NSSC OpenIR
基于树模型机器学习方法的GNSS-R海面风速反演
Alternative TitleGNSS-R Sea Surface Wind Speed Inversion Based on Tree Model Machine Learning Method
骆黎明; 白伟华; 孙越强; 夏俊明
Source Publication空间科学学报
2020
Volume40Issue:4Pages:595-601; AR:0254-6124(2020)40:4<595:JYSMXJ>2.0.TX;2-#
ISSN0254-6124
Language中文
Keyword海面风速 反演 机器学习 GNSS-R GNSS-R Sea surface wind speed Inversion Machine learning
AbstractGNSS-R是基于GNSS卫星反射信号的一种新技术.GNSS-R技术可以运用到海面风场反演中,传统的GNSS-R技术反演海面风场主要有波形匹配和经验函数两种方法,风速反演精度约为2m·s~(-1).波形匹配方法耗时多,计算量大;经验函数方法通常只使用少量物理观测量,会造成信息浪费,损失一定的反演精度.为了提高海面风速的反演精度,引入机器学习领域常用的树模型算法决策树、随机森林、GBDT等对海面风速进行预测.利用GNSS-R与ECMWF数据构成训练集和验证集,训练集用于模型学习,验证集用于检验模型的反演效果.实验结果显示,决策树和随机森林预测误差约为0.6m·s~(-1),GBDT等算法的预测误差约为2m·s~(-1),满足风速反演要求.与GNSS-R传统反演方法相比,机器学习树模型算法效果更好,在验证集上表现稳定且误差较小.因此,可以将机器学习树模型算法运用到海面风速反演中.
Other AbstractGNSS-R is a new technique based on GNSS satellite reflection signals,and it can be applied to the inversion of sea surface wind field.The traditional GNSS-R technology inversion of sea surface wind field mainly has waveform matching and experience function.The waveform matching method is time-consuming and computationally intensive;the empirical function method often uses only a small amount of physical observations,which causes waste of additional information and loss of certain inversion precision.The accuracy of the traditional method of wind speed inversion is about 2 m·s~(-1).In order to improve the inversion accuracy of sea surface wind speed,the tree model algorithm decision tree,random forest and GBDT commonly used in the field of machine learning are introduced to predict the sea surface wind speed.The training set and the verification set are constructed by using GNSS-R and ECMWF data.The training set is used for model learning,and the verification set is used to test the inversion effect of the model.The prediction error of decision tree and random forest is about 0.6m·s~(-1),and the prediction error of GBDT and other algorithms is about 2m·s~(-1),which meets the requirements of wind speed inversion.Compared with the traditional GNSS-R inversion method,the machine learning tree model algorithm performs better and has stable performance and less error on the verification set.Therefore,the machine learning tree model algorithm can be applied to the sea surface wind speed inversion.
Indexed ByCSCD
Citation statistics
Document Type期刊论文
Identifierhttp://ir.nssc.ac.cn/handle/122/7431
Collection中国科学院国家空间科学中心
Affiliation1.骆黎明, 中国科学院国家空间科学中心
2.中国科学院大学
3.北京市天基空间环境探测重点实验室
4.北京市天基空间环境探测重点实验室
5.北京 100190
6.100049
7.100190, 中国.
8.白伟华, 中国科学院国家空间科学中心
9.中国科学院大学
10.北京市天基空间环境探测重点实验室
11.北京市天基空间环境探测重点实验室
12.北京 100190
13.100049
14.100190, 中国.
15.孙越强, 中国科学院国家空间科学中心
16.中国科学院大学
17.北京市天基空间环境探测重点实验室
18.北京市天基空间环境探测重点实验室
19.北京 100190
20.100049
21.100190, 中国.
22.夏俊明, 中国科学院国家空间科学中心
23.北京市天基空间环境探测重点实验室,
24.北京市天基空间环境探测重点实验室
25.北京
26.北京 100190
27.100190, 中国.
28.Luo Liming, National Space Science Center,Chinese Academy of Sciences
29.University of Chinese Academy of Sciences
30.Beijing Key Laboratory of Space Environment Explorations
31.Beijing Key Laboratory of Space Environment Explorations
32., Beijing
33.Beijing
34.Beijing 100190
35.100049
36.100190.
37.Bai Weihua, National Space Science Center,Chinese Academy of Sciences
38.University of Chinese Academy of Sciences
39.Beijing Key Laboratory of Space Environment Explorations
40.Beijing Key Laboratory of Space Environment Explorations
41., Beijing
42.Beijing
43.Beijing 100190
44.100049
45.100190.
46.Sun Yueqiang, National Space Science Center,Chinese Academy of Sciences
47.University of Chinese Academy of Sciences
48.Beijing Key Laboratory of Space Environment Explorations
49.Beijing Key Laboratory of Space Environment Explorations
50., Beijing
51.Beijing
52.Beijing 100190
53.100049
54.100190.
55.Xia Junming, National Space Science Center,Chinese Academy of Sciences
56.Beijing Key Laboratory of Space Environment Explorations,
57.Beijing Key Laboratory of Space Environment Explorations
58.Beijing
59.Beijing 100190
60.100190.
61.limingluo6@163.com
Recommended Citation
GB/T 7714
骆黎明,白伟华,孙越强,等. 基于树模型机器学习方法的GNSS-R海面风速反演[J]. 空间科学学报,2020,40(4):595-601; AR:0254-6124(2020)40:4<595:JYSMXJ>2.0.TX;2-#.
APA 骆黎明,白伟华,孙越强,&夏俊明.(2020).基于树模型机器学习方法的GNSS-R海面风速反演.空间科学学报,40(4),595-601; AR:0254-6124(2020)40:4<595:JYSMXJ>2.0.TX;2-#.
MLA 骆黎明,et al."基于树模型机器学习方法的GNSS-R海面风速反演".空间科学学报 40.4(2020):595-601; AR:0254-6124(2020)40:4<595:JYSMXJ>2.0.TX;2-#.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[骆黎明]'s Articles
[白伟华]'s Articles
[孙越强]'s Articles
Baidu academic
Similar articles in Baidu academic
[骆黎明]'s Articles
[白伟华]'s Articles
[孙越强]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[骆黎明]'s Articles
[白伟华]'s Articles
[孙越强]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.