论文部分内容阅读
柔鱼是西北太平洋的重要经济种类。研究根据1995-2001年7-11月采集的鱿钓生产数据以及相对应的海洋环境因子数据,包括经纬度、表温(SST)和海平面高度距平(SSHA),分别以单位捕捞努力量渔获量(CPUE)和捕捞努力量作为中心渔场指标,采用BP神经网络方法,以经纬度、海洋环境因子作为输入因子,分别以CPUE和捕捞努力量作为输出因子,采用4-3-1和4-2-1两种模型,共4种方案对西北太平洋柔鱼渔场进行预报,并以拟合残差最小的模型作为最优预报模型。分析结果显示,7-11月各月中心渔场预报模型均以4-3-1模型为最优,但7、8月最优预报模型以捕捞努力量为输出的4-3-1模型,9、10、11月最优预报模型以CPUE为输出的4-3-1模型,总体平均误差以捕捞努力量为输出的4-3-1模型为最小。研究认为,CPUE和捕捞努力量作为中心渔场预报指标有差异,以捕捞努力量为输出的4-3-1模型较合适作为柔鱼渔场预报模型。
Squid is an important economic species in the Pacific Northwest. Based on the squid fishing production data collected from July to November in 1995-2001 and corresponding marine environmental factors including latitude, longitude, surface temperature (SST) and sea level anomaly (SSHA) Taking CPUE and fishing effort as the indexes of central fishery, using BP neural network method, latitude and longitude and marine environmental factors as input factors, using CPUE and fishing effort as output factors, using 4-3-1 and 4- 2-1 two models, a total of four kinds of programs to predict the fishing ground of Ommastrephes bartrami in the Northwest Pacific, and take the model with the smallest residual error as the optimal forecast model. The results of the analysis show that the 4-3-1 model is the best for all the monthly fishing ground prediction models from July to November, but the 4-3-1 models are the best for the July and August models with fishing effort as the output, 9 The 4-3-1 model with CPUE as the output of the optimal forecast model in October and November, and the 4-3-1 model with the total average error of fishing effort output as the minimum. The study suggests that there are differences between the CPUE and the fishing effort as the indicators of the central fishing ground, and the 4-3-1 model based on the fishing effort is more suitable as the forecasting model for the fishing ground of Ommastrephes batina.