ОЦЕНКА СРЕДНЕГО ПЕРИОДА ВЕТРОВОГО ВОЛНЕНИЯ ПО ЕДИНИЧНЫМ СНИМКАМ СУДОВОГО НАВИГАЦИОННОГО РАДАРА С ПРИМЕНЕНИЕМ МЕТОДОВ ГЛУБОКОГО ОБУЧЕНИЯ
Аннотация
В настоящей работе представлен метод оценки среднего периода ветрового волнения по данным судового навигационного радара в подходе глубокого обучения. В работе применяется сверточная нейронная сеть на основе ResNet, обрабатывающая единичные предобработанные радарные изображения. Модель оптимизируется на данных периода ветрового волнения, полученных с волномерного Spotter буя в нескольких научных экспедициях. Для оценки качества работы модели рассчитаны среднеквадратичные отклонения и коэффициент детерминации между оценками нейросети и измерениями с буя на отложенной выборке. Результаты демонстрируют применимость нейронных сетей для оценки периода волнения на основе данных мгновенных радарных снимков.
Литература
- Borge J. C. N., Reichert K., Dittmer J. Use of nautical radar as a wave monitoring instrument // Coastal Engineering. 1999. Vol. 37. P. 331. https://doi.org/10.1016/S0378-3839(99)00032-0.
- Campana J., Terrill E. J., de Paolo T. A New Inversion Method to Obtain Upper-Ocean Current-Depth Profiles Using X-Band Observations of Deep-Water Waves // Journal of Atmospheric and Oceanic Technology. 2017. Vol. 34. P. 957. https://doi.org/10.1175/JTECH-D-16-0120.1.
- Chen Z., He Y., Yang W. Study of Ocean Waves Measured by Collocated HH and VV Polarized X-Band Marine Radars // International Journal of Antennas and Propagation. 2016. Vol. 2016. P. 1. https://doi.org/10.1155/2016/8257930.
- Chen Z., He Y., Zhang B., Qiu Z. Determination of nearshore sea surface wind vector from marine X-band radar images // Ocean Engineering. 2015. Vol. 96. P. 79. https://doi.org/10.1016/j.oceaneng.2014.12.019.
- Cornejo-Bueno L., Nieto Borge J. C., Alexandre E., Hessner K., Salcedo-Sanz S. Accurate estimation of significant wave height with Support Vector Regression algorithms and marine radar images // Coastal Engineering. 2016. Vol. 114. P. 233. https://doi.org/10.1016/j.coastaleng.2016.04.007.
- Duan W., Yang K., Huang L., Ma X. Numerical Investigations on Wave Remote Sensing from Synthetic X-Band Radar Sea Clutter Images by Using Deep Convolutional Neural Networks // Remote Sensing. 2020. Vol. 12. P. 1117. https://doi.org/10.3390/rs12071117.
- Elbisy M. S. Sea Wave Parameters Prediction by Support Vector Machine Using a Genetic Algorithm // Journal of Coastal Research. 2015. Vol. 314. P. 892. https://doi.org/10.2112/JCOASTRES-D-13-00087.1.
- Ermoshkin A. V., Kapustin I. A. Estimation of the wind-driven wave spectrum using a high spatial resolution coherent radar // Russ. J. Earth Sci. 2019. Vol. 19. P. 1. https://doi.org/10.2205/2019ES000662.
- Fujiyoshi Y., Osumi K., Ohi M., Yamada Y. Sea Ice Identification and Derivation of Its Velocity Field by X-Band Doppler Radar // Journal of Atmospheric and Oceanic Technology. 2013. Vol. 30. P. 1240. https://doi.org/10.1175/JTECH-D-12-00155.1.
- Gangeskar R. Wave height derived by texture analysis of X-band radar sea surface images, In: IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment // Proceedings (Cat. No.00CH37120); 2000; Honolulu, HI, USA. IEEE; 2000. P. 2952–9. https://doi.org/10.1109/IGARSS.2000.860301.
- Gavrikov A., Ivonin D., Sharmar V., Tilinina N., Gulev S., Suslov A., Fadeev V., Trofimov B., Bargman S., Salavatova L., Koshkina V., Shishkova P., Sokov A. Wind waves in the North Atlantic and Arctic from ship navigational radar (SeaVision system) and wave buoy Spotter during three research cruises in 2020 and 2021, 2021. https://doi.org/10.1594/PANGAEA.939620.
- Greenwood C., Vogler A., Morrison J., Murray A. The approximation of a sea surface using a shore mounted X-band radar with low grazing angle // Remote Sensing of Environment. 2018. Vol. 204. P. 439. https://doi.org/10.1016/j.rse.2017.10.012.
- Goodfellow I., Bengio Y., Courville A. Deep Learning: MIT Press, 2016.
- Hatten H., Seemann J., Horstmann J., Ziemer F. Azimuthal dependence of the radar cross section and the spectral background noise of a nautical radar at grazing incidence // IGARSS’98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174); 1998 Jul.; 1998. Vol. 5. P. 2490–2. https://doi.org/10.1109/IGARSS.1998.702255.
- He K., Zhang X., Ren S., Sun J. Deep Residual Learning for Image Recognition // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016 Jun.; Las Vegas, NV, USA. IEEE; 2016. P. 770–8. https://doi.org/10.1109/CVPR.2016.90.
- Horstmann J., Bödewadt J., Carrasco R., Cysewski M., Seemann J., Streβer M. A Coherent on Receive X-Band Marine Radar for Ocean Observations // Sensors. 2021. Vol. 21. P. 7828. https://doi.org/10.3390/s21237828.
- Huang W., Liu X., Gill E. Ocean Wind and Wave Measurements Using X-Band Marine Radar: A Comprehensive Review // Remote Sensing. 2017. Vol. 9. P. 1261. https://doi.org/10.3390/rs9121261.
- Huang W., Yang Z., Chen X. Wave Height Estimation From X-Band Nautical Radar Images Using Temporal Convolutional Network // IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2021. Vol. 14. P. 11395. https://doi.org/10.1109/JSTARS.2021.3124969.
- Ivonin D. V., Telegin V. A., Bakhanov V. V., Ermoshkin A. V., Azarov A. I. Sample application of a low-cost X-band monitoring system of surface currents at the Black Sea shore // Russ. J. Earth Sci. 2011. Vol. 12. P. 1. https://doi.org/10.2205/2011ES000507.
- Krinitskiy M. A., Golikov V. A., Anikin N. N., Suslov A. I., Gavrikov A. V., Tilinina N. D. Estimating Significant Wave Height from X-Band Navigation Radar Using Convolutional Neural Networks // Moscow Univ. Phys. 2023. Vol. 78. P. S128. https://doi.org/10.3103/S0027134923070159.
- Lee J.-H., Nam Y.-S., Lee J., Liu Y., Kim Y. Estimation of Significant Wave Height Using Wave-Radar Images // JMSE. 2024. Vol. 12. P. 1134. https://doi.org/10.3390/jmse12071134.
- Li B., Xu J., Pan X., Ma L., Zhao Z., Chen R., Liu Q., Wang H. Marine Oil Spill Detection with X-Band Shipborne Radar Using GLCM, SVM and FCM // Remote Sensing. 2022. Vol. 14. P. 3715. https://doi.org/10.3390/rs14153715.
- Liu R., Lehman J., Molino P., Such F. P., Frank E., Sergeev A., Yosinski J. An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution. 2018. https://doi.org/10.48550/arXiv.1807.03247.
- Lund B., Collins C. O., Tamura H., Graber H. C. Multi-directional wave spectra from marine X-band radar // Ocean Dynamics. 2016. Vol. 66. P. 973. https://doi.org/10.1007/s10236-016-0961-z.
- Lund B., Graber H. C., Persson P. O. G., Smith M., Doble M., Thomson J., Wadhams P. Arctic Sea Ice Drift Measured by Shipboard Marine Radar // JGR Oceans. 2018. Vol. 123. P. 4298. https://doi.org/10.1029/2018JC013769.
- Lund B., Haus B. K., Graber H. C., Horstmann J., Carrasco R., Novelli G., Guigand C. M., Mehta S., Laxague N. J. M., Özgökmen T. M. Marine X‐Band Radar Currents and Bathymetry: An Argument for a Wave Number‐Dependent Retrieval Method // JGR Oceans. 2020. Vol. 125. P. e2019JC015618. https://doi.org/10.1029/2019JC015618.
- Lyzenga D. R., Walker D. T. A Simple Model for Marine Radar Images of the Ocean Surface // IEEE Geoscience and Remote Sensing Letters. 2015. Vol. 12. P. 2389. https://doi.org/10.1109/LGRS.2015.2478390.
- Mahjoobi J., Adeli Mosabbeb E. Prediction of significant wave height using regressive support vector machines // Ocean Engineering. 2009. Vol. 36. P. 339. https://doi.org/10.1016/j.oceaneng.2009.01.001.
- Misra D. Mish: A Self Regularized Non-Monotonic Activation Function, 2020.
- Nieto Borge, José C., RodrÍguez G. R., Hessner K., González P. I. Inversion of Marine Radar Images for Surface Wave Analysis // J. Atmos. Oceanic Technol. 2004. Vol. 21. P. 1291. https://doi.org/10.1175/1520-0426(2004)021<1291:IOMRIF>2.0.CO;2.
- Nieto-Borge J. C., Hessner K., Jarabo-Amores P., de la Mata-Moya D. Signal-to-noise ratio analysis to estimate ocean wave heights from X-band marine radar image time series, IET Radar, Sonar & Navigation. 2008. Vol. 2. P. 35. https://doi.org/10.1049/iet-rsn:20070027.
- Park G., Choi J., Kang Y.-T., Ha M. K., Jang H., Park J. H., Park S. G., Kwon S.-H. The Application of Marine X-band Radar to Measure Wave Condition during Sea Trial // Journal of Ship and Ocean Technology. 2006. Vol. 10. P. 34.
- Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Vanderplas J., Passos A., Cournapeau D., Brucher M., Perrot M., Duchesnay E. Scikit-learn: Machine Learning in Python // Journal of Machine Learning Research. 2011. Vol. 12. P. 2825.
- Raghukumar K., Chang G., Spada F., Jones C., Janssen T., Gans A. Performance Characteristics of “Spotter,” a Newly Developed Real-Time Wave Measurement Buoy // Journal of Atmospheric and Oceanic Technology. 2019. Vol. 36. P. 1127. https://doi.org/10.1175/JTECH-D-18-0151.1.
- Rezvov V., Krinitskiy M., Gavrikov A., Golikov V., Borisov M., Suslov A., Tilinina N. Improving data-driven estimation of significant wave height through preliminary training on synthetic X-band radar sea clutter imagery // Front. Mar. Sci. 2024. Vol. 11. P. 1363135. https://doi.org/10.3389/fmars.2024.1363135.
- Salcedo-Sanz S., Nieto Borge J. C., Carro-Calvo L., Cuadra L., Hessner K., Alexandre E. Significant wave height estimation using SVR algorithms and shadowing information from simulated and real measured X-band radar images of the sea surface // Ocean Engineering. 2015. Vol. 101. P. 244. https://doi.org/10.1016/j.oceaneng.2015.04.041.
- Tilinina N., Ivonin D., Gavrikov A., Sharmar V., Gulev S., Suslov A., Fadeev V., Trofimov B., Bargman S., Salavatova L., Koshkina V., Shishkova P., Ezhova E., Krinitskiy M., Razorenova O., Koltermann K. P., Tereschenkov V., Sokov A. Wind waves in the North Atlantic from ship navigational radar: SeaVision development and its validation with the Spotter wave buoy and WaveWatch III // Earth Syst. Sci. Data. 2022. Vol. 14. P. 3615. https://doi.org/10.5194/essd-14-3615-2022.
- Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A. N., Kaiser Ł. Ukasz, Polosukhin I. Attention is All you Need // Advances in Neural Information Processing Systems. 2017. Curran Associates, Inc. 2017.
- Vicen-Bueno R., Lido-Muela C., Nieto-Borge J. C. Estimate of significant wave height from non-coherent marine radar images by multilayer perceptrons // EURASIP Journal on Advances in Signal Processing. 2012. Vol. 2012. P. 84. https://doi.org/10.1186/1687-6180-2012-84.
- Waskom M. L. Seaborn: statistical data visualization // Journal of Open Source Software. 2021. Vol. 6. P. 3021. https://doi.org/10.21105/joss.03021.
- Xue S., Geng X., Yan X.-H., Xie T., Yu Q. Significant wave height retrieval from Sentinel-1 SAR imagery by convolutional neural network // J. Oceanogr. 2020. Vol. 76. P. 465. https://doi.org/10.1007/s10872-020-00557-3.
- Young I. R., Rosenthal W., Ziemer F. A three‐dimensional analysis of marine radar images for the determination of ocean wave directionality and surface currents // J. Geophys. Res. 1985. Vol. 90. P. 1049. https://doi.org/10.1029/JC090iC01p01049.
- Zuo S., Wang D., Wang X., Suo L., Liu S., Zhao Y., Liu D. Wave Height and Period Estimation from X-Band Marine Radar Images Using Convolutional Neural Network, JMSE. 2024. Vol. 12. P. 311. https://doi.org/10.3390/jmse12020311.
Передача авторских прав происходит на основании лицензионного договора между Автором и Федеральным государственным бюджетным учреждением науки Институт океанологии им. П.П. Ширшова Российской академии наук (ИО РАН)