利用机器学习方法改进风云3C星载GNSS掩星温度廓线
作者:
中图分类号:

P228.4

基金项目:

河南省农业气象保障与应用技术重点实验室应用技术研究基金(KM202224)


Improving temperature profile of FY-3C GNSS radio occultation by machine learning methods
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    本文使用BP神经网络、随机森林回归算法,对2017年全年风云三号C星(FY-3C)GNSS掩星温度廓线数据进行修正和评估.结果表明:在全球范围内,两种方法均可以修正GNSS掩星温度数据,随机森林回归算法的修正效果优于神经网络方法,随机森林回归算法和神经网络方法修正后的结果与再分析数据的平均绝对误差分别为0.03K与0.32K,均方误差分别为0.09K2与1.02K2.将全球按照10°×10°划分为324个网格后,随机森林回归算法对平均绝对误差与均方误差修正的正向收益分别为97.53%与92.9%,神经网络方法对平均绝对误差与均方误差修正的正向收益分别为75.61%与67.9%.

    Abstract:

    In this paper,BP neural network and random forest regression algorithm are used to correct the temperature profile data of FY-3C GNSS radio occultation in 2017.The results show that both methods can correct FY-3C radio occultation temperature data,but the performance of the random forest regression is better than that of the neural network.For the random forest regression algorithm and the neural network,the mean absolute errors between the corrected results and the reanalysis data are 0.03 K and 0.32 K,respectively,and the mean square errors are 0.09 K2 and 1.02 K2,respectively.When the globe is divided into 324 grids of 10°×10°,the random forest regression algorithm yields positive returns of 97.53% and 92.9% for average absolute error and mean square error corrections,respectively,and neural network produces positive returns of 75.61% for average absolute error correction and 67.9% for mean square error correction.

    参考文献
    [1] Gobiet A,Kirchengast G.Advancements of global navigation satellite system radio occultation retrieval in the upper stratosphere for optimal climate monitoring utility[J].Journal of Geophysical Research:Atmospheres,2004,109(D24):D24110
    [2] Kursinski E R,Hajj G A,Bertiger W I,et al.Initial results of radio occultation observations of earth's atmosphere using the global positioning system[J].Science,1996,271(5252):1107-1110
    [3] 赵齐乐,刘经南,葛茂荣,等.CHAMP卫星cm级精密定轨[J].武汉大学学报(信息科学版),2006,31(10):879-882 ZHAO Qile,LIU Jingnan,GE Maorong,et al.Precision orbit determination of CHAMP satellite with cm-level accuracy[J].Geomatics and Information Science of Wuhan University,2006,31(10):879-882
    [4] Wickert J,Reigber C,Beyerle G,et al.Atmosphere sounding by GPS radio occultation:first results from CHAMP[J].Geophysical Research Letters,2001,28(17):3263-3266
    [5] 青盛.地基GPS水汽反演的研究[D].成都:西南交通大学,2009 QING Sheng.Research on the computation of atmospheric water vapour base on ground-GPS[D].Chengdu:Southwest Jiaotong University,2009
    [6] Hao N,Koukouli M E,Inness A,et al.GOME-2 total ozone columns from MetOp-A/MetOp-B and assimilation in the MACC system[J].Atmospheric Measurement Techniques,2014,7(9):2937-2951
    [7] Hwang Y,Lee B S,Kim Y R,et al.GPS-based orbit determination for KOMPSAT-5 satellite[J].ETRI Journal,2011,33(4):487-496
    [8] Lin C Y,Lin C C H,Liu J Y,et al.The early results and validation of FORMOSAT-7/COSMIC-2 space weather products:global ionospheric specification and Neaided Abel electron density profile[J].Journal of Geophysical Research:Space Physics,2020,125(10):e2020JA028028
    [9] 郭佳宾,金双根.利用FY-3C卫星GNSS掩星数据分析中国区域对流层顶参数变化[J].大地测量与地球动力学,2021,41(1):21-26 GUO Jiabin,JIN Shuanggen.Variations of tropopause parameters over China from FY-3C GNSS radio occultation observations[J].Journal of Geodesy and Geodynamics,2021,41(1):21-26
    [10] 廖蜜,张鹏,毕研盟,等.风云三号气象卫星掩星大气产品精度的初步检验[J].气象学报,2015,73(6):1131-1140 LIAO Mi,ZHANG Peng,BI Yanmeng,et al.A preliminary estimation of the radio occultation products accuracy from the Fengyun-3C meteorological satellite[J].Acta Meteorologica Sinica,2015,73(6):1131-1140
    [11] 徐晓华,朱洲宗,罗佳.利用IGRA2探空数据和COSMIC掩星资料对FY-3C掩星中性大气产品进行质量分析[J].武汉大学学报(信息科学版),2020,45(3):384-393 XU Xiaohua,ZHU Zhouzong,LUO Jia.Quality analysis of the neutral atmospheric products from FY-3C radio occultation based on IGRA2 radiosonde data and COSMIC radio occulation products[J].Geomatics and Information Science of Wuhan University,2020,45(3):384-393
    [12] 魏晋德.风云三号C星大气掩星数据质量分析及对流层顶特征研究[D].徐州:中国矿业大学,2021 WEI Jinde.An evaluation of FY-3C radio occultation data quality and study of tropopause characteristics[D].Xuzhou:China University of Mining and Technology,2021
    [13] Uppala S,Dee D,Kobayashi S,et al.Towards a climate data assimilation system:status update of ERA-Interim[J].ECMWF Newsletter,2008,115(7):12-18
    [14] Dee D P,Uppala S M,Simmons A J,et al.The ERA-Interim reanalysis:configuration and performance of the data assimilation system[J].Quarterly Journal of the Royal Meteorological Society,2011,137(656):553-597
    [15] 孟宪贵,郭俊建,韩永清.ERA5再分析数据适用性初步评估[J].海洋气象学报,2018,38(1):91-99 MENG Xiangui,GUO Junjian,HAN Yongqing.Preliminarily assessment of ERA5 reanalysis data[J].Journal of Marine Meteorology,2018,38(1):91-99
    [16] Uppala S M,KÅllberg P W,Simmons A J,et al.The ERA-40 re-analysis[J].Quarterly Journal of the Royal Meteorological Society,2005,131(612):2961-3012
    [17] Haykin S.Neural networks and learning machines[M].3rd ed.Upper Saddle River,NJ:Prentice Hall,2008
    [18] Segal M R.Machine learning benchmarks and random forest regression[J].Center for Bioinformatics & Molecular Biostatistics,2004
    [19] Jayalakshmi T,Santhakumaran A.Statistical normalization and back propagation for classification[J].International Journal of Computer Theory and Engineering,2011,3(1):1793-8201
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

郭佳宾,程丽丹,金双根.利用机器学习方法改进风云3C星载GNSS掩星温度廓线[J].南京信息工程大学学报(自然科学版),2022,14(6):667-673
GUO Jiabin, CHENG Lidan, JIN Shuanggen. Improving temperature profile of FY-3C GNSS radio occultation by machine learning methods[J]. Journal of Nanjing University of Information Science & Technology, 2022,14(6):667-673

复制
分享
文章指标
  • 点击次数:456
  • 下载次数: 1440
  • HTML阅读次数: 71
  • 引用次数: 0
历史
  • 收稿日期:2022-07-31
  • 在线发布日期: 2022-12-14

地址:江苏省南京市宁六路219号    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持:北京勤云科技发展有限公司