采用卷积神经网络构建西北太平洋柔鱼渔场预报模型  

Construction of fishing ground forecast model of Ommastrephes bartramii using convolutional neural network in the Northwest Pacific

作　　者：朱浩朋 伍玉梅[2] 唐峰华[2] 靳少非 裴凯洋 崔雪森[2] Zhu Haopeng;Wu Yumei;Tang Fenghua;Jin Shaofei;Pei Kaiyang;Cui Xuesen(College of Marine Sciences,Shanghai Ocean University,Shanghai 201306,China;Key Laboratory of Oceanic and Polar Fisheries,Ministry of Agriculture and Rural Affairs,East China Sea Fisheries Research Institute,Chinese Academy of Fishery Sciences,Shanghai,200090,China;Ocean College,Minjiang University,Fuzhou 350108,China;College of Information,Shanghai Ocean University,Shanghai 201306,China)

机构地区：[1]上海海洋大学海洋科学学院,上海201306 [2]中国水产科学研究院东海水产研究所农业农村部远洋与极地渔业创新重点实验室,上海200090 [3]闽江学院海洋学院,福州350108 [4]上海海洋大学信息学院,上海201306

出　　处：《农业工程学报》2020年第24期153-160,共8页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家重点研发计划(2019YFD0901405);上海市自然科学基金项目(17ZR1439700);中国水产科学研究院基本科研业务费项目(2019T08);中国水产科学研究院院级基本科研业务费(2018GH13)。

摘　　要：对远洋渔场资源和位置进行预报可以为远洋渔业生产及管理提供重要信息。该研究针对西北太平洋柔鱼渔场,利用海洋表面温度遥感信息和中国远洋渔船生产资料,基于深度学习原理,选取卷积神经网络构建西北太平洋柔鱼渔场预报模型。根据不同月份、不同通道构建了多种数据集,用于训练渔场预报模型。训练结果表明,4个通道组合的数据集的训练结果最优,渔汛早期(7—8月)、中期(9月)和后期(10—11月)测试集准确率分别为80.5%、81.5%和81.4%。以2015年的真实渔场数据对模型进行验证,模型的平均召回率为82.3%,平均精确率为66.6%,F1得分平均值为73.1%,预测的高产渔区与实际作业的高单位捕捞努力量渔获量区基本匹配。该研究构建的渔场预报模型可以获得较好的准确率,可为其他鱼种的渔场预报模型构建提供思路。To improve the accuracy and practicability of fishery forecast in the Northwest Pacific,a method of constructing a forecast model of squid was proposed based on the principle of deep learning.In this study,the data included the fishery catch data from the North Pacific squid fishing boat production information and the Sea Surface Temperature(SST)from the moderate-resolution imaging spectroradiometer,from July to November 2000-2015.According to the combination of different channels,four kinds of datasets were formed for the model training,including the single-channel dataset only containing SST;2-channels dataset of SST and month;3-channels dataset of SST,longitude,and latitude;4-channels dataset of SST,month,longitude,and latitude.To match the data of the first channel in dimensionality,the three-input data of longitude,latitude,and month needed to be expanded from a 0-dimensional scalar quantity to a 2-dimensional tensor with pixels of 65×65 and regarded as the second,third,and fourth channel.Because of the insufficiency of effective fishery catch data,these datasets were enhanced by random rotation of the SST image with a small-angle between-10°and+10°and a random 0.1°offset of the image center in four directions,including north,south,east and west.The AlexNet was chosen as the structure of the Convolutional Neural Network(CNN)model,and it consisted of five convolutional layers,three max-pooling layers,and three fully-connected layers with a final 2-way softmax.Different from traditional fishery forecast methods,this method used the Graphics Processing Unit(GPU)to accelerate training,and its extraction of environmental features was automatically completed by computer.SST,latitude,longitude,and month were all factors that needed to be considered when constructing a fishing ground forecast model.The impact of these factors on the accuracy of the fishing ground forecast was compared and analyzed.The results showed that 1)According to the migration laws of squid,the datasets from July to November were divided i

关 键 词：卷积神经网络 模型 渔业 西北太平洋 柔鱼 

分 类 号：S931.3[农业科学—渔业资源]