Application of Artificial Neural Network to Ocean Surface Wind Field Retrieval Modeling for Spaceborne Scatterometer

Acta Scientiarum Naturalium Universitatis Pekinensis

Previous Articles Next Articles

Application of Artificial Neural Network to Ocean Surface Wind Field Retrieval Modeling for Spaceborne Scatterometer

CHEN Kehai¹,XIEXuetong^{1, 2, 3},HUANG Zhou²,FANG Yu²,CHEN Xiaoxiang¹

¹ Department of Remote Sensing and GIS Engineering, Zhongshan University, Guangzhou, 510275; ² Institute of Remote Sensing and Geographic Information System, Peking University, Beijing, 100871; ³Corresponding Author, E-mail: xiexuetong@yahoo.com.cn

Received:2006-06-16 Online:2007-07-20 Published:2007-07-20

人工神经网络在星载散射计海面风场反演建模中的应用

陈克海¹,解学通^1,2,3,黄舟²,方裕²,陈晓翔¹

¹中山大学遥感与地理信息工程系,广州,510275;²北京大学遥感与地理信息系统研究所,北京,100871;³通讯作者，E-mail:xiexuetong@yahoo.com.cn

Abstract

Abstract: Geophysical model function(GMF) is the basis of scatterometer wind field retrieval and the prerequisite to effective running of the retrieval algorithm. GMF modeling using traditional statistical method usually needs a great number of backscattering coefficient measurements under various observing parameter conditions. Taking SeaWinds, a type of conically scanning scatterometer, as an example, a unified neural network model (NN GMF) for two polarization modes is designed. Moreover, effects of wind speed sampling interval, wind relative direction sampling interval, and the number of measurements on modeling precision are also analyzed in detail. Compared with Qscat-1 model function, the neural network model is able to reflect the backscattering signature of SeaWinds scatterometer very well, even on the condition that sampling intervals of wind speed and wind relative direction are large or the number of backscattering measurements is small.

Key words: scatterometer, ocean surface wind field, geophysical model function(GMF), neural network

摘要： 地球物理模型函数(GMF)是散射计风场反演的基础及算法有效运行的前提条件。采用传统的统计方法建立GMF往往需要大量的、多种参数条件下的雷达后向散射测量数据。以圆锥扫描散射计SeaWinds为例，根据其特点，建立了一个两种极化方式下统一的神经网络模型函数(NN GMF)，并对风速、相对风向采样间隔和测量值数目对模型精度的影响进行了详细分析。通过与Qscat-1模型进行比较，发现该神经网络模型在采样间隔较大或测量值数目较少的情况下,仍能较好地体现SeaWinds散射计的海面后向散射特性。

关键词: 散射计, 海面风场, 地球物理模型函数(GMF), 神经网络

CLC Number:

P 208

CHEN Kehai,XIEXuetong,HUANG Zhou,FANG Yu,CHEN Xiaoxiang. Application of Artificial Neural Network to Ocean Surface Wind Field Retrieval Modeling for Spaceborne Scatterometer[J]. Acta Scientiarum Naturalium Universitatis Pekinensis.

陈克海,解学通,黄舟,方裕,陈晓翔. 人工神经网络在星载散射计海面风场反演建模中的应用[J]. 北京大学学报（自然科学版）.

[1]	LI Dai, WANG Tianmu, ZHANG Si, QIN Yue, XIE Fugui, LIU Xinjun, NIE Zhenguo, HUANG Hongshi. Intelligent Diagnosis on Anterior Cruciate Ligament Deficiency Based on Plantar Pressure and ConvLSTM Neural Network [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2024, 60(1): 109-117.
[2]	LIU Jiaju, LI Jincheng, GUO Huaicheng, YUAN Peng, LI Zheng, ZHANG Yang, WANG Zhiyong. Study on Hydrochemical Change Trend of Yarlung Tsangpo River Based on Artificial Neural Network [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023, 59(6): 1043-1051.
[3]	ZHANG Ling, CAO Jian, ZHANG Yuan, FENG Shuo, WANG Yuan. Reinforcement Learning of Spiking Neural Network Based on Knowledge Distillation [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023, 59(5): 757-763.
[4]	LIU Xiangcheng, CAO Jian, YAO Hongyi, XU Pengtao, ZHANG Yuan, WANG Yuan. AdaPruner: Adaptive Channel Pruning and Effective Weights Inheritance [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023, 59(5): 764-772.
[5]	ZHOU Xiangyu, MAO Shanjun, LI Mei. Bearing Fault Diagnosis Method Based on Down-Sampling in Frequency Domain and CNN [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023, 59(2): 251-260.
[6]	ZHAO Dandan, ZHANG Junpeng, MENG Jiana, ZHANG Zhihao, SU Wen. Medical Entity Relation Extraction Based on Pre-trained Model and Hybrid Neural Network [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023, 59(1): 65-75.
[7]	XIE Hao, CAO Jian, LI Pu, ZHAO Xiongbo, ZHANG Xing. A Hardware Accelerator for SSD Object Detection Algorithm Based on FPGA [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2022, 58(6): 1015-1022.
[8]	XU Pengtao, CAO Jian, SUN Wenyu, LI Pu, WANG Yuan, ZHANG Xing. Layer Pruning via Fusible Residual Convolutional Block for Deep Neural Networks [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2022, 58(5): 801-807.
[9]	XU Pengtao, CAO Jian, CHEN Weiqian, LIU Shengrong, WANG Yuan, ZHANG Xing. Post Training Quantization Preprocessing Method of Convolutional Neural Network via Outlier Removal [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2022, 58(5): 808-812.
[10]	QU Yonglin, WEN Xinyu, ZHANG Muqi, LIU Zhe. Develop an Objective Post-processing System with Artificial Neural Network to Improve Numerical Weather Prediction for the Olympic Winter Games Beijing 2022 [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2022, 58(2): 210-220.
[11]	ZHANG Muqi, WEN Xinyu, BAO Yun, QU Yonglin. Statistical Downscaled Climate Projection Dataset for China Using Artificial Neural Network [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2022, 58(2): 221-233.
[12]	ZHANG Yang, XIAN Huiting, ZHAO Zhijie. Real-Time River Water Quality Prediction Model Based on Spatial Correlation and Neural Network Model [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2022, 58(2): 337-344.
[13]	WANG Qian, LI Maoxi, WU Shuixiu, WANG Mingwen. Neural Machine Translation Based on XLM-R Cross-lingual Pre-training Language Model [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2022, 58(1): 29-36.
[14]	LIAO Yiming, OUYANG Chunping, LIU Yongbin, HU Fuyu. Drug-Target Interactions Prediction Based on Meta-path of Heterogeneous Information Network [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2022, 58(1): 37-44.
[15]	WANG Xinlu, HUANG Ran, ZHANG Wenxian, LÜ Baolei, DU Yunsong, ZHANG Wei, LI Bolan, HU Yongtao. Forecasting Ozone and PM_2.5 Pollution Potentials Using Machine Learning Algorithms: A Case Study in Chengdu [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2021, 57(5): 938-950.

Application of Artificial Neural Network to Ocean Surface Wind Field Retrieval Modeling for Spaceborne Scatterometer

人工神经网络在星载散射计海面风场反演建模中的应用

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics