Marine oil spills cause great pollution to the marine environment and require development of efficient cleaning plans. Accurate identification of the oil type involved in the spill is of great significance for rapid and effective treatment. Hyperspectral remote sensing plays an important role in oil spill detection and oil type identification. We designed an outdoor oil spill experiment to simulate an oil spill in a marine environment. Five common oil types were selected as the experimental starting materials: crude oil, fuel oil, diesel oil, gasoline, and palm oil. Hyperspectral data of the five oils were collected from different solar times by Analytical Spectral Devices (ASD) FieldSpec4. The relationship between the spectral absorption baseline height of the different oil types and solar time is investigated. The characteristic analysis method of spectral standard deviation was used to obtain characteristic bands of the different oil types. Using both full spectrum and selected characteristic bands, oil type identification experiments were performed using the Support Vector Machine (SVM) model, respectively. The results show that oil type identification using selected characteristic bands is 3.70% more accurate compared with that using the full spectrum, reaching 83.33%.

This paper describes the use of deep belief networks (DBNs) based on the conjugate gradient (CG) update algorithm for hyperspectral classification. DBNs perform two processes: unsupervised pre-training and supervised fine-tuning. The parameter update method in the fine-tuning stage plays a key role in optimizing the classification model. The proposed method employs CG-based fine-tuning to avoid the “zig-zagging” problem with the gradient descent algorithm and to accelerate the DBN convergence. First, the spectral features and pixel-centric spectral block features are extracted from hyperspectral images for use as the input vectors. The update variables are then calculated based on a CG algorithm and the 2-norm, and the parameters are updated during the backpropagation step of the proposed CGDBN. Two models with different CG methods are applied to a public hyperspectral image benchmark for classification experiments and analysis, and the results are compared with those from several classification methods that are currently in use. The experimental results show that the proposed classification models have advantages in terms of model convergence and low sensitivity to certain parameters. In addition, application to a hyperspectral image of coastal wetlands in the Yellow River Delta produces a satisfactory classification. The results of this study demonstrate that the proposed CG-update-based DBN provides a new approach for hyperspectral dataset classification.

Marine oil spills can damage marine ecosystems, economic development, and human health. It is important to accurately identify the type of oil spills and detect the thickness of oil films on the sea surface to obtain the amount of oil spill for on-site emergency responses and scientific decision-making. Optical remote sensing is an important method for marine oil-spill detection and identification. In this study, hyperspectral images of five types of oil spills were obtained using unmanned aerial vehicles (UAV). To address the poor spectral separability between different types of light oils and weak spectral differences in heavy oils with different thicknesses, we propose the adaptive long-term moment estimation (ALTME) optimizer, which cumulatively learns the spectral characteristics and then builds a marine oil-spill detection model based on a one-dimensional convolutional neural network. The results of the detection experiment show that the ALTME optimizer can store in memory multiple batches of long-term oil-spill spectral information, accurately identify the type of oil spills, and detect different thicknesses of oil films. The overall detection accuracy is larger than 98.09%, and the Kappa coefficient is larger than 0.970. The F₁-score for the recognition of light-oil types is larger than 0.971, and the F₁-score for detecting films of heavy oils with different film thicknesses is larger than 0.980. The proposed optimizer also performs well on a public hyperspectral dataset. We further carried out a feasibility study on oil-spill detection using UAV thermal infrared remote sensing technology, and the results show its potential for oil-spill detection in strong sunlight.

Marine oil spills are an emergency of great harm and have become a hot topic in marine environmental monitoring research. Optical remote sensing is an important means to monitor marine oil spills. Clouds, weather, and light control the amount of available data, which often limit feature characterization using a single classifier and therefore difficult to accurate monitoring of marine oil spills. In this paper, we develop a decision fusion algorithm to integrate deep learning methods and shallow learning methods based on multi-scale features for improving oil spill detection accuracy in the case of limited samples. Based on the multi-scale features after wavelet transform, two deep learning methods and two classical shallow learning algorithms are used to extract oil slick information from hyperspectral oil spill images. The decision fusion algorithm based on fuzzy membership degree is introduced to fuse multi-source oil spill information. The research shows that oil spill detection accuracy using the decision fusion algorithm is higher than that of the single detection algorithms. It is worth noting that oil spill detection accuracy is affected by different scale features. The decision fusion algorithm under the first-level scale features can further improve the accuracy of oil spill detection. The overall classification accuracy of the proposed method is 91.93%, which is 2.03%, 2.15%, 1.32%, and 0.43% higher than that of SVM, DBN, 1D-CNN, and MRF-CNN algorithms, respectively.

Existing red tide detection methods have mainly been developed for ocean color satellite data with low spatial resolution and high spectral resolution. Higher spatial resolution satellite images are required for red tides with fine scale and scattered distribution. However, red tide detection methods for ocean color satellite data cannot be directly applied to medium–high spatial resolution satellite data owing to the shortage of red tide responsive bands. Therefore, a new red tide detection method for medium–high spatial resolution satellite data is required. This study proposes the red tide detection U−Net (RDU−Net) model by considering the HY−1D Coastal Zone Imager (HY−1D CZI) as an example. RDU−Net employs the channel attention model to derive the inter−channel relationship of red tide information in order to reduce the influence of the marine environment on red tide detection. Moreover, the boundary and binary cross entropy (BBCE) loss function, which incorporates the boundary loss, is used to obtain clear and accurate red tide boundaries. In addition, a multi−feature dataset including the HY−1D CZI radiance and Normalized Difference Vegetation Index (NDVI) is employed to enhance the spectral difference between red tides and seawater and thus improve the accuracy of red tide detection. Experimental results show that RDU−Net can detect red tides accurately without a precedent threshold. Precision and Recall of 87.47% and 86.62%, respectively, are achieved, while the F1−score and Kappa are 0.87. Compared with the existing method, the F1−score is improved by 0.07–0.21. Furthermore, the proposed method can detect red tides accurately even under interference from clouds and fog, and it shows good performance in the case of red tide edges and scattered distribution areas. Moreover, it shows good applicability and can be successfully applied to other satellite data with high spatial resolution and large bandwidth, such as GF−1 Wide Field of View 2 (WFV2) images.