Detection and Comparative Analysis of Mucilage from Satellite Images Using Deep Learning Methods

Year 2025, Volume: 14 Issue: 4, 2664 - 2683, 31.12.2025

Yunus Emre Çukur , Ertürk Erdağı

https://doi.org/10.17798/bitlisfen.1773151

Abstract

Mucilage is an environmental problem that threatens biodiversity in marine ecosystems and poses socio-economic risks. In heavily polluted areas like the Marmara Sea, early detection of mucilage is crucial for maintaining ecological balance. Early detection allows policymakers to take swift action. This study utilizes deep learning methods to detect marine mucilage using satellite imagery. The study employed YOLOv7, YOLOv8, YOLOv11, and YOLOv12 models, along with transformer-based RF-DETR and Roboflow 3.0 architectures. A dataset comprising 1113 images from various satellite sources, with mucilage regions marked with bounding boxes, was used. The dataset was expanded using data enhancement techniques. The training process was improved by applying hyperparameters to all models, resulting in performance gains. The performance of the models used in the study was evaluated using precision, recall, mAP@0.5, and mAP@0.5:0.95 metrics. Experimental results show that the YOLOv8 model achieved higher success rates than other methods. Hyperparameter settings were found to significantly impact model performance. Evaluations indicate difficulties in mucilage detection due to low-resolution images and image complexity in coastal areas. This study demonstrates the applicability of artificial intelligence technologies for monitoring environmental problems and provides a decision-support infrastructure for early-warning systems.

Keywords

Mucilage , Sea , YOLO , Deep learning , Satellite imagery , mAP

Ethical Statement

The study is complied with research and publication ethics.

References

• C. Totti et al., ‘Phytoplankton size-distribution and community structure in relation to mucilage occurrence in the northern Adriatic Sea’, Sci. Total Environ., vol. 353, no. 1–3, pp. 204–217, Dec. 2005, doi: 10.1016/j.scitotenv.2005.09.028.
• V. Flander-Putrle and A. Malej, ‘The evolution and phytoplankton composition of mucilaginous aggregates in the northern Adriatic Sea’, Harmful Algae, vol. 7, no. 6, pp. 752–761, 2008.
• B. Yalçın, M. L. Artüz, A. Pavlidou, S. Çubuk, and M. Dassenakis, ‘Nutrient dynamics and eutrophication in the Sea of Marmara: Data from recent oceanographic research’, Sci. Total Environ., vol. 601–602, pp. 405–424, Dec. 2017, doi: 10.1016/j.scitotenv.2017.05.179.
• V. Turk, Å. Hagström, N. Kovač, and J. Faganeli, ‘Composition and function of mucilage macroaggregates in the northern Adriatic’, Aquat. Microb. Ecol., vol. 61, no. 3, pp. 279–289, 2010.
• A. Ü. Kömüşcü, M. Aksoy, and O. H. Dogan, ‘An analysis of meteorological conditions in relation to occurrence of the mucilage outbreaks in Sea of Marmara, March–June 2021’, Int. J. Environ. Geoinformatics, vol. 9, no. 3, pp. 126–145, 2022.
• C. Xie et al., ‘Environmental factors influencing mucilage accumulation of the endangered Brasenia schreberi in China’, Sci. Rep., vol. 8, no. 1, p. 17955, 2018.
• U. Karadurmuş and M. Sari, ‘Marine mucilage in the Sea of Marmara and its effects on the marine ecosystem: mass deaths’, Turk. J. Zool., vol. 46, no. 1, pp. 93–102, 2022.
• D. F. Demirel and E. D. Gönül-Sezer, ‘Analyzing the impacts of mucilage in the Sea of Marmara: A system dynamics approach integrating sustainability perspectives’, Ecol. Model., vol. 507, p. 111166, 2025.
• R. Danovaro et al., ‘Implementing and innovating marine monitoring approaches for assessing marine environmental status’, Front. Mar. Sci., vol. 3, p. 213, 2016.
• P. Cipollini, F. M. Calafat, S. Jevrejeva, A. Melet, and P. Prandi, ‘Monitoring sea level in the coastal zone with satellite altimetry and tide gauges’, Integr. Study Mean Sea Level Its Compon., pp. 35–59, 2017.
• G. Volpe, R. Santoleri, V. Vellucci, M. R. d’Alcalà, S. Marullo, and F. d’Ortenzio, ‘The colour of the Mediterranean Sea: Global versus regional bio-optical algorithms evaluation and implication for satellite chlorophyll estimates’, Remote Sens. Environ., vol. 107, no. 4, pp. 625–638, 2007.
• J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, ‘You Only Look Once: Unified, Real-Time Object Detection’, May 09, 2016, arXiv: arXiv:1506.02640. doi: 10.48550/arXiv.1506.02640.
• S. Ren, K. He, R. Girshick, and J. Sun, ‘Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks’, Jan. 06, 2016, arXiv: arXiv:1506.01497. doi: 10.48550/arXiv.1506.01497.
• R. Sapkota, R. H. Cheppally, A. Sharda, and M. Karkee, ‘RF-DETR Object Detection vs YOLOv12: A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity’, Apr. 17, 2025, arXiv: arXiv:2504.13099. doi: 10.48550/arXiv.2504.13099.
• V. Khryashchev and R. Larionov, ‘Wildfire segmentation on satellite images using deep learning’, in 2020 Moscow Workshop on Electronic and Networking Technologies (MWENT), IEEE, 2020, pp. 1–5.
• R. Danovaro, S. Fonda Umani, and A. Pusceddu, ‘Climate change and the potential spreading of marine mucilage and microbial pathogens in the Mediterranean Sea’, PloS One, vol. 4, no. 9, p. e7006, 2009.
• N. Balkis, H. Atabay, I. Türetgen, S. Albayrak, H. Balkis, and V. Tüfekçi, ‘Role of single-celled organisms in mucilage formation on the shores of Büyükada Island (the Marmara Sea)’, J. Mar. Biol. Assoc. U. K., vol. 91, no. 4, pp. 771–781, 2011.
• A. L. Yagci, I. Colkesen, T. Kavzoglu, and U. G. Sefercik, ‘Daily monitoring of marine mucilage using the MODIS products: a case study of 2021 mucilage bloom in the Sea of Marmara, Turkey’, Environ. Monit. Assess., vol. 194, no. 3, p. 170, 2022.
• A. Tuzcu Kokal, N. Olgun, and N. Musaoğlu, ‘Detection of mucilage phenomenon in the Sea of Marmara by using multi-scale satellite data’, Environ. Monit. Assess., vol. 194, no. 8, p. 585, 2022.
• C. Hu, ‘Sea snots in the Marmara Sea as observed from medium-resolution satellites’, IEEE Geosci. Remote Sens. Lett., vol. 19, pp. 1–5, 2022.
• C. Hu, L. Qi, Y. Xie, S. Zhang, and B. B. Barnes, ‘Spectral characteristics of sea snot reflectance observed from satellites: Implications for remote sensing of marine debris’, Remote Sens. Environ., vol. 269, p. 112842, Feb. 2022, doi: 10.1016/j.rse.2021.112842.
• K. Kikaki, I. Kakogeorgiou, I. Hoteit, and K. Karantzalos, ‘Detecting Marine pollutants and Sea Surface features with Deep learning in Sentinel-2 imagery’, ISPRS J. Photogramm. Remote Sens., vol. 210, pp. 39–54, Apr. 2024, doi: 10.1016/j.isprsjprs.2024.02.017.
• K. G. Toker and S. E. Yuksel, ‘Multi-scale superpixel-based nearest subspace classifier for mucilage detection from hyperspectral PRISMA data’, Digit. Signal Process., vol. 154, p. 104657, Nov. 2024, doi: 10.1016/j.dsp.2024.104657.
• S. Mishra and D. R. Mishra, ‘Normalized difference chlorophyll index: A novel model for remote estimation of chlorophyll-a concentration in turbid productive waters’, Remote Sens. Environ., vol. 117, pp. 394–406, Feb. 2012, doi: 10.1016/j.rse.2011.10.016.
• C. Hu, ‘A novel ocean color index to detect floating algae in the global oceans’, Remote Sens. Environ., vol. 113, no. 10, pp. 2118–2129, Oct. 2009, doi: 10.1016/j.rse.2009.05.012.
• C. E. Binding, T. A. Greenberg, and R. P. Bukata, ‘The MERIS Maximum Chlorophyll Index; its merits and limitations for inland water algal bloom monitoring’, J. Gt. Lakes Res., vol. 39, pp. 100–107, Jan. 2013, doi: 10.1016/j.jglr.2013.04.005.
• M. Drusch et al., ‘Sentinel-2: ESA’s Optical High-Resolution Mission for GMES Operational Services’, Remote Sens. Environ., vol. 120, pp. 25–36, May 2012, doi: 10.1016/j.rse.2011.11.026.
• S. Kay, J. D. Hedley, and S. Lavender, ‘Sun Glint Correction of High and Low Spatial Resolution Images of Aquatic Scenes: a Review of Methods for Visible and Near-Infrared Wavelengths’, Remote Sens., vol. 1, no. 4, pp. 697–730, Oct. 2009, doi: 10.3390/rs1040697.
• X. X. Zhu et al., ‘Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources’, IEEE Geosci. Remote Sens. Mag., vol. 5, no. 4, pp. 8–36, Dec. 2017, doi: 10.1109/MGRS.2017.2762307.
• G. Cheng, J. Han, and X. Lu, ‘Remote Sensing Image Scene Classification: Benchmark and State of the Art’, Proc. IEEE, vol. 105, no. 10, pp. 1865–1883, Oct. 2017, doi: 10.1109/JPROC.2017.2675998.
• L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, ‘Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation’, presented at the Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 801–818. Accessed: Aug. 26, 2025. [Online]. Available: https://openaccess.thecvf.com/content_ECCV_2018/html/Liang-Chieh_Chen_Encoder-Decoder_with_Atrous_ECCV_2018_paper.html
• N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, ‘End-to-End Object Detection with Transformers’, May 28, 2020, arXiv: arXiv:2005.12872. doi: 10.48550/arXiv.2005.12872.
• I. Colkesen, T. Kavzoglu, U. G. Sefercik, and M. Y. Ozturk, ‘Automated mucilage extraction index (AMEI): a novel spectral water index for identifying marine mucilage formations from Sentinel-2 imagery’, Int. J. Remote Sens., vol. 44, no. 1, pp. 105–141, 2023, doi: 10.1080/01431161.2022.2158049.
• C. Shorten and T. M. Khoshgoftaar, ‘A survey on Image Data Augmentation for Deep Learning’, J. Big Data, vol. 6, no. 1, p. 60, Jul. 2019, doi: 10.1186/s40537-019-0197-0.
• M. Leenstra, D. Marcos, F. Bovolo, and D. Tuia, ‘Self-supervised pre-training enhances change detection in Sentinel-2 imagery’, Apr. 11, 2021, arXiv: arXiv:2101.08122. doi: 10.48550/arXiv.2101.08122.
• M. Yurdakul, ‘Mucilage Dataset’, Roboflow Universe. Roboflow, Dec. 2023. [Online]. Available: https://universe.roboflow.com/mustafa-yurdakul/mucilage-bftvt
• C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, ‘YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors’, in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada: IEEE, Jun. 2023, pp. 7464–7475. doi: 10.1109/CVPR52729.2023.00721.
• M. Sohan, T. Ram, and V. Ch, ‘A Review on YOLOv8 and Its Advancements’, 2024, pp. 529–545. doi: 10.1007/978-981-99-7962-2_39.
• R. Khanam and M. Hussain, ‘YOLOv11: An Overview of the Key Architectural Enhancements’, Oct. 23, 2024, arXiv: arXiv:2410.17725. doi: 10.48550/arXiv.2410.17725.
• Y. Tian, Q. Ye, and D. Doermann, ‘YOLOv12: Attention-Centric Real-Time Object Detectors’, Feb. 18, 2025, arXiv: arXiv:2502.12524. doi: 10.48550/arXiv.2502.12524.
• N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, ‘End-to-End Object Detection with Transformers’, May 28, 2020, arXiv: arXiv:2005.12872. doi: 10.48550/arXiv.2005.12872.
• S. Alexandrova, Z. Tatlock, and M. Cakmak, ‘RoboFlow: A flow-based visual programming language for mobile manipulation tasks’, in 2015 IEEE International Conference on Robotics and Automation (ICRA), May 2015, pp. 5537–5544. doi: 10.1109/ICRA.2015.7139973.
• C. Sager, C. Janiesch, and P. Zschech, ‘A survey of image labelling for computer vision applications’, J. Bus. Anal., vol. 4, no. 2, pp. 91–110, Jul. 2021, doi: 10.1080/2573234X.2021.1908861.