基于提升回归树的东、黄海鲐鱼渔场预报

高峰; 陈新军; 官文江; 李纲

doi:10.3969/j.issn.0253-4193.2015.10.004

基于提升回归树的东、黄海鲐鱼渔场预报

doi: 10.3969/j.issn.0253-4193.2015.10.004

上海海洋大学海洋科学学院, 上海 201306;上海海洋大学大洋渔业资源可持续开发省部共建教育部重点实验室, 上海 201306;上海海洋大学国家远洋渔业工程技术研究中心, 上海 201306;远洋渔业协同创新中心, 上海 201306

基金项目: 国家863项目(2012AA092301);国家发改委产业化专项(2159999);国家科技支撑计划(2013BAD13B01);上海市教委科研创新项目(14ZZ147)。

计量
- 文章访问数: 1320
- HTML全文浏览量: 21
- PDF下载量: 1232
- 被引次数: 0
出版历程
- 收稿日期: 2014-12-16

Fishing ground forecasting of chub mackerel in the Yellow Sea and East China Sea using boosted regression trees

College of Marine Sciences, Shanghai Ocean University, Shanghai 201306, China;Key Laboratory of Sustainable Exploitation of Oceanic Fisheries Resources, Ministry of Education, Shanghai Ocean University, Shanghai 201306, China;National Distance-water Fisheries Engineering Research Center, Shanghai Ocean University, Shanghai 201306, China;Collaborative Innovation Center for Distant-water Fisheries, Shanghai 201306, China

摘要

摘要: 为提高东、黄海鲐鱼渔场预报准确率、降低渔业生产成本,研究提出了一种基于提升回归树的渔场预报模型。研究采用2003—2010年我国大型灯光围网渔捞日志数据,以有网次记录的小渔区为渔场,以渔捞日志未记录的区域作为背景场随机选择假定非渔场数据,以海表水温等环境因子作为预测变量构建东、黄海鲐鱼渔场预报模型并以2011年的实际作业记录对预报模型进行精度验证。验证计算得到预报模型的AUC(area under receiver operating curve)值为0.897,表明模型的预报精度较高。模型的空间预测结果表明,预报渔场与实际作业位置基本吻合,其位置移动也与实际情况相符。这表明基于提升回归树的渔场预报模型可以用来进行东、黄海鲐鱼渔场的预报。
- 提升回归树 /
- 鲐鱼 /
- 渔场预报 /
- 东、黄海
Abstract: To improve the accuracy of fishing ground forecasting of chub mackerel (Scomber japonicus) in the Yellow and East China Sea,and reduce the fishery production cost,a new fishing ground forecasting model based on boosted regression trees was proposed in this study. Model was fitted with data extracted from electronic logbooks of Chinese mainland large-type lighting purse seine fishery for chub mackerel,with a range from 2003 to 2010. The fishing area with fishing effort was identified as fishing ground and the pseudo non fishing ground data was randomly collected from background field,which is the fishing areas with no records in the logbooks. The predictive variables were sea surface temperature and other environmental factors. The performance of prediction of the model was evaluated with the testing dataset consist of actual fishing locations of year 2011. The results of the evaluation showed that the prediction model had a high prediction performance with an AUC value of 0.897. The results of spatial prediction showed that the predicted fishing ground and its shifting were coincided with the actual fishing locations,which indicated that the forecasting model based on boosted regression trees can be used to forecasting the fishing ground of chub mackerel in the Yellow and East China Sea.
- boosted regression trees /
- chub mackerel /
- fishing ground forecasting /
- Yellow Sea

HTML全文

参考文献(35)

程家骅,林龙山. 东海区鲐鱼生物学特征及其渔业现状的分析研究[J]. 海洋渔业,2004,26(2): 73-78. Cheng Jiahua,Lin Longshan. Study on the biological characteristics and status of common mackerel (Scomber japonicus Houttuyn) fishery in the East China Sea region[J]. Marine Fisheries,2004,26(2): 73-78.

Li Gang,Chen Xinjun,Lei Lin,et al. Distribution of hotspots of chub mackerel based on remote-sensing data in coastal waters of China[J]. International Journal of Remote Sensing,2014,35(11/12): 4399-4421.

苗振清. 东海北部鲐鲹中心渔场形成机制的统计学[J]. 水产学报,2003,27(2): 143-150. Miao Zhenqing. The statistical research on the formation mechanism of central fishing ground of Pneumatophorus japonicus and Decapterus maruadsi in the north of East China Sea[J]. Journal of Fisheries of China,2003,27(2): 143-150.

李曰嵩,潘灵芝,严利平,等. 基于个体模型的东海鲐鱼渔场形成机制研究[J]. 海洋学报,2014,36(6): 67-74. Li Yuesong,Pan Lingzhi,Yan Liping,et al. Individual-based model study on the fishing ground of chub mackerel (Scomber japonicus) in the East China Sea[J]. Haiyang Xuebao,2014,36(6): 67-74.

李纲,陈新军. 东海鲐鱼资源和渔场时空分布特征的研究[J]. 中国海洋大学学报,2007,37(6): 921-926. Li Gang,Chen Xinjun. Tempo-spatial characteristic analysis of the mackerel resource and its fishing ground in the East China Sea[J]. Periodical of Ocean University of China,2007,37(6): 921-926.

郑波,陈新军,李纲. GLM和GAM模型研究东黄海鲐资源渔场与环境因子的关系[J]. 水产学报,2008,32(3): 379-386. Zheng Bo,Chen Xinjun,Li Gang. Relationship between the resource and fishing ground of mackerel and environmental factors based on GAM and GLM models in the East China Sea and Yellow Sea[J]. Journal of Fisheries of China,2008,32(3): 379-386.

Chen Xinjun,Li Gang,Feng Bo,et al. Habitat suitability index of chub mackerel (Scomber japonicus) from July to September in the East China Sea[J]. Journal of Oceanography,2009,65(1): 93-102.

张月霞,丘仲锋,伍玉梅,等. 基于案例推理的东海区鲐鱼中心渔场预报[J]. 海洋科学,2009,33(6): 8-11. Zhang Yuexia,Qiu Zhongfeng,Wu Yumei,et al. Predicting central fishing ground of Scomber japonica in East China Sea based on case-based reasoning[J]. Marine Sciences,2009,33(6): 8-11.

陈峰,雷林,毛志华,等. 基于遥感水质的夏季东海鲐鱼渔情预报研究[J]. 广东海洋大学学报,2011,31(3): 56-62. Chen Feng,Lei Lin,Mao Zhihua,et al. Fishery forecasting for chub mackerel (Scomber japonicus) in summer in the East China Sea based on water quality from remote sensing[J]. Journal of Guangdong Ocean University,2011,31(3): 56-62.

Franklin J. Mapping species distributions: spatial inference and prediction[M]. New York: Cambridge University Press,2009: 200-205.

Hastie T,Tibshirani R,Friedman J. The elements of statistical learning: data mining,inference,and prediction[M]. New York: Springer-Verlag,2001: 299-345.

Abeare S. Comparisons of boosted regression tree,GLM and GAM performance in the standardization of yellowfin tuna catch-rate data from the Gulf of Mexico longline fishery[D]. Baton Rouge: Louisiana State University,2009: 1-94.

Elith J,Leathwick J R,Hastie T. A working guide to boosted regression trees[J]. Journal of Animal Ecology,2008,77(4): 802-813.

Froeschke B F,Tissot P,Stunz G W,et al. Spatiotemporal predictive models for juvenile southern flounder in Texas estuaries[J]. North American Journal of Fisheries Management,2013,33(4): 817-828.

Lewin W C,Mehner T,Ritterbusch D,et al. The influence of anthropogenic shoreline changes on the littoral abundance of fish species in German lowland lakes varying in depth as determined by boosted regression trees[J]. Hydrobiologia,2014,724(1): 293-306.

Compton T J,Morrison M A,Leathwick J R,et al. Ontogenetic habitat associations of a demersal fish species,Pagrus auratus,identified using boosted regression trees[J]. Marine Ecology Progress Series,2012,462: 219-230.

Soykan C U,Eguchi T,Kohin S,et al. Prediction of fishing effort distributions using boosted regression trees[J]. Ecological Applications,2014,24(1): 71-83.

Pearce J L,Boyce M S. Modelling distribution and abundance with presence-only data[J]. Journal of Applied Ecology,2006,43(3): 405-412.

Barbet-Massin M,Jiguet F,Albert C H,et al. Selecting pseudo-absences for species distribution models: how,where and how many？[J]. Methods in Ecology and Evolution,2012,3(2): 327-338.

李纲,陈新军. 夏季东海渔场鲐鱼产量与海洋环境因子的关系[J]. 海洋学研究,2009,27(1): 1-8. Li Gang,Chen Xinjun. Study on the relationship between catch of mackerel and environmental factors in the East China Sea in summer[J]. Journal of Marine Sciences,2009,27(1): 1-8.

官文江,陈新军,高峰,等. 海洋环境对东、黄海鲐鱼灯光围网捕捞效率的影响[J]. 中国水产科学,2009,16(6): 949-958. Guan Wenjiang,Chen Xinjun,Gao Feng,et al. Environmental effects on fishing efficiency of Scomber japonicus for Chinese large lighting purse seine fishery in the Yellow and East China Seas[J]. Journal of Fishery Sciences of China,2009,16(6): 949-958.

官文江,陈新军,李纲. 海表水温和拉尼娜事件对东海鲐鱼资源时空变动的影响[J]. 上海海洋大学学报,2011,20(1): 102-107. Guan Wenjiang,Chen Xinjun,Li Gang. Influence of sea surface temperature and La Nia event on temporal and spatial fluctuation of chub mackerel (Scomber japonicus) stock in the East China Sea[J]. Journal of Shanghai Ocean University,2011,20(1): 102-107.

陈新军,刘必林,田思泉,等. 利用基于表温因子的栖息地模型预测西北太平洋柔鱼(Ommastrephes bartramii)渔场[J]. 海洋与湖沼,2009,40(6): 707-713. Chen Xinjun,Liu Bilin,Tian Siquan,et al. Forecasting the fishing ground of Ommastrephes bartramii with SSJ-based habitat suitability modelling in Northwestern Pacific[J]. Oceanologia et Limnologia Sinica,2009,40(6): 707-713.

Ridgeway G. Generalized boosted regression models: A guide to the gbm package[EB/OL]. (2007-08-03)[2014-09-30]. http://ftp.ctex.org/mirrors/cran/web/packages/gbm/.

Friedman J H. Greedy function approximation: a gradient boosting machine[J]. The Annals of Statistics,2001,29(5): 1189-1232.

Brieman L,Friedman J,Olshen R A,et al. Classification and regression trees[M]. Belmont: Chapman & Hall/CRC,1984: 1-368.

Friedman J H. Stochastic gradient boosting[J]. Computational Statistics & Data Analysis,2002,38(4): 367-378.

Swets J A. Measuring the accuracy of diagnostic systems[J]. Science,1988,240(4857): 1285-1293.

Freeman E A,Moisen G. PresenceAbsence: An R package for presence absence analysis[J]. Journal of Statistical Software,2008,23(11): 1-31.

崔雪森,伍玉梅,张晶,等. 基于分类回归树算法的东南太平洋智利竹筴鱼渔场预报[J]. 中国海洋大学学报,2012,42(7/8): 53-59. Cui Xuesen,Wu Yumei,Zhang Jing,et al. Fishing ground forecasting of Chilean jack mackerel (Trachurus murphyi) in the Southeast Pacific Ocean based on CART decision tree[J]. Periodical of Ocean University of China,2012,42(7/8): 53-59.

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. Chen Xuezhong,Fan Wei,Cui Xuesen,et al. Fishing ground forecasting of Thunnus alalung in Indian Ocean based on random forest[J]. Haiyang Xuebao,2013,35(1): 158-164.

Andrade H A. The relationship between the skipjack tuna (Katsuwonus pelamis) fishery and seasonal temperature variability in the south-western Atlantic[J]. Fisheries Oceanography,2003,12(1): 10-18.

VanDerWal J,Shoo L P,Graham C,et al. Selecting pseudo-absence data for presence-only distribution modeling: how far should you stray from what you know？[J]. Ecological Modelling,2009,220(4): 589-594.

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. 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.

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.

施引文献

资源附件(0)

访问统计