Recent developments in AI-based oceanic eddy identification

doi:10.3969/j.issn.1001-909X.2024.03.003

Abstract

Abstract:

Ocean eddies are prevalent oceanic phenomenon that play a crucial role in the global transportation of oceanic materials and energy. Although traditional methods for detecting ocean eddies are widely used, they suffer from significant drawbacks such as excessive reliance on expert-set thresholds, continuous manual intervention, large detection errors, low efficiency, and poor global applicability, making it difficult to adapt to the complex and variable marine environment. Currently, the rapid development of artificial intelligence (AI) presents a promising solution for the intelligent detection of ocean eddies. AI can automatically and rapidly extract deep features from images, effectively address the challenges posed by the high similarity in oceanic phenomenon features and significant geometric variability. This paper provides an overview of AI-based oceanic eddy identification methods based on different deep learning methods, focuses on coder-decoder structure, fully convolutional neural network, multi-scale context method and attention mechanism, and aims to provide valuable insights and references for future ocean eddy research.

Key words: oceanic eddy, artificial intelligence, feature detection, deep learning, coder-decoder structure, fully convolutional neural network, multi-scale context method, attention mechanism

CLC Number:

P731.2

XU Guangjun, SHI Yucheng, YU Yang, XIE Huarong, XIE Wenhong, LIU Jingyuan, LIN Xiayan, LIU Yu, DONG Changming. Recent developments in AI-based oceanic eddy identification[J]. Journal of Marine Sciences, 2024, 42(3): 38-50.

Figures/Tables 7

Fig.1 Representation of mesoscale eddies in three different images

Fig.2 Oceanic eddy detection model based on CNN[26] (Blue: convolution, batch normalization and ReLU-activation layers; green: pooling layers; orange: up-sampling layers; red: softmax-activation layer.)

Fig.3 Schematic diagram of the deep learning-based abnormal eddy detection DL-AED model and its output (Figure is redrawn from reference [35].)

Fig.4 Intelligent detection of oceanic eddies based on HFR[41]

Fig.5 Schematic diagram of the pyramid scene parsing network (PSPNet) (Figure is redrawn from reference [42].)

Fig.6 Schematic diagram of context and edge association network (CEA-Net) (Figure is redrawn from reference [48].)

Fig.7 Schematic diagram of the dual attention network (Danet) (Figure is redrawn from reference [49].)

References 52

[1]	MORROW R, LE TRAON P Y. Recent advances in observing mesoscale ocean dynamics with satellite altimetry[J]. Advances in Space Research, 2012, 50(8): 1062-1076.
[2]	WANG H Z, LIU D, ZHANG W M, et al. Characterizing the capability of mesoscale eddies to carry drifters in the northwest Pacific[J]. Journal of Oceanology and Limnology, 2020, 38(6): 1711-1728.
[3]	DONG C M, MCWILLIAMS J C, LIU Y, et al. Global heat and salt transports by eddy movement[J]. Nature Commu-nications, 2014, 5: 3294.
[4]	JI J L, DONG C M, ZHANG B, et al. An oceanic eddy statistical comparison using multiple observational data in the Kuroshio extension region[J]. Acta Oceanologica Sinica, 2017, 36(3): 1-7.
[5]	FRENGER I, MÜNNICH M, GRUBER N, et al. Southern Ocean eddy phenomenology[J]. Journal of Geophysical Research: Oceans, 2015, 120(11): 7413-7449.
[6]	CHELTON D B, SCHLAX M G, SAMELSON R M, et al. Global observations of large oceanic eddies[J]. Geophysical Research Letters, 2007, 34(15): L15606.
[7]	董昌明. 海洋涡旋探测与分析[M]. 北京: 科学出版社, 2015.
	DONG C M. Oceanic eddy detection and analysis[M]. Beijing: Science Press, 2015.
[8]	FRENGER I, GRUBER N, KNUTTI R, et al. Imprint of Southern Ocean eddies on winds, clouds and rainfall[J]. Nature Geoscience, 2013, 6: 608-612.
[9]	GAUBE P, CHELTON D B, SAMELSON R M, et al. Satellite observations of mesoscale eddy-induced Ekman pumping[J]. Journal of Physical Oceanography, 2015, 45(1): 104-132.
[10]	GAUBE P, BARCELÓ C, MCGILLICUDDY D J Jr, et al. The use of mesoscale eddies by juvenile loggerhead sea turtles (Caretta caretta) in the southwestern Atlantic[J]. PLoS One, 2017, 12(3): e0172839.
[11]	李佳讯, 张韧, 陈奕德, 等. 海洋中尺度涡建模及其在水声传播影响研究中的应用[J]. 海洋通报, 2011, 30(1):37-46.
	LI J X, ZHANG R, CHEN Y D, et al. Ocean mesoscale eddy modeling and its application in studying the effect on underwater acoustic propagation[J]. Marine Science Bulletin, 2011, 30(1): 37-46.
[12]	DONG C M, LIU Y, LUMPKIN R, et al. A scheme to identify loops from trajectories of oceanic surface drifters: An application in the Kuroshio extension region[J]. Journal of Atmospheric and Oceanic Technology, 2011, 28(9): 1167-1176.
[13]	NENCIOLI F, DONG C M, DICKEY T, et al. A vector geometry-based eddy detection algorithm and its application to a high-resolution numerical model product and high-frequency radar surface velocities in the southern California bight[J]. Journal of Atmospheric and Oceanic Technology, 2010, 27(3): 564-579.
[14]	ZHANG C H, LI H L, LIU S T, et al. Automatic detection of oceanic eddies in reanalyzed SST images and its application in the East China Sea[J]. Science China Earth Sciences, 2015, 58(12): 2249-2259.
[15]	SUN W J, LIU Y, CHEN G X, et al. Three-dimensional properties of mesoscale cyclonic warm-core and anticyclonic cold-core eddies in the South China Sea[J]. Acta Oceanologica Sinica, 2021, 40(10): 17-29.
[16]	XU G J, YANG J S, DONG C M, et al. Statistical study of submesoscale eddies identified from synthetic aperture radar images in the Luzon Strait and adjacent seas[J]. International Journal of Remote Sensing, 2015, 36(18): 4621-4631.
[17]	JI Y X, XU G J, DONG C M, et al. Submesoscale eddies in the East China Sea detected from SAR images[J]. Acta Oceanologica Sinica, 2021, 40(3): 18-26.
[18]	OKUBO A. Horizontal dispersion of floatable particles in the vicinity of velocity singularities such as convergences[J]. Deep Sea Research and Oceanographic Abstracts, 1970, 17(3): 445-454.
[19]	WEISS J. The dynamics of enstrophy transfer in two-dimensional hydrodynamics[J]. Physica D: Nonlinear Phenomena, 1991, 48(2/3): 273-294.
[20]	HUNT J C R. Vorticity and vortex dynamics in complex turbulent flows[J]. Transactions of the Canadian Society for Mechanical Engineering, 1987, 11(1): 21-35.
[21]	LIU C Q, WANG Y Q, YANG Y, et al. New omega vortex identification method[J]. Science China Physics, Mechanics & Astronomy, 2016, 59(8): 684711.
[22]	CHONG M S, PERRY A E, CANTWELL B J. A general classification of three-dimensional flow fields[J]. Physics of Fluids A: Fluid Dynamics, 1990, 2(5): 765-777.
[23]	JEONG J, HUSSAIN F. On the identification of a vortex[J]. Journal of Fluid Mechanics, 1995, 285: 69-94.
[24]	DOGLIOLI A M, BLANKE B, SPEICH S, et al. Tracking coherent structures in a regional ocean model with wavelet analysis: Application to Cape Basin eddies[J]. Journal of Geophysical Research: Oceans, 2007, 112(C5): C05043.
[25]	CHAIGNEAU A, GIZOLME A, GRADOS C. Mesoscale eddies off Peru in altimeter records: Identification algorithms and eddy spatio-temporal patterns[J]. Progress in Oceano-graphy, 2008, 79(2/3/4): 106-119.
[26]	FRANZ K, ROSCHER R, MILIOTO A, et al. Ocean eddy identification and tracking using neural networks[C]//2018 IEEE International Geoscience and Remote Sensing Sympo-sium(IGARSS). IEEE, 2018: 6887-6890.
[27]	LGUENSAT R, SUN M, FABLET R, et al. EddyNet: A deep neural network for pixel-wise classification of oceanic eddies[C]//2018 IEEE International Geoscience and Remote Sensing Symposium(IGARSS). IEEE, 2018: 1764-1767.
[28]	LI X F, LIU B, ZHENG G, et al. Deep-learning-based information mining from ocean remote-sensing imagery[J]. National Science Review, 2020, 7(10): 1584-1605. DOI PMID
[29]	DUO Z J, WANG W K, WANG H Z. Oceanic mesoscale eddy detection method based on deep learning[J]. Remote Sensing, 2019, 11(16): 1921.
[30]	SANTANA O J, HERNÁNDEZ-SOSA D, SMITH R N. Oceanic mesoscale eddy detection and convolutional neural network complexity[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 113: 102973.
[31]	张盟, 杨玉婷, 孙鑫, 等. 基于深度卷积网络的海洋涡旋检测模型[J]. 南京航空航天大学学报, 2020, 52(5):708-713.
	ZHANG M, YANG Y T, SUN X, et al. Ocean eddy detection model based on deep convolution neural network[J]. Journal of Nanjing University of Aeronautics & Astronautics, 2020, 52(5): 708-713.
[32]	刘启明, 杨树国, 赵莉. 基于深度卷积神经网络的海洋多目标涡旋检测方法[J]. 青岛科技大学学报:自然科学版, 2022, 43(4):120-126.
	LIU Q M, YANG S G, ZHAO L. Ocean multi-eddy detection method based on deep convolution neural network[J]. Journal of Qingdao University of Science and Technology: Natural Science Edition, 2022, 43(4): 120-126.
[33]	LIU Y J, LI X F, REN Y B. A deep learning model for oceanic mesoscale eddy detection based on multi-source remote sensing imagery[C]//2020 IEEE International Geoscience and Remote Sensing Symposium(IGARSS). IEEE, 2020: 6762-6765.
[34]	沈飙, 陈扬, 杨琛, 等. 海洋科学中尺度涡的计算机视觉检测和分析方法[J]. 数据与计算发展前沿, 2020, 2(6):30-41.
	SHEN B, CHEN Y, YANG C, et al. Computer vision detection and analysis of mesoscale eddies in marine science[J]. Frontiers of Data & Computing, 2020, 2(6): 30-41.
[35]	LIU Y J, ZHENG Q A, LI X F. Characteristics of global ocean abnormal mesoscale eddies derived from the fusion of sea surface height and temperature data by deep learning[J]. Geophysical Research Letters, 2021, 48(17): e94772.
[36]	CAO L J, ZHANG D J, ZHANG X F, et al. Detection and identification of mesoscale eddies in the South China Sea based on an artificial neural network model—YOLOF and remotely sensed data[J]. Remote Sensing, 2022, 14(21): 5411.
[37]	YAN Z F, CHONG J S, ZHAO Y W, et al. Multifeature fusion neural network for oceanic phenomena detection in SAR images[J]. Sensors, 2019, 20(1): 210.
[38]	DU Y L, SONG W, HE Q, et al. Deep learning with multi-scale feature fusion in remote sensing for automatic oceanic eddy detection[J]. Information Fusion, 2019, 49: 89-99.
[39]	ZHANG D, GADE M, ZHANG J W. SAR eddy detection using mask-RCNN and edge enhancement[C]//2020 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), September 26-October 2, 2020, Waikoloa, HI, USA. IEEE, 2020: 1604-1607.
[40]	贾翊文, 荆文龙, 杨骥, 等. 基于深度学习的SAR影像海洋涡旋检测算法对比分析[J]. 海洋科学进展, 2024, 42(1):137-148.
	JIA Y W, JING W L, YANG J, et al. Comparative analysis of ocean eddy detection algorithms based on deep learning in SAR images[J]. Advances in Marine Science, 2024, 42(1): 137-148.
[41]	LIU F Y, ZHOU H, HUANG W M, et al. Cross-domain submesoscale eddy detection neural network for HF radar[J]. Remote Sensing, 2021, 13(13): 2441.
[42]	XU G J, CHENG C, YANG W X, et al. Oceanic eddy identification using an AI scheme[J]. Remote Sensing, 2019, 11: 1349.
[43]	XU G J, XIE W H, DONG C M, et al. Application of three deep learning schemes into oceanic eddy detection[J]. Frontiers in Marine Science, 2021, 8: 672334.
[44]	HANG R L, LI G, XUE M, et al. Identifying oceanic eddy with an edge-enhanced multiscale convolutional network[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 9198-9207.
[45]	ZHAO Y X, FAN Z L, LI H T, et al. SymmetricNet: End-to-end mesoscale eddy detection with multi-modal data fusion[J]. Frontiers in Marine Science, 2023, 10: 1174818.
[46]	杜艳玲, 王丽丽, 黄冬梅, 等. 融合密集特征金字塔的改进R²CNN海洋涡旋自动检测[J]. 智能系统学报, 2023, 18(2):341-351.
	DU Y L, WANG L L, HUANG D M, et al. Improved R²CNN ocean eddy automatic detection with a dense feature pyramid[J]. CAAI Transactions on Intelligent Systems, 2023, 18(2): 341-351.
[47]	FAN Z L, ZHONG G Q. SymmetricNet: A mesoscale eddy detection method based on multivariate fusion data[Z/OL]. arXiv, 2019: 1909. 13411. https://arxiv.org/abs/1909.13411v1.
[48]	XIA L H, CHEN G, CHEN X Y, et al. Submesoscale oceanic eddy detection in SAR images using context and edge association network[J]. Frontiers in Marine Science, 2022, 9: 1023624.
[49]	ZHANG Y Y, LIU N, ZHANG Z Y, et al. Detection of Bering Sea slope mesoscale eddies derived from satellite altimetry data by an attention network[J]. Remote Sensing, 2022, 14(19): 4974.
[50]	SAIDA S J, SAHOO S P, ARI S. Deep convolution neural network based semantic segmentation for ocean eddy detection[J]. Expert Systems with Applications, 2023, 219: 119646.
[51]	ZHAO N, HUANG B X, YANG J, et al. Oceanic eddy identification using pyramid split attention U-net with remote sensing imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2023, 20: 1-5.
[52]	杜艳玲, 吴天宇, 陈括, 等. 融合上下文和注意力的海洋涡旋小目标检测[J]. 中国图象图形学报, 2023, 28(11):3509-3519.
	DU Y L, WU T Y, CHEN K, et al. Small object detection for ocean eddies using contextual information and attention mechanism[J]. Journal of Image and Graphics, 2023, 28(11): 3509-3519.