摘要
本文利用来自中西太平洋渔业委员会(WCPFC)黄鳍金枪鱼延绳钓2000-2011年的历史渔获数据和美国国家海洋和大气管理局(NOAA)气候预报中心提供的海表温度最优插值数据和法国空间局(CNES)卫星海洋数据中心提供的多卫星融合高度计月合成海面高度资料,基于贝叶斯分类器,根据模型中环境因子的选取以及渔区分类策略的不同预拟了8种构建方案对2011年南海外海黄鳍金枪鱼的渔场进行分类预报,并将预报结果与实际渔场进行对比检验,比较分析不同方案对最终分类结果和精度的影响。检验结果表明,方案1-8总体精度分别为71.4%、75%、70.8%、74.4%、66.7%、68.5%、57.7%和63.7%。方案1-6在65%以上,均能够满足实际渔场预报业务化需求。采用SST和SSH双环境因子的方案均比采用单SST环境因子的方案总体精度稍高,一定程度上提高了预报精度,其中采用去除SST和SSH相关性的第一主分量作为预报因子的方案2达到了75%最高精度。采用CPUE平均值正负标准差作为节点比以33.3%与66.7%作为节点来区分高、中、低CPUE渔区的预报结果要更加准确。因此在模型筛选的基础上,选用模型方案2完成南海金枪鱼渔场渔情预报服务系统的系统实现。
Eight plans were made based on Bayes classifier to forecast the YFT fishing ground in the open South China Sea (SCS) according to different strategies on the choice of environment factor and classification of fishing zones. The yellowfin tuna (YFT) longline fishing data provided by the WCPFC, the optimum interpolation sea surface temperature (OISST) from CPC/NOAA, and the multi-satellites altimetric monthly averaged sea surface height (SSH) released by OCC/CNES were used in the present study. The classification forecast results were compared with the actual ones for the validation of the different plans. The results of validation show that the precision of the eight plans are 71.4%, 75%, 70.8%,74. 4%, 66. 7%, 68. 5%, 57. 7% and 63.7% in sequence, and the first sixth ones above 65 % would meet the practical application needs basically. The plans which use SST and SSH simultaneously as environmental factor have higher precision than those only use SST environmental factor. The addition of SSH can improve the model precision to a certain extent. The plans using the CPUE's mean standard deviation as threshold have higher precision than those using the CPUE's 33.3 % and 66.7%quantilesas the threshold. The fishing ground forecasting information system has been built based on the plans using SST and SSH simultaneously as environmental factor.
出处
《海洋湖沼通报》
CSCD
北大核心
2018年第1期116-122,共7页
Transactions of Oceanology and Limnology
基金
国家科技支撑计划项目--南海外海捕捞技术与新资源开发(2013BAD13B06)
国家自然科学基金(31602206)
上海市自然科学基金项目(16ZR1444700)资助
关键词
贝叶斯分类器
南海
黄鳍金枪鱼
渔场预报
Bayes classifier
South China Sea
yellowfin tuna
fishing ground forecasting