Effects of Different Spatial Resolutions on Prediction Accuracy of Thunnus alalunga Fishing Ground in Waters Near the Cook Islands Based on Long Short-Term Memory(LSTM)Neural Network Model

Albacore tuna(Thunnus alalunga)is one of the target species of tuna longline fishing,and waters near the Cook Islands are a vital albacore tuna fishing ground.Marine environmental data are usually presented with different spatial resolutions,which leads to different results in tuna fishery prediction.Study on the impact of different spatial resolutions on the prediction accuracy of albacore tuna fishery to select the best spatial resolution can contribute to better management of albacore tuna resources.The nominal catch per unit effort(CPUE)of albacore tuna is calculated according to vessel monitor system(VMS)data collected from Chinese distantwater fishery enterprises from January 1,2017 to May 31,2021.A total of 26 spatiotemporal and environmental factors,including temperature,salinity,dissolved oxygen of 0–300 m water layer,chlorophyll-a concentration in the sea surface,sea surface height,month,longitude,and latitude,were selected as variables.The temporal resolution of the variables was daily and the spatial resolutions were set to be 0.5°×0.5°,1°×1°,2°×2°,and 5°×5°.The relationship between the nominal CPUE and each individual factor was analyzed to remove the factors irrelavant to the nominal CPUE,together with a multicollinearity diagnosis on the factors to remove factors highly related to the other factors within the four spatial resolutions.The relationship models between CPUE and spatiotemporal and environmental factors by four spatial resolutions were established based on the long short-term memory(LSTM)neural network model.The mean absolute error(MAE)and root mean square error(RMSE)were used to analyze the fitness and accuracy of the models,and to determine the effects of different spatial resolutions on the prediction accuracy of the albacore tuna fishing ground.The results show the resolution of 1°×1°can lead to the best prediction accuracy,with the MAE and RMSE being 0.0268 and 0.0452 respectively,followed by 0.5°×0.5°,2°×2°and 5°×5°with declining prediction accuracy.The results suggested that 1)albacore tuna fishing ground can be predicted by LSTM;2)the VMS records the data in detail and can be used scientifically to calculate the CPUE;3)correlation analysis,and multicollinearity diagnosis are necessary to improve the prediction accuracy of the model;4)the spatial resolution should be 1°×1°in the forecast of albacore tuna fishing ground in waters near the Cook Islands.

Fishing Production and Fishing Changes in Hong Kong after the Ground Trawl Ban of 31st December 2012:A Geospatial Evaluation

From data published by the Hong Kong SAR(HKSAR)government in their two sole fisheries surveys of 2006 and 2016/2017,the current authors produced regional maps using spatial interpolation to more accurately describe and estimate the geographic coverage of changes in fishing production in Hong Kong waters since the ground trawl ban of 2012 December 31st.These suggest the fishing industry has adapted to smaller craft,and that fishing production increased in several areas in the period after the ground trawl ban came into effect.In addition,the maps enable a smoother assessment to be made of the geospatial changes in fishing production which have occurred since the ground trawl ban and suggest a‘workaround’by fishermen.In particular,small fishing craft known as sampans are able to take advantage by being more suitable vessels for areas such as narrower or shallower bays.Marine plastics pollution is also a proxy indicator of these activities,as evidenced by discarded fishing gear that includes plastic nets,floats,and other fishing boat equipment.

Variations of oceanic fronts and their influence on the fishing grounds of Ommastrephes bartramii in the Northwest Pacific

Two predominant currents, the warm Kuroshio Current and the cold Oyashio Current, meet in the North- west Pacific Ocean. The dynamics of physical oceanographic structures in this region, including frontal zones and meandering eddies, result in a highly productive habitat that serves as a favorable feeding ground for various commercially important species. Neon flying squid, Ommastrephes bartramii, is an im- portant oceanic squid, which is widely distributed in the North Pacific Ocean. Based on the catch data col- lected by Chinese squid jigging fleets and relevant environmental data, including sea surface temperature （SST） and fronts （represented by gradients of SST and thermocline） during 1998-2009, the variations of oceanic fronts and their influence on the fishing grounds of O. bartramii were evaluated, and the differ- ences in distribution of fishing grounds of O. bartramii in 2000 and 2002 were compared by describing the differences in vertical temperature between 0-300 m. It was found that the preferred horizontal tem- perature gradient of SST for O. bartramii tended to be centered at 0.01-0.02~C/nm, which attracted nearly 80% of the total fishing effort, and the preferred horizontal temperature gradients at the 50 m and 105 m layers were mainly located at 0.01-0.03~C/nm, which accounted for more than 70% of the total fishing effort during August-October. The preferred vertical temperature gradient within the 0-50 m layer for O. bartramii tended to be centered at 0.15-0.25~C/m during August and September and at 0.10-0.15~C/m in October, implying that the mixed surface layer was distributed at depths of 0-50 m. It was concluded that the vertical temperature gradient was more important than the horizontal temperature gradient in playing a role in forming the fishing ground. The results improved our understanding of the spatial dynamics of the 0. bartramii fishery.

Fishing Ground Distribution of Neon Flying Squid (Ommastrephes bartramii) in Relation to Oceanographic Conditions in the Northwest Pacific Ocean

Neon flying squid, Ommastrephes bartramii, is a squid species of the North Pacific Ocean, which plays an important economical role in the international fishery. Logbook data for Chinese squid-jigging fishery over 2004–2011 were used to evaluate the relationship between the fishing grounds of the squid and the convergent frontal areas, which were defined by the contour lines of specific sea surface temperature(SST) and chlorophyll-a(Chl-a) concentration. Our results indicate that the SST in the range of 15 to 19℃ and the Chl-a concentration in the range of 0.1 to 0.4 mg m^(-3) are the favorable conditions for the aggregation of the squid. Additionally, we deduced that the SST at 17.5℃ and the Chl-a concentration at 0.25 mg m^(-3) are the optimal environmental conditions for the aggregation of O. bartramii. In August, the annual CPUE is positively correlated with the proportion of the fishing grounds with favorable SST and Chl-a concentration, as well as the combination of the two variables, implying that the abundance of the squid annually is largely depending on the presence of the favorable environmental conditions for fishery in August. Minor spatial difference between mean latitudinal location of the 17.5℃ SST and 0.25 mg m^(-3) Chl-a fronts can increase the CPUEs of O. bartramii. Furthermore, the monthly latitudinal gravity centers of the CPUE closely followed the mean latitudinal position of the contour lines of the 17.5℃ SST and the 0.25 mg m^(-3) Chl-a concentration. Our findings suggest the convergent oceanographic features(fronts) play significant roles in regulating the distribution and abundance of the western stock of the winter-spring cohort of O. bartramii, which can help people to improve their ability to discover the O. bartramii fishing grounds with higher productivity.

Analyses of Trawling Track and Fishing Activity Based on the Data of Vessel Monitoring System(VMS): A Case Study of the Single Otter Trawl Vessels in the Zhoushan Fishing Ground

The original purpose of Vessel Monitoring System(VMS) is for enforcement and control of vessel sailing. With the application of VMS in fishing vessels, more and more population dynamic studies have used VMS data to improve the accuracy of fisheries stock assessment. In this paper, we simulated the trawl trajectory under different time intervals using the cubic Hermite spline(c Hs) interpolation method based on the VMS data of 8 single otter trawl vessels(totally 36000 data items) fishing in Zhoushan fishing ground from September 2012 to December 2012, and selected the appropriate time interval. We then determined vessels' activities(fishing or non-fishing) by comparing VMS speed data with the corresponding speeds from logbooks. The results showed that the error of simulated trajectory greatly increased with the increase of time intervals of VMS data when they were longer than 30 minutes. Comparing the speeds from VMS with those from the corresponding logbooks, we found that the vessels' speeds were between 2.5 kn and 5.0 kn in fishing. The c Hs interpolation method is a new choice for improving the accuracy of estimation of sailing trajectory, and the VMS can be used to determine the vessels' activities with the analysis of their trajectories and speeds. Therefore, when the fishery information is limited, VMS can be one of the important data sources for fisheries stock assessment, and more attention should be paid to its construction and application to fisheries stock assessment and management.

Assessment of Heavy Metals,Polycyclic Aromatic Hydrocarbons,and Perfluorinated Alkyl Substances in two Marine Crustaceans(Oratosquilla oratoria and Portunus trituberculatus)in the Zhoushan Fishing Ground of China East Sea

Heavy metals,polycyclic aromatic hydrocarbons(PAHs),and perfluorinated alkyl substances(PFASs)polluted in 155 samples of two marine crustaceans(Oratosquilla oratoria and Portunus trituberculatus)harvested in the Zhoushan fishing ground in the East China Sea were assessed.The results showed that Pb,Hg,and iAs in the whole edible parts of O.oratoria and P.trituberculatus were at trace levels,far below the limits set by the China’s national standard,whereas the exceeding standard rates of Cd in the whole edible parts of O.oratoria and P.trituberculatus were 98.6%and 75.6%,respectively.Moreover,the average Cd levels and the exceeding standard rates of Cd in the visceral tissues of O.oratoria were significantly higher than those in the muscle tissues(4.64 mg kg^(−1)vs.0.49 mg kg^(−1)and 96.7%vs 30%,respectively).PAHs with high detection frequency in the two marine crustaceans included NA,AC,FL,and PHE.Total contents of 15 PAHs(abbreviated asΣ15 PAHs)in whole edible parts of O.oratoria and P.trituberculatus were 10.75–65.9μg kg^(−1)(mean=18.7μg kg^(−1)and 13.26–181μg kg^(−1)(mean=24.2μg kg^(−1),and those in the muscle and the visceral tissues of P.trituberculatus were 9.58–160μg kg^(−1)(mean=21.1μg kg^(−1)and 18.22–201μg kg^(−1)(mean=32.7μg kg^(−1),respectively.Furthermore,PFASs that were found at high contents included PFOA,PFOS,and PFOSA,and total contents of 23 PFASs(Σ23 PFASs)ranged 0.0162–5.104μg kg^(−1)(mean=0.915μg kg^(−1).Collectively,the present work provides new data on the contamination in two marine crustaceans captured in the Zhoushan fishing ground in the China East Sea,which can be useful for making suggestions on proper consumption amounts of the two marine crustaceans.

A New model to forecast fishing ground of Scomber japonicus in the Yellow Sea and East China Sea

The pelagic species is closely related to the marine environmental factors, and establishment of forecasting model of fishing ground with high accuracy is an important content for pelagic fishery. The chub mackerel（Scomber japonicus） in the Yellow Sea and East China Sea is an important fishing target for Chinese lighting purse seine fishery. Based on the fishery data from China＇s mainland large-type lighting purse seine fishery for chub mackerel during the period of 2003 to 2010 and the environmental data including sea surface temperature（SST）, gradient of the sea surface temperature（GSST）, sea surface height（SSH） and geostrophic velocity（GV）, we attempt to establish one new forecasting model of fishing ground based on boosted regression trees. In this study, the fishing areas with fishing effort is considered as one fishing ground, and the areas with no fishing ground are randomly selected from a background field, in which the fishing areas have no records in the logbooks. The performance of the forecasting model of fishing ground is evaluated with the testing data from the actual fishing data in 2011. The results show that the forecasting model of fishing ground has a high prediction performance, and the area under receiver operating curve（AUC） attains 0.897. The predicted fishing grounds are coincided with the actual fishing locations in 2011, and the movement route is also the same as the shift of fishing vessels, which indicates that this forecasting model based on the boosted regression trees can be used to effectively forecast the fishing ground of chub mackerel in the Yellow Sea and East China Sea.

A new model to extract environmental pattern for fishing ground

The relationship between the forming of fishing ground and the oceanic spatio-temporal field is nonlinear. In order to analyse the relationship between variables with spatio-temporal structures, a spatio-temporal pattern extracting model is provided to find the reason for the forming of fishing ground. In the model, the spatio-temporal structure of the oceanic factors is expressed as neighbour. The elements in the neighbour are filled in the table of decision-making system. After a recursion processing the spatio-temporal rule will be extracted with the spatio-temporal structure. And a experiment is given to show how to find the temperature pattern for the forming of the fishing grounds in Dasha area. It shows that the model is active and it should be the research front for the marine fishery.

A preliminary study on stocks of round scad Decapterus maruadsi from Minnan-Taiwan Bank Fishing Ground

ＡｐｒｅｌｉｍｉｎａｒｙｓｔｕｄｙｏｎｓｔｏｃｋｓｏｆｒｏｕｎｄｓｃａｄＤｅｃａｐｔｅｒｕｓｍａｒｕａｄｓｉｆｒｏｍＭｉｎｎａｎ－ＴａｉｗａｎＢａｎｋＦｉｓｈｉｎｇＧｒｏｕｎｄＩＮＴＲＯＤＵＣＴＩＯＮＲｏｕｎｄｓｃａｄ，Ｄｅｃａｐｔｅｒｕｓｍａｒｕａ...

Seasonal Variations of Picoeukaryote Community Structure in Zhoushan Fishing Ground,East China Sea

Picoeukaryotes(<2-3μm)are major oceanic primary producers and play a crucial role for the functioning of marine ecosystems.However,the community structure of such communities remains poorly understood,especially in the East China Sea(ECS).We investigated the seasonal variations of abundance and diversity of picoeukaryotes,and recorded environmental variables,along a transect in Zhoushan Fishing Ground.High-throughput sequencing was used for sequencing the V4-V5 variable region within the 18S rRNA gene to analyze genetic diversity and relative abundance of picoeukaryotes.A total of 40 phyla,68 classes,99 orders,126 families,and 140 genera were observed.The estimated richness and diversity indices were both higher in each season.The composition and dominant picoeukaryotes changed significantly at the class level with the seasons alternating.Basidiomycota,Ciliophora,Ascomycota and Cryptomonadales were observed throughout the year.The Linear Discriminant Analysis(LDA)revealed the predominant discriminant taxa of four seasonal groups.Redundancy analysis(RDA)showed that NO2^−and salinity played very important roles to picoeukaryotes for all the spring samples and DS5 sample in winter,PO4^3−and pH affected mostly picoeukaryotes for winter samples and autumn samples.

Change of upwelling over Southern Fujian-Taiwan Shoal Fishing Ground and its relation to the fisheries

On the basis of the temperature and salinity survey data of July, 1975 and the historical da-ta of relevant hydrological and meteorological stations, this paper discusses the change patternand cause of the upwelling and its relation to the fisheries in the Southern Fujian-Taiwan ShoalFishing Ground. Being important for the benefit of fisheries, the above points have received

Preliminary studies on the characteristics of growth of released prawn, Penaeus orientalis Kishinouye, for reproduction in middle Huanghai Sea fishing ground

The growing demand of prawn protein in the world has been demanding an increasing catch of prawn from the sea which, however, fails to meet the needs due to over exploitation. This ease has always been a keen subject among us fishery seientists. With the support and guidance of the Provincial Government of Shandong, the Shandong Fishery Bureau has been carrying out a project of "the Ex-

船舶自动识别系统(AIS)数据在海洋渔业中研究应用现状

在全球海洋主要经济渔业资源衰退的背景下,如何保护和可持续开发利用海洋渔业资源受到全球各国、地区和组织高度重视,一直是研究热点。受传统海洋渔业数据的制约,一直难以全面了解远洋渔船的捕捞足迹,因此,无法对其实行有效监控和管理。船舶自动识别系统(automatic identification system,AIS)提供的全球远洋渔船轨迹数据可以用于量化分析从单艘到全球渔船行为,挖掘的历史捕捞强度空间信息可为海洋捕捞活动的监测管理和生态压力评估提供良好的可替代数据来源,成为近年海洋信息和海洋渔业研究的新热点。为促进AIS数据在我国海洋渔业中的研究应用,对AIS近年的研究内容和应用现状进行总结,指出AIS数据目前研究的不足和未来潜在的研究方法,以期为AIS在海洋渔业中的研究和应用提供参考。

长江上游江津段产漂流性卵鱼类早期资源现状及繁殖需求

研究长江上游江津段产漂流性卵鱼类早期资源现状和繁殖水文需求,可为长江上游鱼类资源保护和管理提供数据基础。2019-2022年鱼类繁殖季节,在长江上游保护区江津断面开展鱼类早期资源调查,以了解该区域鱼类早期资源种类组成、鱼卵密度的时间动态以及与水文、水环境因子的关系。结果表明,所采集到的67种鱼类卵苗中典型产漂流性种类26种;从各种类繁殖规模比例来看,吻鮈(Rhinogobio typus)、圆筒吻鮈(R.cylindricus)、铜鱼(Coreius heterodon)、草鱼(Ctenopharyngodon idellus)等占比较高;长鳍吻鮈(R.ventralis)繁殖高峰集中在4月,圆筒吻鮈和铜鱼集中在5月中下旬至7月上旬,四大家鱼集中在6月中旬至7月上旬,吻鮈的繁殖时间较长,高峰期集中在4月下旬至6月中下旬;产漂流性卵鱼类的主要产卵场分布在泸州弥陀镇、重庆朱杨溪-石门和金刚沱-油溪镇江段;相关分析结果表明,日均鱼卵密度与透明度呈显著负相关,与流量呈显著正相关;分类回归树结果表明,涨水过程中的水位涨幅、初始流量和透明度最小值是影响保护区产漂流性卵鱼类繁殖规模大小的重要因素,对于不同种类而言,所需的积温、流量条件不尽相同。长江上游保护区江段是多种产漂流性卵鱼类的产卵场,金沙江下游梯级电站陆续运行后,原产卵场位置和规模均发生了一定的变化,建议在实施生态调度来减缓其影响时,不仅需要考虑水文、积温条件对鱼类性腺的影响,还需要考虑水文过程与产卵场形成之间的联系。

白洋淀鱼类产卵场初步调查

为了解白洋淀鱼类产卵场,更好地保护渔业资源,于2021年4—6月首次进行了白洋淀鱼类产卵场调查,掌握了3种黏草性卵鱼类:鲫(Carassius auratus)、小黄黝鱼(Micropercops swinhonis)、鲤(Cyprinus carpio)的产卵及产卵场分布情况,其中后塘淀产卵场分布最为密集。

金沙江水富段向家坝库区邵女坪库汊人工鱼巢布设效果研究

向家坝水电站的建设,给金沙江下游段鱼类的产卵场及栖息地造成了严重破坏,渔业资源日渐衰减。为探索人工鱼巢建设对渔业资源保护的效果,2022年2月至4月在金沙江下游水富段向家坝库区水富邵女坪库汊进行人工鱼巢的布设和效果检测。2022年2月14日~28日开展人工鱼巢布设,3月4日~4月29日进行效果检测。检测结果显示,布设人工鱼巢面积7000 m^(2),产卵5批次,累计1.7亿粒以上,孵化率达到38.9%。3月份产卵量显著高于4月份。该研究结果为电站修建后鱼类多样性保护和重要生境修复措施的制定提供了科学依据。

Response of Spatio-temporal Distribution of Fishery Resources to Mairne Environment in the Northern South China Sea

[Objective] The paper was to investigate the spatio-temporal distribution of fishery resources in the northern South China Sea and to provide reference for scientific evaluation and effective protection of fishery resources in the northern South China Sea. [Methods] Based on monitoring data and satellite remote sensing data [including Sea Surface Temperature(SST), Chlorophyll a concentration(Chl a) and Sea Surface Wind(SSW)] in winter(January to February) and summer(August to September) in the northern South China Sea, the relationship between spatio-temporal distribution of fishery resources and marine environment was investigated by using Generalized Linear Models(GLM), fishing ground gravity and correlation analysis. [Results] The suitable SST and Chl a of light falling-net fishing ground in winter were 17-23°C and 0.2-0.6 mg/m3, respectively. The suitable SST and Chl a in summer were approximately 28°C and 0.2-1.0 mg/m3. Standardized Catch Per Unit Effort(SCPUE) was higher in summer(2-4) and lower in winter(1-3). From winter to summer, the fishing ground gravity migrated to the east about 1 °E. [Conclusion] The spatio-temporal distribution of fishery resources is related to eastern Hainan-western Guangdong upwelling and the coastal flow, caused by the monsoon in the northern South China Sea, and the major catch species of light falling-net.

三峡库区涪陵江段产漂流性卵鱼类的早期资源及其对水文和水温特征的响应

三峡水库调度运行改变了库区江段的水文情势,影响漂流性卵苗在库区江段内的时空分布特征。在水库低水位运行时,具有流水生境特征的库中和库尾江段是产漂流性卵鱼类在整个三峡库区内重要的产卵江段。了解三峡库中和库尾江段产漂流性卵鱼类的早期资源状况及其对水文和水温特征的响应关系,对于采取适宜的保护措施促进鱼类早期资源的恢复具有重要的意义。本文通过2017-2020年5-7月在库中涪陵断面进行的逐日早期资源监测,了解三峡库中和库尾江段产漂流性卵鱼类早期资源的种类组成、产卵规模、产卵场分布及其年际变动特征,并采用随机森林(RF)模型,分析鱼类逐日产卵规模变动与水文、水温格局及其过程的关系,辨识影响不同种类产卵规模变动的关键水文及水温要素。结果表明:2017-2020年共采集到漂流性鱼卵21种,包括长江上游特有鱼类鱼卵3种;以圆筒吻鮈Rhinagobio cylindricus、蒙古鲌Chanodichthys mongolicus、贝氏■Hemiculter bleekeri等6种鱼类的鱼卵为主,占总采集鱼卵数的88.76%;各年的鱼卵规模分别为83.04×10^(8)、14.29×10^(8)、20.43×10^(8)和22.83×10^(8)粒;涪陵以上干流江段分布有6个鱼类的集中产卵场,是圆筒吻鮈、长鳍吻鮈R.ventralis、长薄鳅Leptobotia elongata等长江上游特有鱼类重要的产卵场所;逐日产卵规模主要受产卵时透明度及流量大小、产卵前流量或水位上涨过程以及产卵前积温大小的影响,且影响不同鱼类自然繁殖的关键水温、水文因素在不同种类间存在差异。研究结果可为三峡库区鱼类资源保护措施特别是生态调度措施的实施提供科学依据。

基于集成学习的大西洋热带水域大眼金枪鱼渔情预报

为提高大西洋大眼金枪鱼渔场预报模型的准确率,实验利用13艘中国延绳钓渔船2013—2019年的渔捞日志数据和对应的海洋环境数据(海表面风速、叶绿素a浓度、涡动能、混合层深度和0~500 m水层的垂直温度、盐度和溶解氧等),以天为时间分辨率、2°×2°为空间分辨率、以数据集的75%为训练数据建立了K最近邻(KNN)、逻辑斯蒂回归(LR)、分类与回归树(CART)、支持向量机(SVM)、人工神经网络(ANN)、随机森林(RF)、梯度提升决策树(GBDT)和Stacking集成(STK)渔情预报模型,以25%的测试数据进行模型性能测试、比较。结果显示,(1)STK(由KNN、RF、GBDT模型集成)模型的大眼金枪鱼渔场预报性能较KNN、LR、CART、SVM、ANN、RF和GBDT模型有所提高且相对稳定,上述模型对应的准确率和ROC曲线下面积(AUC)依次分别为81.62%、0.781,79.44%、0.778,72.81%、0.685,74.84%、0.717,73.67%、0.702,67.70%、0.500,80.96%、0.780和78.13%、0.747;(2)STK模型预测的中心渔场与实际中心渔场基本吻合,主要在5°N~10°N,33°W~43°W海域附近;(3)影响大西洋大眼金枪鱼渔场分布的海洋环境因子主要有300 m水层的溶解氧、500 m水层的盐度、海面风速和混合层深度,相对重要性分别为13.24%、9.12%、9.12%和8.81%。研究表明,STK模型对大西洋大眼金枪鱼渔场的预报准确率较高。

海洋捕捞技术、渔具渔法研究进展与趋势

综合应用船舶、机械、信息、新材料等技术,从海洋中捕捞经济渔获物并综合利用,是现代海洋捕捞业的主要特征。海洋捕捞技术的发展和创新,对保障我国食物安全、保护近海生态与资源、实现渔民增收和新渔村建设、推动渔业产业结构调整和转型、维护我国海洋权益等方面具有非常重要的作用。本文通过简析海洋捕捞渔场探测、渔具渔法与高效自动化辅渔助渔技术等方面的研究进展,提出海洋捕捞技术的重点发展方向,以期为我国海洋捕捞实现节能高效、生态友好和资源可持续利用,海洋捕捞技术升级和产业高质量发展提供参考。