Spectral characteristics play an important role in the classification of oil film, but the presence of too many bands can lead to information redundancy and reduced classification accuracy. In this study, a classification model that combines spectral indices-based band selection (SIs) and one-dimensional convolutional neural networks was proposed to realize automatic oil films classification using hyperspectral remote sensing images. Additionally, for comparison, the minimum Redundancy Maximum Relevance (mRMR) was tested for reducing the number of bands. The support vector machine (SVM), random forest (RF), and Hu’s convolutional neural networks (CNN) were trained and tested. The results show that the accuracy of classifications through the one dimensional convolutional neural network (1D CNN) models surpassed the accuracy of other machine learning algorithms such as SVM and RF. The model of SIs+1D CNN could produce a relatively higher accuracy oil film distribution map within less time than other models.

The synthetic aperture radar (SAR) has a special ability to detect objects in any climate and weather conditions. Consequently, SAR images are widely used in maritime transportation safety and fishery law enforcement for maritime object detection. Currently, deep-learning models are being extensively used for the detection of objects from images. Among them, the feature pyramid network (FPN) uses pyramids for representing semantic information regardless of the scale and has an improved accuracy of object detection. It is also suitable for the detection of multiple small ship objects in SAR images. This study aims to resolve the problems associated with small-object and multi-object ship detection in complex scenarios e.g., when a ship nears the port, by proposing a detection method based on an optimized FPN model. The feature pyramid model is first embedded in a traditional region proposal network (RPN) and mapped into a new feature space for object identification. Subsequently, the k-means clustering algorithm based on the shape similar distance (SSD) measure is used to optimize the FPN. Initial anchor boxes and tests are created using the SAR ship dataset. Experimental results show that the proposed algorithm for object detection shows an accuracy of 98.62%. Compared with Yolo, the RPN based on VGG/ResNet, FPN based on VGG/ResNet, and other models in complex scenarios, the proposed model shows a higher accuracy rate and better overall performance.

Oil spills bring great damage to the environment and, in particular, to coastal ecosystems. The ability of identifying them accurately is important to prompt oil spill response. We propose a semi-automatic oil spill detection method, where texture analysis, machine learning, and adaptive thresholding are used to process X-band marine radar images. Coordinate transformation and noise reduction are first applied to the sampled radar images, coarse measurements of oil spills are then subjected to texture analysis and machine learning. To identify the loci of oil spills, a texture index calculated by four textural features of a grey level co-occurrence matrix is proposed. Machine learning methods, namely support vector machine, k-nearest neighbor, linear discriminant analysis, and ensemble learning are adopted to extract the coarse oil spill areas indicated by the texture index. Finally, fine measurements can be obtained by using adaptive thresholding on coarsely extracted oil spill areas. Fine measurements are insensitive to the results of coarse measurement. The proposed oil spill detection method was used on radar images that were sampled after an oil spill accident that occurred in the coastal region of Dalian, China on 21 July 2010. Using our processing method, thresholds do not have to be set manually and oil spills can be extracted semi-automatically. The extracted oil spills are accurate and consistent with visual interpretation.

The routine surveillance of oil spills in major ports is important. However, existing techniques and sensors are unable to trace oil and micron-thin oil films on the surface of seawater. Therefore, we designed and studied a coastal-mounted sensor, using ultraviolet-induced fluorescence and fluorescence-filter systems (FFSs), to monitor oil spills and overcome the disadvantages of traditional surveillance systems. Using seawater from the port of Lingshui (Yellow Sea, China) and six oil samples of different types, we found that diesel oil’s relative fluorescence intensity (RFI) was significantly higher than those of heavy fuel and crude oils in the 180–300 nm range—in the 300–400 nm range, the RFI value of diesel is far lower. The heavy fuel and crude oils exhibited an opposite trend in their fluorescence spectra. A photomultiplier tube, employed as the fluorescence detection unit, efficiently monitored different oils on seawater in field experiments. On-site tests indicated that this sensor system could be used as a coastal-mounted early-warning detection system for oil spills.

Pollution caused by ship emissions has drawn attention from various countries. Because of the high density of ships in ports, channels, and anchorages and their proximity to the densely populated areas, ship emissions will considerably impact these areas. Herein, a Chinese seagoing ship is selected and a platform is established for monitoring the ship emissions to obtain detailed characteristics of the ship’s nearshore emissions. The ship navigation and pollution emission data are obtained under six complete operating conditions, i.e., berthing, manoeuvring in port, acceleration in a channel, cruising, deceleration before anchoring, and anchoring. This study analyzes the concentrations of the main emission gases (O₂, NO_X, SO₂, CO₂, and CO) and the average emission factors (EFs) of the pollution gases (NO_X, SO₂, CO₂, and CO) based on the engine power under different operating conditions. Results show that the change in O₂ concentration reflects the load associated with the main engine of the ship. The NO_X, SO₂, and CO₂ emission concentrations are the highest during cruising, whereas the peak CO emission concentration is observed during anchoring. The average EFs of NO_X and SO₂ based on the power of the main engine are the highest during cruising, and those of CO₂ and CO are the highest after anchoring. The ship EFs are different during acceleration and deceleration. By comparing the EFs along the coast of China and the global EFs commonly used to perform the emission inventory calculations in China, the NO_X EFs under different operating conditions is observed to be generally lower than the global EFs under the corresponding operating conditions. Furthermore, the SO₂ EF is considerably affected by the sulfur content in the fuel oil and the operating conditions of the ship. The average CO₂ EFs are higher than the global EFs commonly used during cruising, and the CO EFs are higher than the global EFs under all the conditions. Our results help to supplement the EFs for this type of ship under different operating conditions, resolve the lack of emission data under anchoring conditions, and provide data support to conduct nearshore environmental monitoring and assessment.

Marine oil spills seriously impact the marine environment and transportation. When oil spill accidents occur, oil spill distribution information, in particular, the relative thickness of the oil film, is vital for emergency decision-making and cleaning. Hyperspectral remote sensing technology is an effective means to extract oil spill information. In this study, the concept of deep learning is introduced to the classification of oil film thickness based on hyperspectral remote sensing technology. According to the spatial and spectral characteristics, the stacked autoencoder network model based on the support vector machine is improved, enhancing the algorithm’s classification accuracy in validating data sets. A method for classifying oil film thickness using the convolutional neural network is designed and implemented to solve the problem of space homogeneity and heterogeneity. Through numerous experiments and analyses, the potential of the two proposed deep learning methods for accurately classifying hyperspectral oil spill data is verified.