Unsupervised Oil Spill Detection in Shipborne Radar Imagery Using Autoencoder-Enhanced Q-Learning and Improved Bat Optimization.
Saved in:
| Title: | Unsupervised Oil Spill Detection in Shipborne Radar Imagery Using Autoencoder-Enhanced Q-Learning and Improved Bat Optimization. |
|---|---|
| Authors: | Yan, Jin1,2 (AUTHOR), Chen, Binghui1,2 (AUTHOR), Xu, Jin1,2,3 (AUTHOR) jinxu@gdou.edu.cn, Guo, Zekun1,2 (AUTHOR), Yan, Minghao1,2 (AUTHOR), Sun, Mengxin1,2,3 (AUTHOR), Qiao, Lin3 (AUTHOR) |
| Source: | Remote Sensing. Jun2026, Vol. 18 Issue 12, p1876. 30p. |
| Subjects: | Autoencoders, Reinforcement learning, Oil spill management, K-means clustering, Radar in aeronautics, Optimization algorithms, Machine learning |
| Abstract: | Highlights: What are the main findings? The proposed unsupervised framework, combining autoencoder-based feature learning, K-Means pseudo-labeling, Q-learning, and an improved bat algorithm, effectively detected oil spill regions in shipborne radar images without using manual annotations for model training. The method achieved better oil-slick segmentation performance than classic intelligent optimization methods and the conventional bat algorithm, and ablation tests confirmed the value of autoencoder feature extraction, K-Means pseudo-labeling, and Q-learning-based ROI localization. What are the implications of the main findings? The study provides a practical technical route for timely shipborne offshore oil spill monitoring, especially in complex radar scenes with blurred boundaries, strong co-frequency interference, and speckle noise. The unsupervised design reduces reliance on labeled data, which may improve deployment feasibility for emergency response and environmental protection applications in real-world marine monitoring systems. Marine oil spill accidents pose a serious threat to the marine ecological environment. Therefore, efficient and accurate oil spill detection is of great significance for emergency response. To address the issues of blurred oil-slick boundaries, prominent co-frequency interference and severe speckle noise in shipborne radar images, this study proposed an oil spill detection method based on radar data collected from a real oil spill event at a terminal in Dalian Bay. The proposed method integrates an autoencoder, feature dimensionality reduction, pseudo-labeling, reinforcement learning and an improved intelligent optimization algorithm. First, an autoencoder was adopted to extract compact nonlinear local features from the radar images, and principal component analysis (PCA) was employed for feature dimensionality reduction. Subsequently, K-Means clustering was used to construct pseudo-labels, and the reduced features were discretized to build the state space for reinforcement learning. Based on this, the Q-learning algorithm was introduced to automatically extract the region of interest (ROI). Finally, for the ROI, an improved bat algorithm incorporating a dynamic weighting factor and a multi-constraint fitness function was designed to achieve fine segmentation of the oil-slick target. The experimental results showed that the proposed method outperformed classic intelligent optimization algorithms and the conventional bat optimization algorithm in oil-slick segmentation performance. Ablation experiments further verified the effectiveness of autoencoder-based feature learning, K-Means pseudo-labeling, and Q-learning-based ROI localization. This method may provide a new technical approach for timely offshore oil spill monitoring and emergency analysis. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? The proposed unsupervised framework, combining autoencoder-based feature learning, K-Means pseudo-labeling, Q-learning, and an improved bat algorithm, effectively detected oil spill regions in shipborne radar images without using manual annotations for model training. The method achieved better oil-slick segmentation performance than classic intelligent optimization methods and the conventional bat algorithm, and ablation tests confirmed the value of autoencoder feature extraction, K-Means pseudo-labeling, and Q-learning-based ROI localization. What are the implications of the main findings? The study provides a practical technical route for timely shipborne offshore oil spill monitoring, especially in complex radar scenes with blurred boundaries, strong co-frequency interference, and speckle noise. The unsupervised design reduces reliance on labeled data, which may improve deployment feasibility for emergency response and environmental protection applications in real-world marine monitoring systems. Marine oil spill accidents pose a serious threat to the marine ecological environment. Therefore, efficient and accurate oil spill detection is of great significance for emergency response. To address the issues of blurred oil-slick boundaries, prominent co-frequency interference and severe speckle noise in shipborne radar images, this study proposed an oil spill detection method based on radar data collected from a real oil spill event at a terminal in Dalian Bay. The proposed method integrates an autoencoder, feature dimensionality reduction, pseudo-labeling, reinforcement learning and an improved intelligent optimization algorithm. First, an autoencoder was adopted to extract compact nonlinear local features from the radar images, and principal component analysis (PCA) was employed for feature dimensionality reduction. Subsequently, K-Means clustering was used to construct pseudo-labels, and the reduced features were discretized to build the state space for reinforcement learning. Based on this, the Q-learning algorithm was introduced to automatically extract the region of interest (ROI). Finally, for the ROI, an improved bat algorithm incorporating a dynamic weighting factor and a multi-constraint fitness function was designed to achieve fine segmentation of the oil-slick target. The experimental results showed that the proposed method outperformed classic intelligent optimization algorithms and the conventional bat optimization algorithm in oil-slick segmentation performance. Ablation experiments further verified the effectiveness of autoencoder-based feature learning, K-Means pseudo-labeling, and Q-learning-based ROI localization. This method may provide a new technical approach for timely offshore oil spill monitoring and emergency analysis. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18121876 |
