基于最大熵和栖息地指数模型预测东、黄海日本鲭渔场分布

曹睿星; 官文江; 高峰; 贺伟伟

doi:10.12284/hyxb2023136

基于最大熵和栖息地指数模型预测东、黄海日本鲭渔场分布

doi: 10.12284/hyxb2023136

曹睿星^1,,
官文江^{1, 2},
高峰^{1, 3, ,},
贺伟伟¹

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教育部重点实验室，上海 201306
3.
上海海洋大学国家远洋渔业工程技术研究中心，上海 201306

基金项目: 国家自然科学基金（32072981）。

详细信息

作者简介:
曹睿星(1999-)，女，安徽省无为市人，研究方向为渔业资源评估与管理。E-mail：13955930469@163.com

通讯作者:
高峰，男，讲师，研究方向为渔业地理信息系统与渔业海图。E-mail：gaofeng@shou.edu.cn

中图分类号: P714⁺.5；S932.4
计量
- 文章访问数: 262
- HTML全文浏览量: 122
- PDF下载量: 42
- 被引次数: 0
出版历程
- 收稿日期: 2023-03-22
- 修回日期: 2023-06-26
- 网络出版日期: 2023-09-08
- 刊出日期: 2023-09-30

Prediction of chub mackerel fishing ground distribution in the East China Sea and Yellow Sea based on maximum entropy model and habitat suitability index model

Cao Ruixing^1
,,
Guan Wenjiang^{1, 2},
Gao Feng^{1, 3
, ,},
He Weiwei¹

1.
College of Marine Sciences, Shanghai Ocean University, Shanghai 201306, China
2.
The Key Laboratory of Sustainable Exploitation of Oceanic Fisheries Resources, Ministry of Education, Shanghai 201306, China
3.
National Distant-water Fisheries Engineering Research Center, Shanghai Ocean University, Shanghai 201306, China

摘要

摘要: 最大熵模型（Maximum Entropy Model，Maxent）和栖息地指数（Habitat Suitability Index，HSI）模型均广泛应用于渔情预报研究中。为比较两模型渔情预报效果以提升日本鲭（Scomber japonicus）资源的科学管理水平，本研究利用2003−2012年东、黄海日本鲭的渔业数据以及海表温度、海面高度、海表盐度、海表温度梯度等海洋环境数据，构建最大熵模型和HSI模型，以分析、比较两模型对东、黄海日本鲭栖息地的预测效果，并利用受试者工作特征（Receiver Operating Characteristic，ROC）曲线下面积（Area Under Curve，AUC）、模型预测的渔场概率与实际渔获量百分比之间的对应关系对两模型渔情预报效果进行了定量评价。结果表明：（1）最大熵模型预测的渔场发生高概率位置与捕捞位置基本重合，在无历史捕捞数据海域预测渔场发生的概率较低；HSI模型预测的高栖息地指数位置与捕捞位置部分重合，在无历史捕捞数据海域也可获得较高的栖息地指数，将非渔场预测为渔场的概率较高；（2）最大熵模型和HSI模型的月平均AUC值分别为0.95和0.66，故最大熵模型的预测结果相对较好；（3）使用HSI模型时，应在模型中加入非渔场数据，并加强对此类数据的收集，否则该类模型预报渔场时有扩大化的可能；使用最大熵模型时，必须提高渔业数据的空间覆盖率，否则无法全面反映渔场时空分布动态。本文研究结果可为提升东、黄海日本鲭渔情预报精度提供参考。
- 最大熵模型 /
- 栖息地指数模型 /
- 模型比较 /
- 日本鲭
Abstract: The maximum entropy model (Maxent) and habitat suitability index (HSI) model are widely used in fishery forecasting studies. To compare the forecasting performance of these two models on fishing grounds and improve the scientific management of chub mackerel (Scomber japonicus) resources, this study used the fishery data of chub mackerel in the East China Sea and Yellow Sea from 2003 to 2012, and marine environmental data, including sea surface temperature, sea surface height, sea surface salinity and sea surface temperature gradient, to construct the Maxent model and HSI model. The aim was to analyze and compare the effectiveness of these two models in predicting the habitat of chub mackerel in the East China Sea and Yellow Sea. The quantitative evaluation of the prediction performance of the two models was conducted using the area under curve (AUC) of the receiver operating characteristic (ROC), and the correspondence between the probability of fishing grounds predicted by the models and the percentage of the actual catches. The results showed that: (1) locations predicted by the maximum entropy model to have a high probability of fishing occurrence coincided with actual fishing locations. The probability of predicting fishery occurrence in the sea area without historical fishing data was lower. Locations predicted to have a high habitat index by the HSI model partially overlapped with actual fishing locations. A high habitat index was obtained in the sea area without historical fishing data. The probability of the HSI model predicting non-fishing grounds as fishing grounds was higher than that of the Maxent model; (2) the monthly average AUC values of the Maxent and HSI model were 0.95 and 0.66, respectively, indicating that the Maxent had relatively better predictive results; (3) when using the HSI model, non-fishing grounds data should be added to the model, and the collection of such data should be strengthened otherwise, there is a possibility of overestimation when such models forecast fishing grounds. When using the Maxent, the spatial coverage of fishery data must be improved otherwise, it cannot fully reflect the spatial and temporal distribution dynamics of the fishery. The results of this study provide a reference for improving the accuracy of forecasting for the chub mackerel fishery in the East China Sea and Yellow Sea.
- maximum entropy model /
- habitat suitability index model /
- model comparison /
- chub mackerel

HTML全文

图 1 基于Maxent预测的渔场分布概率与捕捞作业位置

Fig. 1 Distribution probability of fishing grounds and location of fishing operation predicted by maximum entropy model

下载: 全尺寸图片幻灯片

图 2 HSI模型预测的渔场分布概率与捕捞作业位置

Fig. 2 Distribution of habitat suitability index and locations of fishing operation predicted by the Habitat Suitability Index model

下载: 全尺寸图片幻灯片

图 3 栖息地指数模型和最大熵模型的ROC曲线

Fig. 3 ROC curve of habitat suitability index model and maximum entropy model

下载: 全尺寸图片幻灯片

图 4 实际作业渔获量百分比与两个模型预测渔场概率的关系

Fig. 4 Relationship between the percentage of total catch and the predicted probability of fishing grounds by two models

下载: 全尺寸图片幻灯片

表 1 利用AMM和GMM分别构建栖息地指数模型的作业次数比重的比较

Tab. 1 Comparison of the weight of the number of operations for constructing habitat index model using AMM and GMM respectively

HSI	7月作业次数比重/%		8月作业次数比重/%		9月作业次数比重/%		10月作业次数比重/%		11月作业次数比重/%		12月作业次数比重/%		平均值作业次数比重/%
HSI	AMM	GMM	AMM	GMM	AMM	GMM	AMM	GMM	AMM	GMM	AMM	GMM	AMM	GMM
[0, 0.2)	3.37	49.44	0.00	4.19	39.88	85.28	10.53	23.16	27.27	87.02	2.99	62.69	14.01	51.96
[0.2, 0.4)	10.11	21.35	4.79	23.95	48.46	13.50	8.42	7.37	46.10	5.84	32.83	11.94	25.12	13.99
[0.4, 0.6)	41.57	6.75	27.55	25.15	11.66	1.22	35.79	35.79	20.14	7.14	26.86	7.46	27.26	13.92
[0.6, 0.8)	35.96	13.48	43.11	30.54	0.00	0.00	34.74	26.31	6.49	0.00	32.84	17.91	25.52	14.71
[0.8, 1.0]	8.99	8.99	24.55	16.17	0.00	0.00	10.52	7.37	0.00	0.00	4.48	0.00	8.09	5.42

下载: 导出CSV

表 2 基于两种模型不同月份的AUC值

Tab. 2 The AUC values on different months based on two models

模型	7月	8月	9月	10月	11月	12月	平均
最大熵模型	0.98	0.96	0.93	0.93	0.95	0.94	0.95
栖息地指数模型	0.59	0.60	0.68	0.69	0.60	0.78	0.66

下载: 导出CSV

参考文献(50)

[1]	官文江, 马雪莲. 利用贝叶斯动态产量模型评估东、黄海日本鲭资源状况[J]. 上海海洋大学学报, 2022, 31(3): 749−760. Guan Wenjiang, Ma Xuelian. Assessment of the status of Scomber japonicus resources in the East China Sea and Yellow Sea using a Bayesian biomass dynamic model[J]. Journal of Shanghai Ocean University, 2022, 31(3): 749−760.
[2]	高峰. 基于提升回归树的东、黄海鲐鱼渔场预报模型研究[D]. 上海: 上海海洋大学, 2016. Gao Feng. Fishing ground forecasting of chub mackerel in the East China Sea and Yellow Sea using boosted regression trees[D]. Shanghai: Shanghai Ocean University, 2016.
[3]	郭爱. 气候与海洋环境变化对东黄海鲐鱼栖息地时空变动的影响[D]. 上海: 上海海洋大学, 2020. Guo Ai. Impacts of the climatic and environmental variations on the spatio-temporal distribution of potential habitat of chub mackerel Scomber japonicus in the East China Sea and Yellow Sea[D]. Shanghai: Shanghai Ocean University, 2020.
[4]	Phillips S J, Anderson R P, Schapire R E. Maximum entropy modeling of species geographic distributions[J]. Ecological Modelling, 2006, 190(3/4): 231−259.
[5]	陈新军, 高峰, 官文江, 等. 渔情预报技术及模型研究进展[J]. 水产学报, 2013, 37(8): 1270−1280. doi: 10.3724/SP.J.1231.2013.38313 Chen Xinjun, Gao Feng, Guan Wenjiang, et al. Review of fishery forecasting technology and its models[J]. Journal of Fisheries of China, 2013, 37(8): 1270−1280. doi: 10.3724/SP.J.1231.2013.38313
[6]	Wang Lifei, Kerr L A, Record N R, et al. Modeling marine pelagic fish species spatiotemporal distributions utilizing a maximum entropy approach[J]. Fisheries Oceanography, 2018, 27(6): 571−586. doi: 10.1111/fog.12279
[7]	杨胜龙, 范秀梅, 伍玉梅, 等. 基于GAM模型的阿拉伯海鲐鱼渔场分布与环境关系[J]. 生态学杂志, 2019, 38(8): 2466−2470. Yang Shenglong, Fan Xiumei, Wu Yumei, et al. The relationship between the fishing ground of mackerel (Scomber australasicus) in Arabian Sea and the environment based on GAM model[J]. Chinese Journal of Ecology, 2019, 38(8): 2466−2470.
[8]	易炜, 郭爱, 陈新军. 不同环境因子权重对东海鲐鱼栖息地模型的影响研究[J]. 海洋学报, 2017, 39(12): 90−97. Yi Wei, Guo Ai, Chen Xinjun. A study on influence of different environmental factors weights on the habitat model for Scomber japonicus[J]. Haiyang Xuebao, 2017, 39(12): 90−97.
[9]	Lee D, Son S, Kim W, et al. Spatio-temporal variability of the habitat suitability index for chub mackerel (Scomber Japonicus) in the East/Japan Sea and the South Sea of South Korea[J]. Remote Sensing, 2018, 10(6): 938. doi: 10.3390/rs10060938
[10]	刘思源, 张衡, 杨超, 等. 基于最大熵模型的西北太平洋远东拟沙丁鱼和日本鲭栖息地差异[J/OL]. [2023−05−05]. 上海海洋大学学报, 2023: 1−13. http://kns.cnki.net/kcms/detail/31.2024.S.20230421.1814.004.html. Liu Siyuan, Zhang Heng, Yang Chao, et al. Differences in habitat distribution of Sardinopsmelanostictus and Scomber japonicus in the Northwest Pacific based on a maximum entropy model[J/OL]. [2023−05−05]. Journal of Shanghai Ocean University, 2023: 1−13. http://kns.cnki.net/kcms/detail/31.2024.S.20230421.1814.004.html.
[11]	陈芃, 陈新军. 基于最大熵模型分析西南大西洋阿根廷滑柔鱼栖息地分布[J]. 水产学报, 2016, 40(6): 893−902. Chen Peng, Chen Xinjun. Analysis of habitat distribution of Argentine shortfin squid (Illex argentinus) in the southwest Atlantic Ocean using maximum entropy model[J]. Journal of Fisheries of China, 2016, 40(6): 893−902.
[12]	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.
[13]	Monk J, Ierodiaconou D, Versace V L, et al. Habitat suitability for marine fishes using presence-only modelling and multibeam sonar[J]. Marine Ecology Progress Series, 2010, 420: 157−174. doi: 10.3354/meps08858
[14]	Fourcade Y, Engler J O, Rödder D, et al. Mapping species distributions with MAXENT using a geographically biased sample of presence data: a performance assessment of methods for correcting sampling bias[J]. PLoS One, 2014, 9(5): e97122. doi: 10.1371/journal.pone.0097122
[15]	龚彩霞, 陈新军, 高峰. 基于最大熵模型模拟西北太平洋柔鱼潜在栖息地分布[J]. 中国水产科学, 2020, 27(3): 336−345. Gong Caixia, Chen Xinjun, Gao Feng. Modeling the potential distribution of the neon flying squid (Ommastrephes bartramii) in the Northwest Pacific Ocean based on a MaxEnt model[J]. Journal of Fishery Sciences of China, 2020, 27(3): 336−345.
[16]	Lee P Y, Suen J P. Comparing habitat suitability indices (HSIs) based on abundance and occurrence data[J]. North American Journal of Fisheries Management, 2013, 33(1): 89−96. doi: 10.1080/02755947.2012.743933
[17]	Zaniewski A E, Lehmann A, Overton J M. Predicting species spatial distributions using presence-only data: a case study of native New Zealand ferns[J]. Ecological Modelling, 2002, 157(2/3): 261−280.
[18]	Jaynes E T. Information theory and statistical mechanics[J]. Physical Review, 1957, 106(4): 620−630. doi: 10.1103/PhysRev.106.620
[19]	Shannon C E. A mathematical theory of communication[J]. The Bell System Technical Journal, 1948, 27(3): 379−423. doi: 10.1002/j.1538-7305.1948.tb01338.x
[20]	张劳模, 庞丽峰, 许等平, 等. 基于最大熵模型预测东北地区红松潜在分布[J]. 江西农业大学学报, 2020, 42(1): 74−83. Zhang Laomo, Pang Lifeng, Xu Dengping, et al. Potential distribution of Pinus koraiensis in northeastern China predicted by the MaxEnt model[J]. Acta Agriculturae Universitatis Jiangxiensis, 2020, 42(1): 74−83.
[21]	杨庭潇, 马力. 基于最大熵原理的四川省干旱灾害致灾危险性研究[J]. 高原山地气象研究, 2021, 41(3): 103−107. Yang Tingxiao, Ma Li. Research on the disaster hazard of drought disasters in Sichuan Province based on the principle of maximum entropy[J]. Plateau and Mountain Meteorology Research, 2021, 41(3): 103−107.
[22]	熊东阳, 张林, 李国庆. 基于最大熵模型的遥感土地利用多分类研究[J]. 自然资源遥感, 2023, 35(2): 140−148. Xiong Dongyang, Zhang Lin, Li Guoqing. MaxEnt-based multi-class classification of land use in remote sensing image interpretation[J]. Remote Sensing for Natural Resources, 2023, 35(2): 140−148.
[23]	Phillips S J, Dudík M, Schapire R E. Maxent software for modeling species niches and distributions (Version 3.4. 1)[EB/OL]. [2023−07−05]. http://biodiversityinformatics.amnh.org/open_source/maxent/.
[24]	冯志萍, 余为, 陈新军, 等. 基于最大熵模型的智利外海竹筴鱼栖息地研究[J]. 中国水产科学, 2021, 28(4): 431−441. Feng Zhiping, Yu Wei, Chen Xinjun, et al. Distribution of Chilean jack mackerel (Trachurus murphyi) habitats off Chile based on a maximum entropy model[J]. Journal of Fishery Sciences of China, 2021, 28(4): 431−441.
[25]	殷晓洁, 周广胜, 隋兴华, 等. 蒙古栎地理分布的主导气候因子及其阈值[J]. 生态学报, 2013, 33(1): 103−109. doi: 10.5846/stxb201110111495 Yin Xiaojie, Zhou Guangsheng, Sui Xinghua, et al. Dominant climatic factors of Quercus mongolica geographical distribution and their thresholds[J]. Acta Ecologica Sinica, 2013, 33(1): 103−109. doi: 10.5846/stxb201110111495
[26]	Phillips S J, Dudík M. Modeling of species distributions with Maxent: new extensions and a comprehensive evaluation[J]. Ecography, 2008, 31(2): 161−175. doi: 10.1111/j.0906-7590.2008.5203.x
[27]	刘丹, 李玉堂, 洪玲霞, 等. 基于最大熵模型的吉林省主要天然林潜在分布适宜性[J]. 林业科学, 2018, 54(7): 1−15. Liu Dan, Li Yutang, Hong Lingxia, et al. The suitability of potential geographic distribution of natural forest types in Jilin Province based on maximum entropy models[J]. Scientia Silvae Sinicae, 2018, 54(7): 1−15.
[28]	Mohri M. Seasonal changes in bigeye tuna fishing areas in relation to the oceanographic parameters in the Indian Ocean[J]. Journal of National Fisheries University, 1999, 47(2): 43−54.
[29]	范秀梅, 唐峰华, 崔雪森, 等. 基于栖息地指数的西北太平洋日本鲭渔情预报模型构建[J]. 海洋学报, 2020, 42(12): 34−43. Fan Xiumei, Tang Fenghua, Cui Xuesen, et al. Habitat suitability index for chub mackerel (Scomber japonicus) in the Northwest Pacific Ocean[J]. Haiyang Xuebao, 2020, 42(12): 34−43.
[30]	施展. 基于最大熵模型的森林土壤呼吸分布模拟研究[D]. 杭州: 浙江农林大学, 2021. Shi Zhan. Simulation research on forest soil respiration distribution based on maximum entropy model[D]. Hangzhou: Zhejiang A&F University, 2021.
[31]	王运生, 谢丙炎, 万方浩, 等. ROC曲线分析在评价入侵物种分布模型中的应用[J]. 生物多样性, 2007, 15(4): 365−372. doi: 10.1360/biodiv.060280 Wang Yunsheng, Xie Bingyan, Wan Fanghao, et al. Application of ROC curve analysis in evaluating the performance of alien species’ potential distribution models[J]. Biodiversity Science, 2007, 15(4): 365−372. doi: 10.1360/biodiv.060280
[32]	蒋帅. 基于AUC的分类器性能评估问题研究[D]. 长春: 吉林大学, 2016. Jiang Shuai. Researches on performance evaluation of classifier based on AUC[D]. Changchun: Jilin University, 2016.
[33]	Metz C E. Basic principles of ROC analysis[J]. Seminars in Nuclear Medicine, 1978, 8(4): 283−298. doi: 10.1016/S0001-2998(78)80014-2
[34]	王茹琳, 李庆, 封传红, 等. 基于MaxEnt的西藏飞蝗在中国的适生区预测[J]. 生态学报, 2017, 37(24): 8556−8566. Wang Rulin, Li Qing, Feng Chuanhong, et al. Predicting potential ecological distribution of Locusta migratoria tibetensis in China using MaxEnt ecological niche modeling[J]. Acta Ecologica Sinica, 2017, 37(24): 8556−8566.
[35]	崔雪森, 唐峰华, 周为峰, 等. 基于支持向量机的西北太平洋柔鱼渔场预报模型构建[J]. 南方水产科学, 2016, 12(5): 1−7. Cui Xuesen, Tang Fenghua, Zhou Weifeng, et al. Fishing ground forecasting model of Ommastrephes bartramii based on support vector machine (SVM) in the Northwest Pacific[J]. South China Fisheries Science, 2016, 12(5): 1−7.
[36]	Ismail A I, Morrison E C, Burt B A, et al. Natural history of periodontal disease in adults: findings from the Tecumseh Periodontal Disease Study, 1959−87[J]. Journal of Dental Research, 1990, 69(2): 430−435. doi: 10.1177/00220345900690020201
[37]	Development Core R Team. R: A Language and Environment for Statistical Computing[M]. Vienna, Austria: R Foundation for Statistical Computing, 2021.
[38]	Freeman E A, Moisen G. PresenceAbsence: an R package for presence absence analysis[J]. Journal of Statistical Software, 2008, 23(11): 1−31.
[39]	刘庆, 杜雨彤, 邢丹, 等. 基于MaxEnt模型对我国三带喙库蚊潜在分布区的预估研究[J]. 寄生虫与医学昆虫学报, 2022, 29(4): 203−211. Liu Qing, Du Yutong, Xing Dan, et al. Prediction of the potential distribution areas of Culex tritaeniorhynchus in China based on MaxEnt model[J]. Acta Parasitologica et Medica Entomologica Sinica, 2022, 29(4): 203−211.
[40]	孔维尧, 李欣海, 邹红菲. 最大熵模型在物种分布预测中的优化[J]. 应用生态学报, 2019, 30(6): 2116−2128. Kong Weiyao, Li Xinhai, Zou Hongfei. Optimizing MaxEnt model in the prediction of species distribution[J]. Chinese Journal of Applied Ecology, 2019, 30(6): 2116−2128.
[41]	邢丁亮, 郝占庆. 最大熵原理及其在生态学研究中的应用[J]. 生物多样性, 2011, 19(3): 295−302. doi: 10.3724/SP.J.1003.2011.08318 Xing Dingliang, Hao Zhanqing. The principle of maximum entropy and its applications in ecology[J]. Biodiversity Science, 2011, 19(3): 295−302. doi: 10.3724/SP.J.1003.2011.08318
[42]	Berger A L, Della Pietra V J, Della Pietra S A. A maximum entropy approach to natural language processing[J]. Computational Linguistics, 1996, 22(1): 39−71.
[43]	Bovee K D. Development and evaluation of habitat suitability criteria for use in the instream flow incremental methodology[R]. Washington: USDI Fish and Wildlife Service, 1986.
[44]	Franklin J. Mapping Species Distributions: Spatial Inference and Prediction[M]. Cambridge: Cambridge University Press, 2010.
[45]	Elith J, Graham C H, Anderson R P, et al. Novel methods improve prediction of species’ distributions from occurrence data[J]. Ecography, 2006, 29(2): 129−151. doi: 10.1111/j.2006.0906-7590.04596.x
[46]	Li Wenkai, Guo Qinghua, Elkan C. Can we model the probability of presence of species without absence data?[J]. Ecography, 2011, 34(6): 1096−1105. doi: 10.1111/j.1600-0587.2011.06888.x
[47]	Tian Siquan, Chen Xinjun, Chen Yong, et al. Evaluating habitat suitability indices derived from CPUE and fishing effort data for Ommatrephes bratramii in the northwestern Pacific Ocean[J]. Fisheries Research, 2009, 95(2/3): 181−188.
[48]	崔雪森, 周灿, 唐峰华, 等. 西北太平洋柔鱼渔场非参数栖息地适宜性指数模型[J]. 广东海洋大学学报, 2020, 40(6): 53−62. Cui Xuesen, Zhou Can, Tang Fenghua, et al. Nonparametric habitat suitability index model for Ommastrephes bartramii fishing ground in the Northwest Pacific Ocean[J]. Journal of Guangdong Ocean University, 2020, 40(6): 53−62.
[49]	晏然, 范江涛, 徐姗楠, 等. 南海北部近海竹荚鱼栖息地分布特征[J]. 生态学杂志, 2018, 37(8): 2430−2435. Yan Ran, Fan Jiangtao, Xu Shannan, et al. Distribution characteristics of jack mackerel (Trachurus japonicus) habitat in the offshore waters of northern South China Sea[J]. Chinese Journal of Ecology, 2018, 37(8): 2430−2435.
[50]	易明华, 官文江, 陈新军. 基于理想自由分布理论对CPUE与渔业资源关系的探讨——以我国近海鲐灯光围网渔业为例[J]. 大连水产学院学报, 2009, 24(4): 325−330. Yi Minghua, Guan Wenjiang, Chen Xinjun. The relationship between CPUE and fish abundance based on ideal free distribution theory: take the large light purse seine fishery of mackerel in Yellow Sea and East China Sea as an example[J]. Journal of Dalian Fisheries University, 2009, 24(4): 325−330.