{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:34:01Z","timestamp":1786494841678,"version":"3.56.0"},"reference-count":31,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 41871325"],"award-info":[{"award-number":["No. 41871325"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&amp;D Program of China","award":["No. 2019YFD0900805"],"award-info":[{"award-number":["No. 2019YFD0900805"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>In response to the deficiency of the detection capability of traditional remote sensing means (scatterometer, microwave radiometer, etc.) for high wind speed above 25 m\/s, this paper proposes a GNSS-R technique combined with a machine learning method to invert high wind speed at sea surface. The L1-level satellite-based data from the Cyclone Global Navigation Satellite System (CYGNSS), together with the European Centre for Medium-Range Weather Forecasts (ECMWF) and the National Centers for Environmental Prediction (NCEP) data, constitute the original sample set, which is processed and trained with Support Vector Regression (SVR), the combination of Principal Component Analysis (PCA) and SVR (PCA-SVR), and Convolutional Neural Network (CNN) methods, respectively, to finally construct a sea surface high wind speed inversion model. The three models for high wind speed inversion are certified by the test data collected during Typhoon Bavi in 2020. The results show that all three machine learning models can be used for high wind speed inversion on sea surface, among which the CNN method has the highest inversion accuracy with a mean absolute error of 2.71 m\/s and a root mean square error of 3.80 m\/s. The experimental results largely meet the operational requirements for high wind speed inversion accuracy.<\/jats:p>","DOI":"10.3390\/rs13163324","type":"journal-article","created":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T04:22:20Z","timestamp":1629692540000},"page":"3324","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["High Wind Speed Inversion Model of CYGNSS Sea Surface Data Based on Machine Learning"],"prefix":"10.3390","volume":"13","author":[{"given":"Yun","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Marine Intelligent Information and Navigation Remote Sensing Engineering Technology Research Center, Shanghai Ocean University, Shanghai 201306, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiwei","family":"Yin","sequence":"additional","affiliation":[{"name":"Shanghai Marine Intelligent Information and Navigation Remote Sensing Engineering Technology Research Center, Shanghai Ocean University, Shanghai 201306, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9967-7756","authenticated-orcid":false,"given":"Shuhu","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Marine Intelligent Information and Navigation Remote Sensing Engineering Technology Research Center, Shanghai Ocean University, Shanghai 201306, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanting","family":"Meng","sequence":"additional","affiliation":[{"name":"Shanghai Spaceflight Institute of TT&C and Telecommunication, Shanghai 201109, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0682-9157","authenticated-orcid":false,"given":"Yanling","family":"Han","sequence":"additional","affiliation":[{"name":"Shanghai Marine Intelligent Information and Navigation Remote Sensing Engineering Technology Research Center, Shanghai Ocean University, Shanghai 201306, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyu","family":"Yan","sequence":"additional","affiliation":[{"name":"Shanghai Marine Intelligent Information and Navigation Remote Sensing Engineering Technology Research Center, Shanghai Ocean University, Shanghai 201306, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,8,23]]},"reference":[{"key":"ref_1","first-page":"35","article-title":"Study on the inversion method of ocean wind field measurement by satellite-borne microwave scatterometer","volume":"5","author":"Lin","year":"1997","journal-title":"Acta Oceanol. Sin."},{"key":"ref_2","first-page":"76","article-title":"Key technologies and scientific aspects of remote sensing of sea surface wind fields by all-polarization microwave radiometer","volume":"10","author":"Wang","year":"2008","journal-title":"Strateg. Stud. CAE"},{"key":"ref_3","first-page":"2436","article-title":"Evaluation of variational scheme for synthetic aperture radar wind field inversion","volume":"64","author":"Zhang","year":"2021","journal-title":"Chin. J. Geophys."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"375","DOI":"10.5194\/wes-5-375-2020","article-title":"Europe\u2019s offshore winds assessed with synthetic aperture radar, ASCAT and WRF","volume":"5","author":"Hasager","year":"2020","journal-title":"Wind Energy Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"7683","DOI":"10.1029\/2019JC015493","article-title":"Comparisons of Ocean Radiative Transfer Models With SMAP and AMSR2 Observations","volume":"124","author":"Kilic","year":"2019","journal-title":"J. Geophys. Res. Oceans"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"6829","DOI":"10.1109\/TGRS.2014.2303831","article-title":"Spaceborne GNSS-R Minimum Variance Wind Speed Estimator","volume":"52","author":"Clarizia","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4419","DOI":"10.1109\/TGRS.2016.2541343","article-title":"Wind Speed Retrieval Algorithm for the Cyclone Global Navigation Satellite System (CYGNSS) Mission","volume":"58","author":"Clarizia","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1016\/j.asr.2018.01.013","article-title":"Waveform-based spaceborne GNSS-R wind speed observation: Demonstration and analysis using UK TechDemoSat-1 data","volume":"61","author":"Wang","year":"2018","journal-title":"ADV Space Res."},{"key":"ref_9","first-page":"66","article-title":"Development of the CYGNSS Geophysical Model Function for Wind Speed","volume":"12","author":"Ruf","year":"2018","journal-title":"IEEE J-STARS"},{"key":"ref_10","first-page":"708","article-title":"Wind Speed Estimation from CYGNSS Using Artificial Neural Networks","volume":"13","author":"Reynolds","year":"2020","journal-title":"IEEE J-STARS"},{"key":"ref_11","first-page":"462","article-title":"Research on the inversion method of satellite-based GNSS-R sea surface wind speed","volume":"40","author":"Yang","year":"2018","journal-title":"J. Electron. Inform. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ruf, C., Asharaf, S., Balasubramaniam, R., Gleason, S., Lang, T., McKague, D., Twigg, D., and Waliser, D. (2019). InOrbit Performance of the Constellation of CYGNSS Hurricane Satellites. Bull. Am. Meteorol. Soc.","DOI":"10.1175\/BAMS-D-18-0337.1"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1142","DOI":"10.1109\/TGRS.2015.2475317","article-title":"Generalized Linear Observables for Ocean Wind Retrieval From Calibrated GNSS-R Delay\u2013Doppler Maps","volume":"54","author":"Garrison","year":"2016","journal-title":"IEEE Trans. Geosci. Remote"},{"key":"ref_14","first-page":"3799","article-title":"Retrieving Hurricane Maximum Winds Using Simulated CYGNSS Power-Versus-Delay Waveforms","volume":"10","author":"Said","year":"2017","journal-title":"IEEE J-STARS"},{"key":"ref_15","first-page":"21","article-title":"Track-Based Cyclone Maximum Wind Retrievals Using the Cyclone Global Navigation Satellite System (CYGNSS) Mission Full DDMs","volume":"13","author":"Johnson","year":"2019","journal-title":"IEEE J-STARS"},{"key":"ref_16","first-page":"3591","article-title":"Matched Filter Cyclone Maximum Wind Retrievals Using CYGNSS: Progress Update and Error Analysis","volume":"99","author":"Katzberg","year":"2021","journal-title":"IEEE J-STARS"},{"key":"ref_17","first-page":"22","article-title":"An inversion method for ocean surface wind speed based on time-lapse-Doppler images","volume":"35","author":"Wu","year":"2019","journal-title":"Bull. Sci. Technol."},{"key":"ref_18","first-page":"198","article-title":"GNSS-R sea surface wind speed inversion based on BP neural network","volume":"40","author":"Gao","year":"2019","journal-title":"Chin. J. Aeronaut"},{"key":"ref_19","unstructured":"Wang, S. (2020). Research on GNSS-R Sea Surface Wind Speed Inversion Algorithm Based on Neural Network Model. [Master\u2019s Thesis, University of Chinese Academy of Sciences]."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Cardellach, E., Nan, Y., and Li, W. (2020). Variational Retrievals of High Winds Using Uncalibrated CyGNSS Observables. Remote Sens., 12.","DOI":"10.3390\/rs12233930"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Sa\u00efd, F., Jelenak, Z., Park, J., and Chang, P. (2021). The NOAA Track-Wise Wind Retrieval Algorithm and Product Assessment for CyGNSS. IEEE Trans. Geosci. Remote Sens., 1\u201324.","DOI":"10.1109\/TGRS.2021.3087426"},{"key":"ref_22","first-page":"35","article-title":"Analysis of satellite-based GNSS-R typhoon observations","volume":"4","author":"Shao","year":"2020","journal-title":"Remote Sens. Inf."},{"key":"ref_23","first-page":"1497","article-title":"Evaluation of mean sea level pressure and surface wind speed from two numerical models in China","volume":"37","author":"Gong","year":"2015","journal-title":"J. Glaciol. Geocryol."},{"key":"ref_24","first-page":"109","article-title":"Analysis of wind speed characteristics based on four reanalysis data offshore China","volume":"44","author":"Hou","year":"2017","journal-title":"Tianjin Sci. Technol."},{"key":"ref_25","first-page":"53","article-title":"Simulation of the 2015 Northwest Pacific tropical cyclone based on the East Asian regional reanalysis system","volume":"40","author":"Pan","year":"2020","journal-title":"J. Zhanjiang Ocean Univ."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"115376","DOI":"10.1016\/j.eswa.2021.115376","article-title":"Fuzzy Inference System Tree with Particle Swarm Optimization and Genetic Algorithm: A novel approach for PM10 forecasting","volume":"183","author":"Saini","year":"2021","journal-title":"Syst. Appl."},{"key":"ref_27","first-page":"171","article-title":"Machine Learning: ECML-94 Volume 784|| Estimating attributes: Analysis and extensions of RELIEF","volume":"11","author":"Bergadano","year":"1997","journal-title":"LNCS"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1730","DOI":"10.1198\/jasa.2006.s153","article-title":"Kernel Methods for Pattern Analysis","volume":"101","author":"Last","year":"2006","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1023\/B:STCO.0000035301.49549.88","article-title":"A tutorial on support vector regression","volume":"14","author":"Alex","year":"2004","journal-title":"Stat. Comput."},{"key":"ref_30","first-page":"69","article-title":"Research on prediction of industrial solid waste generation in China based on PCA-SVR model","volume":"48","author":"Liu","year":"2020","journal-title":"J. Henan Normal Univ."},{"key":"ref_31","unstructured":"Ma, Q., Zhang, X., Zhang, C., Zhou, H., and Wu, Z. (2021). Cross-wave velocity prediction based on one-dimensional convolutional neural network. Lith Res., 1\u201310. Available online: http:\/\/kns.cnki.net\/kcms\/detail\/62.1195.TE.20210530.1549.002.html."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/16\/3324\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:49:30Z","timestamp":1760165370000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/16\/3324"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,23]]},"references-count":31,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2021,8]]}},"alternative-id":["rs13163324"],"URL":"https:\/\/doi.org\/10.3390\/rs13163324","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,23]]}}}