Underwater object detection plays a significant role in marine ecosystem research and marine species conservation. The improvement of related technologies holds practical significance. Although existing object-detection algorithms have achieved an excellent performance on land, they are not satisfactory in underwater scenarios due to two limitations: the underwater objects are often small, densely distributed, and prone to occlusion characteristics, and underwater embedded devices have limited storage and computational capabilities. In this paper, we propose a high-precision, lightweight underwater detector specifically optimizing for underwater scenarios based on the You Only Look Once Version 8 (YOLOv8) model. Firstly, we replace the Darknet-53 backbone of YOLOv8s with FasterNet-T0, reducing model parameters by 22.52%, FLOPS by 23.59%, and model size by 22.73%, achieving model lightweighting. Secondly, we add a Prediction Head for Small Objects, increase the number of channels for high-resolution feature map detection heads, and decrease the number of channels for low-resolution feature map detection heads. This results in a 1.2% improvement in small-object detection accuracy, while the remaining model parameters and memory consumption are nearly unchanged. Thirdly, we use Deformable ConvNets and Coordinate Attention in the neck part to enhance the accuracy in the detection of irregularly shaped and densely occluded small targets. This is achieved by learning convolution offsets from feature maps and emphasizing the regions of interest (RoIs). Our method achieves 52.12% AP on the underwater dataset UTDAC2020, with only 8.5 M parameters, 25.5 B FLOPS, and 17 MB model size. It surpasses the performance of large model YOLOv8l, at 51.69% AP, with 43.6 M parameters, 164.8 B FLOPS, and 84 MB model size. Furthermore, by increasing the input image resolution to 1280 × 1280 pixels, our model achieves 53.18% AP, making it the state-of-the-art (SOTA) model for the UTDAC2020 underwater dataset. Additionally, we achieve 84.4% mAP on the Pascal VOC dataset, with a substantial reduction in model parameters compared to previous, well-established detectors. The experimental results demonstrate that our proposed lightweight method retains effectiveness on underwater datasets and can be generalized to common datasets.

Marine heatwaves (MHWs) refer to a phenomenon where the sea surface temperature is significantly higher than the historical average for that region over a period, which is typically a result of the combined effects of climate change and local meteorological conditions, thereby potentially leading to alterations in marine ecosystems and an increased incidence of extreme weather events. MHWs have significant impacts on the marine environment, ecosystems, and economic livelihoods. In recent years, global warming has intensified MHWs, and research on MHWs has rapidly developed into an important research frontier. With the development of deep learning models, they have demonstrated remarkable performance in predicting sea surface temperature, which is instrumental in identifying and anticipating marine heatwaves (MHWs). However, the complexity of deep learning models makes it difficult for users to understand how the models make predictions, posing a challenge for scientists and decision-makers who rely on interpretable results to manage the risks associated with MHWs. In this study, we propose an interpretable model for discovering MHWs. We first input variables that are relevant to the occurrence of MHWs into an LSTM model and use a posteriori explanation method called Expected Gradients to represent the degree to which different variables affect the prediction results. Additionally, we decompose the LSTM model to examine the information flow within the model. Our method can be used to understand which features the deep learning model focuses on and how these features affect the model’s predictions. From the experimental results, this study provides a new perspective for understanding the causes of MHWs and demonstrates the prospect of future artificial intelligence-assisted scientific discovery.

In addressing the challenges of non-standardization and limited annotation resources in Chinese marine domain texts, particularly with complex entities like long and nested entities in coral reef ecosystem-related texts, existing Named Entity Recognition (NER) methods often fail to capture deep semantic features, leading to inefficiencies and inaccuracies. This study introduces a deep learning model that integrates Bidirectional Encoder Representations from Transformers (BERT), Bidirectional Gated Recurrent Units (BiGRU), and Conditional Random Fields (CRF), enhanced by an attention mechanism, to improve the recognition of complex entity structures. The model utilizes BERT to capture context-relevant character vectors, employs BiGRU to extract global semantic features, incorporates an attention mechanism to focus on key information, and uses CRF to produce optimized label sequences. We constructed a specialized coral reef ecosystem corpus to evaluate the model’s performance through a series of experiments. The results demonstrated that our model achieved an F1 score of 86.54%, significantly outperforming existing methods. The contributions of this research are threefold: (1) We designed an efficient named entity recognition framework for marine domain texts, improving the recognition of long and nested entities. (2) By introducing the attention mechanism, we enhanced the model’s ability to recognize complex entity structures in coral reef ecosystem texts. (3) This work offers new tools and perspectives for marine domain knowledge graph construction and study, laying a foundation for future research. These advancements propel the development of marine domain text analysis technology and provide valuable references for related research fields.

Existing marine sensor networks acquire data from sea areas that are geographically divided, and store the data independently in their affiliated sea area data centers. In the case of marine events across multiple sea areas, the current network structure needs to retrieve data from multiple data centers, and thus severely affects real-time decision making. In this study, in order to provide a fast data retrieval service for a marine sensor network, we use all the marine sensors as the vertices, establish the edge based on marine events, and abstract the marine sensor network as a graph. Then, we construct a multi-objective balanced partition method to partition the abstract graph into multiple regions and store them in the cloud computing platform. This method effectively increases the correlation of the sensors and decreases the retrieval cost. On this basis, an incremental optimization strategy is designed to dynamically optimize existing partitions when new sensors are added into the network. Experimental results show that the proposed method can achieve the optimal layout for distributed storage in the process of disaster data retrieval in the China Sea area, and effectively optimize the result of partitions when new buoys are deployed, which eventually will provide efficient data access service for marine events.

Cephalopods are an essential component of marine ecosystems, which are of great significance for the development of marine resources, ecological balance, and human food supply. At the same time, the preservation of cephalopod resources and the promotion of sustainable utilization also require attention. Many studies on the classification of cephalopods focus on the analysis of their beaks. In this study, we propose a feature fusion-based method for the identification of beaks, which uses the convolutional neural network (CNN) model as its basic architecture and a multi-class support vector machine (SVM) for classification. First, two local shallow features are extracted, namely the histogram of the orientation gradient (HOG) and the local binary pattern (LBP), and classified using SVM. Second, multiple CNN models were used for end-to-end learning to identify the beaks, and model performance was compared. Finally, the global deep features of beaks were extracted from the Resnet50 model, fused with the two local shallow features, and classified using SVM. The experimental results demonstrate that the feature fusion model can effectively fuse multiple features to recognize beaks and improve classification accuracy. Among them, the HOG+Resnet50 method has the highest accuracy in recognizing the upper and lower beaks, with 91.88% and 93.63%, respectively. Therefore, this new approach facilitated identification studies of cephalopod beaks.