[1]袁红春,张硕,陈冠奇.基于双模态深度学习模型的渔场渔情预报[J].江苏农业学报,2021,(02):435-442.[doi:doi:10.3969/j.issn.1000-4440.2021.02.021]
　YUAN Hong-chun,ZHANG Shuo,CHEN Guan-qi.Fishery forecasting in the fishing ground based on dual-modal deep learning model[J].,2021,(02):435-442.[doi:doi:10.3969/j.issn.1000-4440.2021.02.021]
点击复制

基于双模态深度学习模型的渔场渔情预报()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2021年02期
页码:
435-442
栏目:
畜牧兽医·水产养殖
出版日期:
2021-04-30

文章信息/Info

Title:
Fishery forecasting in the fishing ground based on dual-modal deep learning model
作者:
袁红春1; 2; 张硕1; 陈冠奇1
(1.上海海洋大学信息学院，上海201306;2.农业农村部渔业信息重点实验室，上海201306)
Author(s):
YUAN Hong-chun1; 2; ZHANG Shuo1; CHEN Guan-qi1
(1.College of Information Technology, Shanghai Ocean University, Shanghai 201306, China;2.Key Laboratory of Fisheries Information，Ministry of Agriculture and Rural Affairs，Shanghai 201306, China)
关键词:
双模态深度学习模型; 渔场渔情预报; 长鳍金枪鱼
Keywords:
dual-modal deep learning model; fishery forecasting in the fishing ground; albacore tuna
分类号:
S934
DOI:
doi:10.3969/j.issn.1000-4440.2021.02.021
文献标志码:
A
摘要:
为解决传统渔场渔情预测方法在处理高维复杂海洋数据时存在人工干预较多、拟合困难、精度不高的问题，提出了一种基于双模态深度学习的渔场渔情预测方法。首先，该方法将不同海洋环境因子在5°×5°渔业作业区域范围内按照空间相对位置映射为三维矩阵。然后，分别使用卷积神经网络模型（CNN）和深度神经网络模型（DNN）对海洋环境因子和时空因子2种异构数据进行特征提取。最后，将基于时空信息的深度神经网络模型与卷积结构进行特征融合，再将融合后的特征经过全连接层进行分类。试验结果表明，双模态深度学习模型对南太平洋长鳍金枪鱼中心渔场的渔场渔情预报率达到了89.8%，较其他渔场渔情预报模型精度提高10%～30%。同时由于该模型使用卷积神经网络，可以对任意空间分辨率的海洋环境因子进行特征提取，省去了手动匹配不同空间分辨率的过程，减少了人工干预，对南太平洋长鳍金枪鱼的渔业作业与渔场渔情预报有极高的指导意义。
Abstract:
To solve the problems of much manual intervention, difficulty in fitting and low accuracy in processing ocean data of high-dimensional complex by traditional fishery forecasting methods in the fishing ground, a fishery forecasting method based on dual-modal deep learning was proposed. Firstly, the method mapped different marine environmental factors within a 5°×5° fishery operation area into a three-dimensional matrix according to their relative spatial positions. Secondly, features of two heterogeneous data such as marine environmental factors and spatiotemporal factors were extracted by convolutional neural network (CNN) model and deep neural network (DNN) model respectively. Finally, the deep neural network model based on spatiotemporal information and the convolution structure were fused by feature, and the fused features were classified through the fully connected layer. The results showed that, the forecast rate of fishery by dual-modal deep learning model in the central fishing ground of albacore in the South Pacific reached 89.8%, which improved the forecast accuracy by 10%-30% compared with forecast models in other fishing grounds. At the same time, because the model used a convolutional neural network, which could extract features of marine environmental factors with any spatial resolution, thus eliminated the process of matching different spatial resolutions by manual and reduced manual intervention, which showed extremely high guiding significance for the fishing operations and fishery forecast in the fishing ground of albacore in the South Pacific.

参考文献/References:

[1]NIKOLIC N, MORANDEAU G, HOARAU L, et al. Review of albacore tuna, Thunnus alalunga, biology, fisheries and management[J]. Reviews in Fish Biology and Fisheries, 2017, 27(4): 775-810.
[2]ZAGAGLIA C R, LORENZZETTI J A, STECH J L. Remote sensing data and longline catches of yellowfin tuna (Thunnus albacares) in the equatorial Atlantic[J]. Remote Sensing of Environment, 2004, 93(1/2): 267-281.
[3]ZAINUDDIN M, SAITOH K, SAITOH S E I I. Albacore (Thunnus alalunga) fishing ground in relation to oceanographic conditions in the western North Pacific Ocean using remotely sensed satellite data[J]. Fisheries Oceanography, 2008, 17(2): 61-73.
[4]崔雪森,唐峰华,张衡,等.基于朴素贝叶斯的西北太平洋柔鱼渔场预报模型的建立[J].中国海洋大学学报(自然科学版),2015,45(2):37-43.
[5]宋利明,周建坤,沈智宾,等.基于支持向量机的库克群岛海域长鳍金枪鱼栖息环境综合指数[J].海洋通报,2017,36(2):195-208.
[6]HARRELL F E, LEE K L, MARK D B. Tutorial in biostatistics multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors[J]. Statistics in Medicine,1996,1 (15) : 361-387.
[7]袁红春,陈冠奇,张天蛟,等.基于全卷积网络的南太平洋长鳍金枪鱼渔场预报模型[J].江苏农业学报,2020,36(2):423-429.
[8]LIU Q, YU F, WU S, et al. A convolutional click prediction model[C]//ASSOCIATION FOR COMPUTING MACHINERY. Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. New York， USA: ACM, 2015: 1743-1746.
[9]WANG P, XU B, XU J, et al. Semantic expansion using word embedding clustering and convolutional neural network for improving short text classification [J]. Neurocomputing, 2016，174:806-814.
[10]毛江美,陈新军,余景.基于神经网络的南太平洋长鳍金枪鱼渔场预报[J].海洋学报,2016,38(10):34-43.
[11]宋利明,谢凯,赵海龙,等.库克群岛海域海洋环境因子对长鳍金枪鱼渔获率的影响[J].海洋通报,2017,36(1):96-106.
[12]范永超,戴小杰,朱江峰,等.南太平洋长鳍金枪鱼延绳钓渔业CPUE标准化[J].海洋湖沼通报,2017(1):122-132.
[13]ZAINUDDIN M, SAITOH S, SAIROH K. Detection of potential fishing ground for albacore tuna using synoptic measurements of ocean color and thermal remote sensing in the northwestern North Pacific[J]. Geophysical Research Letters, 2004, 31(20): 183-213.
[14]ISMAIL A I, MORRISION E C, BURT B A, et al. Natural history of periodontal disease in adults: findings from the Tecumseh Periodontal Disease Study, 1959-1987[J]. Journal of Dental Research, 1990, 69(2): 430-435.
[15]陈雪忠,樊伟,崔雪森,等.基于随机森林的印度洋长鳍金枪鱼渔场预报[J].海洋学报,2013,35(1):158-164.
[16]高峰,陈新军,官文江,等.基于提升回归树的东、黄海鲐鱼渔场预报[J].海洋学报,2015,37(10):39-48.
[17]张衡,崔雪森,樊伟.基于遥感数据的智利竹筴鱼渔场预报系统[J].农业工程学报,2012,28(15):140-144.
[18]SRIVASTAVA N, SALAKHUTDINOV R. Multimodal learning with deep boltzmann machines[J]. Journal of Machine Learning Research,2014,15(8):1967-2006.
[19]林大超,安凤平,郭章林,等.滑坡位移的多模态支持向量机模型预测[J].岩土力学,2011,32(S1):451-458.
[20]姜远,黎铭,周志华.一种基于半监督学习的多模态Web查询精化方法[J].计算机学报,2009,32(10):2099-2106.

备注/Memo

备注/Memo:
收稿日期：2020-07-19基金项目：国家自然科学基金项目（41776142）；国家重点研发计划项目（2018YFD0701003）作者简介：袁红春（1971-），男，江苏海门人，博士，教授，主要从事专家系统、智能计算、智能信息处理等研究工作。(E-mail)hcyuan@shou.edu.cn
更新日期/Last Update: 2021-05-10