空天地海一体化海洋环境数据多步预测 |
| |
引用本文: | 李志刚,孙晨伟,魏彪,孙晓川. 空天地海一体化海洋环境数据多步预测[J]. 信号处理, 2022, 38(8): 1620-1631. DOI: 10.16798/j.issn.1003-0530.2022.08.007 |
| |
作者姓名: | 李志刚 孙晨伟 魏彪 孙晓川 |
| |
作者单位: | 1.华北理工大学人工智能学院,河北 唐山 063210 |
| |
基金项目: | 国家重点研发计划项目---政府间国际科技创新合作重点专项2017YFE0135700河北省高等学校科学技术研究项目---重点项目ZD2021088 |
| |
摘 要: | 辅助海洋管理决策的多步预测预警意义重大且极具挑战性。实时、稳定、高效的广域海洋环境数据获取是保障多步预测性能的前提,未来6G空天地海一体化网络部署将有效地提升海洋分布式态势感知能力,提供高质量的数据支撑。众所周知,多步长模式下数据间的时序依赖性被极大地弱化,对此,本文提出了基于多阶段特征学习的海洋环境数据多步预测模型。结构上,该模型主要包括卷积神经网络(Convolutional Neural Networks,CNN)、优化组合的长短期记忆网络(Long Short-Term Memory Network,LSTM)和全连接层。这里,CNN用于提取海洋环境数据的细粒度特征,而基于粒子群优化的多LSTM组合方法,可以有效地挖掘数据间的时序依赖关系(粗粒度特征)。实验结果表明该模型的预测性能明显优于CNN、LSTM以及门控制循环单元,并进行了统计验证。
|
关 键 词: | 空天地海一体化 海洋环境数据 多步预测 卷积神经网络 长短期记忆网络 粒子群优化 |
收稿时间: | 2021-12-10 |
Multi-step Prediction of Ocean Environmental Data Based on Space-Air-Ground-Sea Integration |
| |
Affiliation: | 1.College of Artificial Intelligence, North China of Science and Technology, Tangshan, Hebei 063210, China2.Hebei Key Laboratory of Industrial Intelligent Perception, Tangshan, Hebei 063210, China |
| |
Abstract: | ? ?Multi-step prediction and early warning to assist ocean management and decision making were significant and challenging. Real-time, stable and efficient acquisition of wide-area ocean environment data was the premise to guarantee multi-step prediction performance. The air-space-ground-sea integrated 6G network deployment could effectively improve distributed perception capacity, and provide high-quality data support. As we all know, the temporal dependence between data in multi-step mode was greatly weakened. The paper proposed a multi-step prediction model of ocean environmental data based on multi-stage feature learning. In structure, it mainly included a convolutional neural networks (CNN), optimally combined LSTMs (OLSTMs), and a fully connected layer. Here, CNN was used to extract fine-grained features between data, while the multi-LSTM combination method based on particle swarm optimization could effectively capture the temporal dependencies between data (coarse-grained features). Experimental results show that the prediction performance of our proposal is significantly better than CNN, LSTM, and gated recurrent unit (GRU), and some statistical verifications are carried out. |
| |
Keywords: | |
|
| 点击此处可从《信号处理》浏览原始摘要信息 |
|
点击此处可从《信号处理》下载免费的PDF全文 |