Abstract：Since traditional fishery forecasting methods cannot accurately analyze the key factors in the face of increasingly complex ocean data, the light gradient boosting machine (LightGBM), an integrated learning model, was used to predict albacore tuna Thunnus alalunga fishery via the albacore tuna longline fishing production data in the south Pacific ocean from 2000 to 2015, combined with the sea surface temperature, concentration of chlorophyll a and sea surface height, latitude and longitude in marine environment factor and spatio-temporal data, and then the results were compared with naive bayes, XGBoost and BP neural networks. Meanwhile, the optimal parameters of LightGBM model were obtained by grid search method, and the stability of the model was verified by cross validation method. Results showed that the best prediction accuracy of the LightGBM model for albacoren tuna fishery in the south Pacific reached 72.6%, and the accuracy of the LightGBM model was significantly improved compared with other models. Finally, analysis of the importance of each input factor in the prediction of fishery revealed that sea surface height and sea surface temperature were important factors influencing the distribution of fisheries.
宫鹏, 王德兴, 袁红春, 陈冠奇, 吴若有. 基于LightGBM的南太平洋长鳍金枪鱼渔场预报模型研究[J]. 水产科学, 2021, 40(5): 762-767.
GONG Peng, WANG Dexing, YUAN Hongchun, CHEN Guanqi, WU Ruoyou. Fishing Ground Forecast Model of Albacore Tuna Based on LightGBM in the South Pacific Ocean. Fisheries Science, 2021, 40(5): 762-767.
[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. [2]杨嘉樑,黄洪亮,宋利明,等.基于分位数回归的库克群岛海域长鳍金枪鱼栖息环境综合指数[J].中国水产科学,2014,21(4):832-851. [3]魏联,陈新军,雷林,等.西北太平洋柔鱼BP神经网络渔场预报模型比较研究[J].上海海洋大学学报,2017,26(3):450-457. [4]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(中文版),2013,35(1):158-164. [5]范永超,陈新军,汪金涛.基于多因子栖息地指数模型的南太平洋长鳍金枪鱼渔场预报[J].海洋湖沼通报,2015(2):36-44. [6]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. [7]Ke G, Meng Q, Finley T, et al. Lightgbm: a highly efficient gradient boosting decision tree[G]∥ Guyon I, Luxburg U V, Bengio S, et al. Advances in Neural Information Processing Systems 30 (NIPS 2017). Long Beach:NIPS,2017:3146-3154. [8]田思泉,陈新军.不同名义CPUE计算法对CPUE标准化的影响[J].上海海洋大学学报,2010,19(2):240-245. [9]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. [10]樊伟,张晶,周为峰.南太平洋长鳍金枪鱼延绳钓渔场与海水表层温度的关系分析[J].大连水产学院学报,2007,22(5):366-371. [11]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. [12]范江涛.南太平洋长鳍金枪鱼延绳钓渔业渔情预报研究[D].上海:上海海洋大学,2011. [13] Grabner H, Bischof H. On-line boosting and vision[G]∥CVPR 2006.2006 IEEE computer society conference on computer vision & pattern recognition.New York:ACM,2006:260-267. [14]Chen T Q, Guestrin C. XGBoost:a scalable tree boosting system[G]∥Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining.New York:ACM Press,2016:785-794. [15]Tyree S, Weinberger K Q, Agrawal K, et al. Parallel boosted regression trees for web search ranking[G]∥Proceedings of the 20th international conference on World wide web - WWW′11.March 28-April 1,2011.Hyderabad,India.New York:ACM Press,2011:387-396. [16]崔雪森,唐峰华,张衡,等.基于朴素贝叶斯的西北太平洋柔鱼渔场预报模型的建立[J].中国海洋大学学报(自然科学版),2015,45(2):37-43. [17]Olden J D, Jackson D A. Illuminating the “black box”:a randomization approach for understanding variable contributions in artificial neural networks[J].Ecological Modelling,2002,154(1/2):135-150. [18]胡贯宇,陈新军,汪金涛.基于不同权重的栖息地指数模型预报阿根廷滑柔鱼中心渔场[J].海洋学报,2015,37(8):88-95. [19]牛明香,李显森,戴芳群,等.智利外海西部渔场智利竹筴鱼资源与海表温度分布特征[J].海洋环境科学,2010,29(3):373-377. [20]陈新军,田思泉,许柳雄.西北太平洋海域柔鱼产卵场和作业渔场的水温年间比较及其与资源丰度的关系[J].上海水产大学学报,2005,14(2):168-175. [21]李世通,唐衍力.瓦努阿图及周边海域金枪鱼延绳钓上钩率和渔场分布的初步研究[J].水产科学,2017,36(6):714-721. [22]朱国平,李凤莹,陈锦淘,等.印度洋中南部长鳍金枪鱼繁殖栖息的适应性[J].海洋环境科学,2012,31(5):697-700 [23]杨胜龙,周为峰,伍玉梅,等.西北印度洋大眼金枪鱼渔场预报模型建立与模块开发[J].水产科学,2011,30(11):666-672. [24]杨胜龙,张忭忭,张衡,等.黄鳍金枪鱼垂直移动及水层分布研究进展[J].水产科学,2019,38(1):119-126.
2021, Vol. 40 
