基于机器学习的海洋中尺度涡检测识别研究综述

摘要/Abstract

摘要： 海洋中尺度涡是一种重要的海洋中尺度现象，在海洋环流、物质能量传输中发挥重要作用，对舰船航行安全、水声通信等也具有重要的影响。高效准确地检测识别出海洋中尺度涡无论对于物理海洋认知还是海洋开发利用都有着重要的研究价值。传统涡旋检测识别方法依赖专家经验设计的单一阈值，具有显著的主观性。随着深度学习的兴起，机器学习方法在涡旋检测识别的准确性和自动化程度上表现出一定的优势。通过总结与对比分析现有基于机器学习的检测识别方法，为发展海洋中尺度涡检测识别的研究提供系统认知和参考依据。

关键词: 中尺度涡, 人工智能, 机器学习, 深度学习

Abstract: Ocean mesoscale eddy is an important ocean mesoscale phenomenon that plays an important role in ocean circulation, material and energy transport, and has an important impact on the safety of ship navigation and hydroacoustic communication. Efficient and accurate detection and identification of ocean mesoscale eddies are of great research value for both physical ocean cognition and ocean exploitation. Traditional eddy detection and identification methods rely on a single threshold designed by experts' experiences. With the rise of deep learning, the current machine learning methods show certain advantages in the accuracy and automation of eddy detection and identification. This paper summarizes and comparatively analyzes the existing machine learning-based detection and identification methods to provide a systematic knowledge and reference basis for the development of ocean mesoscale eddy detection and identification research.

Key words: mesoscale eddy, artificial intelligence, machine learning, deep learning

张家灏, 邓科峰, 聂腾飞, 任开军, 宋君强. 基于机器学习的海洋中尺度涡检测识别研究综述[J]. 计算机工程与科学, 2021, 43(12): 2115-2125.

ZHANG Jia-hao, DENG Ke-feng, NIE Teng-fei, REN Kai-jun, SONG Jun-qiang. Overview on ocean mesoscale eddy detection and identification based on machine learning[J]. Computer Engineering & Science, 2021, 43(12): 2115-2125.

参考文献［40］

［1］	Chelton D B, Schlax M G, Samelson R M , et al. Global observations of large oceanic eddies［J］. Geophysical Research Letters, 2007, 34(15):87-101.
［2］	McGillicuddy D J, Liang X F, Mullineaux L S, et al. Surface-generated mesoscale eddies transport deep-sea products from hydrothermal vents ［J］.Science, 2011, 332(6029):580-583.
［3］	Siegel D A, Granata T C, Michaels A F, et al. Mesoscale eddy diffusion, particle sinking, and the interpretation of sediment trap data［J］. Journal of Geophysical Research,1990, 95(C4):5305-5311.
［4］	Wyrtki K, Magaard L, Hager J. Eddy energy in the oceans［J］. Journal of Geophysical Research, 1976, 81(15):2641-2646.
［5］	Chelton D B, Schlax M G, Samelson R M. Global observations of nonlinear mesoscale eddies［J］. Progress in Ocean- ography, 2011, 91(2):167-216.
［6］	Wang X, Du Y Y, Zhou C H, et al.An improved, SSH-based method to automatically identify mesoscale eddies in the ocean ［J］. Journal of Tropical Oceanography, 2013, 32(2):15-23.
［7］	Sadarjoen I A, Post F H. Detection, quantification, and tracking of vortices using streamline geometry［J］. Computers & Graphics, 2000, 24(3):333-341.
［8］	Chaigneau A, Gizolme A, Grados C. Mesoscale eddies off Peru in altimeter records: Identification algorithms and eddy spatio-temporal patterns［J］. Progress in Oceanography, 2008, 79(2-4):106-119.
［9］	Liu Y, Chen G, Sun M, et al. A Parallel SLA-based algorithm for global mesoscale eddy identification［J］. Journal of Atmospheric & Oceanic Technology, 2016, 33(12):2743-2754.
［10］	Rio M H, Poulain P M, Pascual A, et al. A mean dynamic topography of the mediterranean sea computed from altimetric data, in-situ measurements and a general circulation model［J］. Journal of Marine Systems, 2007, 65(1-4):484-508.
［11］	Paterson H L,Ming F, Waite A M, et al. Physical and chemical signatures of a developing anticyclonic eddy in the Leeuwin Current, eastern Indian Ocean［J］. Journal of Geophysical Research, 2008, 113(C7):1-14.
［12］	Alimonte D D. Detection of mesoscale eddy-related structures through iso-SST patterns［J］. IEEE Geoscience and Remote Sensing Letters, 2009, 6(2):189-193.
［13］	Moschos E, Stegner A, Schwander O, et al. Classification of eddy sea surface temperature signatures under cloud coverage［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13: 3437-3447.
［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: 2249-2259.
［15］	Bai X, Wang C B, Li C H. A streampath-based RCNN approach to ocean eddy detection［J］. IEEE Access,2019, 7:106336-106345.
［16］	Fu L L, Ferrari R. Observing oceanic submesoscale processes from space［J］.Eos, Transactions American Geophysical Union, 2008, 89(48): 485-493.
［17］	Karimova S. An approach to automated spiral eddy detection in SAR images［C］∥Proc of IEEE International Geo- science & Remote Sensing Symposium, 2017:743-746.
［18］	Huang D, Du Y, He Q, et al. DeepEddy: A simple deep architecture for mesoscale oceanic eddy detection in SAR images［C］∥ Proc of IEEE International Conference on Networking, 2017:673-678.
［19］	Lguensat R, Sun M, Fablet R, et al. EddyNet: A deep neural network for pixel-wise classification of oceanic eddies［C］∥ Proc of 2018 IEEE International Geoscience and Remote Sensing Symposium, 2018:1.
［20］	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.
［21］	Moschos E, Schwander O, Stegner A, et al. DEEP-SST- EDDIES: A deep learning framework to detect oceanic eddies in sea surface temperature images［C］∥Proc of IEEE 2020 International Conference on Acoustics, Speech, and Signal Processing, 2020:1.
［22］	Yi J, Du Y, Zhou C, et al. Automatic identification of oceanic multieddy structures from satellite altimeter datasets［J］. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 2015, 8(4):1555-1563.
［23］	Dong C, Nencioli F, Yu L, et al. An automated approach to detect oceanic eddies from satellite remotely sensed sea surface temperature data［J］. IEEE Geoscience & Remote Sensing Letters, 2011, 8(6):1055-1059.
［24］	Okubo A. Horizontal dispersion of floatable particles in vicinity of velocity singularities such as convergences［J］. Deep Sea Research and Oceanographic Abstracts, 1970, 17(3):445-454.
［25］	Weiss J. The dynamics of enstrophy transfer in 2-dimensional hydrodynamics［J］. Physica D Nonlinear Phenomena, 1991, 48(2-3):273-294.
［26］	Hunt J. Vorticity and vortex dynamics in complex turbulent flows［J］. Transactions of the Canadian Society for Mechanical Engineering, 1987, 11(1):21-35.
［27］	Liu C Q, Wang Y Q, Yang Y, et al. New omega vortex identification method［J］. Science China, 2016, 59(8):684711.
［28］	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.
［29］	Jeong J, Hussain F. On the identification of a vortex［J］. Journal of Fluid Mechanics, 1995, 332(1):339-363.
［30］	Isern-Fontanet J, Font J, Garcia-Ladona E, et al. Spatial structure of anticyclonic eddies in the algerian basin (Mediterranean Sea) analyzed using the Okubo-Weiss parameter［J］. Deep Sea Research Part II: Topical Studies in Ocean- ography,2004,51(25-26): 3009-3028.
［31］	McWilliams J C. The emergence of isolated coherent vortices in turbulent flow［J］. Journal of Fluid Mechanics,1984,146: 21-43.
［32］	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 & Oceanic Technology, 2010, 27(3):564-579.
［33］	Dong C M, Mavor T, Nencioli F, et al. An oceanic cyclonic eddy on the lee side of Lanai Island, Hawai'i［J］. Journal of Geophysical Research, 2009, 114(C10):1-13.
［34］	Sadarjoen I A,Post F H, Ma B, et al. Selective visualization of vortices in hydrodynamic flows［C］∥ Proc of Visualization’98, 1998: 419-422.
［35］	Serra M, Haller G. Objective Eulerian coherent structures［J］. Chaos, 2016, 26(5):95-105.
［36］	Haller G, Hadjighasem A, Farazmand M, et al. Defining coherent vortices objectively from the vorticity［J］. Journal of Fluid Mechanics, 2015, 795(7):136-173.
［37］	Faghmous J H, Frenger I, Yao Y, et al. A daily global mesoscale ocean eddy dataset from satellite altimetry［J］. Scientific Data, 2015, 2: Article Number:150028.
［38］	Wang G, Su J, Chu P C. Mesoscale eddies in the South China Sea observed with altimeter data［J］. Geophysical Research Letters, 2003, 30(21):OCE 6-1- OCE 6-4.
［39］	Pascual A, Nardelli B B, Larnicol G, et al. A case of an intense anticyclonic eddy in the balearic sea (western mediterranean)［J］. Journal of Geophysical Research, 2002, 107(C11):4-1 - 4-14.
［40］	Hao Ying-jie. Research on ocean mesoscale eddy detection algorithm based on convolutional neural network［D］.Qingdao:Shandong University of Science and Technology, 2017.(in Chinese)
［41］	Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation［C］∥Proc of International Conference on Medical Image Computing and Computer-Assisted Intervention, 2015: 234-241.
［42］	Zeiler M D, Krishnan D, Taylor G W, et al. Deconvolutional networks［C］∥Proc of the the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010: 2528-2535.
［43］	Zhao H, Shi J, Qi X, et al. Pyramid scene parsing network［C］∥Proc of the 2017 IEEE Conference on Computer Vision and Pattern Recognition,2017:6230-6239.
［44］	He K, Zhang X, Ren S, et al.Deep residual learning for image recognition［C］∥Proc of the 2016 IEEE Conference on Computer Vision and Pattern Recognition,2016: 770-778.
［45］	Amores A, Gabriel J, Arsouze T, et al. Up to what extent can we characterize ocean eddies using present-day gridded altimetric products?［J］. Journal of Geophysical Research, 2018,123(10): 7220-7236.
［46］	Zhang L P, Zhang L F, Du B, et al. Deep learning for remote sensing data: A technical tutorial on the state of the art［J］. IEEE Geoscience & Remote Sensing Magazine, 2016, 4(2):22-40.
［47］	Rolnick D, Donti P L, Kaack L H, et al. Tackling climate change with machine learning［J］. arXiv:1906.05433,2019.
［48］	Franz K, Roscher R, Milioto A, et al. Ocean eddy identification and tracking using neural networks［C］∥Proc of 2018 IEEE International Geoscience and Remote Sensing Symposium, 2018:6887-6890.
［49］	Ashkezari M D, Hill C N,Follett C N, et al. Oceanic eddy detection and lifetime forecast using machine learning methods［J］. Geophysical Research Letters,2016 ,43(23):12234-12241.
［50］	Du Y, Liu J, Song W, et al.Ocean eddy recognition in SAR images with adaptive weighted feature fusion［J］. IEEE Access 2019, 7:152023-152033.
［51］	Camps-Valls G, Bruzzone L. Kernel-based methods for hyperspectral image classification［J］. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(6):1351-1362.
［52］	Saleh A, Abdel-Nasser M, Garcia M A, et al. Aggregating the temporal coherent descriptors in videos using multiple learning kernel for action recognition ［J］.Pattern Recognition Letters, 2018, 105:4-12.
［53］	Zhang Y, Yang H L, Prasad S, et al. Ensemble multiple kernel active learning for classification of multisource remote sensing data［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(2):845-858.
［54］	Anna C, Tapio P, Sandor S, et al. Learning with multiple pairwise kernels for drug bioactivity prediction ［J］. Bio- informatics (Oxford, England), 2018, 34(13):i509-i518.
［55］	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.
［56］	Ghassemian H. A review of remote sensing image fusion methods［J］. Information Fusion, 2016,32:75-89.
［57］	Chan T H, Jia K, Gao S, et al. PCANet: A simple deep learning baseline for image classification［J］. IEEE Transactions on Image Processing, 2015, 24(12):5017-5032.
［58］	Xu G, Cheng C, Yang W, et al. Oceanic eddy identification using an AI scheme［J］. Remote Sensing, 2019, 11:Article Number:1349.
［59］	Fan Z, Zhong G. SymmetricNet: A mesoscale eddy detection method based on multivariate fusion data［J］. arXiv:1909.13411,2019.
［60］	Topouzelis K, Kitsiou D. Detection and classification of mesoscale atmospheric phenomena above sea in SAR imagery［J］. Remote Sensing of Environment, 2015, 160:263-272.
	附中文参考文献：
［40］	郝滢洁.基于卷积神经网络的海洋中尺度涡旋检测算法研究［D］.青岛：山东科技大学,2017.

[1]	赵振宇, 杨天豪, 蒋汶乘, 张书政. 基于机器学习的多压多温多参标准单元延迟快速计算方法[J]. 计算机工程与科学, 2023, 45(08): 1331-1338.
[2]	马思远, 焦佳辉, 任晟岐, 宋伟. 基于注意力机制的城市多元空气质量数据缺失值填充[J]. 计算机工程与科学, 2023, 45(08): 1354-1364.
[3]	易啸, 马胜, 肖侬. 深度学习加速器在不同剪枝策略下的运行优化[J]. 计算机工程与科学, 2023, 45(07): 1141-1148.
[4]	康宇晗, 时洋, 陈照云, 文梅. 面向迈创+MatrixZone异构系统的深度学习编程框架[J]. 计算机工程与科学, 2023, 45(07): 1149-1158.
[5]	刘浩翰, 孙铖, 贺怀清, 惠康华. 基于改进YOLOv3的金属表面缺陷检测[J]. 计算机工程与科学, 2023, 45(07): 1226-1235.
[6]	田秀霞, 刘正, 刘秋旭, 李浩然. 一种改进Faster R-CNN的图像篡改检测模型[J]. 计算机工程与科学, 2023, 45(06): 1030-1039.
[7]	濮子俊, 张寿明. 基于特征融合与Transformer模型的声音事件定位与检测算法研究[J]. 计算机工程与科学, 2023, 45(06): 1097-1105.
[8]	李小玲, 方建滨, 马俊, 谭霜, 谭郁松. 基于监督学习的稀疏矩阵自动任务分配[J]. 计算机工程与科学, 2023, 45(05): 782-789.
[9]	邓姗姗, 黄慧, 马燕. 基于改进Faster R-CNN的小目标检测算法[J]. 计算机工程与科学, 2023, 45(05): 869-877.
[10]	霍爱清, 张书涵, 杨玉艳, 胥静蓉, 王泽文. 密集交通场景中改进YOLOv3目标检测优化算法[J]. 计算机工程与科学, 2023, 45(05): 878-884.
[11]	方雪杉, 杨云飞, 冯松. 基于多尺度多模态学习的光球亮点曲线轨迹段检测方法研究[J]. 计算机工程与科学, 2023, 45(05): 885-894.
[12]	黄星威, 陈曦, 张塑凡. 改进特征金字塔的小目标深度学习模型[J]. 计算机工程与科学, 2023, 45(04): 734-742.
[13]	董佩杰, 牛新, 魏自勉, 陈学晖. 单次神经网络结构搜索研究综述[J]. 计算机工程与科学, 2023, 45(02): 191-203.
[14]	马铭苑, 李虎, 王梓斌, 况晓辉. 深度神经网络模型后门植入与检测技术研究综述[J]. 计算机工程与科学, 2022, 44(11): 1959-1968.
[15]	胡艳芳, 熊文, 高炜. 基于 Spark 平台的网络游戏用户流失预测方法[J]. 计算机工程与科学, 2022, 44(10): 1730-1737.