Fishing ground forecasting of Thunnus alalung in Indian Ocean based on random forest
-
摘要: 为了提高远洋渔场预报水平和满足渔业生产的需要,提出了一种基于随机森林建立印度洋长鳍金枪鱼(Thunnus alalunga)渔场预报模型的方法。选取2002-2009年各个月份印度洋5°×5°格点渔业环境和时空数据(包括海表温度、叶绿素a浓度、表温距平、叶绿素a浓度距平、海表温度梯度强度和海面高度异常等数据)作为预测变量,利用长鳍金枪鱼的CPUE(Catch per unit effort,单位:尾/千钩数)的三分位点将渔区划分为高CPUE、中等CPUE和低CPUE三种类型,作为响应变量,对数据进行训练。结果表明,当随机森林中决策树达到100以上时,袋外数据OOB(out-of-bag)的分类误差率趋于平稳。将训练得到的随机森林用于2010年印度洋长鳍金枪鱼分月渔场的预测,其概率等值面图与实际生产的渔场分布进行叠加比较,显示高CPUE渔场概率分布与实际渔场的位置及范围变化情况符合。通过ROC(Relative Operating Characteristic)分析,高CPUE、中等CPUE和低CPUE的AUC(Area Under ROC Curve)分别达到0.847、0.743和0.803,表明预测精度较高。最后对中等CPUE渔区预测精度相对较低的原因进行了分析。Abstract: To improve the forecasting accuracy of pelagic fishing ground and meet the needs of the practical fishery production, a method of albacore fishing ground forecast model in the Indian Ocean based on random forest was proposed.The Indian Ocean fishery environmental and spatio-temporal data by 5°×5° grid of every month from 2002 to 2009 were taken as predictor variables and the CPUE(catch per unit effort,unit∶inds per 1 000 hooks)of albacore,classified into high CPUE, moderate CPUE and low CPUE by tertile, was selected as the response variable in the random forest training. The training result indicated that the OOB(out-of-bag)misclassification rate tends to be steady when the number of decision trees reached 100. The random forest obtained through the training was applied to the albacore fishing ground monthly forecast in 2010.The isosurface chart on forecasted probabilities was overlapped on the practical fishery production and a comparison was made between them.The result demonstrated that the high CPUE fishing ground probability distribution and the CPUE of actual fishery ground tally well. Through the ROC analysis, AUCs (Area Under ROC Curve)of high CPUE, moderate CPUE and low CPUE were 0.847,0.743 and 0.803 respectively, indicating that the forecast precision was high. Finally the reason of the relatively low precision of medium CPUE probability in the forecast was analyzed.
-
Key words:
- random forest /
- Thunnus alalung /
- fishing ground forecast /
- Indian Ocean
-
崔利锋,许柳雄.世界大洋性渔业概况[M].北京:海洋出版社,2011,4:3-4. Childers J, Snyder S, Kohin S. Migration and behavior of juvenile North Pacific albacore (Thunnus alalunga)[J]. Fisheries Oceanography, 2011, 20(3): 157-173. Zainuddin M, Saitoh K, Saitoh S. Albacore(Thunnus alalunga)fishing ground in relation to oceanographic conditions in the western North Pacific Ocean using remotely sensed satellite data[J]. Fish Oceanogr,2008, 17(2):61-73. Laurs R M, Fielder P C, Montgomery D R. Albacore tuna catch distributions relative to environmental features observed from satellites[J]. Deep-Sea Research,1984,31(9): 1085-1099. 苏奋振,周成虎,杜云艳,等. 海洋渔业资源地理信息系统应用的时空问题[J].应用生态学报,2003,14(9): 1569-1572. 叶施仁,史忠植.基于CBR的中心渔场预报[J].高技术通讯,2001,11(5):64-68. 冯波,陈新军,许柳雄.应用栖息地指数对印度洋大眼金枪鱼分布模式研究[J].水产学报, 2007, 31(6): 805-812. 方宇,邹晓荣,张敏,等.东南太平洋智利竹筴鱼栖息地指数的比较研究[J].海洋渔业,2010,32(2): 178-185. 牛明香,李显森,徐玉成.基于广义可加模型的时空和环境因子对东南太平洋智利竹筴鱼渔场的影响[J].应用生态学报,2004,21(4):1049-1055. Pan R, Yang Q, Pan S J. Mining Competent Case Bases for Case-based Reasoning[J]. Artificial Intelligence,2007,171(16/17): 1039-1068. Lucas P J F. Bayesian analysis,pattern analysis and data mining in health care[J]. Current Opinion in Critical Care Medicine,2004,10(5):399-403. Tu J V. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes[J].J Clin Epidemiol, 1996,49(11):1225-1231. Cutler D R, Edwards T C, Jr Beard, et al. Random forests for classification in ecology[J]. Ecology,2007,88(11): 2783-2792. 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. Pi Qingling, Hu Jianyu. Analysis of Sea surface temperature fronts in the Taiwan Strait and its adjacent area using an Advanced Edge Detection Method[J]. Science China Earth Science, 2010,53(7):1008-1016. Breiman L, Friedman J H, Olshen R A, et al. Classification and Regression Trees [C]. Belmont (CA): Wadsworth International Group, 1984. Breiman L. Random forests[J]. Machine Learning, 2001,45: 5-32. Breiman L. Manual On Setting Up, Using, And UnderstandingRandom Forests V3.1 [EB/OL].http://oz.berkeley.edu/users/breiman/Using_random_forests_V3.1.pdf Arnold J B. A Multidimensional Scaling Study of Semantic Distance[J]. Journal of Experimental Psychology Monograph,1973, 90(2):349-372. Tom F. An introduction to ROC analysis[J]. Pattern Recognition Letters,2006,27: 861-874. Hosmer D W,Lemeshow S. Applied Logistic Regression. 2nd[M]. New York: John Wiley & Sons, Inc., 2000: 156-164. Macskassy S, Provost F. Confidence Bands for ROC Curves: Methods and an Empirical Study [R]. Proc. 1st Workshop ROC Analysis in AI: ROCAI, 2004: 61-70. Segal M R. Machine Learning Benchmarks and Random Forest Regression. San Francisco: Technical Report, Center for Bioinformatics & Molecular Biostatistics, University of California, 2004. Reka D, Michael P S, Jeffrey J, et al. Oceanographic investigation of the American Samoa albacore(Thunnus alalunga) habitat and longline fishing grounds[J]. Fish. Oceanogr. 2007,16(6): 555-572. Saito S. Studies on fishing of albacore, Thunnus alalunga(Bonnaterre),by experimental deep-sea tuna longline [EB/OL].http://eprints.lib.hokudai.ac.jp/dspace/bitstream/2115/21856/1/21(2)_P107-184.pdf. Cutler D R, Edwards T C, Beard K H, et al. Random forests for classification in ecology[J]. Ecology,2007, 88(11): 2783-2792.
点击查看大图
计量
- 文章访问数: 1685
- HTML全文浏览量: 5
- PDF下载量: 2231
- 被引次数: 0