Optimizing Data Augmentation Parameters in YOLOv11 for Enhanced Rip Current Detection on Small Datasets from Depok-Parangtritis Coastline

Madina Hayva  Putri; Umar  Zaky; Bayu Argadyanto  Prabawa

doi:10.52436/1.jutif.2025.6.5.5352

Authors

Madina Hayva Putri Informatics, Universitas Teknologi Yogyakarta, Indonesia
Umar Zaky Information Systems, Universitas Teknologi Yogyakarta, Indonesia
Bayu Argadyanto Prabawa Urban and Regional Planning, Universitas Teknologi Yogyakarta, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2025.6.5.5352

Keywords:

Data Augmentation, Deep Learning, Object Detection, Rip Current, Small Datasets, YOLOv11

Abstract

Rip currents are powerful ocean currents that can suddenly pull swimmer offshore and are often difficult to recognize visually. However, automatic monitoring technology for detecting rip currents is still limited, while small datasets often lead to overfitting problems and reduce detection accuracy. This study aims to optimize data augmentation parameters in YOLOv11 to improve the mean Average Precision (mAP) value and enable rip current detection even with limited data. The dataset was collected from Google Earth and aerial photographs from the Depok-Parangtritis coastline. Preprocessing includes manual labelling, cropping, and resizing to 640 x 640 pixels. Four augmentation techniques were applied, namely crop (0-10%), rotation (-10% to +10%), brightness adjustment (-10% to +10%), and 1 pixel blur using Roboflow. The dataset was split into 70% training and 30% validation. The YOLOv11 model was then trained and evaluated with precision, recall, and mAP metrics. Results show that data augmentation significantly improves model performance. Dataset 2 without augmentation achieved only 31.8% precision, 32.8% recall, and 23.8% mAP50, while the best model from a combination of the original Dataset 1 and the augmented Dataset 3 reached 90.6% precision, 85.7% recall, and 90.4% mAP50. The integration of YOLOv11 into a web application enables automatic detection in both images and videos with bounding box and confidence score. This study emphasizes the importance of visual variation in the dataset for improving the model generalization and provide a practical foundation of real-time coastal monitoring system.

Downloads

Download data is not yet available.

References

N. Kh. K. Et Al., “TOURIST DESTINATION AS AN OBJECT OF RESEARCH OF SOCIAL AND ECONOMIC GEOGRAPHY,” pae, vol. 58, no. 1, hlm. 2058–2067, Jan 2021, doi: 10.17762/pae.v58i1.1082.

A. De Silva, I. Mori, G. Dusek, J. Davis, dan A. Pang, “Automated rip current detection with region based convolutional neural networks,” Coastal Engineering, vol. 166, hlm. 103859, Jun 2021, doi: 10.1016/j.coastaleng.2021.103859.

M. Najafzadeh, S. Basirian, dan Z. Li, “Vulnerability of the rip current phenomenon in marine environments using machine learning models,” Results in Engineering, vol. 21, hlm. 101704, Mar 2024, doi: 10.1016/j.rineng.2023.101704.

“Pusat Meteorologi Maritim BMKG, ‘Rip Currents.’” Diakses: 20 April 2025. [Daring]. Tersedia pada: https://pusmar.id/glossaries/58/RIP-Currents

B. Castelle, J. Dehez, J.-P. Savy, S. Liquet, dan D. Carayon, “Semi-empirical forecast modelling of rip-current and shore-break wave hazards,” Nat. Hazards Earth Syst. Sci., vol. 25, no. 7, hlm. 2379–2397, Jul 2025, doi: 10.5194/nhess-25-2379-2025.

N. Rampal, T. Shand, A. Wooler, dan C. Rautenbach, “Interpretable Deep Learning Applied to Rip Current Detection and Localization,” Remote Sensing, vol. 14, no. 23, hlm. 6048, Nov 2022, doi: 10.3390/rs14236048.

A. H. Rashid, I. Razzak, M. Tanveer, dan A. Robles-Kelly, “RipDet: A Fast and Lightweight Deep Neural Network for Rip Currents Detection,” dalam 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China: IEEE, Jul 2021, hlm. 1–6. doi: 10.1109/IJCNN52387.2021.9533849.

W. Wahyudi, H. Fatchurohman, V. P. R. Natasya, S. Sujantoko, dan L. E. Sembiring, “Rip Current Hazard in Klayar Beach, Pacitan, Indonesia: Inferred from Fluorescent Dye and UAV,” IJMEIR, vol. 9, no. 2, Jun 2024, doi: 10.12962/j25481479.v9i2.20784.

Y. Yuan, H. Yang, F. Yu, Y. Gao, B. Li, dan C. Xing, “A wave-resolving modeling study of rip current variability, rip hazard, and swimmer escape strategies on an embayed beach,” Nat. Hazards Earth Syst. Sci., vol. 23, no. 11, hlm. 3487–3507, Nov 2023, doi: 10.5194/nhess-23-3487-2023.

A. Dumitriu, F. Tatui, F. Miron, R. T. Ionescu, dan R. Timofte, “Rip Current Segmentation: A Novel Benchmark and YOLOv8 Baseline Results,” dalam 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, BC, Canada: IEEE, Jun 2023, hlm. 1261–1271. doi: 10.1109/CVPRW59228.2023.00133.

A. Dumitriu, F. Tatui, F. Miron, A. Ralhan, R. T. Ionescu, dan R. Timofte, “RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety,” dalam 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA: IEEE, Jun 2025, hlm. 3427–3437. doi: 10.1109/CVPR52734.2025.00325.

F. Khan, A. De Silva, A. Palinkas, G. Dusek, J. Davis, dan A. Pang, “RipFinder: real-time rip current detection on mobile devices,” Front. Mar. Sci., vol. 12, hlm. 1549513, Mei 2025, doi: 10.3389/fmars.2025.1549513.

F. H. Khan dkk., “RipScout: Realtime ML-Assisted Rip Current Detection and Automated Data Collection Using UAVs,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 18, hlm. 7742–7755, 2025, doi: 10.1109/JSTARS.2025.3543695.

A. Dumitriu dkk., “AIM 2025 Rip Current Segmentation (RipSeg) Challenge Report,” 3 September 2025, arXiv: arXiv:2508.13401. doi: 10.48550/arXiv.2508.13401.

Z. Wang, T. Ding, S. Liang, H. Cui, dan X. Gao, “Workpiece surface defect detection based on YOLOv11 and edge computing,” PLoS One, vol. 20, no. 7, hlm. e0327546, Jul 2025, doi: 10.1371/journal.pone.0327546.

F. Wang, “Improving YOLOv11 for marine water quality monitoring and pollution source identification,” Sci Rep, vol. 15, no. 1, hlm. 21367, Jul 2025, doi: 10.1038/s41598-025-04842-3.

Y.-S. Lee, M. P. Patil, J. G. Kim, Y. B. Seo, D.-H. Ahn, dan G.-D. Kim, “Hyperparameter Optimization for Tomato Leaf Disease Recognition Based on YOLOv11m,” Plants, vol. 14, no. 5, hlm. 653, Feb 2025, doi: 10.3390/plants14050653.

L. He, Y. Zhou, L. Liu, W. Cao, dan J. Ma, “Research on object detection and recognition in remote sensing images based on YOLOv11,” Sci Rep, vol. 15, no. 1, hlm. 14032, Apr 2025, doi: 10.1038/s41598-025-96314-x.

Z. Tian, F. Yang, L. Yang, Y. Wu, J. Chen, dan P. Qian, “An Optimized YOLOv11 Framework for the Efficient Multi-Category Defect Detection of Concrete Surface,” Sensors, vol. 25, no. 5, hlm. 1291, Feb 2025, doi: 10.3390/s25051291.

Ultralytics, “YOLO11 vs YOLOv8: Detailed Comparison.” Diakses: 3 September 2025. [Daring]. Tersedia pada: https://docs.ultralytics.com/compare/yolo11-vs-yolov8

L. T. Ramos dan A. D. Sappa, “A Decade of You Only Look Once (YOLO) for Object Detection: A Review,” 3 Agustus 2025, arXiv: arXiv:2504.18586. doi: 10.48550/arXiv.2504.18586.

S. Zhou dkk., “A Lightweight Drone Detection Method Integrated into a Linear Attention Mechanism Based on Improved YOLOv11,” Remote Sensing, vol. 17, no. 4, hlm. 705, Feb 2025, doi: 10.3390/rs17040705.

A. Wang, Z. Fu, Y. Zhao, dan H. Chen, “A Remote Sensing Image Object Detection Model Based on Improved YOLOv11,” Electronics, vol. 14, no. 13, hlm. 2607, Jun 2025, doi: 10.3390/electronics14132607.

H. Chen, J. Zhou, dan Q. Zhao, “YOLO-PFS: Improved YOLOv11 for Remote Sensing Object Detection and Recognition,” dalam Advanced Intelligent Computing Technology and Applications, D.-S. Huang, Y. Pan, W. Chen, dan B. Li, Ed., Singapore: Springer Nature, 2025, hlm. 454–466. doi: 10.1007/978-981-96-9815-8_38.

R. Hataya, J. Zdenek, K. Yoshizoe, dan H. Nakayama, “Meta Approach to Data Augmentation Optimization,” dalam 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA: IEEE, Jan 2022, hlm. 3535–3544. doi: 10.1109/WACV51458.2022.00359.

M. A. Lara, I. A. Hameed, dan J. Koziorek, “Anomaly-Focused Augmentation Method for Industrial Visual Inspection,” IEEE Access, vol. 13, hlm. 89118–89139, 2025, doi: 10.1109/ACCESS.2025.3570075.

T. Kumar, R. Brennan, A. Mileo, dan M. Bendechache, “Image Data Augmentation Approaches: A Comprehensive Survey and Future Directions,” IEEE Access, vol. 12, hlm. 187536–187571, 2024, doi: 10.1109/ACCESS.2024.3470122.

C. Shorten, T. M. Khoshgoftaar, dan B. Furht, “Text Data Augmentation for Deep Learning,” J Big Data, vol. 8, no. 1, hlm. 101, Des 2021, doi: 10.1186/s40537-021-00492-0.

V. Li dkk., “A Closer Look at Data Augmentation Strategies for Finetuning-Based Low/Few-Shot Object Detection,” dalam 2024 IEEE 14th International Symposium on Industrial Embedded Systems (SIES), Okt 2024, hlm. 156–163. doi: 10.1109/SIES62473.2024.10767915.

P. Alimisis, I. Mademlis, P. Radoglou-Grammatikis, P. Sarigiannidis, dan G. Th. Papadopoulos, “Advances in diffusion models for image data augmentation: a review of methods, models, evaluation metrics and future research directions,” Artif Intell Rev, vol. 58, no. 4, hlm. 112, Jan 2025, doi: 10.1007/s10462-025-11116-x.

B. W. Mutaqin, M. Alwi, dan N. M. Adalya, “Analisis Spasial Arus Retas sebagai Upaya Pengurangan Risiko Bencana di Desa Parangtritis Yogyakarta,” Media Komun. Geogr., vol. 22, no. 2, hlm. 195, Des 2021, doi: 10.23887/mkg.v22i2.40014.

B. S. Widartono, M. N. Wachid, D. A. Umarhadi, A. N. Azizah, dan R. D. Cahyo, “Kite Aerial Photography (KAP) for rip current identification in Parangtritis Beach,” E3S Web Conf., vol. 76, hlm. 03005, 2019, doi: 10.1051/e3sconf/20197603005.

E. K. S. H. Muntasib, R. Meilani, dan J. Muthiah, “Ecotourism hazard management in South Beaches of Java, Indonesia,” IOP Conf. Ser.: Earth Environ. Sci., vol. 196, hlm. 012021, Nov 2018, doi: 10.1088/1755-1315/196/1/012021.

A. D. Febriani dan M. D. Kartikasari, “Detecting Avocado Freshness In Real-Time: A Yolo-Based Deep Learning Approach,” J. Tek. Inform. (JUTIF), vol. 6, no. 3, hlm. 1485–1502, Jun 2025, doi: 10.52436/1.jutif.2025.6.3.4626.

N. L. Anggreini, A. Yuliana, D. S. Ramdan, dan W. Al-Dayyeni, “Improving Diabetes Prediction Performance Using Random Forest Classifier with Hyperparameter Tuning,” vol. 6, no. 4, 2025.

I. K. Seneng, P. D. W. Ayu, dan R. R. Huizen, “Comparative Analysis of Augmentation and Filtering Methods in VGG19 and DenseNet121 for Breast Cancer Classification,” J. Tek. Inform. (JUTIF), vol. 6, no. 3, hlm. 1131–1146, Jun 2025, doi: 10.52436/1.jutif.2025.6.3.4397.

A. Kebaili, J. Lapuyade-Lahorgue, dan S. Ruan, “Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review,” J. Imaging, vol. 9, no. 4, hlm. 81, Apr 2023, doi: 10.3390/jimaging9040081.

E. Goceri, “Medical image data augmentation: techniques, comparisons and interpretations,” Artif Intell Rev, vol. 56, no. 11, hlm. 12561–12605, Nov 2023, doi: 10.1007/s10462-023-10453-z.

S. Sierra, R. Ramo, M. Padilla, dan A. Cobo, “Optimizing deep neural networks for high-resolution land cover classification through data augmentation,” Environ Monit Assess, vol. 197, no. 4, hlm. 423, Mar 2025, doi: 10.1007/s10661-025-13870-5.

H. Kwon, S. Choi, W. Woo, dan H. Jung, “Evaluating Segmentation-Based Deep Learning Models for Real-Time Electric Vehicle Fire Detection,” Fire, vol. 8, no. 2, hlm. 66, Feb 2025, doi: 10.3390/fire8020066.

M. R. Sholahuddin dkk., “Optimizing YOLOv8 for Real-Time CCTV Surveillance: A Trade-off Between Speed and Accuracy,” join, vol. 8, no. 2, hlm. 261–270, Des 2023, doi: 10.15575/join.v8i2.1196.

D. Zhu, R. Qi, P. Hu, Q. Su, X. Qin, dan Z. Li, “YOLO-Rip: A modified lightweight network for Rip currents detection,” Front. Mar. Sci., vol. 9, hlm. 930478, Agu 2022, doi: 10.3389/fmars.2022.930478.

L. Tang dan Q. H. Mahmoud, “A Deep Learning-Based Framework for Phishing Website Detection,” IEEE Access, vol. 10, hlm. 1509–1521, 2022, doi: 10.1109/ACCESS.2021.3137636.

A. Morchid dkk., “IoT-enabled fire detection for sustainable agriculture: A real-time system using flask and embedded technologies,” Results in Engineering, vol. 23, hlm. 102705, Sep 2024, doi: 10.1016/j.rineng.2024.102705.

“Yolov8s-RIP-no-augmentation - v12 2024-05-04 5:06pm.” Diakses: 19 September 2025. [Daring]. Tersedia pada: https://universe.roboflow.com/rip-txzm1/yolov8s-rip-no-augmentation

J. Choi, M. Rajendran, dan Y. Cheol Suh, “Explainable Rip Current Detection and Visualization with XAI EigenCAM,” dalam 2024 26th International Conference on Advanced Communications Technology (ICACT), Pyeong Chang, Korea, Republic of: IEEE, Feb 2024, hlm. 1–6. doi: 10.23919/ICACT60172.2024.10471913.