Study on center of gravity prediction of albacore tuna (Thunnus alalunga) fishing grounds in the south Pacific
-
摘要: 长鳍金枪鱼（Thunnus alalunga）是大洋洄游性鱼类，其渔场分布与多种环境因子存在一定联系。根据2016−2021年的南太平洋长鳍金枪鱼延绳钓渔捞日志，利用南方涛动指数（Southern Oscilllation Index，SOI）、海表温度（Sea Surface Temperature，SST）、叶绿素（chlorophyll-a，CHLA）浓度、溶解氧（Dissolved Oxygen，DO）浓度等海洋遥感资料，把时空和环境因子作为输入层，单位捕捞努力量渔获量（Catch per unit effort，CPUE）作为输出层，采用遗传算法（genetic algorithm，GA）优化结构为9-13-1的BP神经网络。GA-BP神经网络预测的均方误差（MSE）和R2分别为
0.0074 和0.397，均优于BP神经网络。预测分析显示，SST和DO浓度是长鳍金枪鱼渔场重心变动的主要环境因子，CPUE较高的渔场SST范围为18～20℃，DO浓度范围为210 mmol/m3以上。预测与实际渔场重心基本一致，且标准化的CPUE与名义CPUE的时间变化趋势总体一致。研究表明，GA-BP神经网络能够较好地预测长鳍金枪鱼的渔场，为金枪鱼渔业生产与管理提供参考依据。Abstract: The albacore tuna (Thunnus alalunga) is an oceanic migratory fish species, whose fishing ground distribution is linked to various environmental factors. Based on the longline fishing logs of albacore tuna in the south Pacific from 2016 to 2021, oceanic remote sensing data including the Southern Oscillation Index (SOI), Sea Surface Temperature (SST), Chlorophyll-a (CHLA) concentration and Dissolved Oxygen (DO) concentration were utilized. With spatiotemporal and environmental factors as input layer and catch per unit effort (CPUE) as output layer, a genetic algorithm (GA) was utilized to optimize the structure of a 9-13-1 BP neural network. CPUE standardization was carried out for albacore based on GA-BP neural network to investigate the spatiotemporal variation and influencing factors on the abundance of albacore tuna resources. The model evaluation results indicated that the GA-BP neural network had better effect than the BP neural network. Predictive analysis showed that SST and DO concentration were the primary environmental factors influencing the shifts in the core area of albacore tuna fishing grounds, with the most productive fishing areas having SSTs between 18℃ and 20℃, and DO concentration levels above 210 mmol/m³. The predicted and actual center of gravity for fishing grounds largely coincided, and the standardized CPUE trends over time were generally consistent with nominal CPUE. The research has demonstrated that the utilization of GA-BP neural networks can effectively predict the distribution of fishing grounds for albacore tuna, providing a reference basis for tuna fishery production and management.-
Key words:
- Thunnus alalunga /
- genetic algorithm /
- BP neural network /
- standardization /
- the South Pacific
-
图 3 隐藏层神经元个数选择图。a. MSE，b. R2
Fig. 3 Neurons’ amount selection of hidden layer. a. MSE, b. R2
图 6 主要环境与CPUE的依赖关系
a. SST，b. DO，其中灰色的阴影带为95%置信区间
Fig. 6 The dependency relationship between main environmental factors and CPUE
a. SST, b. DO concentration, with the gray shaded area representing the 95% confidence interval
图 7 2016−2021年月间渔场重心变动与年均SST叠加分布
Fig. 7 Distribution of changes in the gravity of fishing grounds with average SST between 2016 and 2021
图 8 2016−2021年月间渔场重心变动与年均DO浓度叠加分布
Fig. 8 Distribution of changes in the gravity of fishing grounds with average DO concentration between 2016 and 2021
图 10 标准化CPUE与名义CPUE对比
Fig. 10 Comparation for standardized CPUE and nominal CPUE of trends in survey years
表 1 BP和GA-BP对比分析
Tab. 1 Comparation analysis of BP and GA-BP model
BP神经网络 GA-BP神经网络 训练集 测试集 训练集 测试集 MSE 9.4×10−3 8.3×10−3 8.6×10−3 7.4×10−3 R2 0.324 0.318 0.375 0.397 
下载: 导出CSV
-
[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. doi: 10.1007/s11160-016-9453-y [2] Hoyle S, Langley A, Hampton J. Stock assessment of albacore tuna in the south Pacific Ocean[R]. Port Moresby, Papua New Guinea: Western and Central Pacific Fisheries Commission, 2008: 11−22. [3] 刘洪生, 蒋汉凌, 戴小杰. 中西太平洋长鳍金枪鱼渔场与海温的关系[J]. 上海海洋大学学报, 2014, 23(4): 602−607.Liu Hongsheng, Jiang Hanling, Dai Xiaojie. Relationship between albacore (Thunnus alalunga) fishing grounds in the western and central Pacific and sea surface temperature[J]. Journal of Shanghai Ocean University, 2014, 23(4): 602−607. [4] 任中华, 陈新军, 方学燕. 基于栖息地指数的东太平洋长鳍金枪鱼渔场分析[J]. 海洋渔业, 2014, 36(5): 385−395. doi: 10.3969/j.issn.1004-2490.2014.05.001Ren Zhonghua, Chen Xinjun, Fang Xueyan. Forecasting fishing grounds of Thunnus alalunga in the eastern Pacific based on habitat suitability index[J]. Marine Fisheries, 2014, 36(5): 385−395. doi: 10.3969/j.issn.1004-2490.2014.05.001 [5] 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.Fan Yongchao, Dai Xiaojie, Zhu Jiangfeng, et al. CPUE standardization of longline fishing Thunnus alalunga in south Pacific Ocean[J]. Transactions of Oceanology and Limnology, 2017(1): 122−132. [6] 许回, 宋利明, 沈介然, 等. 基于GAM的库克群岛海域长鳍金枪鱼CPUE时空分布与海洋环境的关系[J]. 海洋通报, 2023, 42(4): 444−455.Xu Hui, Song Liming, Shen Jieran, et al. The relationship between the spatial-temporal distribution of albacore tuna CPUE and the marine environment variables in waters near the Cook Islands based on GAM[J]. Marine Science Bulletin, 2023, 42(4): 444−455. [7] 张嘉容, 杨晓明, 田思泉. 基于最大熵模型的南太平洋长鳍金枪鱼栖息地预测[J]. 中国水产科学, 2020, 27(10): 1222−1233.Zhang Jiarong, Yang Xiaoming, Tian Siquan. Analysis of albacore (Thunnus alalunga) habitat distribution in the south Pacific using maximum entropy model[J]. Journal of Fishery Sciences of China, 2020, 27(10): 1222−1233. [8] 周为峰, 陈亮亮, 崔雪森, 等. 异常气候下温跃层及时空因子对中西太平洋黄鳍金枪鱼渔场分布的影响[J]. 中国农业科技导报, 2021, 23(10): 192−201.Zhou Weifeng, Chen Liangliang, Cui Xuesen, et al. Effects of thermocline and space-time factors on yellowfin tuna fishing ground distribution in the central and western pacific in abnormal climate[J]. Journal of Agricultural Science and Technology, 2021, 23(10): 192−201. [9] 陈洋洋, 陈新军. 厄尔尼诺/拉尼娜现象对中西太平洋鲣资源丰度的影响[J]. 上海海洋大学学报, 2017, 26(1): 113−120. doi: 10.12024/jsou.20160601795Chen Yangyang, Chen Xinjun. Influence of El Nino/La Nina on the abundance index of skipjack in the western and central Pacific Ocean[J]. Journal of Shanghai Ocean University, 2017, 26(1): 113−120. doi: 10.12024/jsou.20160601795 [10] Senina I N, Lehodey P, Hampton J, et al. Quantitative modelling of the spatial dynamics of south Pacific and Atlantic albacore tuna populations[J]. Deep Sea Research Part II: Topical Studies in Oceanography, 2020, 175: 104667. doi: 10.1016/j.dsr2.2019.104667 [11] 官文江, 田思泉, 王学昉, 等. CPUE标准化方法与模型选择的回顾与展望[J]. 中国水产科学, 2014, 21(4): 852−862.Guan Wenjiang, Tian Siquan, Wang Xuefang, et al. A review of methods and model selection for standardizing CPUE[J]. Journal of Fishery Sciences of China, 2014, 21(4): 852−862. [12] Zainuddin M, Saitoh K, Saitoh S 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. doi: 10.1111/j.1365-2419.2008.00461.x [13] 杨胜龙, 张禹, 张衡, 等. 不同模型在渔业CPUE标准化中的比较分析[J]. 农业工程学报, 2015, 31(21): 259−264. doi: 10.11975/j.issn.1002-6819.2015.21.034Yang Shenglong, Zhang Yu, Zhang Heng, et al. Comparison and analysis of different model algorithms for CPUE standardization in fishery[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(21): 259−264. doi: 10.11975/j.issn.1002-6819.2015.21.034 [14] Ivakhenko A G, Savchenko E A, Ivakhenko G A. Problems of future GMDH algorithms development[J]. Systems Analysis Modelling Simulation, 2003, 43(10): 1301−1309. doi: 10.1080/0232929032000115029 [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. doi: 10.3969/j.issn.0253-4193.2013.01.018Chen Xuezhong, Fan Wei, Cui Xuesen, et al. Fishing ground forecasting of Thunnus alalunga in Indian Ocean based on random forest[J]. Haiyang Xuebao, 2013, 35(1): 158−164. doi: 10.3969/j.issn.0253-4193.2013.01.018 [16] 程懿麒, 张俊波, 汪金涛, 等. 基于神经网络的印度洋长鳍金枪鱼(Thunnus alalunga)时空分布与海洋环境关系研究[J]. 海洋与湖沼, 2021, 52(4): 960−970. doi: 10.11693/hyhz20210100003Cheng Yiqi, Zhang Junbo, Wang Jintao, et al. Study on the relationship between temporal-spatial distribution of Indian Ocean albacore (Thunnus alalunga) and marine environment based on neural network[J]. Oceanologia et Limnologia Sinca, 2021, 52(4): 960−970. doi: 10.11693/hyhz20210100003 [17] 郭彦龙, 赵泽芳, 乔慧捷, 等. 物种分布模型面临的挑战与发展趋势[J]. 地球科学进展, 2020, 35(12): 1292−1305. doi: 10.11867/j.issn.1001-8166.2020.110Guo Yanlong, Zhao Zefang, Qiao Huijie, et al. Challenges and development trend of species distribution model[J]. Advances in Earth Science, 2020, 35(12): 1292−1305. doi: 10.11867/j.issn.1001-8166.2020.110 [18] 章贤成, 汪金涛, 陈新军. 基于BP神经网络的阿根廷滑柔鱼资源CPUE标准化研究[J]. 渔业科学进展, 2022, 43(2): 11−20.Zhang Xiancheng, Wang Jintao, Chen Xinjun. CPUE standardization of Illex angentinus based on BP neural network[J]. Progress in Fishery Sciences, 2022, 43(2): 11−20. [19] 常亮, 陈芳霖, 陈新军, 等. 基于BP神经网络的西北太平洋柔鱼资源丰度预测[J]. 上海海洋大学学报, 2022, 31(2): 524−533. doi: 10.12024/jsou.20210703510Chang Liang, Chen Fanglin, Chen Xinjun, et al. Prediction of the CPUE of neon flying squid in the northwest Pacific Ocean based on back propagation neural network[J]. Journal of Shanghai Ocean University, 2022, 31(2): 524−533. doi: 10.12024/jsou.20210703510 [20] 王新环, 刘志超. 一种基于遗传算法的极限学习机改进算法研究[J]. 软件导刊, 2017, 16(9): 79−82,86.Wang Xinhuan, Liu Zhichao. The modified study on extreme learning machine based on genetic algorithm[J]. Software Guide, 2017, 16(9): 79−82,86. [21] 冯永玖, 陈新军, 杨晓明, 等. 基于遗传算法的渔情预报HSI建模与智能优化[J]. 生态学报, 2014, 34(15): 4333−4346.Feng Yongjiu, Chen Xinjun, Yang Xiaoming, et al. HSI modeling and intelligent optimization for fishing ground forecasts using a genetic algorithm[J]. Acta Ecologica Sinica, 2014, 34(15): 4333−4346. [22] Mirjalili S. Evolutionary Algorithms and Neural Networks: Theory and Applications[M]. Cham: Spring, 2019: 43−55. [23] Feng Yongjiu, Chen Xinjun, Gao Feng, et al. Impacts of changing scale on Getis-Ord Gi* hotspots of CPUE: a case study of the neon flying squid (Ommastrephes bartramii) in the northwest Pacific Ocean[J]. Acta Oceanologica Sinica, 2018, 37(5): 67−76. doi: 10.1007/s13131-018-1212-6 [24] 王嵘冰, 徐红艳, 李波, 等. BP神经网络隐含层节点数确定方法研究[J]. 计算机技术与发展, 2018, 28(4): 31−35. doi: 10.3969/j.issn.1673-629X.2018.04.007Wang Rongbing, Xu Hongyan, Li Bo, et al. Research on method of determining hidden layer nodes in BP neural network[J]. Computer Technology and Development, 2018, 28(4): 31−35. doi: 10.3969/j.issn.1673-629X.2018.04.007 [25] Garson G D. Interpreting neural-network connection weights[J]. AI Expert, 1991, 6(4): 46−51. [26] Mohamed S, Rosca M, Figurnov M, et al. Monte Carlo gradient estimation in machine learning[J]. The Journal of Machine Learning Research, 2020, 21(1): 132. [27] Ding Shifei, Su Chunyang, Yu Junzhao. An optimizing BP neural network algorithm based on genetic algorithm[J]. Artificial Intelligence Review, 2011, 36(2): 153−162. doi: 10.1007/s10462-011-9208-z [28] Wang Jintao, Chen Xinjun, Chen Yong. Spatio-temporal distribution of skipjack in relation to oceanographic conditions in the west-central Pacific Ocean[J]. International Journal of Remote Sensing, 2016, 37(24): 6149−6164. doi: 10.1080/01431161.2016.1256509 [29] Chang Keyang, Chen C S, Wang Huiyu, et al. The Antarctic Oscillation index as an environmental parameter for predicting catches of the Argentine shortfin squid (Illex argentinus) (Cephalopoda: Ommastrephidae) in southwest Atlantic waters[J]. Fishery Bulletin, 2015, 113(2): 202−212. doi: 10.7755/FB.113.2.8 [30] Boyce D G, Tittensor D P, Worm B. Effects of temperature on global patterns of tuna and billfish richness[J]. Marine Ecology Progress Series, 2008, 355: 267−276. doi: 10.3354/meps07237 [31] Arrizabalaga H, Dufour F, Kell L, et al. Global habitat preferences of commercially valuable tuna[J]. Deep Sea Research Part II: Topical Studies in Oceanography, 2015, 113: 102−112. doi: 10.1016/j.dsr2.2014.07.001 [32] Kai E T, Marsac F. Influence of mesoscale eddies on spatial structuring of top predators’ communities in the Mozambique Channel[J]. Progress in Oceanography, 2010, 86(1/2): 214−223. [33] Zhou Cheng, He Pingguo, Xu Liuxiong, et al. The effects of mesoscale oceanographic structures and ambient conditions on the catch of albacore tuna in the south Pacific longline fishery[J]. Fisheries Oceanography, 2020, 29(3): 238−251. doi: 10.1111/fog.12467 [34] Shcherbina A Y, D'Asaro E A, Riser S C, et al. Variability and interleaving of upper-ocean water masses surrounding the north Atlantic salinity maximum[J]. Oceanography, 2015, 28(1): 106−113. doi: 10.5670/oceanog.2015.12 [35] 闫敏, 张衡, 樊伟, 等. 南太平洋长鳍金枪鱼渔场CPUE时空分布及其与关键海洋环境因子的关系[J]. 生态学杂志, 2015, 34(11): 3191−3197.Yan Min, Zhang Heng, Fan Wei, et al. Spatial-temporal CPUE profiles of the albacore tuna (Thunnus alalunga) and their relations to marine environmental factors in the south Pacific Ocean[J]. Chinese Journal of Ecology, 2015, 34(11): 3191−3197. [36] Lehodey P, Chai F, Hampton J. Modelling climate-related variability of tuna populations from a coupled ocean-biogeochemical-populations dynamics model[J]. Fisheries Oceanography, 2003, 12(4/5): 483−494. [37] Kumar P S, Pillai G N, Manjusha U. El Nino southern oscillation (ENSO) impact on tuna fisheries in Indian Ocean[J]. SpringerPlus, 2014, 3(1): 591. doi: 10.1186/2193-1801-3-591 [38] Santiago J, Arrizabalaga H. An integrated growth study for north Atlantic albacore (Thunnus alalunga Bonn. 1788)[J]. ICES Journal of Marine Science, 2005, 62(4): 740−749. doi: 10.1016/j.icesjms.2005.01.015 [39] Moore B R, Bell J D, Evans K, et al. Defining the stock structures of key commercial tunas in the Pacific Ocean I: current knowledge and main uncertainties[J]. Fisheries Research, 2020, 230: 105525. doi: 10.1016/j.fishres.2020.105525 [40] Song Liming, Li Tianlai, Zhang Tianjiao, et al. Comparision of machine learning models within different spatial resolutions for predicting the bigeye tuna fishing grounds in tropical waters of the Atlantic Ocean[J]. Fisheries Oceanography, 2023, 32(6): 509−526 [41] Maunder M N, Punt A E. Standardizing catch and effort data: a review of recent approaches[J]. Fisheries Research, 2004, 70(2/3): 141−159. -
图(10) / 表(1)
计量
- 文章访问数: 140
- HTML全文浏览量: 73
- PDF下载量: 29
- 被引次数: 0
