| 190 | 1 | 154 |
| 下载次数 | 被引频次 | 阅读次数 |
构建了一种适用于CALIOP透明云下数据的深度神经网络模型，用于反演海面风速。通过使用2017年1、4、7、10月的CALIOP夜间数据和准同步的AMSR-2风速数据对模型进行训练，然后将该模型应用于2018年1—9月的夜间云下数据，实现海面风速的反演。与无云数据对比，所得反演结果表明精度接近，标准偏差最大为0.89 m/s,最低相关系数为0.94。在引入ERA5有效波高数据后，反演精度进一步提升，标准偏差最大为0.68 m/s,相关系数达到0.96以上。研究结果表明，透明云下数据同样可用于风速反演，深度神经网络能够有效地从CALIOP数据中提取风速信息，并结合有效波高数据进一步提高反演精度。
Abstract：A deep neural network model was developed to retrieve sea surface wind speed from CALIOP transparent cloud data. The model was trained using CALIOP nighttime data from January, April, July, and October 2017 along with quasi-synchronous AMSR-2 wind speed data. Subsequently, it was applied to nighttime sub-cloud data from January to September 2018 for surface wind speed inversion. Comparative analysis with cloud-free data revealed close accuracy, a maximum standard deviation of 0.89 m/s, and a minimum correlation coefficient of 0.94. Upon integration of ERA5 significant wave height data, the inversion accuracy improved further with a reduced maximum standard deviation of 0.68 m/s and a correlation coefficient exceeding 0.96. These results demonstrate the potential use of transparent cloud data for wind velocity inversion and highlight the effectiveness of deep neural networks in extracting wind velocity information from CALIOP data while enhancing inversion accuracy through integration with significant wave height data.
[1] Hong B,Xue H,Zhu L,et al.Climatic change of summer wind direction and its impact on hydrodynamic circulation in the Pearl River Estuary[J].Journal of Marine Science and Engineering,2022,10(7):842-847.
[2] Cox C,Munk W.Measurement of the roughness of the sea surface from photographs of the Sun’s Glitter[J].Journal of the Optical Society of America,1954,44(11):838-850.
[3] Wu Jin.Mean square slopes of the wind-disturbed water surface,their magnitude,directionality,and composition[J].Radio Science,1990,25(1):37-48
[4] Hu Y,Stamnes K,Vaughan M,et al.Sea surface wind speed estimation from space-based lidar measurements[J].Atmospheric Chemistry and Physics,2008,8(13):3593-3601.
[5] 吴东，张小雪，阎逢旗，等.基于星载激光雷达数据的海面风速探测[J].光学学报，2012,32(8):251-257.Wu D,Zhang X X,Yan F Q,et al.Sea surface wind speed detection by using the data of CALIPSO lidar[J].Acta Optica Sinica,2012,32(8):251-257.
[6] Monaldo F,Dobson E.On using significant wave height and radar cross section to improve radar altimeter measurements of wind speed[J].Journal of Geophysical Research,1989,94:12699-12701.
[7] Gourrion J,Vandemark D,Bailey S,et al.Satellite Altimeter models for Surface Wind Speed Developed Using Ocean Satellite Crossovers [R].[s.l.]:Ifremer,2000.
[8] Han S,Zhang H,Zheng Y.A global study of temporal and spatial variation of SWH and wind speed and their correlation[J].Acta Oceanologica Sinica,2014,33(11):48-54.
[9] Tian J,Hang X,Jian S.The research on ocean surface wind speed retrieval by neural network algorithm for HY2 Altimeter[J].Geosciences Research,2017,2(1).doi:10.22606/GR.2017.21001.
[10] Li X,Qin T,Wu K.Retrieval of sea surface wind speed from spaceborne SAR over the Arctic marginal ice zone with a neural network[J].Remote Sensing,2020,12(20):3291.
[11] Liu X,Bai W,Xia J,et al.FA-RDN:A hybrid neural network on GNSS-R sea surface wind speed retrieval[J].Remote Sensing,2021,13(23):4820.
[12] Murphy A,Hu Y X.Retrieving aerosol optical depth and high spatial resolution ocean surface wind speed from CALIPSO:A neural network approach[J].Frontiers in Remote Sensing,2021,1:614029.
[13] 张馨毅，吴东，杨振威，等.星载激光雷达数据海面风速反演模型研究[J].光学学报，2022,42(18):183-189.Zhang X Y,Wu D,Yang Z W,et al.Models of sea surface wind speed retrieval by spaceborne lidar data[J].Acta Optica Sinica,2022,42(18):183-189.
[14] He M,Hu Y,Huang J,et al.Aerosol optical depth under "clear" sky conditions derived from sea surface reflection of lidar signals[J].Optics Express,2016,24(26):A1618-A1634.
[15] Kodis R.A note on the theory of scattering from an irregular surface[J].IEEE Transactions on Antennas and Propagation,1966,14(1):77-82.
[16] Menzies R,Tratt D,Hunt W.Lidar in-space technology experiment measurements of sea surface directional reflectance and the link to surface wind speed[J].Applied Optics,1998,37(24):5550-5559.
[17] Huang X,Zhang B,Perrie W,et al.A novel deep learning method for marine oil spill detection from satellite synthetic aperture radar imagery[J].Marine Pollution Bulletin,2022,179:113666.doi:10.1016/j.marpolbul.2022.113666.
[18] Lyu G.SAR target detection based on domain adaptive faster R-CNN with small training data size[J].Remote Sensing,2021,13(21):4202.
[19] Jiang Y,Qiao R,Zhu Y,et al.Data fusion of atmospheric ozone remote sensing Lidar according to deep learning[J].The Journal of Supercomputing,2021,77:6904-6919.doi:10.1007/s11277-020-03537-y.
[20] 陈标，吴东.基于CALIOP和MODIS的北极地区海雾检测研究[J].大气与环境光学学报，2022,17(2):267-278.Chen B,Wu D.Arctic sea fog detection using CALIOP and MODIS[J].Journal of Atmospheric and Environmental Optics,2022,17(2):267-278.
[21] He K M,Zhang X Y,Ren S Q,et al.Deep residual learning for image recognition[J].IEEE Conference on Computer Vision and Pattern Recognition,2016:770-778.
[22] Ioffe S,Szegedy C.Batch Normalization:Accelerating Deep Network Training by Reducing Internal Covariate Shift[C].Lille,France:Proceedings of the 32nd International Conference on International Conference on Machine Learning,2015:448-456.
[23] Geoffrey E,Nitish S,Alex K,et al.Improving neural networks by preventing co-adaptation of feature detectors[EB/OL].(2012-07-03)[2023-8-15].https://www.semanticscholar.org/reader/0060745e006c5f14ec326904119dca19c6545e51.
[24] Jeffrey L,Owen M.Automated analysis of ocean surface directional wave spectra[J].American Meteorological Society,2001,18(2):277-293.
[25] Jean-Raymond B.Ocean wave model output parameters [EB/OL].(2020-02-27)[2023-8-15].https://confluence.ecmwf.int/download/attachments/59774192/wave_parameters.
[26] 冯士笮，李凤岐，李少菁.海洋科学导论[M].北京：高等教育出版社，1999.Feng Shizuo,Li Fengqi,Li Shaojing.Introduction to Marine Science[M].Beijing:Higher Education Press,1999.
基本信息:
DOI：10.16441/j.cnki.hdxb.20230241
中图分类号:P715.7
引用信息:
[1]罗敦艺,吴东,张馨毅,等.基于深度神经网络的CALIOP透明云下海面风速反演[J].中国海洋大学学报(自然科学版),2024,54(12):130-139.DOI:10.16441/j.cnki.hdxb.20230241.
基金信息:
中国科学院空间激光信息传输与探测技术重点实验室开放基金项目“星载激光海面粗糙度探测及其应用研究”资助~~
2023-08-13
2023
2024-04-03
2024-04-12
2024
1
2024-11-26
2024-11-26