| 基于深度学习的赤潮发生预报方法研究 |
| |
| 引用本文： | 余璇,石绥祥,徐凌宇,王蕾.基于深度学习的赤潮发生预报方法研究[J].海洋通报,2021(5). |
| |
| 作者姓名： | 余璇 石绥祥 徐凌宇 王蕾 |
| |
| 作者单位： | 上海大学 计算机工程与科学学院，上海 200444;上海大学 计算机工程与科学学院，上海 200444；国家海洋信息中心，天津 300171;上海大学 计算机工程与科学学院，上海 200444；上海大学 上海先进通信与数据科学研究院，上海 200444 |
| |
| 基金项目： | 国家重点研发计划 （2016YFC1401900）；海洋信息技术创新中心开放基金 （B201801030） |
| |
| 摘 要： | 赤潮作为海洋灾害,对海洋渔业、生态、经济,以及人类生产、生活造成了严重影响。一直以来,赤潮受到研究者的广泛关注,但由于它的形成机制比较复杂,使得赤潮预报极具挑战性。针对赤潮预报的研究问题,本文收集了厦门海域赤潮发生前后的海洋监测数据,结合皮尔逊相关系数、散布矩阵、复相关系数方法,分析多环境因子与赤潮发生多要素的关联情况,重点采用基于深度学习的LSTM与CNN融合方法,挖掘环境因子的时序依赖,发现序列数据的局部特征,对赤潮发生进行预报。在厦门一号和厦门二号数据集中,本方法在预报未来12 h内的赤潮情况时,RMSE、MAE误差分别达到0.521 8、0.504 3。通过协同对比模型进一步确定赤潮发生的预报概率,在两个数据集上的最终预报准确率分别为67.58%和63.49%。本研究为赤潮的分析预报提供了探索经验,证明了将深度学习方法应用于赤潮预报的可行性。
|
| 关 键 词： | 深度学习 神经网络 赤潮 相关性分析 预报 |
| 收稿时间： | 2021/3/14 0:00:00 |
| 修稿时间： | 2021/6/1 0:00:00 |
Research on red tide occurrence forecast based on deep learning |
| |
| YU Xuan,SHI Suixiang,XU Lingyu,WANG Lei.Research on red tide occurrence forecast based on deep learning[J].Marine Science Bulletin,2021(5). |
| |
| Authors: | YU Xuan SHI Suixiang XU Lingyu WANG Lei |
| |
| Institution: | School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China;School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China; National Marine Data and Information Service, Tianjin 300171, China;School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China;Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai 200444, China; East Sea Information Center of State Oceanic Administration, Shanghai 200136, China |
| |
| Abstract: | Red tides have serious impact on marine fisheries, ecology, economy, and human activities. Red tides have been widely concerned by researchers for a long time. However, due to its complex formation mechanism, red tide forecasting is very challenging. Aiming at the challenges of red tide forecasting, this paper collects the marine monitoring data before and after the occurrence of red tide in Xiamen sea area, and analyzes the correlation between multiple environmental factors and the occurrence of red tide by combining the methods of Pearson correlation coefficient, Scatter matrix, and Multiple correlation coefficient. The fusion method of LSTM and CNN based on deep learning was applied to mine the temporal dependence of environmental factors and find the local features of sequence data, then predict the occurrence of red tides. In the Xiamen No.1 and Xiamen No.2 float datasets, the RMSE and MAE errors of this method reach 0.521 8 and 0.504 3 respectively. The forecast probability of red tide occurrence was further determined through the collaborative comparison model. The final forecast accuracy of the two datasets is 67.58% and 63.49%, respectively. This study provides reference for the analysis and forecasting of red tides, which proves the feasibility of applying deep learning methods to red tide forecasting |
| |
| Keywords: | deep learning neural network red tide correlation analysis forecasting |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《海洋通报》浏览原始摘要信息 |
| 点击此处可从《海洋通报》下载免费的PDF全文 |
|
