Abstract
As an emerging remote sensing technology, GNSS reflectometry (GNSS-R) has been widely investigated for retrieving ocean parameters including ocean significant wave height (SWH). Ocean SWH consists of contribution from swell and wind waves, which are commonly modeled separately in the field of marine science and engineering to facilitate practical application. In this study, we present a deep convolutional neural network (DCNN) model for retrieving swell and wind wave SWHs. The DCNN model makes use of auxiliary data and effective DDM features extracted in the convolution layer, and it is trained by using the ERA5 data and CYGNSS observations. The proposed DCNN model and seven existing models [i.e., random forest, extremely randomized trees, bagging tree (BT), decision tree, support vector machine (SVM), artificial neural network, and convolutional neural network] were extensively tested using the ERA5 and WaveWatch III (WW3) data. The results show that when ERA5 is used as reference data, the proposed DCNN model performs best among the eight models, with the root mean square errors (RMSEs) of retrieving swell and wind wave SWH being better than 0.394 m and 0.397 m, respectively, and the correlation coefficient (R) being 0.90. Compared with the SVM model, RMSEs are improved by 28.82% and 31.92%, respectively. When WW3 is employed as reference, the RMSEs of retrieving swell and wind wave SWH are better than 0.497 m and 0.502 m, respectively, with R of 0.89 and 0.90. Compared with the BT model, RMSEs are improved by 26.74% and 27.41%, respectively. The research also found that the auxiliary variables are important for swell and wind wave SWH retrieval. Furthermore, the retrieval of SWH for swells and wind waves using spaceborne GNSS-R technology is affected by rainfall, resulting in about 6% increase in RMSE. This method provides a new idea for studying global ocean swell and wind waves using CYGNSS data.
Similar content being viewed by others
Data availability
The CYGNSS data used for this study can be downloaded from the Web site (https://podaac.jpl.nasa.gov/dataset/CYGNSS_L1_V3.0); the ERA5 swell SWH and wind waves SWH data are available at https://cds.climate.copernicus.eu/cdsapp#!/home; the Wavewatch III (WW3) swell SWH and wind waves SWH data are available at https://pae-paha.pacioos.hawaii.edu/thredds/catalog/ww3_global/catalog.html?dataset=ww3_global/WaveWatch_III_Global_Wave_Model_best.ncd; the IMERG rainfall data can be downloaded from the Web site (https://gpm.nasa.gov/data/directory).
References
Alonso-Arroyo A, Camps A, Park H, Pascual D, Onrubia R, Martin F (2015) Retrieval of significant wave height and mean sea surface level using the GNSS-R interference pattern technique: results from a three-month field campaign. IEEE Trans Geosci Remote Sens 53(6):3198–3209. https://doi.org/10.1109/tgrs.2014.2371540
Alpers W, Hasselmann K (2007) Spectral signal to clutter and thermal noise properties of ocean wave imaging synthetic aperture radars. Int J Remote Sens 3(4):423–446. https://doi.org/10.1080/01431168208948413
Asgarimehr M, Zavorotny V, Wickert J, Reich S (2018) Can GNSS reflectometry detect precipitation over oceans? Geophys Res Lett 45(22):12585–12592. https://doi.org/10.1029/2018gl079708
Asgarimehr M, Zhelavskaya I, Foti G, Reich S, Wickert J (2020) A GNSS-R geophysical model function: machine learning for wind speed retrievals. IEEE Geosci Remote Sens Lett 17(8):1333–1337. https://doi.org/10.1109/lgrs.2019.2948566
Asgarimehr M, Arnold C, Weigel T, Ruf C, Wickert J (2022) GNSS reflectometry global ocean wind speed using deep learning: development and assessment of CyGNSSnet. Remote Sens Environ 269:112801. https://doi.org/10.1016/j.rse.2021.112801
Balasubramaniam R, Ruf C (2020) Characterization of rain impact on l-band GNSS-R ocean surface measurements. Remote Sens Environ 239:111607. https://doi.org/10.1016/j.rse.2019.111607
Brown GS (1978) Backscattering from a Gaussian-distributed perfectly conducting rough surface. IEEE Trans Antennas Propag 26(3):472–482
Bu J, Yu K (2022a) A new integrated method of CYGNSS DDMA and LES measurements for significant wave height estimation. IEEE Geosci Remote Sens Lett 19:1505605. https://doi.org/10.1109/LGRS.2022.3198131
Bu J, Yu K (2022b) Sea surface rainfall detection and intensity retrieval based on GNSS-reflectometry data from the CYGNSS mission. IEEE Trans Geosci Remote Sens 60:5802015. https://doi.org/10.1109/TGRS.2021.3127943
Bu J, Yu K (2022c) Significant wave height retrieval method based on spaceborne GNSS reflectometry. IEEE Geosci Remote Sens Lett 19:1503705. https://doi.org/10.1109/LGRS.2022.3155563
Bu J, Yu K, Zhu Y, Qian N, Chang J (2020) Developing and testing models for sea surface wind speed estimation with GNSS-R delay Doppler maps and delay waveforms. Remote Sens 12(22):3760. https://doi.org/10.3390/rs12223760
Bu J, Park H, Yu K, Camps A (2022a) Estimation of significant wave height using the features of CYGNSS delay doppler map. In: IGARSS 2022a—2022a IEEE international geoscience and remote sensing symposium, pp 7639–7642. https://doi.org/10.1109/IGARSS46834.2022.9884806
Bu J, Yu K, Han S, Qian N, Lin Y, Wang J (2022b) Retrieval of sea surface rainfall intensity using spaceborne gnss-r data. IEEE Trans Geosci Remote Sens 60:5803116. https://doi.org/10.1109/TGRS.2022.3168928
Bu J, Yu K, Ni J, Yan Q, Han S, Wang J, Wang C (2022c) Machine learning-based methods for sea surface rainfall detection from CYGNSS delay-doppler maps. GPS Solut 26(4):132. https://doi.org/10.1007/s10291-022-01320-5
Bu J, Yu K, Zuo X, Ni J, Li Y, Huang W (2023) GloWS-Net: a deep learning framework for retrieving global sea surface wind speed using spaceborne GNSS-R data. Remote Sens 15(3):590. https://doi.org/10.3390/rs15030590
Chen-Zhang DD, Ruf CS, Ardhuin F, Park J (2016) GNSS-R nonlocal sea state dependencies: model and empirical verification. J Geophys Res Oceans 121(11):8379–8394. https://doi.org/10.1002/2016jc012308
Chu X, He J, Song H, Qi Y, Sun Y, Bai W, Li W, Wu Q (2020) Multimodal deep learning for heterogeneous GNSS-R data fusion and ocean wind speed retrieval. IEEE J Sel Top Appl Earth Observ Remote Sens 13:5971–5981. https://doi.org/10.1109/jstars.2020.3010879
Clarizia MP, Ruf CS (2016) Wind speed retrieval algorithm for the cyclone global navigation satellite system (CYGNSS) mission. IEEE Trans Geosci Remote Sens 54(8):4419–4432. https://doi.org/10.1109/tgrs.2016.2541343
Durden S, Vesecky J (1985) A physical radar cross-section model for a wind-driven sea with swell. IEEE J Ocean Eng 10(4):445–451. https://doi.org/10.1109/JOE.1985.1145133
Elfouhaily T, Chapron B, Katsaros K, Vandemark D (1997) A unified directional spectrum for long and short wind-driven waves. J Geophys Res Oceans 102(C7):15781–15796. https://doi.org/10.1029/97jc00467
Foti G, Gommenginger C, Jales P, Unwin M, Shaw A, Robertson C, Rosello J (2015) Spaceborne GNSS reflectometry for ocean winds: first results from the UK techdemosat-1 mission. Geophys Res Lett 42(13):5435–5441. https://doi.org/10.1002/2015gl064204
Ghavidel A, Camps A (2016) Impact of rain, swell, and surface currents on the electromagnetic bias in GNSS-reflectometry. IEEE J Sel Top Appl Earth Observ Remote Sens 9(10):4643–4649. https://doi.org/10.1109/jstars.2016.2538181
Guo W, Du H, Cheong JW, Southwell BJ, Dempster AG (2022a) GNSS-R wind speed retrieval of sea surface based on particle swarm optimization algorithm. IEEE Trans Geosci Remote Sens 60:4202414. https://doi.org/10.1109/tgrs.2021.3082916
Guo W, Du H, Guo C, Southwell BJ, Cheong JW, Dempster AG (2022b) Information fusion for GNSS-R wind speed retrieval using statistically modified convolutional neural network. Remote Sens Environ 272:112934. https://doi.org/10.1016/j.rse.2022.112934
Hammond ML, Foti G, Gommenginger C, Srokosz M (2020) Temporal variability of GNSS-reflectometry ocean wind speed retrieval performance during the UK TechDemoSat-1 mission. Remote Sens Environ 242:111744. https://doi.org/10.1016/j.rse.2020.111744
Huang F, Garrison JL, Leidner SM, Annane B, Hoffman RN, Grieco G, Stoffelen A (2021) A forward model for data assimilation of GNSS ocean reflectometry delay-Doppler maps. IEEE Trans Geosci Remote Sens 59(3):2643–2656. https://doi.org/10.1109/tgrs.2020.3002801
Huffman GJ, Bolvin DT, Braithwaite D, Hsu K, Joyce R, Kidd C, Nelkin EJ, Sorooshian S, Tan J, Xie P (2019) Algorithm theoretical basis document (ATBD) version 06 NASA global precipitation measurement (GPM) integrated multi-satellite retrievals for gpm (IMERG). National Aeronautics and Space Administration NASA, Washington, pp 1–34
Ichikawa K, Wang X-F, Tamura H (2020) Capability of Jason-2 subwaveform retrackers for significant wave height in the calm semi-enclosed celebes sea. Remote Sens 12(20):3367. https://doi.org/10.3390/rs12203367
Jia Y, Lin M, Zhang Y (2020a) Evaluations of the significant wave height products of HY-2b satellite radar altimeters. Mar Geod 43(4):396–413. https://doi.org/10.1080/01490419.2020.1750513
Jia Y, Yang J, Lin M, Zhang Y, Ma C, Fan C (2020b) Global assessments of the HY-2B measurements and cross-calibrations with Jason-3. Remote Sens 12(15):2470. https://doi.org/10.3390/rs12152470
Jing C, Niu X, Duan C, Lu F, Di G, Yang X (2019) Sea surface wind speed retrieval from the first chinese GNSS-R mission: technique and preliminary results. Remote Sens 11(24):3013. https://doi.org/10.3390/rs11243013
Leader JC (1978) Incoherent backscatter from rough surfaces: the two-scale model reexamined. Radio Sci 13(3):441–457
Li M, Zhang T, Chen Y, Smola AJ (2014) Efficient mini-batch training for stochastic optimization. In: Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining, pp 661–670. https://doi.org/10.1145/2623330.2623612
Li W, Rius A, Fabra F, Cardellach E, Ribo S, Martin-Neira M (2018) Revisiting the GNSS-R waveform statistics and its impact on altimetric retrievals. IEEE Trans Geosci Remote Sens 56(5):2854–2871. https://doi.org/10.1109/tgrs.2017.2785343
Li B, Yang L, Zhang B, Yang D, Wu D (2020) Modeling and simulation of GNSS-R observables with effects of swell. IEEE J Sel Top Appl Earth Observ Remote Sens 13:1833–1841. https://doi.org/10.1109/JSTARS.2020.2992037
Li X, Yang D, Yang J, Zheng G, Han G, Nan Y, Li W (2021) Analysis of coastal wind speed retrieval from CYGNSS mission using artificial neural network. Remote Sens Environ 260:112454. https://doi.org/10.1016/j.rse.2021.112454
Liu Y, Collett I, Morton YJ (2019) Application of neural network to GNSS-R wind speed retrieval. IEEE Trans Geosci Remote Sens 57(12):9756–9766. https://doi.org/10.1109/tgrs.2019.2929002
Marchan-Hernandez JF, Valencia E, Rodriguez-Alvarez N, Ramos-Perez I, Bosch-Lluis X, Camps A, Eugenio F, Marcello J (2010) Sea-state determination using GNSS-R data. IEEE Geosci Remote Sens Lett 7(4):621–625. https://doi.org/10.1109/lgrs.2010.2043213
Mäyrä J, Keski-Saari S, Kivinen S, Tanhuanpää T, Hurskainen P, Kullberg P, Poikolainen L, Viinikka A, Tuominen S, Kumpula T, Vihervaara P (2021) Tree species classification from airborne hyperspectral and lidar data using 3D convolutional neural networks. Remote Sens Environ 256:112322. https://doi.org/10.1016/j.rse.2021.112322
Munoz-Martin JF, Fernandez L, Perez A, Ruiz-de-Azua JA, Park H, Camps A, Domínguez BC, Pastena M (2020) In-orbit validation of the FMPL-2 instrument—the GNSS-R and L-band microwave radiometer payload of the FSSCat mission. Remote Sens 13(1):121. https://doi.org/10.3390/rs13010121
Peng Q, Jin S (2019) Significant wave height estimation from space-borne cyclone-GNSS reflectometry. Remote Sens 11(5):584. https://doi.org/10.3390/rs11050584
Pramudya FS, Pan J, Devlin AT (2019) Estimation of significant wave height of near-range traveling ocean waves using Sentinel-1 SAR images. IEEE J Sel Top Appl Earth Observ Remote Sens 12(4):1067–1075. https://doi.org/10.1109/jstars.2019.2902566
Pramudya FS, Pan J, Devlin AT, Lin H (2021) Enhanced estimation of significant wave height with dual-polarization Sentinel-1 SAR imagery. Remote Sens 13(1):124. https://doi.org/10.3390/rs13010124
Qin L, Li Y (2021) Significant wave height estimation using multi-satellite observations from GNSS-R. Remote Sens 13(23):4806. https://doi.org/10.3390/rs13234806
Quach B, Glaser Y, Stopa JE, Mouche AA, Sadowski P (2020) Deep learning for predicting significant wave height from synthetic aperture radar. IEEE Trans Geosci Remote Sens 59:1–9. https://doi.org/10.1109/tgrs.2020.3003839
Reynolds J, Clarizia MP, Santi E (2020) Wind speed estimation from CYGNSS using artificial neural networks. IEEE J Sel Top Appl Earth Observ Remote Sens 13:708–716. https://doi.org/10.1109/jstars.2020.2968156
Ruf CS, Balasubramaniam R (2019) Development of the CYGNSS geophysical model function for wind speed. IEEE J Sel Top Appl Earth Observ Remote Sens 12(1):66–77. https://doi.org/10.1109/jstars.2018.2833075
Ruf CS, Atlas R, Chang PS, Clarizia MP, Garrison JL, Gleason S, Katzberg SJ, Jelenak Z, Johnson JT, Majumdar SJ, O’brien A, Posselt DJ, Ridley AJ, Rose RJ, Zavorotny VU (2016) New ocean winds satellite mission to probe hurricanes and tropical convection. Bull Am Meteorol Soc 97(3):385–395. https://doi.org/10.1175/bams-d-14-00218.1
Ruf C, Asharaf S, Balasubramaniam R, Gleason S, Lang T, McKague D, Twigg D, Waliser D (2019) In-orbit performance of the constellation of CYGNSS hurricane satellites. Bull Am Meteorol Soc 100(10):2009–2023. https://doi.org/10.1175/bams-d-18-0337.1
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323(6088):533–536
Shah R, Garrison JL, Egido A, Ruffini G (2016) Bistatic radar measurements of significant wave height using signals of opportunity in L-, S-, and Ku-bands. IEEE Trans Geosci Remote Sens 54(2):826–841. https://doi.org/10.1109/tgrs.2015.2466682
Soisuvarn S, Jelenak Z, Said F, Chang PS, Egido A (2016) The GNSS reflectometry response to the ocean surface winds and waves. IEEE J Sel Top Appl Earth Observ Remote Sens 9(10):4678–4699. https://doi.org/10.1109/jstars.2016.2602703
Soulat F, Caparrini M, Germain O, Lopez-Dekker P, Taani M, Ruffini G (2004) Sea state monitoring using coastal GNSS-R. Geophys Res Lett 31(21):L21303. https://doi.org/10.1029/2004gl020680
Voronovich AG, Zavorotny VU (2018) Bistatic radar equation for signals of opportunity revisited. IEEE Trans Geosci Remote Sens 56(4):1959–1968. https://doi.org/10.1109/tgrs.2017.2771253
Wang C, Xi Y (1997) Convolutional neural network for image classification. Johns Hopkins University, Baltimore, p 21218
Wang T, Zavorotny V U, Johnson J, Ruf C, Yi Y (2018) Modeling of sea state conditions for improvement of CYGNSS L2 wind speed retrievals. In: IGARSS 2018—2018 IEEE international geoscience and remote sensing symposium, pp 8288–8291. https://doi.org/10.1109/IGARSS.2018.8518686
Wang J, Aouf L, Jia Y, Zhang Y (2020) Validation and calibration of significant wave height and wind speed retrievals from HY2B altimeter based on deep learning. Remote Sens 12(17):2858. https://doi.org/10.3390/rs12172858
Wang C, Yu K, Qu F, Bu J, Han S, Zhang K (2022a) Spaceborne GNSS-R wind speed retrieval using machine learning methods. Remote Sens 14(14):3507. https://doi.org/10.3390/rs14143507
Wang F, Yang D, Zhang B, Li B, Zhang G (2022b) Modeling and simulation of spaceborne GNSS ocean-reflectometry. J Beijing Univ Aeronaut Astronaut 48(3):419–429. https://doi.org/10.13700/j.bh.1001-5965.2020.0575
Wang H, Mouche A, Husson R, Grouazel A, Chapron B, Yang J (2022c) Assessment of ocean swell height observations from Sentinel-1A/B wave mode against buoy in situ and modeling hindcasts. Remote Sens 14(4):862. https://doi.org/10.3390/rs14040862
Wang H, Yang J, Lin M, Li W, Zhu J, Ren L, Cui L (2022d) Quad-polarimetric SAR sea state retrieval algorithm from Chinese Gaofen-3 wave mode imagettes via deep learning. Remote Sens Environ. https://doi.org/10.1016/j.rse.2022.112969
Yan Q, Huang W (2016) Spaceborne GNSS-R sea ice detection using delay-Doppler maps: first results from the U.K. TechDemoSat-1 mission. IEEE J Sel Top Appl Earth Observ Remote Sens 9(10):4795–4801. https://doi.org/10.1109/jstars.2016.2582690
Yan Q, Huang W (2020) Sea ice thickness measurement using spaceborne GNSS-R: first results with TechDemoSat-1 data. IEEE J Sel Top Appl Earth Observ Remote Sens 13:577–587. https://doi.org/10.1109/jstars.2020.2966880
Yang J, Zhang J, Jia Y, Fan C, Cui W (2020) Validation of Sentinel-3A/3B and Jason-3 altimeter wind speeds and significant wave heights using buoy and ascat data. Remote Sens 12(13):2079. https://doi.org/10.3390/rs12132079
Yang S, Jin S, Jia Y, Ye M (2021a) Significant wave height estimation from joint CYGNSS DDMA and LES observations. Sensors 21(18):6123. https://doi.org/10.3390/s21186123
Yang Z, Song L, Mu L, Jiang H (2021b) Separation of wind-sea and swell wave heights using altimeter data. In: 2021 IEEE international geoscience and remote sensing symposium IGARSS, pp 7564–7567. https://doi.org/10.1109/IGARSS47720.2021.9554818
Yang G, Bai W, Wang J, Hu X, Zhang P, Sun Y, Xu N, Zhai X, Xiao X, Xia J, Huang F, Yin C, Du Q, Wang X, Cai Y, Meng X, Tan G, Hu P, Liu C (2022) FY3E GNOS II GNSS reflectometry: mission review and first results. Remote Sens 14(4):998. https://doi.org/10.3390/rs14040988
Yu K (2016) Weak tsunami detection using GNSS-R-based sea surface height measurement. IEEE Trans Geosci Remote Sens 54(3):1363–1375. https://doi.org/10.1109/tgrs.2015.2478776
Yu K (2021) Theory and practice of GNSS reflectometry. Springer, Berlin. https://doi.org/10.1007/978-981-16-0411-9
Yu K, Li Y, Chang X (2019) Snow depth estimation based on combination of pseudorange and carrier phase of GNSS dual-frequency signals. IEEE Trans Geosci Remote Sens 57(3):1817–1828. https://doi.org/10.1109/tgrs.2018.2869284
Zavorotny V, Voronovich AG (2000) Scattering of GPS signals from the ocean with wind remote sensing application. IEEE Trans Geosci Remote Sens 38:951–964. https://doi.org/10.1109/36.841977
Zhong L, Hu L, Zhou H (2019) Deep learning based multi-temporal crop classification. Remote Sens Environ 221:430–443. https://doi.org/10.1016/j.rse.2018.11.032
Zhong Y, Hu X, Luo C, Wang X, Zhao J, Zhang L (2020) WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF. Remote Sens Environ 250:112012. https://doi.org/10.1016/j.rse.2020.112012
Zhu Y, Tao T, Zou J, Yu K, Wickert J, Semmling M (2020a) Spaceborne GNSS reflectometry for retrieving sea ice concentration using TDS-1 data. IEEE Geosci Remote Sens Lett 18:612–616. https://doi.org/10.1109/lgrs.2020.2982959
Zhu Y, Wickert J, Tao T, Yu K, Li Z, Qu X, Ye Z, Geng J, Zou J, Semmling M (2020b) Sensing sea ice based on doppler spread analysis of spaceborne GNSS-R data. IEEE J Sel Top Appl Earth Observ Remote Sens 13:217–226. https://doi.org/10.1109/jstars.2019.2955175
Acknowledgements
We would like to express my gratitude to NASA for providing CYGNSS data, the European Center for Medium-Range Weather Forecasts (ECMWF) for providing swell and wind wave SWHs data, the developers of WaveWatch III (WW3) product for providing the swell and wind wave SWHs data freely available to public, and the makers of IMERG products for making the rainfall data publicly available. The authors also want to express their gratitude to the anonymous reviewers for their thorough critiques and useful ideas, which have greatly aided in the improvement of this research. This research was supported in part by the National Natural Science Foundation of China under Grant 42174022 and Grant 41574031, in part by the Postgraduate Research & Practice Innovation Program of Jiangsu Province under Grant KYCX20_2003, in part by the Future Scientists Program of China University of Mining and Technology under Grant 2020WLKXJ049, in part by the Independent Innovation Project of ‘‘Double-First Class’’ Construction of the China University of Mining and Technology under Grant 2018ZZCX08, in part by the Jiangsu Dual Creative Teams Programme Project Awarded in 2017 under Grant CUMT07180005, and in part by the China Scholarship Council (CSC) through a State Scholarship Fund (No.202106420009).
Author information
Authors and Affiliations
Contributions
All authors have made significant contributions to this manuscript. JB partly designed the improved method, analyzed the data, wrote the initial version of paper, and validated the improved method; KY conceived the improved method; WH wrote the revised version of the paper and provided supervision; JN checked and revised this paper. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bu, J., Yu, K., Ni, J. et al. Combining ERA5 data and CYGNSS observations for the joint retrieval of global significant wave height of ocean swell and wind wave: a deep convolutional neural network approach. J Geod 97, 81 (2023). https://doi.org/10.1007/s00190-023-01768-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00190-023-01768-4