海洋学报

项目	海域	Min	P₂₅	P₅₀	P₇₅	Max	平均
黄鳍金枪鱼CPUE	赤道以北	0.779	2.750	4.823	6.914	18.208	5.118
赤道以南	0	6.129	7.489	9.321	16.460	7.735
鲣CPUE	赤道以北	3.217	9.362	13.380	17.077	32.286	13.491
赤道以南	6.858	14.803	18.758	22.559	35.583	18.777
海洋尼诺指数	\	−1.870	−0.603	−0.050	0.510	2.710	0.016

项目	海域	Min	P₂₅	P₅₀	P₇₅	Max	平均
黄鳍金枪鱼CPUE	赤道以北	0.779	2.750	4.823	6.914	18.208	5.118
赤道以南	0	6.129	7.489	9.321	16.460	7.735
鲣CPUE	赤道以北	3.217	9.362	13.380	17.077	32.286	13.491
赤道以南	6.858	14.803	18.758	22.559	35.583	18.777
海洋尼诺指数	\	−1.870	−0.603	−0.050	0.510	2.710	0.016

滞后时间/月	黄鳍金枪鱼		鲣
0	9.90828	0.14917	0.15540		1.79009	0.10379	0.12012		3.28223	0.19211	0.23032		0.75190	0.14909	0.17050
1	2.97018	0.04652	0.06101	2.58407	0.15056	0.16129	2.56779	0.15519	0.18690	0.58860	0.13732	0.17983
2	3.52192	0.06414	0.06885	2.78081	0.14993	0.17108	2.32455	0.14219	0.16376	0.60977	0.12596	0.14845
3	9.52831	0.14418	0.14977	1.37389	0.09502	0.12549	3.84945	0.22736	0.26697	0.79580	0.17736	0.18951
4	7.90549	0.10914	0.12458	1.35588	0.08262	0.09750	5.67477	0.38144	0.39281	0.95240	0.21992	0.25508
5	4.71259	0.06653	0.07531	1.53034	0.08917	0.10222	5.84598	0.36893	0.39745	0.51162	0.10161	0.11268
6	4.69040	0.06422	0.07334	1.39996	0.07823	0.11137	5.46671	0.34900	0.37072	1.28165	0.28839	0.31291
7	6.63161	0.12643	0.13064	1.24703	0.07832	0.10089	5.51127	0.34509	0.37413	0.66225	0.14054	0.15561
8	5.21586	0.08945	0.09143	2.90610	0.16607	0.17832	7.08355	0.45903	0.48260	1.01102	0.21614	0.21883
9	6.85734	0.09821	0.10819	2.59891	0.14291	0.15865	3.05708	0.18717	0.21077	0.64069	0.14251	0.15294
10	9.78094	0.15027	0.15517	1.72018	0.11157	0.13687	4.22249	0.26537	0.28988	0.57465	0.12541	0.15013
11	5.93768	0.08297	0.09254	0.90011	0.06141	0.07853	2.54923	0.16213	0.19257	0.43067	0.09660	0.10529
12	2.53704	0.04456	0.05823	0.85169	0.05599	0.06346	1.01160	0.08631	0.12771	0.35689	0.07898	0.09953

滞后时间/月	黄鳍金枪鱼		鲣
0	9.90828	0.14917	0.15540		1.79009	0.10379	0.12012		3.28223	0.19211	0.23032		0.75190	0.14909	0.17050
1	2.97018	0.04652	0.06101	2.58407	0.15056	0.16129	2.56779	0.15519	0.18690	0.58860	0.13732	0.17983
2	3.52192	0.06414	0.06885	2.78081	0.14993	0.17108	2.32455	0.14219	0.16376	0.60977	0.12596	0.14845
3	9.52831	0.14418	0.14977	1.37389	0.09502	0.12549	3.84945	0.22736	0.26697	0.79580	0.17736	0.18951
4	7.90549	0.10914	0.12458	1.35588	0.08262	0.09750	5.67477	0.38144	0.39281	0.95240	0.21992	0.25508
5	4.71259	0.06653	0.07531	1.53034	0.08917	0.10222	5.84598	0.36893	0.39745	0.51162	0.10161	0.11268
6	4.69040	0.06422	0.07334	1.39996	0.07823	0.11137	5.46671	0.34900	0.37072	1.28165	0.28839	0.31291
7	6.63161	0.12643	0.13064	1.24703	0.07832	0.10089	5.51127	0.34509	0.37413	0.66225	0.14054	0.15561
8	5.21586	0.08945	0.09143	2.90610	0.16607	0.17832	7.08355	0.45903	0.48260	1.01102	0.21614	0.21883
9	6.85734	0.09821	0.10819	2.59891	0.14291	0.15865	3.05708	0.18717	0.21077	0.64069	0.14251	0.15294
10	9.78094	0.15027	0.15517	1.72018	0.11157	0.13687	4.22249	0.26537	0.28988	0.57465	0.12541	0.15013
11	5.93768	0.08297	0.09254	0.90011	0.06141	0.07853	2.54923	0.16213	0.19257	0.43067	0.09660	0.10529
12	2.53704	0.04456	0.05823	0.85169	0.05599	0.06346	1.01160	0.08631	0.12771	0.35689	0.07898	0.09953

基于LSTM的气候变化对中西太平洋围网黄鳍金枪鱼和鲣CPUE影响的滞后效应

PDF下载

张健 ¹^,²^,³^,⁴ , 宋厚成 ¹ , 刘文俊 ¹ , 石建高 ⁵

海洋学报 | 论文 2024,46(7): 62-72

收起

海洋学报 | 论文 2024, 46(7): 62-72

基于LSTM的气候变化对中西太平洋围网黄鳍金枪鱼和鲣CPUE影响的滞后效应

全屏

张健¹^,²^,³^,⁴, 宋厚成¹, 刘文俊¹, 石建高⁵

作者信息

1.上海海洋大学海洋生物资源与管理学院，上海 201306

2.上海海洋大学国家远洋渔业工程技术研究中心，上海 201306

3.上海海洋大学大洋渔业资源可持续开发教育部重点实验室，上海 201306

4.上海海洋大学农业农村部大洋渔业开发重点实验室，上海 2013064

5.中国水产科学研究院东海水产研究所，上海 200090

张健（1979—），男，上海市人，教授，从事生态型渔具渔法研究。E-mail：j-zhang@shou.edu.cn

Lag effect of climate change on CPUE of Thunnus albacares and Katsuwonus pelamis in the western and central Pacific Ocean purse seine fishery: An LSTM-Based study

Jian Zhang¹^,²^,³^,⁴, Houcheng Song¹, Wenjun Liu¹, Jiangao Shi⁵

Affiliations

1. College of Marine Living Resource Sciences and Management, Shanghai Ocean University, Shanghai 201306, China

2. National Engineering Research Centre for Oceanic Fisheries, Shanghai Ocean University, Shanghai 201306, China

3. Key Laboratory of Sustainable Exploitation of Oceanic Fisheries Resources, Ministry of Education, Shanghai Ocean University, Shanghai 201306, China

4. Key Laboratory of Ocean Fisheries Development, Ministry of Agriculture and Rural Affairs, Shanghai Ocean University, Shanghai 201306, China

5. East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai 200090, China

出版时间: 2024-07-31 doi: 10.12284/hyxb2024080

文章导航

摘要

收起

黄鳍金枪鱼（Thunnus albacares）和鲣（Katsuwonus pelamis）是大洋性高度洄游物种，也是全球大洋性渔业的主要捕捞对象，其种群分布和资源密度容易受气候变化所引起的海洋环境变化影响，且存在响应滞后。为了探索气候变化对中西太平洋海域（WCPO）低龄黄鳍金枪鱼和鲣群体影响及滞后效应，本研究基于长短期记忆神经网络(LSTM)分析了海洋尼诺指数（ONI）对1982年至2021年间WCPO围网黄鳍金枪鱼和鲣单位捕捞努力量渔获量（CPUE）的影响，利用不同时间步长模拟不同滞后期（0～12个月）下CPUE对ONI响应。结果表明：LSTM适用于对黄鳍金枪鱼和鲣等大洋性种群资源密度与ONI等环境因素间滞后效应的分析；WCPO赤道南北不同海域围网黄鳍金枪鱼和鲣CPUE对ONI的响应存在滞后，且不同海域的最佳滞后期均为12个月；最佳滞后期与渔获群体年龄相当，表明WCPO黄鳍金枪鱼和鲣的繁殖能力或幼鱼存活率易受到气候变化及其引起的海洋环境变动影响，表现出时长为捕捞年龄的滞后时间。研究方法与结果为后续开展WCPO关键物种群体分布研究提供了资源变动机制上的新思路。

关键词

黄鳍金枪鱼 / 鲣 / 海洋尼诺指数 / 滞后效应 / LSTM / 中西太平洋

Abstract

收起

Yellowfin tuna (Thunnus albacares) and skipjack tuna (Katsuwonus pelamis) are pelagic and highly migratory species, serving as primary targets in global pelagic fisheries. Their population distribution and abundance are susceptible to the impacts of climate-induced changes in the marine environment, exhibiting a response lag. In order to explore the influence of climate change on the juvenile populations of yellowfin tuna and skipjack tuna in the western and central Pacific Ocean (WCPO) and the associated lag effects, this study, based on Long Short-Term Memory (LSTM) neural networks, analyzed the impact of the Oceanic Niño index (ONI) on the Catch per Unit Effort (CPUE) of yellowfin tuna and skipjack tuna in the WCPO purse seine fishery from 1982 to 2021. Different time step lengths were employed to simulate the lag effects (0−12 months) of CPUE response to ONI. The results indicate LSTM is a suitable tool for analyzing the lag effects of relationship between the abundance of pelagic species, such as yellowfin tuna and skipjack tuna, and environmental factors like ONI. In the WCPO regions north and south of the equator, there exists a time lag in the response of juvenile yellowfin tuna and skipjack tuna CPUE to ONI, with the optimal lag period being 12 months for each region. The correspondence of the optimal lag period with the age of the harvested population (nearly 1 year) suggests that the reproductive capacity or survival rate of juvenile yellowfin tuna and skipjack tuna is influenced by climate change and the resulting changes in the marine environment. The research methodology and results provide new insights for subsequent studies in analyzing the stock dynamics and distribution of key species in the WCPO.

Key words

Thunnus albacares / Katsuwonus pelamis / Oceanic Niño index / lag effect / LSTM / western and central Pacific Ocean

引用本文

张健, 宋厚成, 刘文俊, 石建高. 基于LSTM的气候变化对中西太平洋围网黄鳍金枪鱼和鲣CPUE影响的滞后效应. 海洋学报, 2024 , 46 (7) : 62 -72 . DOI: 10.12284/hyxb2024080

Jian Zhang, Houcheng Song, Wenjun Liu, Jiangao Shi. Lag effect of climate change on CPUE of Thunnus albacares and Katsuwonus pelamis in the western and central Pacific Ocean purse seine fishery: An LSTM-Based study[J]. Haiyang Xuebao, 2024 , 46 (7) : 62 -72 . DOI: 10.12284/hyxb2024080

正文

收起

1 引言

收起

黄鳍金枪鱼（Thunnus albacares）和鲣（Katsuwonus pelamis）广泛分布于全球热带和亚热带的中上层水域，在全球各大洋生态系统中扮演着不可或缺的角色^[1–3]，也是全球大洋性渔业的主要捕捞对象^[4–5]，年产量分别达到157万t和283万t^[6]。黄鳍金枪鱼和鲣都具有生长快、高度洄游、产卵期长等生物学特性^[7–8]。黄鳍金枪鱼和鲣的种群分布和资源密度对海洋环境变动的响应敏感^[9–13]，海洋环境变化不仅会影响这些群体的摄食、生长、发育和繁殖等行为^[9,14–18]，同时也会影响其适宜栖息地的水平和垂直分布^[19–20]，从而引发一系列复杂、多层次的生态效应^[3]。

气候变化所驱动的海洋环境变化对大洋性种群动态的影响在时间上会呈现滞后效应^[21–22]。在海洋生态系统中，气候变化通过直接影响或自下而上的生态过程改变上层捕食者的行为和分布^[23–24]。尽管黄鳍金枪鱼和鲣具有高度的生态适应性^[25]，但在面对环境变动时仍需要时间来调整迁徙和捕食等行为^[26]，同时通过寻找适宜的产卵场、调整产卵季节和频率等应对行为以适应新的生态条件，确保群体在生态系统中的相对稳定性^[3]，表现为对海洋环境变动的响应存在滞后^[27]。深入了解环境变动对黄鳍金枪鱼和鲣群体影响的滞后效应，对于种群资源养护、稳定大洋生态系统以及实现渔业可持续发展具有重要的理论和实践价值。

气候变化对热带金枪鱼种群影响滞后效应已得到了关注，但大多研究以成鱼群体（延绳钓渔获）为目标，探索较大时间尺度（常以年为单位）上的滞后效应^[9,28–30]。黄鳍金枪鱼和鲣幼鱼群体具有集群性更强，栖息水层更浅、对环境的适应阈值较低、敏感性更强，游泳能力较弱以及难以突破温跃层等海洋物理屏障的特点，群体在栖息地（尤其是垂直方向）的选择上更为局促^[19]，对环境变化的响应可能更加直接^[15]。中西太平洋（Western and Central Pacific Ocean, WCPO）金枪鱼围网以低龄黄鳍金枪鱼和鲣为目标种类^[15]，探索该渔业单位捕捞努力量的渔获量（Catch Per Unit Effort, CPUE）时空分布对气候指数的响应可以在一定程度上解释低龄群体对气候变化的响应及滞后机制。

长短期记忆（Long Short-Term Memory, LSTM）解决了循环神经网络（Recurrent Neural Network, RNN）长延迟和长间隔的时间序列问题^[31]。在渔业科学研究中，Jiao^[32]利用LSTM分析了苏格兰附近海域大西洋鲱（Clupea harengus）和大西洋鲭（Scomber scombrus）群体响应海表温变化的洄游路线；Cavieses Núñez等^[33]认为LSTM适用于预测数据贫乏的小规模渔业；Xu等^[34]基于LSTM比较了不同空间分辨率对长鳍金枪鱼（T. alalunga）CPUE预测精度的影响。不仅如此，LSTM网络结构还能通过链接相关输入事件之间的时滞，检测不同时间序列间的滞后效应^[31,35]。

海洋尼诺指数（Oceanic Niño Index，ONI）提供了对于热带太平洋海温异常的评估，是用于描述ENSO事件的常见指数之一^[36–37]。本研究旨在基于LSTM，分析1982年—2021年WCPO赤道南北不同海域围网黄鳍金枪鱼和鲣CPUE对ONI的响应机制，一方面探究LSTM在气候变化对海洋生物种群动态影响滞后效应分析中的适用性，另一方面探索在较小时间尺度（月）上ONI对低龄黄鳍金枪鱼和鲣群体影响的滞后机制，以期为WCPO金枪鱼种群养护与合理开发提供科学依据。

2 材料与方法

收起

2.1 数据来源

2.1.1 渔业数据

WCPO围网黄鳍金枪鱼和鲣的捕捞渔业数据取自中西太平洋渔业委员会（Western & Central Pacific Fisheries Commission, WCPFC）公共领域渔获量和努力量的综合数据（https://www.wcpfc.int/public-domain/）。选取的数据的时间跨度为1982年至2021年，分辨率为月；空间范围为纬度45°N至55°S和经度105°E至135°W海域。因为WCPO围网作业范围主要涵盖了西太平洋暖池（主要分布在赤道以北）和群岛深海盆地（赤道以南）这两个具有不同生态地理特征的区域^[38]，且这两个区域在海洋物理条件和生态系统结构与功能方面均呈现出显著差异^[39]，所以将WCPO海域划分为赤道以南和赤道以北的两个区域，分别进行时间序列建模分析可以更全面地揭示大尺度气候变化对黄鳍金枪鱼和鲣种群时空动态的影响。

2.1.2 气候数据

ONI数据来自于美国国家海洋和大气管理局（National Oceanic and Atmospheric Administration, NOAA，https://origin.cpc.ncep.noaa.gov/products/analysis_monitoring/ensostuff/ONI_v5.php）。分别以ONI > 0.5和 < −0.5作为厄尔尼诺和拉尼娜现象出现的判定条件，而−0.5 < ONI < 0.5作为中性现象判定条件^[36–37]。

2.2 研究方法

2.2.1 CPUE计算

以网次渔获质量作为围网CPUE单位，不同时间下赤道南北海域的CPUE为

(1)

$ {\mathrm{CPUE}}_{t,z}=\frac{\displaystyle\sum {C}_{t,z}}{\displaystyle\sum {E}_{t,z}}， $

式中，

$\displaystyle \sum {C}_{t,z} $

为t时间内不同海域的总渔获产量（单位t）；

$\displaystyle \sum {E}_{t,z} $

为对应t时间不同海域的总作业网次数（单位net）。

2.2.2 LSTM建模

LSTM使用门结构来控制单元的状态。门结构包括输入门、遗忘门和输出门；输入门确定向单元添加多少信息；遗忘门控制着单元中丢失的信息；输出门决定最终输出值（图1）^[35]，其中

遗忘门：

(2)

$ {f}_{t}=\sigma \left({W}_{f}{h}_{t-1}+{U}_{f}{X}_{t}+{b}_{f}\right)， $

式中，f_t是时间t遗忘门的输出，σ是激活函数，W是模型输入连接的权重，U是模型循环连接的权重，h_t是时间t的输出，X_t是时间t的输入，b是模型偏差。

输入门：

(3)

$ {i}_{t}=\sigma \left({W}_{i}{h}_{t-1}+{U}_{i}{X}_{t}+{b}_{i}\right)， $

(4)

$ {\hat{c}}_{t}=\mathrm{tanh}\left({W}_{\hat{c}}{h}_{t-1}+{U}_{\hat{c}}{X}_{t}+{b}_{\hat{c}}\right)， $

式中：i_t是时间t输入门的输出，h_t是单元输出向量，

$ {\hat{c}}_{t} $

为候选门。

单元：

(5)

$ {C}_{t}={C}_{t-1}\odot {f}_{t}+{i}_{t}\odot \hat{c}_t ，$

式中，C_t是时间t的单元状态。

输出门：

(6)

$ {o}_{t}=\sigma \left({W}_{o}{h}_{t-1}+{U}_{0}{X}_{t}+{b}_{0}\right) ，$

(7)

$ {h}_{t}={o}_{t}\odot \mathrm{tanh}\left({C}_{t}\right)， $

式中，o_t是时间t时输出门的输出。

基于LSTM构建黄鳍金枪鱼和鲣CPUE对ONI的响应预测模型，即将历史特征数据和当前特征数据作为输入，以未来某一时刻的CPUE特征数据作为输出。通过训练网络与实际观测值进行对比，构建历史CPUE与未来CPUE之间的映射关系，以实现对未来CPUE的估算和预测。本研究将ONI作为影响CPUE的一项特征数据,将连续n个时刻的黄鳍金枪鱼和鲣的CPUE特征数据：{ONI(t − n + 1), ··· , ONI(t − 1), ONI(t)}作为网络输入，n对应输入层的滞后时间大小；将t + 1时刻黄鳍金枪鱼和鲣的CPUE表征数据：CPEU(t + 1)作为输出，最终实现预测。黄鳍金枪鱼和鲣CPUE预测模型的表达式为

(8)

$ {\mathrm{CPUE}}(t + 1) = F({{\mathrm{ONI}}(t - n + 1),\cdots, {\mathrm{ONI}}(t - 1), {\mathrm{ONI}}(t)}) .$

2.2.3 滞后时间选择

在LSTM中，时间步长决定了网络在对应时间间隔上观察和学习的信息，通过特定时间步长设置可以分析对应特征数据的时滞效应^[40]。此项研究中，笔者通过设置不同步长以模拟黄鳍金枪鱼和鲣CPUE在不同滞后时间下对ONI的响应。相关研究发现，金枪鱼群体对气候变化响应的滞后可能与群体年龄有关^[27,30,41]。作为WCPO围网的目标群体，黄鳍金枪鱼和鲣渔获群体上岸体长主要集中在35～70 cm范围，年龄主要分布在1龄以下^[3,42]，因此选择0−12个月作为作为滞后时间范围。

2.2.4 模型性能评价指标

将匹配后的ONI 作为训练参数，将研究海域内各月对应的CPUE 值作为预测参数，以数据集90%的数据用作训练集，5%用作验证集，剩余5%作为测试集以检验模型预测，并在迭代中获得模型预测误差。当损失值不随迭代次数的增加而变化时，迭代结束，得到迭代次数与损失值的变化关系图。使用平均绝对误差（Mean Absolute Error, MAE）、均方根误差（Root Mean Square Error, RMSE）以及平均绝对百分比误差（Mean Arctangent Absolute Percentage Error, MAPE）等3个指标评价不同滞后期下的模型对黄鳍金枪鱼和鲣月度CPUE的拟合优劣性^[43]。MAE是实际值和拟合值的平均误差, MAE结果越小，模型准确度越高^[44]；RMSE是度量拟合值与真实值的偏离程度，用以反映模型的稳定程度，RMSE越小，模型越稳定^[45]；MAPE通常用作回归问题和模型评估中的损失函数，MAPE越小，模型准确度越高^[46]。MAE、RMSE和MAPE的计算如下：

(9)

$ {\mathrm{MAE}}=\frac{1}{N}\sum _{i=1}^{N}|{X}_{i}-{X}_{i}'|， $

(10)

$ {\mathrm{RMSE}}=\sqrt{\frac{1}{N}\sum _{i=1}^{N}|{X}_{i}-{X}_{i}'|^{2}}， $

(11)

$ {\mathrm{MAPE}}=\frac{1}{N}\sum _{i=1}^{N}\left|\frac{{X}_{i}'-{X}_{i}}{{X}_{i}'}\right|， $

式中，N表示CPUE的总数量，

$ {X}_{i} $

表示拟合值，

$ {X}_{i}' $

表示实际值。

使用软件Python 3.9.13及软件包pandas 1.4.4，matplotlib 3.5.2，sklearn 1.0.2，tensorflow 2.10.1，keras 2.10.0，numpy 1.21.5等完成模型的构建与实现。

3 结果

收起

3.1 黄鳍金枪鱼、鲣CPUE和ONI的时序特征

1982−2021年WCPO围网黄鳍金枪鱼和鲣月度CPUE以及ONI时序分布特征及变化如图2所示，数据指标如表1所示。从图中可以看出，赤道南北海域黄鳍金枪鱼和鲣月度CPUE的时序波动特征存在一定差异，赤道以北海域CPUE波动总体小于赤道以南海域；不同海域黄鳍金枪鱼和鲣CPUE时序呈现出较大差异，赤道以南海域CPUE呈现出随时间增加且显著高于赤道以北海域的趋势。

3.2 潜在滞后期

基于LSTM 的不同滞后时间的黄鳍金枪鱼和鲣CPUE对ONI的响应预测误差结果如表2所示。不难发现，无论赤道南北，滞后时间为12个月的预测效果均为最好，即WCPO黄鳍金枪鱼和鲣CPUE对ONI的响应存在12个月的潜在滞后期。

3.3 LSTM模型稳定性检验

滞后时间为12个月的训练集与验证集数据输入LSTM 预测进行迭代，迭代次数与损失值统计如图3所示。由图3可得，时间步长为12的数据集在LSTM 中均未出现明显的欠拟合和过拟合的情况，预测集与训练集整体偏于稳定。相比较其他时间步长，滞后时间为12个月的模型拟合效果最好，模型复杂度最低，在一定程度上提高了模型收敛速度，同时降低了波动性。

3.4 LSTM模型预测评价

选取2020年黄鳍金枪鱼和鲣CPUE作为验证集，实际CPUE和预测CPUE分布如图4所示。总体上，滞后时间为12个月的黄鳍金枪鱼和鲣的预测CPUE与实际CPUE基本一致，表明模型具有良好的预测效果。

4 讨论

收起

4.1 黄鳍金枪鱼、鲣CPUE时序区域差异

近些年，黄鳍金枪鱼和鲣在赤道以南海域的CPUE要显著高于赤道以北海域，这与Erauskin-Extramiana等^[2]的研究结果一致∶在赤道以北海域温跃层分别随着厄尔尼诺和拉尼娜的到来而压缩或扩张，从而改变黄鳍金枪鱼和鲣的栖息空间^[10,47]，导致围网渔业资源的变动。而赤道以南海域群岛广泛分布，厄尔尼诺对黄鳍金枪鱼和鲣种群的直接影响被干扰和削弱^[39]，所以两种群在渔业产量上的波动不明显。考虑到近20年厄尔尼诺在WCPO的影响更为广泛，无论是渔业资源本身的变动还是渔业活动对这种变动所做出的反应，最后呈现出黄鳍金枪鱼和鲣CPUE南多北少的现象。尽管WCPO黄鳍金枪鱼和鲣群体分布与资源密度在赤道南北海域出现了差异，但研究结果显示这些群体对ONI响应存在滞后、且滞后期基本一致，这表明滞后机制可能是一致的。

4.2 潜在滞后期的机制探索

ONI作为一种ENSO的检测指标，可以表述热带太平洋中部当期海温的历史区位^[36–37]。从黄鳍金枪鱼和鲣的空间分布而言，厄尔尼诺事件（拉尼娜事件）期间赤道暖池区的温跃层上升（下降）与海水含氧量减少（增加）的共同作用下，缩小（扩展）了黄鳍金枪鱼和鲣的活动空间，增加（降低）了围网捕获的效率^[48–50]，加之渔业活动需要时间对渔业资源的变动改变捕捞策略^[51]，使得ONI对黄鳍金枪鱼和鲣CPUE的影响出现了滞后效应。然而仅气候变化对群体空间分布而言，渔业CPUE对ONI等气候指数响应的滞后大多集中在3月^[28]，并不能解释本研究中滞后12个月的结果。

现有研究表明，大洋性高度洄游的鱼类对气候变化响应的滞后通常与其年龄有关。Lehodey等^[15]认为鲣等生活史较短的金枪鱼类通过捕获率和捕获大小的频率更容易检测到环境变化对其资源密度的影响；Hou等^[27]发现WCPO海域鲣对大西洋多年代际振荡（Atlantic Multidecadal Oscillation, AMO）响应的滞后期与其成熟年龄有着密切的关系；Singh等^[41]发现南太平洋海域长鳍金枪鱼产卵和早期生命阶段受太平洋年代际振荡（Pacific Decadal Oscillation, PDO）的影响会在其捕捞年龄进行体现；Domokos^[30]发现ENSO对太平洋海域的黄鳍和大眼金枪鱼（T. obesus）CPUE的正向影响可以延续至渔获的捕捞年龄。群体对气候变化的响应滞后与群体年龄相一致的事实表明这一响应可能与群体的繁殖行为和幼体的存活存在紧密的联系^[8,52–53]，滞后最终以年龄的形式体现在渔业CPUE上^[9,54]。

WCPO黄鳍金枪鱼和鲣群体全年分批产卵^[55–56]，产卵场通常是SST超过24℃的海域^[57–58]，这说明ONI变化带来的SST变化会影响群体繁殖行为。黄鳍金枪鱼和鲣在繁殖期所需的能量主要来自食物摄入，而不是积累的能量储备^[59–60]，在厄尔尼诺期间，WCPO浮游动物聚集，黄鳍金枪鱼和鲣的产卵场会随着赤道暖池的扩大而扩大^[53]，有利于金枪鱼生存和幼体发育，而推测在金枪鱼幼鱼群体会在6～12个月后补充至渔业的可捕群体^[13]，WCPO金枪鱼资源密度上升^[53,61]；但随着金枪鱼群体中的个体增多，种内食物竞争加剧，密度效应会对个体的生殖激素产生负面影响，可能会导致资源量的下降^[62]。此外，黄鳍金枪鱼和鲣仔幼鱼的自然死亡率远高于成鱼^[63–64]，仔幼鱼在孵化后的2～4 d 就开始进行摄食^[65–66]，幼体完成消化系统发育并开始摄食的时间与海面温度呈正相关^[67]；初级生产力的变动与ENSO的变化同时发生^[54]，较高的初级生产力可以减小黄鳍金枪鱼和鲣幼体的死亡率进而对其初期的生长有着积极的影响^[11,54]，幼鱼经过12个月左右的快速生长达到围网捕获的体长范围^[3,42]。因此，WCPO金枪鱼群体繁殖能力或幼鱼的存活率会受气候振荡影响，导致了群体补充量的波动，这种温度上影响在滞后时间上多以渔获捕获年龄的方式得以体现。同时Sardenne等^[68]通过稳定同位素和中性脂肪酸的研究认为较小个体的金枪鱼群体之间存在种群共栖的可能性，印证了黄鳍金枪鱼和鲣对ONI存在相同滞后时间的研究结论。

4.3 LSTM模型在滞后研究中的优势

在渔业中对滞后的研究主要用到统计学方法^[9,69–70]和神经网络^[71–72]。但是主流的统计学方法中的自回归移动平均模型(Autoregressive Integrated Moving Average Model, ARIMA)是基于线性关系的假设，而许多时间序列数据可能包含非线性关系，这意味着ARIMA可能无法很好地捕捉非线性趋势和模式^[73]。尽管需要花费大量的时间来训练模型且需要大量的数据样本^[74]，但是对于复杂的非线性模式，尤其是在大规模、高维度数据集上，神经网络中的LSTM可能更具优势^[75]。本研究中LSTM的计算出的结果仅仅反映了数据本身的潜在模式，且结果显示LSTM适用于对黄鳍金枪鱼和鲣等大洋性种群资源密度与ONI等环境因素间滞后效应的分析。在这一点上，LSTM模型比传统的基于经验的模型更加客观。

5 结论

收起

本研究基于LSTM分析了不同滞后期数下ONI对WCPO赤道南北海域围网黄鳍金枪鱼和鲣CPUE影响的滞后效应，发现了不同海域低龄黄鳍金枪鱼和鲣群体对ONI的响应存在滞后，且滞后期为12个月时响应最为精准。基于上述研究，可以得出以下结论：第一，调整ONI的最大滞后期数对黄鳍金枪鱼CPUE和鲣CPUE的滞后响应至关重要；其次，LSTM模型可用于检验黄鳍金枪鱼CPUE和鲣CPUE对ONI的滞后效应，并能做出短时间的预测，为全面地理解气候变化所引起的海洋环境变化对黄鳍金枪鱼和鲣等生态系统关键物种的影响提供了重要线索，为未来制定有效的种群养护和渔业管理策略提供了有益的参考。

然而在本研究中仅只考虑了ONI对黄鳍金枪鱼CPUE和鲣CPUE的滞后效应，在之后的研究中应纳入其他环境因子，进一步研究环境气候对黄鳍金枪鱼CPUE和鲣CPUE的滞后效应。

基金

收起

农业农村部全球重要鱼种资源动态监测评估项目、国家重点研发计划项目(2020YFD0900803)

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

Houssard P, Lorrain A, Tremblay-Boyer L, et al. Trophic position increases with thermocline depth in yellowfin and bigeye tuna across the Western and Central Pacific Ocean[J]. Progress in Oceanography, 2017, 154: 49−63.

Erauskin-Extramiana M, Arrizabalaga H, Hobday A J, et al. Large-scale distribution of tuna species in a warming ocean[J]. Global Change Biology, 2019, 25(6): 2043−2060.

Artetxe-Arrate I, Fraile I, Marsac F, et al. A review of the fisheries, life history and stock structure of tropical tuna (skipjack Katsuwonus pelamis, yellowfin Thunnus albacares and bigeye Thunnus obesus) in the Indian Ocean[J]. Advances in Marine Biology, 2021, 88: 39−89.

Nimit K, Masuluri N K, Berger A M, et al. Oceanographic preferences of yellowfin tuna (Thunnus albacares) in warm stratified oceans: a remote sensing approach[J]. International Journal of Remote Sensing, 2020, 41(15): 5785−5805.

Kim J, Na Hanna, Park Y G, et al. Potential predictability of skipjack tuna (Katsuwonus pelamis) catches in the Western Central Pacific[J]. Scientific Reports, 2020, 10(1): 3193.

Fao. The state of world fisheries and aquaculture 2022. Towards blue transformation[R]. Rome: Food and Agriculture Organization of the United Nations, 2022.

Monllor-Hurtado A, Pennino M G, Sanchez-Lizaso J L. Shift in tuna catches due to ocean warming[J]. PLoS One, 2017, 12(6): e0178196.

Murua H, Rodriguez-Marin E, Neilson J D, et al. Fast versus slow growing tuna species: age, growth, and implications for population dynamics and fisheries management[J]. Reviews in Fish Biology and Fisheries, 2017, 27(4): 733−773.

Wu Yanlun, Lan Kuowei, Tian Yongjun. Determining the effect of multiscale climate indices on the global yellowfin tuna (Thunnus albacares) population using a time series analysis[J]. Deep Sea Research Part II: Topical Studies in Oceanography, 2020, 175: 104808.

Zhou Weifeng, Hu Huijuan, Fan Wei, et al. Impact of abnormal climatic events on the CPUE of yellowfin tuna fishing in the central and western Pacific[J]. Sustainability, 2022, 14(3): 1217.

Fadhilah A, Leidonald R, Susetya I E, et al. Analysis of the relationship between the ENSO phenomenon, Net Primary Productivity and catches of yellowfin tuna in Sibolga Waters, Indonesia[J]. Biodiversitas Journal of Biological Diversity, 2022, 23(9): 4440−4447.

Miller K A. Climate variability and tropical tuna: management challenges for highly migratory fish stocks[J]. Marine Policy, 2007, 31(1): 56−70.

Lehodey P. The pelagic ecosystem of the tropical Pacific Ocean: dynamic spatial modelling and biological consequences of ENSO[J]. Progress in Oceanography, 2001, 49(1/4): 439−468.

Kim J, Na Hanna. Interannual variability of yellowfin tuna (Thunnus albacares) and bigeye tuna (Thunnus obesus) catches in the southwestern Tropical Indian Ocean and its relationship to climate variability[J]. Frontiers in Marine Science, 2022, 9: 857405.

Lehodey P, Bertrand A, Hobday A J, et al. ENSO impact on marine fisheries and ecosystems[M]//McPhaden M J, Santoso A, Cai Wenju. El Niño Southern Oscillation in a Changing Climate. Washington: American Geophysical Union, 2021: 429−451.

Langley A, Briand K, Kirby D S, et al. Influence of oceanographic variability on recruitment of yellowfin tuna (Thunnus albacares) in the western and central Pacific Ocean[J]. Canadian Journal of Fisheries and Aquatic Sciences, 2009, 66(9): 1462−1477.

Dueri S, Bopp L, Maury O. Projecting the impacts of climate change on skipjack tuna abundance and spatial distribution[J]. Global Change Biology, 2014, 20(3): 742−753.

Zainuddin M, Nelwan A, Farhum S A, et al. Characterizing potential fishing zone of Skipjack Tuna during the southeast monsoon in the Bone Bay-Flores Sea using remotely sensed oceanographic data[J]. International Journal of Geosciences, 2013, 4(1): 259−266.

Schaefer K M, Fuller D W, Block B A. Vertical movements and habitat utilization of skipjack (Katsuwonus pelamis), yellowfin (Thunnus albacares), and bigeye (Thunnus obesus) tunas in the equatorial eastern Pacific Ocean, ascertained through archival tag data[M]//Nielsen J L, Arrizabalaga H, Fragoso N, et al. Tagging and Tracking of Marine Animals with Electronic Devices. Dordrecht: Springer, 2009: 121−144.

Yen K W, Wang Guihua, Lu H J. Evaluating habitat suitability and relative abundance of skipjack (Katsuwonus pelamis) in the western and central Pacific during various El Niño events[J]. Ocean & Coastal Management, 2017, 139: 153−160.

Bell J D, Senina I, Adams T, et al. Pathways to sustaining tuna-dependent Pacific Island economies during climate change[J]. Nature Sustainability, 2021, 4(10): 900−910.

Salazar J E, Benavides I F, Cabrera C V P, et al. Generalized additive models with delayed effects and spatial autocorrelation patterns to improve the spatiotemporal prediction of the skipjack (Katsuwonus pelamis) distribution in the Colombian Pacific Ocean[J]. Regional Studies in Marine Science, 2021, 45: 101829.

Qiu Yongsong, Lin Zhaojin, Wang Yuezhong. Responses of fish production to fishing and climate variability in the northern South China Sea[J]. Progress in Oceanography, 2010, 85(3/4): 197−212.

Lan Kuowei, Wu Yanlun, Chen Luchi, et al. Effects of climate change in marine ecosystems based on the spatiotemporal age structure of top predators: a case study of bigeye tuna in the Pacific Ocean[J]. Frontiers in Marine Science, 2021, 8: 614594.

Brill R W, Dewar H, Graham J B. Basic concepts relevant to heat transfer in fishes, and their use in measuring the physiological thermoregulatory abilities of tunas[J]. Environmental Biology of Fishes, 1994, 40(2): 109−124.

Ménard F, Marsac F, Bellier E, et al. Climatic oscillations and tuna catch rates in the Indian Ocean: a wavelet approach to time series analysis[J]. Fisheries Oceanography, 2007, 16(1): 95−104.

Hou Xiangyun, Ma Shuyang, Tian Yongjun, et al. The effects of trans-basin climate variability on skipjack tuna in the northwest Pacific Ocean: causal and nonstationary[J]. Frontiers in Marine Science, 2022, 9: 895219.

Lu H J, Lee K T, Lin H L, et al. Spatio-temporal distribution of yellowfin tuna Thunnus albacares and bigeye tuna Thunnus obesus in the Tropical Pacific Ocean in relation to large-scale temperature fluctuation during ENSO episodes[J]. Fisheries Science, 2001, 67(6): 1046−1052.

Singh A A, Suzuki N, Sakuramoto K. Influence of climatic conditions on the time series fluctuation of yellowfin tuna Thunnus albacares in the south Pacific Ocean[J]. Open Journal of Marine Science, 2015, 5(3): 247−264.

Domokos R. Influence of El Niño-Southern Oscillation on bigeye and yellowfin tuna longline catch per unit effort in the equatorial Pacific[J]. Fisheries Oceanography, 2023, 32(6): 527−540.

Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735−1780.

Jiao Yuanjie. Prediction of fish migration based on LSTM model[C]//2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA). Shenyang: IEEE, 2021: 697−701.

Cavieses Núñez R A, Ojeda Ruiz de la Peña M Á, Flores Irigollen A, et al. Deep learning models for the prediction of small-scale fisheries catches: finfish fishery in the region of “Bahía Magadalena-Almejas”[J]. ICES Journal of Marine Science, 2018, 75(6): 2088−2096.

Xu Hui, Song Liming, Zhang Tianjiao, et al. 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[J]. Journal of Ocean University of China, 2023, 22(5): 1427−1438.

Gers F A, Schmidhuber J, Cummins F. Learning to forget: continual prediction with LSTM[J]. Neural Computation, 2000, 12(10): 2451−2471.

Prasetyo Y, Nabilah F. Pattern analysis of El Nino and La Nina phenomenon based on sea surface temperature (SST) and rainfall intensity using oceanic Nino Index (ONI) in West Java Area[J]. IOP Conference Series: Earth and Environmental Science, 2017, 98: 012041.

Kiem A S, Verdon-Kidd D C. Climatic drivers of Victorian streamflow: is ENSO the dominant influence?[J]. Australasian Journal of Water Resources, 2009, 13(1): 17−29.

Longhurst A R. Ecological Geography of the Sea[M]. 2nd ed. Burlington: Academic Press, 2010.

Le Borgne R, Allain V, Griffiths S P, et al. Vulnerability of open ocean food webs in the tropical Pacific to climate change[M]//Bell J D, Johnson J E, Hobday A J. Vulnerability of Tropical Pacific Fisheries and Aquaculture to Climate Change. New Caledonia: Secretariat of the Pacific Community, 2011: 189−250.

Mazumder A N, Rashid H A, Mohsenin T. An energy-efficient low power LSTM processor for human activity monitoring[C]//2020 IEEE 33rd International System-on-Chip Conference (SOCC). Las Vegas: IEEE, 2020: 54−59.

Singh A A, Sakuramoto K, Suzuki N. Impact of climatic factors on albacore tuna Thunnus alalunga in the south Pacific Ocean[J]. American Journal of Climate Change, 2015, 4(4): 295−312.

Hampton J, Fournier D A. A spatially disaggregated, length-based, age-structured population model of yellowfin tuna (Thunnus albacares) in the western and central Pacific Ocean[J]. Marine and Freshwater Research, 2001, 52(7): 937−963.

Foster R G, Roenneberg T. Human responses to the geophysical daily, annual and lunar cycles[J]. Current Biology, 2008, 18(17): R784−R794.

Hodson T O. Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not[J]. Geoscientific Model Development, 2022, 15(14): 5481−5487.

Chai Tianfeng, Draxler R R. Root mean square error (RMSE) or mean absolute error (MAE)?–Arguments against avoiding RMSE in the literature[J]. Geoscientific Model Development, 2014, 7(3): 1247−1250.

De Myttenaere A, Golden B, Le Grand B, et al. Mean absolute percentage error for regression models[J]. Neurocomputing, 2016, 192: 38−48.

Reglero P, Tittensor D P, Álvarez-Berastegui D, et al. Worldwide distributions of tuna larvae: revisiting hypotheses on environmental requirements for spawning habitats[J]. Marine Ecology Progress Series, 2014, 501: 207−224.

Leung S, Thompson L, McPhaden M J, et al. ENSO drives near-surface oxygen and vertical habitat variability in the tropical Pacific[J]. Environmental Research Letters, 2019, 14(6): 064020.

Yen K W, Lu H J, Chang Yi, et al. Using remote-sensing data to detect habitat suitability for yellowfin tuna in the western and central Pacific Ocean[J]. International Journal of Remote Sensing, 2012, 33(23): 7507−7522.

Lehodey P, Hampton J, Brill R W, et al. Vulnerability of oceanic fisheries in the tropical Pacific to climate change[M]//Bell J D, Johnson J E, Hobday A J. Vulnerability of Tropical Pacific Fisheries and Aquaculture to Climate Change. New Caledonia: Secretariat of the Pacific Community, 2011: 433−492.

Peña-Torres J, Dresdner J, Vasquez F. El Niño and fishing location decisions: the Chilean straddling jack mackerel fishery[J]. Marine Resource Economics, 2017, 32(3): 249−275.

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.

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.

Yen K W, Lu H J. Spatial-temporal variations in primary productivity and population dynamics of skipjack tuna Katsuwonus pelamis in the western and central Pacific Ocean[J]. Fisheries Science, 2016, 82(4): 563−571.

Shi Xiaofei, Zhang Jian, Wang Xiao, et al. Reproductive biology of yellowfin tuna (Thunnus albacares) in tropical western and central Pacific Ocean[J]. Fishes, 2022, 7(4): 162.

Ohashi S, Aoki Y, Tanaka F, et al. Reproductive traits of female skipjack tuna Katsuwonus pelamis in the western central Pacific Ocean (WCPO)[C]//15th Regular Session of the Scientific Committee. Pohnpei, Micronesia: WCPFC, 2019.

Schaefer K M, Fuller D W, Block B A. Movements, behavior, and habitat utilization of yellowfin tuna (Thunnus albacares) in the northeastern Pacific Ocean, ascertained through archival tag data[J]. Marine Biology, 2007, 152(3): 503−525.

Ashida H. Spatial and temporal differences in the reproductive traits of skipjack tuna Katsuwonus pelamis between the subtropical and temperate western Pacific Ocean[J]. Fisheries Research, 2020, 221: 105352.

Grande M, Murua H, Zudaire I, et al. Energy allocation strategy of skipjack tuna Katsuwonus pelamis during their reproductive cycle[J]. Journal of Fish Biology, 2016, 89(5): 2434−2448.

Zudaire I, Murua H, Grande M, et al. Variations in the diet and stable isotope ratios during the ovarian development of female yellowfin tuna (Thunnus albacares) in the Western Indian Ocean[J]. Marine Biology, 2015, 162(12): 2363−2377.

Chan H L. How climate change and climate variability affected trip distance of a commercial fishery[J]. PLoS Climate, 2023, 2(2): e0000143.

Kim E, Moon D, Kim S. Effects of climate-induced variation in the catch distribution and biological characteristics of skipjack tuna Katsuwonus pelamis in the western and central Pacific Ocean[J]. Korean Journal of Fisheries and Aquatic Sciences, 2015, 48(4): 489−497.

Bigelow K, Hampton J, Fournier D. Preliminary application of the MULTIFAN-CL model to skipjack tuna in the tropical WCPO[C]//13th Meeting of the Standing Committee on Tuna and Billfish. Noumea: SPC, 2000.

Hoyle S D, Williams A J, Minte-Vera C V, et al. Approaches for estimating natural mortality in tuna stock assessments: application to global yellowfin tuna stocks[J]. Fisheries Research, 2023, 257: 106498.

Matsumoto W M, Skillman R A, Dizon A E. Synopsis of Biological Data on Skipjack Tuna, Katsuwonus Pelamis[M]. Seattle: U. S. Department of Commerce, National Oceanic and Atmospheric Administration, National Marine Fisheries Services, 1984.

Kaji T, Tanaka M, Oka M, et al. Growth and morphological development of laboratory-reared yellowfin tuna Thunnus albacares larvae and early juveniles, with special emphasis on the digestive system[J]. Fisheries Science, 1999, 65(5): 700−707.

Ashida H, Watanabe K, Tanabe T. Growth variability of juvenile skipjack tuna (Katsuwonus pelamis) in the western and central Pacific Ocean[J]. Environmental Biology of Fishes, 2018, 101(3): 429−439.

Sardenne F, Bodin N, Chassot E, et al. Trophic niches of sympatric tropical tuna in the western Indian Ocean inferred by stable isotopes and neutral fatty acids[J]. Progress in Oceanography, 2016, 146: 75−88.

Benavides I F, Romero-Leiton J P, Santacruz M, et al. Applying seasonal time series modeling to forecast marine fishery landings for six species in the Colombian Pacific Ocean[J]. Regional Studies in Marine Science, 2022, 56: 102716.

LEE B, SUHARTONO S, LIM A, et al. Forecasting world tuna catches with ARIMA-spline and ARIMA-neural networks models[J]. Walailak Journal of Science and Technology, 2021, 18(17): 9726.

Cavieses-Núñez R, Ojeda-Ruiz M A, Flores-Irigollen A, et al. Focused small-scale fisheries as complex systems using deep learning models[J]. Latin American Journal of Aquatic Research, 2021, 49(2): 342−353.

Nagano K, Yamamura O. Predicting catch of Giant Pacific octopus Enteroctopus dofleini in the Tsugaru Strait using a machine learning approach[J]. Fisheries Research, 2023, 261: 106622.

Siami-Namini S, Tavakoli N, Namin A S. A comparison of ARIMA and LSTM in forecasting time series[C]//2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA). Orlando: IEEE, 2018: 1394−1401.

Qian Fei, Chen Xianfu. Stock prediction based on LSTM under different stability[C]//2019 IEEE 4th International Conference on Cloud Computing and Big Data Analysis (ICCCBDA). Chengdu: IEEE, 2019: 483−486.

Zhao J, Huang F, Lv J, et al. Do RNN and LSTM have long memory?[C]// Daumé III H, Singh A. Proceedings of the 37th International Conference on Machine Learning. PMLR, 2020: 11365−11375.

2024年第46卷第7期

PDF下载

180

引用本文

BibTeX

文章信息

doi: 10.12284/hyxb2024080

接收时间：2024-02-03
首发时间：2025-11-26
出版时间：2024-07-31

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2024-02-03
修回日期：2024-04-03

基金

农业农村部全球重要鱼种资源动态监测评估项目、国家重点研发计划项目(2020YFD0900803)

作者信息

1.上海海洋大学海洋生物资源与管理学院，上海 201306

2.上海海洋大学国家远洋渔业工程技术研究中心，上海 201306

3.上海海洋大学大洋渔业资源可持续开发教育部重点实验室，上海 201306

4.上海海洋大学农业农村部大洋渔业开发重点实验室，上海 2013064

5.中国水产科学研究院东海水产研究所，上海 200090

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/hyxb/CN/10.12284/hyxb2024080

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT

项目	海域	Min	P₂₅	P₅₀	P₇₅	Max	平均
黄鳍金枪鱼CPUE	赤道以北	0.779	2.750	4.823	6.914	18.208	5.118
赤道以南	0	6.129	7.489	9.321	16.460	7.735
鲣CPUE	赤道以北	3.217	9.362	13.380	17.077	32.286	13.491
赤道以南	6.858	14.803	18.758	22.559	35.583	18.777
海洋尼诺指数	\	−1.870	−0.603	−0.050	0.510	2.710	0.016

项目

海域

Min

P₂₅

P₅₀

P₇₅

Max

平均

黄鳍金枪鱼CPUE

赤道以北

0.779

2.750

4.823

6.914

18.208

5.118

赤道以南

6.129

7.489

9.321

16.460

7.735

鲣CPUE

赤道以北

3.217

9.362

13.380

17.077

32.286

13.491

赤道以南

6.858

14.803

18.758

22.559

35.583

18.777

海洋尼诺指数

−1.870

−0.603

−0.050

0.510

2.710

0.016

滞后时间/月	黄鳍金枪鱼		鲣
0	9.90828	0.14917	0.15540		1.79009	0.10379	0.12012		3.28223	0.19211	0.23032		0.75190	0.14909	0.17050
1	2.97018	0.04652	0.06101	2.58407	0.15056	0.16129	2.56779	0.15519	0.18690	0.58860	0.13732	0.17983
2	3.52192	0.06414	0.06885	2.78081	0.14993	0.17108	2.32455	0.14219	0.16376	0.60977	0.12596	0.14845
3	9.52831	0.14418	0.14977	1.37389	0.09502	0.12549	3.84945	0.22736	0.26697	0.79580	0.17736	0.18951
4	7.90549	0.10914	0.12458	1.35588	0.08262	0.09750	5.67477	0.38144	0.39281	0.95240	0.21992	0.25508
5	4.71259	0.06653	0.07531	1.53034	0.08917	0.10222	5.84598	0.36893	0.39745	0.51162	0.10161	0.11268
6	4.69040	0.06422	0.07334	1.39996	0.07823	0.11137	5.46671	0.34900	0.37072	1.28165	0.28839	0.31291
7	6.63161	0.12643	0.13064	1.24703	0.07832	0.10089	5.51127	0.34509	0.37413	0.66225	0.14054	0.15561
8	5.21586	0.08945	0.09143	2.90610	0.16607	0.17832	7.08355	0.45903	0.48260	1.01102	0.21614	0.21883
9	6.85734	0.09821	0.10819	2.59891	0.14291	0.15865	3.05708	0.18717	0.21077	0.64069	0.14251	0.15294
10	9.78094	0.15027	0.15517	1.72018	0.11157	0.13687	4.22249	0.26537	0.28988	0.57465	0.12541	0.15013
11	5.93768	0.08297	0.09254	0.90011	0.06141	0.07853	2.54923	0.16213	0.19257	0.43067	0.09660	0.10529
12	2.53704	0.04456	0.05823	0.85169	0.05599	0.06346	1.01160	0.08631	0.12771	0.35689	0.07898	0.09953

滞后时间/月

黄鳍金枪鱼

鲣

赤道以北

赤道以南

赤道以北

赤道以南

MAPE

MAE

RMSE

MAPE

MAE

RMSE

MAPE

MAE

RMSE

MAPE

MAE

RMSE

9.90828

0.14917

0.15540

1.79009

0.10379

0.12012

3.28223

0.19211

0.23032

0.75190

0.14909

0.17050

2.97018

0.04652

0.06101

2.58407

0.15056

0.16129

2.56779

0.15519

0.18690

0.58860

0.13732

0.17983

3.52192

0.06414

0.06885

2.78081

0.14993

0.17108

2.32455

0.14219

0.16376

0.60977

0.12596

0.14845

9.52831

0.14418

0.14977

1.37389

0.09502

0.12549

3.84945

0.22736

0.26697

0.79580

0.17736

0.18951

7.90549

0.10914

0.12458

1.35588

0.08262

0.09750

5.67477

0.38144

0.39281

0.95240

0.21992

0.25508

4.71259

0.06653

0.07531

1.53034

0.08917

0.10222

5.84598

0.36893

0.39745

0.51162

0.10161

0.11268

4.69040

0.06422

0.07334

1.39996

0.07823

0.11137

5.46671

0.34900

0.37072

1.28165

0.28839

0.31291

6.63161

0.12643

0.13064

1.24703

0.07832

0.10089

5.51127

0.34509

0.37413

0.66225

0.14054

0.15561

5.21586

0.08945

0.09143

2.90610

0.16607

0.17832

7.08355

0.45903

0.48260

1.01102

0.21614

0.21883

6.85734

0.09821

0.10819

2.59891

0.14291

0.15865

3.05708

0.18717

0.21077

0.64069

0.14251

0.15294

9.78094

0.15027

0.15517

1.72018

0.11157

0.13687

4.22249

0.26537

0.28988

0.57465

0.12541

0.15013

5.93768

0.08297

0.09254

0.90011

0.06141

0.07853

2.54923

0.16213

0.19257

0.43067

0.09660

0.10529

2.53704

0.04456

0.05823

0.85169

0.05599

0.06346

1.01160

0.08631

0.12771

0.35689

0.07898

0.09953