| 时间序列分析模型在黄海南部小黄鱼资源量预测中的应用 |
| |
| 引用本文： | 宋大德,汪金涛,陈新军,仲霞铭,熊瑛,汤建华,吴磊.时间序列分析模型在黄海南部小黄鱼资源量预测中的应用[J].海洋学报,2020,42(12):26-33. |
| |
| 作者姓名： | 宋大德 汪金涛 陈新军 仲霞铭 熊瑛 汤建华 吴磊 |
| |
| 作者单位： | 1.上海海洋大学 海洋科学学院，上海 201306 |
| |
| 基金项目： | 国家自然科学基金;江苏省"六大人才高峰"高层次人才项目;农业部专项;江苏省水生野生动物普查专项;江苏省农业农村综合信息统计监测调查 |
| |
| 摘 要： | 本文选取2003?2014年黄海南部帆式张网小黄鱼渔获量的监测数据，运用时间序列分析模型ARIMA (1，2，0)进行拟合及预测，并用2015?2016年小黄鱼年单位捕捞努力量渔获量值进行验证。结果显示，2003?2014年的小黄鱼年单位捕捞努力量渔获量模拟值与真实值接近，相关系数为0.881 (p<0.05)，相关性显著；2015年和2016年预测值分别为47.66 kg/网和49.16 kg/网，与实际值(51.10 kg/网和40.05 kg/网)相对误差分别为6.73%和22.75%，总体相对误差为14.74%。表明ARIMA (1，2，0)模型对黄海南部小黄鱼渔获量时间序列的变化趋势进行拟合和预测是可行的，在短期预测方面更具优势。不同时间序列数据ARIMA模型的p、d、q值不尽一致，在数据分析时不能简单地套用固定模型，应根据相关理论指导和分析，确定适宜的p、d、q值。
|
| 关 键 词： | 小黄鱼 资源量 时间序列分析 ARIMA模型 黄海南部 |
| 收稿时间： | 2020-03-25 |
Application of time series analysis model on stock prediction of small yellow croaker (Larimichthys polyactis) in the southern Yellow Sea |
| |
| Institution: | 1.College of Marine Sciences, Shanghai Ocean University, Shanghai 201306, China2.Jiangsu Marine Fisheries Research Institute, Nantong 226007, China |
| |
| Abstract: | In this paper, the time series analysis model ARIMA (1, 2, 0) was applied to simulate and predict the stock of small yellow croaker (Larimichthys polyactis) based on the monitoring catches data of canvas stow net in the southern Yellow Sea from 2003 to 2014 and verified by the monitoring catches data of 2015 and 2016. The results showed that the simulated and actual values for the catch yield from 2003 to 2014 were correlated significantly (p<0.05) and the correlation coefficient was 0.881. The relative error between predicted and actual value in 2015 and 2016 were respectively 6.73% and 22.75%, the overall relative error was 14.74% and the regression equation fitted the real situation better, which illustrated that the time series analysis model ARIMA (1, 2, 0) can be applied to simulate the catches trend of L. polyactis and predict the catch stock, especially superior in short-term forecasting. However, in any case the fixed model of L. polyactis is not always suitable for all data analysis, and the values of p, d and q in ARIMA model are considered to be variable according to different time series. Therefore, the optimal values of p, d and q should be determined based on the guidance and analysis of relevant theories in order to avoid copying directly the fixed model. |
| |
| Keywords: | |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《海洋学报》浏览原始摘要信息 |
| 点击此处可从《海洋学报》下载免费的PDF全文 |
|
