阿根廷滑柔鱼渔场预报模型最适时空尺度和环境因子分析  

Impacts of temporal and spatial scale as well as environmental data on fishery forecasting models for Illex argentinus in the southwest Atlantic

作　　者：汪金涛[1,2,3,4] 高峰[1,2,3,4] 雷林[1,2,3,4] 官文江[1,2,3,4] 陈新军[1,2,3,4] 

机构地区：[1]上海海洋大学海洋科学学院,上海201306 [2]大洋渔业资源可持续开发省部共建教育部重点实验室,上海201306 [3]国家远洋渔业工程技术研究中心,上海201306 [4]远洋渔业协同创新中心,上海201306

出　　处：《中国水产科学》2015年第5期1007-1014,共8页Journal of Fishery Sciences of China

基　　金：国家863计划项目(2012AA092303);国家发改委产业化专项(2159999);上海市科技创新行动计划项目(12231203900);国家科技支撑计划项目(2013BAD13B01)

摘　　要：根据2003―2011年主渔汛期间中国鱿钓船队在西南大西洋的鱿钓生产数据,结合海洋遥感获得的海表温度(SST)、海面高度(SSH)和叶绿素a浓度(CHL-a)数据,匹配组织成不同时空尺度和环境因子的样本集,使用人工神经网络(artificial neural network,ANN)作为中心渔场的预报模型,比较所匹配的样本集对阿根廷滑柔鱼中心渔场预报模型的影响。研究表明,样本的时间尺度为周时,1.0o×1.0o的空间尺度和环境因子为SST所建立的BP中心渔场预报模型,具有最高的预报精度和最小的平均相对变动值(average relative variance,ARV);样本时间尺度为月时,0.25o×0.25o的空间尺度和环境因子为SST所建立的BP中心渔场预报模型,具有最高的预报精度和最小的ARV值。对这两种最优样本集建立的BP中心渔场预报模型进行灵敏度分析发现,不同样本集建立的中心渔场预报模型表达的渔场栖息地适宜程度也不尽相同。研究认为,在建立中心渔场预报模型时,需要考虑海洋环境因子的时空尺度。Fishery forecasting is an important component of fisheries science. It has vital significance for fishery production and management. Illex argentinus is an important target for Chinese squid jigging fleets in the southwest Atlantic Ocean. Some previous studies employed various approaches to forecast optimal I. argentinus fishing grounds based on environmental factors, such as sea surface temperature （SST）, sea surface height （SSH）, and chlorophyll-a concentration （Chl-a）. These approaches use experiential knowledge obtained from historical fisheries and environmental data to forecast fishing grounds, but there is no research on how to select the most appropriate spatial and temporal scales or environmental data to forecast models. In this study, models were constructed based on different environmental factors with various spatial and temporal scales to better forecast optimal I. argentinus fishing grounds in the southwest Atlantic Ocean. In this study, historical fishing data from Chinese mainland squid jigging fleets from 2003 to 2011, sea surface temperature （SST）, sea surface height （SSH）, and chlorophyll-a （CHL-a） data were divided into different temporal and spatial scales. Temporal scales included “weekly” and “monthly, ” spatial scales included “0.25° × 0.25°, ” “0.5°× 0.5°,”and“1.0° × 1.0°,”environmental factors were divided into four categories, including I （SST）, II （SST and SSH）, III （SST and Chl-a）, and IV （SST, SSH, and Chl-a）. A total of 24 models were constructed using error backpropagation artificial neural network; model training, validating, and testing were completed in Matlab. Mean square error and average relative variance （ARV） were used to evaluate accuracy, and sensitivity analyses were used to evaluate the interpretation of models for fishing grounds. The results indicated that the fishery forecasting model with maximum accuracy and minimum ARV was constructed by two models, one was with a “weekly” temporal sca

关 键 词：阿根廷滑柔鱼 渔情预报 神经网络 时空尺度 环境因子 

分 类 号：S965.399[农业科学—水产养殖]