Weifeng Zhou

With the increase in global fishing activities, the transparency of fishery data has drawn increasing attention. Data transparency enables stakeholders to play a greater role in ensuring that fisheries are legal, ethical, and sustainable. Improving the transparency of fishing vessel data can effectively support vessel monitoring and enhance fishery safety. This paper presents a systematic review of satellite remote sensing modalities and datasets currently available for fishing vessel identification and monitoring. Conducted in accordance with the PRISMA 2020 guidelines, this study employs a dual-track search strategy to retrieve, screen, and synthesize academic literature and public datasets from mainstream databases, including the Web of Science Core Collection, IEEE Xplore, and CNKI. First, the existing remote sensing modalities were classified into three major categories based on their imaging principles: synthetic aperture radar (SAR), optical remote sensing, and nighttime light (NTL) remote sensing. In addition, the mainstream satellite data sources and their corresponding parameters were summarized for each category. Second, an in-depth comparative analysis of these remote sensing modalities is conducted from core dimensions such as target detection sensitivity, robustness under complex environments and meteorological conditions, and spatiotemporal resolution. This reveals the performance limitations and significant complementarity of different sensor data in fishing vessel detection. Finally, mainstream remote sensing datasets for fishing vessels (such as xView3-SAR, xView, and VBD) are summarized and evaluated, pointing out the gaps in certain types of datasets. In conclusion, this paper suggests that building a “full spatiotemporal and multi-scale” observation framework based on multi-source heterogeneous data fusion is an important trend for the future development of fishing vessel detection using remote sensing, aiming to provide a reference for relevant researchers.

Fishery resources of tuna serve as a vital source of global protein. This study investigates the key environmental drivers influencing the spatial distribution of yellowfin tuna (Thunnus albacares) in the western tropical Pacific Ocean. A comprehensive dataset was constructed by linking the catch per unit effort (CPUE) from 43 Chinese longline fishing vessels (2008–2019) with 24 multi-source environmental variables. To accurately model this complex relationship, a total of 16 machine learning regression models, including advanced ensemble methods like Light Gradient Boosting Machine (LightGBM), Random Forest, and Categorical Boosting Regressor (CatBoost), were evaluated and compared using multiple performance metrics (e.g., Coefficient of Determination [R²], Root Mean Squared Error [RMSE]). The results indicated that the Light Gradient Boosting Machine (LightGBM) model achieved superior performance, demonstrating excellent nonlinear fitting capabilities and generalization ability. For robust feature interpretation, the study employed both the model’s internal feature importance metrics and the SHapley Additive exPlanations (SHAP) method. Both approaches yielded highly consistent results, identifying temporal (month), spatial (longitude, latitude), and key seawater temperature indicators at intermediate depths (T450, T300, T150) as the most critical predictors. This highlights significant spatiotemporal heterogeneity in the distribution of Thunnus albacares. The analysis suggests that mid-layer ocean temperatures directly influence catch rates by governing the species’ vertical and horizontal movements. In contrast, large-scale climate indices such as the Oceanic Niño Index (ONI) exert indirect effects by modulating ocean thermal structures. This research confirms the dominance of spatiotemporal and thermal variables in predicting yellowfin tuna distribution and provides a reliable, data-driven framework for supporting sustainable fishery management, resource assessment, and operational forecasting.

High-resolution spatiotemporal prediction information on fishing vessel activities is essential for formulating and effectively implementing fisheries policies that ensure the sustainability of marine resources and fishing practices. This study focused on the tuna longline fishery in the Western and Central Pacific Ocean (130° E–150° W, 20° S–20° N) and constructed a CLA U-Net deep learning model to predict fishing effort (FE) distribution based on 2017–2023 FE records and environmental variables. Two modeling schemes were designed: Scheme 1 incorporated both historical FE and environmental data, while Scheme 2 used only environmental variables. The model predicts not only the binary outcome (presence or absence of fishing effort) but also the magnitude of FE. Results show that in short-term predictions, Scheme 1 achieved F1 scores of 0.654 at the 0.5°-1-day scale and 0.763 at the 1°-1-day scale, indicating substantial improvement from including historical FE data. In medium-term predictions, Scheme 1 and Scheme 2 reached maximum F1 scores of 0.77 and 0.72, respectively, at the optimal spatiotemporal scale of 1°-30 days. The analysis also quantified the relative importance of environmental variables, with sea surface temperature (SST) and chlorophyll-a (Chl-a) identified as the most influential. These findings provide methodological insights for spatiotemporal prediction of fishing effort and support the refinement of fisheries management and sustainability strategies.

Accurate identification of fishing vessel operations is vital for sustainable fishery management. Existing methods inadequately exploit spatiotemporal contextual information in vessel trajectories and fail to effectively fuse multimodal data. To address this, this study proposes a novel framework integrating Geohash-based geocoding with embedding techniques inspired by natural language processing to extract spatiotemporal features from trajectory sequences. We develop a multi-branch 1D convolutional neural network (MB-1dCNN) to minimize feature engineering dependency while enhancing operational-type recognition. Comparative experiments evaluate Geohash encoding lengths and network architectures (single-branch vs. multi-branch, fully-connected vs. 1D-CNN). Results indicate optimal Geohash encoding at length 5. The multi-branch structure significantly outperforms single-branch counterparts, and MB-1dCNN demonstrates superior performance over multi-branch model with fully connected layers (MB-FCNN), achieving additional gains in accuracy and F1-score. Key findings reveal: (1) 1D-CNN processing surpasses fully-connected networks in sequential feature extraction, (2) Multi-branch architectures enhance information fusion capabilities. The proposed MB-1dCNN establishes state-of-the-art performance for trajectory-based fishing operation recognition, offering valuable insights for spatial computing applications in maritime surveillance.

Sea surface temperature (SST) are the focus of attention in global climate discussion. In particular, for pelagic fisheries that depend on the marine environment, understanding and mastering changes in SST is of great significance for managing fisheries resources to promote their sustainability. Multiscale variation analysis of SST from 1982 to 2021 has been done in this paper concerning the main eight fishing grounds of pelagic fisheries using the Optimum Interpolation Sea Surface Temperature(OISST) released by NOAA. The mean, incremental quantity, standard deviation, and overall mean standard deviation of SST per decade in these eight fishing grounds are calculated. Fast Fourier Transform, STL decomposition, and PELT of change point detection method are used get the trends and fluctuations of SST by obtaining the metrics, such as seasonal intensity indices, cycles, and change points. The study results show that: ① Over the past 40 years according to the average SST per 10 years, the main fishing grounds worldwide have warmed significantly. The cumulative warming of the fishing grounds in the northwest Pacific and the western Pacific is most obvious. However, except for the northwest Pacific, the increase of the average SST in the last 10 years is higher than in the previous 10 years in all areas. Among them, there are 5 regions which increase of the average SST in the last 10 years is higher than in the previous 2 decades, while the central Atlantic and the eastern Indian Ocean showed that the most significant increases of the average SST take place in the period from 1992 to 2001. ② From the standard deviation, and overall mean standard deviation of SST per decade, the West Pacific and the Northwest Pacific have the most significant long-term and short-term fluctuations. ③ The two regions with the highest seasonal intensity index are the northwest Pacific and the eastern Indian Ocean. ④ 1987, 1997, 2001, 2007, 2012, and 2017 were years in which change points occurred. However, except in the Indian Ocean, the number of change points and the years they occurred were inconsistent in the oceans.

In modern fishery management, fishing vessel trajectory data are used to monitor and analyze fishing vessel activities. However, trajectory data are often of low quality, probably due to environmental factors, equipment failures, signal loss and operation errors, leading to numerous outliers in these data. These outliers not only undermine the credibility of the data but also negatively affect the subsequent data mining and decision-making. In this study, a data cleaning method for the identification of outlier points in fishing vessel trajectories based on the Geohash geocoding algorithm is given, which involves several key steps: obtaining and preprocessing the raw trajectory data; generating the corresponding Geohash codes for each ship position based on its latitude and longitude; calculating the reachable distance considering the time interval between the current point and the following points and their speeds; querying the neighborhood of the current point based on the reachable distance; and obtaining all Geohash codes of the reachable areas of the fishing vessels within the time interval as the reachable range grid set of the current position. The reachable range grid set of the current position is compared with the reachable range grid sets of the previous point identified as normal and the next point in the fishing vessel trajectory. If there is no intersection, it is determined that the current fishing vessel position is an outlier, and this point will be excluded. The method proposed in this study is able to effectively identify outliers in trajectory data, achieving efficient and effective trajectory data cleaning and improving the accuracy and reliability of the data.

This research evaluates the potential spaces of deep offshore waters for cultivating the Larimichthys crocea, analyzing ocean profile temperature data from 2000 to 2022 according to the species’ environmental temperature suitability. There are significant seasonal variations and differences in habitat distributions of different temperature ranges in China’s surrounding waters. The range of maximum living space obtained according to the tolerance temperature shows a trend of being larger in summer and smaller in winter; and the range of viable habitat space obtained based on the suitable and optimal temperature shows a trend of being smaller in summer and larger in winter. Broad areas meeting tolerance temperatures offer broad, yet impractical, site selection options. In contrast, areas with optimal temperatures are limited, which means the availability of ideal site locations is very restricted. Regions consistently within the 20–28 °C range are best for practical site selection. Year-round suitable areas are primarily found at depths of 30 to 90 m in the southern East China Sea and the South China Sea, particularly within the 40 to 50 m depth range. Water mass like the South China Sea Surface Water and the Kuroshio Surface Water consistently maintain suitable temperatures, making them ideal for aquaculture.

Understanding ocean temperature distribution is vital for ocean stratification, currents, and marine ecosystems. This study analyzed the global 0.5-degree ocean temperature dataset from the Chinese Academy of Sciences Marine Data Center (July 2020) to identify regional temperature patterns. After standardizing the data, Principal Component Analysis (PCA) reduced the dimensionality from 32 to 7, preserving key temperature variations. A Gaussian Mixture Model (GMM) determined that 18 classifications were optimal by evaluating the variance and category weights. Applying GMM to the reduced data identified 18 distinct temperature distribution patterns across various marine environments, including polar currents, warm current mixing zones, ocean fronts, and enclosed basins, each with unique geographical and physical characteristics. Most classifications showed high posterior probabilities, indicating model accuracy, though lower probabilities were observed in complex regions like the Indian Ocean. The results highlight the significant roles of ocean currents, climatic phenomena, and ecological factors in temperature distribution, providing insights for ocean circulation studies, climate modeling, and marine biodiversity conservation. Future research should enhance the model accuracy by optimizing the parameters, expanding data coverage, integrating additional features, and combining marine observations with climate models to better understand ocean temperature patterns and their global climate impacts.

Large language model (LLM) processing, with natural language as its core, carries out information retrieval through intelligent Q&A. It has a wide range of application scenarios and is commonly considered a kind of generative AI. However, when LLMs handle generation tasks, the results generated by fundamental LLMs with an insufficient comprehensive performance, specifically in the vertical domain, are often inaccurate due to a poor generalization ability, resulting in the so-called “hallucination” phenomenon. To solve these problems, in this study, an enhanced retrieval scheme for LLM processing was developed, named the BM-RAGAM (BM25 retrieval-augmented generation attention mechanism), by constructing a vectorized knowledge base, utilizing a hybrid joint retrieval strategy of keyword matching through searching and a semantic-enhanced association with an attention mechanism and taking ocean-front- and eddy-related knowledge in oceanography as an example. This scheme realized accurate word-based matching with the BM25 algorithm and text generation through a semantic-enhanced association using RAG, and it was used to construct a vector database of the text knowledge on ocean fronts and eddies. The output was compared and analyzed with the fundamental LLM of Qwen2-72B using the proposed scheme, and an ablation experiment was conducted. The results show that the proposed scheme greatly reduced hallucination generation in the process of text generation, making its outputs more interpretable.

Ecosystem-based fisheries management requires high-precision fisheries information to provide relevant data for natural resource management, assessment, and marine spatial planning. This study utilizes Automatic Identification System (AIS) data from light purse seine vessels from the Chinese mainland that were collected from May to November between 2020 and 2022, along with the corresponding environmental data. By applying boosted regression trees (BRTs) and generalized additive models (GAMs), this study establishes nonlinear relationships between fishing intensity and predictor variables and explores the ecological and environmental drivers behind the spatial distribution of light purse seine vessels from the Chinese mainland in the Northwest Pacific. This research identifies the key influencing factors and reveals significant seasonal preferences for different marine environments in various months, with chlorophyll-a being the primary influencing factor. The predicted fishing effort closely resembles observed data, providing valuable information to support fisheries resource management and planning.