ID 原文 译文
54407 海洋相关参数的遥感反演对灾害预警等有重要作用。 Remote sensing plays an important role in retrievals of ocean-related parameters, which are vital in disaster warning.
54408 随着硬件的发展，星上实时处理成为可能。 With the development of hardware on-board satellites, real-time retrievals become possible.
54409 海洋参数中，海面风场和浪场占据了重要地位。 Among ocean parameters, sea surface wind fields and wave heights are important.
54410 本文的研究，首先对星上处理进行说明，并叙述星上环境的仿真方法。 The research in this paper firstly explains the on-board processing procedures and describes the simulation method of the on-board environment.
54411 然后针对台风海面风场和海面浪场，使用散射计、辐射计联合观测以及高度计的观测，进行星上快速处理的实现方法研究。对选取的方法，使用卫星遥感数据，在星上仿真环境下实现运行。 Then, combined observation of scatterometer and radiometer, along with altimeter observations are used to realize corresponding method of fast processing on-board the satellites for the typhoon sea surface wind field and sea surface wave height
54412 结果表明，研究中使用的方法能有效实现星上处理。 The results show that the method used in the study can effectively achieve on-board processing.
54413 在“通导遥”一体化趋势下，该方法的应用将有效辅助自动的实时决策，实现灾害预警。 Under the trend of integration of “communication, navigation and remote sensing”, the application of this method will effectively assist automatic real-time decision-making and contribute to disaster warning.
54414 下一步研究将实现更多参数的星上平台仿真。 The next step of the research will be to achieve more parameters on-board via platform simulation.
54415 当前海面目标检测方法多基于统计理论，检测性能受背景统计特性假设的影响， In this paper, the feature generalization learning ability of deep learning is used to process the signal time series amplitude information.
54416 本文从信号预测和特征分类两个角度，分别采用长短时记忆网络(LSTM)和卷积神经网络(CNN)对信号时间序列幅度信息进行处理，用于海上目标一维序列雷达信号检测，该方法不需事先假设背景统计特性，泛化能力更强。 From the perspectives of signal prediction and feature classification, respectively, long short-term memory networks(LSTM) and convolutional neural networks(CNN) are used for the detection of target's one-dimensional sequence radar signal.