.S.H., Saad, M.H.M., and Hussain, A. (2021). A review of monitoring technologies for solar PV systems using data processing modules and transmission protocols: Progress, challenges and prospects. Sustainability, 13.","DOI":"10.3390\/su13158120"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"52233","DOI":"10.1109\/ACCESS.2022.3174555","article-title":"Grid integration challenges and solution strategies for solar PV systems: A review","volume":"10","author":"Shafiullah","year":"2022","journal-title":"IEEE Access"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"112186","DOI":"10.1016\/j.solener.2023.112186","article-title":"A review of automated solar photovoltaic defect detection systems: Approaches, challenges, and future orientations","volume":"266","author":"Hijjawi","year":"2023","journal-title":"Sol. Energy"},{"key":"ref_16","first-page":"1174","article-title":"Revolutionizing solar energy with ai-driven enhancements in photovoltaic technology","volume":"2","author":"Mohammad","year":"2023","journal-title":"Bullet J. Multidisiplin Ilmu"},{"key":"ref_17","first-page":"27","article-title":"A study of IoT based real-time solar power remote monitoring system","volume":"9","author":"Cheragee","year":"2021","journal-title":"Int. J. Ambient Syst. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/JPROC.2022.3226481","article-title":"Efficient acceleration of deep learning inference on resource-constrained edge devices: A review","volume":"111","author":"Shuvo","year":"2022","journal-title":"Proc. IEEE"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions","volume":"8","author":"Alzubaidi","year":"2021","journal-title":"J. Big Data"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, X. (2021, January 24\u201326). The AlexNet, LeNet-5 and VGG NET applied to CIFAR-10. Proceedings of the 2021 2nd International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE), Zhuhai, China.","DOI":"10.1109\/ICBASE53849.2021.00083"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Muhammad, U., Wang, W., Chattha, S.P., and Ali, S. (2018, January 20\u201324). Pre-trained VGGNet architecture for remote-sensing image scene classification. Proceedings of the 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China.","DOI":"10.1109\/ICPR.2018.8545591"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Xu, W., Fu, Y.L., and Zhu, D. (2023). ResNet and its application to medical image processing: Research progress and challenges. Comput. Methods Programs Biomed., 240.","DOI":"10.1016\/j.cmpb.2023.107660"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Koonce, B. (2021). EfficientNet. Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, Springer.","DOI":"10.1007\/978-1-4842-6168-2"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Maity, R., Shamaun Alam, M., and Pati, A. (2020). An approach for detection of dust on solar panels using CNN from RGB dust image to predict power loss. Cognitive Computing in Human Cognition: Perspectives and Applications, Springer.","DOI":"10.1007\/978-3-030-48118-6_4"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Sharma, J., Khattar, S., and Verma, T. (2024, January 5\u20137). Design and Development of Soil Detection Framework From Solar Panel Using Deep Learning. Proceedings of the 2024 OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 4.0, Raigarh, India.","DOI":"10.1109\/OTCON60325.2024.10688333"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"663","DOI":"10.3390\/solar3040036","article-title":"A survey of CNN-based approaches for crack detection in solar PV modules: Current trends and future directions","volume":"3","author":"Hassan","year":"2023","journal-title":"Solar"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3505244","article-title":"Transformers in vision: A survey","volume":"54","author":"Khan","year":"2022","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., and Funtowicz, M. (2020, January 16\u201320). Transformers: State-of-the-art natural language processing. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Online.","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., and Joulin, A. (2021, January 11\u201317). Emerging properties in self-supervised vision transformers. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref_30","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., and El-Nouby, A. (2023). Dinov2: Learning robust visual features without supervision. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"8762","DOI":"10.1109\/ACCESS.2021.3049294","article-title":"Multi-head self-attention transformation networks for aspect-based sentiment analysis","volume":"9","author":"Lin","year":"2021","journal-title":"IEEE Access"},{"key":"ref_32","first-page":"1","article-title":"Ultra-Lightweight Feature-Compressed Multi-Head Self-Attention Learning Networks for Hyperspectral Image Classification","volume":"62","author":"Li","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Pierdicca, R., Paolanti, M., Felicetti, A., Piccinini, F., and Zingaretti, P. (2020). Automatic faults detection of photovoltaic farms: SolAIr, a deep learning-based system for thermal images. Energies, 13.","DOI":"10.3390\/en13246496"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Mehta, S., Azad, A.P., Chemmengath, S.A., Raykar, V., and Kalyanaraman, S. (2018, January 12\u201315). Deepsolareye: Power loss prediction and weakly supervised soiling localization via fully convolutional networks for solar panels. Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA.","DOI":"10.1109\/WACV.2018.00043"},{"key":"ref_35","first-page":"50","article-title":"Deep learning approaches for crack detection in solar PV panels","volume":"1","author":"Umar","year":"2024","journal-title":"Int. J. Adv. Eng. Technol. Innov."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Parikh, H.R., Buratti, Y., Spataru, S., Villebro, F., Reis Benatto, G.A.D., Poulsen, P.B., Wendlandt, S., Kerekes, T., Sera, D., and Hameiri, Z. (2020). Solar cell cracks and finger failure detection using statistical parameters of electroluminescence images and machine learning. Appl. Sci., 10.","DOI":"10.3390\/app10248834"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"e18826","DOI":"10.1016\/j.heliyon.2023.e18826","article-title":"Solar panel defect detection design based on YOLO v5 algorithm","volume":"9","author":"Huang","year":"2023","journal-title":"Heliyon"},{"key":"ref_38","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18\u201322). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_40","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the knowledge in a neural network. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: A survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"ref_42","unstructured":"hemanthsai7 (2024, February 26). Solar Panel Dust Detection. Available online: https:\/\/www.kaggle.com\/datasets\/pythonafroz\/solar-panel-images."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"117185","DOI":"10.1016\/j.measurement.2025.117185","article-title":"Efficient combination of deep learning models for solar panel damage and soiling detection","volume":"251","author":"Noura","year":"2025","journal-title":"Measurement"}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/10\/433\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:47:49Z","timestamp":1760035669000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/10\/433"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,23]]},"references-count":43,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["fi17100433"],"URL":"https:\/\/doi.org\/10.3390\/fi17100433","relation":{},"ISSN":["1999-5903"],"issn-type":[{"type":"electronic","value":"1999-5903"}],"subject":[],"published":{"date-parts":[[2025,9,23]]}}}