發(fā)布時(shí)間：2018-05-16 23:32

  本文選題：海洋遙感影像 + 中尺度渦　； 參考：《上海海洋大學(xué)》2017年博士論文

【摘要】：現(xiàn)階段,人類已進(jìn)入大規(guī)模開發(fā)利用海洋時(shí)期,海洋成為世界各國競相爭奪的主要戰(zhàn)場。依賴于高新海洋科學(xué)技術(shù),不斷加深對海洋的全面認(rèn)識,是實(shí)現(xiàn)合理管控、高效開發(fā)、可持續(xù)發(fā)展海洋的核心。中尺度渦作為重要的海洋現(xiàn)象廣泛存在于世界大洋和邊緣海中,攜帶了海洋中超過90%的動(dòng)能,以非規(guī)則螺旋狀結(jié)構(gòu)持續(xù)高速自轉(zhuǎn)和水平運(yùn)動(dòng),并改變著海洋中能量和物質(zhì)的垂直與水平分布。海洋中物質(zhì)和能量的時(shí)空動(dòng)態(tài)變化對氣候和生態(tài)具有深遠(yuǎn)的影響,因此,實(shí)現(xiàn)中尺度渦的動(dòng)態(tài)監(jiān)測和時(shí)空特征分析,不僅有助于海洋氣候變化和海洋生態(tài)資源分布的研究,同時(shí)在深海捕撈和遠(yuǎn)洋漁業(yè)等實(shí)際應(yīng)用中發(fā)揮重要作用。中尺度渦的自動(dòng)識別是實(shí)現(xiàn)其動(dòng)態(tài)監(jiān)測、進(jìn)行時(shí)空動(dòng)態(tài)變化特征分析的重要手段。海洋遙感可遠(yuǎn)距離、非接觸、快速地獲取海洋現(xiàn)象和海洋環(huán)境要素信息,為中尺度渦自動(dòng)識別研究提供了不可替代的數(shù)據(jù)源�；�于海洋遙感數(shù)據(jù)的中尺度渦識別成為研究熱點(diǎn),主要的研究方法可分為基于物理特征、基于流場幾何特征以及兩種方法的結(jié)合。但是,現(xiàn)有基于物理特征識別方法在人工設(shè)計(jì)特征過程中引入了大量人為主觀因素,導(dǎo)致中尺度渦識別精準(zhǔn)度低的問題。同時(shí),與陸地遙感相比,海洋遙感影像具有顯著的弱特征性,主要表現(xiàn)為光譜低反差性和高動(dòng)態(tài)海洋要素特征表達(dá)的不確定性,加劇了現(xiàn)有基于人工設(shè)計(jì)特征識別方法精準(zhǔn)度低的問題。此外,基于流場幾何特征識別方法采用專家設(shè)定閾值的特點(diǎn)缺乏泛化能力。特別地,中尺度渦由具體海域多種海洋要素相互作用形成,呈現(xiàn)出與空間差異相關(guān)的高動(dòng)態(tài)性;并且其幾何形狀和物理特性在運(yùn)動(dòng)過程中隨著能量的注入或消散均發(fā)生高度的動(dòng)態(tài)變化,基于單一閾值的識別方法無法滿足高動(dòng)態(tài)中尺度渦自動(dòng)識別的需求,極大地限制了中尺度渦研究的進(jìn)展。論文以中尺度渦自動(dòng)精準(zhǔn)識別為研究目標(biāo),針對現(xiàn)有方法對于高動(dòng)態(tài)中尺度渦自動(dòng)識別的局限性,結(jié)合深度學(xué)習(xí)的思想,提出了基于特征學(xué)習(xí)的中尺度渦自動(dòng)識別模型,論文主要研究內(nèi)容為:(1)構(gòu)建基于SAR影像的中尺度渦訓(xùn)練數(shù)據(jù)集。SAR衛(wèi)星具有全天時(shí)、全天候、高分辨率的觀測優(yōu)勢,為中尺度渦的精細(xì)化研究提供了必要的數(shù)據(jù)基礎(chǔ)。本文采用歐空局提供的2005-2010年,5°N-25°N,108°E-125°E范圍海域的ESA-2和Envisat SAR影像,基于人工目視方法,采用外接矩形對中尺度渦進(jìn)行手工標(biāo)注,并采用數(shù)據(jù)擴(kuò)充方法提升訓(xùn)練數(shù)據(jù)集規(guī)模,增加訓(xùn)練數(shù)據(jù)集的多樣性;(2)研究基于特征學(xué)習(xí)的中尺度渦自動(dòng)識別模型。中尺度渦的高層本質(zhì)特征的獲取與表達(dá)是實(shí)現(xiàn)其自動(dòng)識別的關(guān)鍵。本文基于SAR影像中尺度渦訓(xùn)練數(shù)據(jù)集規(guī)模小的現(xiàn)況,從模型框架和模型參數(shù)初始化兩方面入手,構(gòu)建適合于高動(dòng)態(tài)中尺度渦自動(dòng)識別的多層網(wǎng)絡(luò)模型Deep Eddy,通過Deep Eddy的多層網(wǎng)絡(luò)模型對中尺度渦高層本質(zhì)特征的逐級抽象與表達(dá),進(jìn)而實(shí)現(xiàn)中尺度渦的自動(dòng)精準(zhǔn)識別。實(shí)驗(yàn)表明Deep Eddy模型的最優(yōu)中尺度渦識別精準(zhǔn)度達(dá)96.88%。(3)提出形態(tài)和尺度魯棒的中尺度渦自動(dòng)識別模型。中尺度渦存在嚴(yán)重的幾何形變和空間尺度差異,顯著影響其自動(dòng)識別的精準(zhǔn)度。其中,多尺度空間特征的獲取是降低幾何形變和空間尺度差異影響識別精準(zhǔn)度的關(guān)鍵,本文基于空間金字塔模型對中尺度渦自動(dòng)識別的多層網(wǎng)絡(luò)模型進(jìn)行改進(jìn),記作Deep Eddy+,實(shí)現(xiàn)中尺度渦多尺度空間特征的提取與表達(dá)。實(shí)驗(yàn)表明,在同樣模型參數(shù)設(shè)置情況下,Deep Eddy+模型的中尺度渦識別精準(zhǔn)度明顯優(yōu)于Deep Eddy模型,其中,Deep Eddy+模型的中尺度渦最優(yōu)識別精準(zhǔn)度達(dá)98.47%。(4)中尺度渦自動(dòng)識別模型的實(shí)證分析。采用Deep Eddy+模型對獲取的研究海域SAR影像進(jìn)行自動(dòng)識別,依據(jù)自動(dòng)識別結(jié)果對中尺度渦的尺寸大小、時(shí)空特征進(jìn)行分析,并與基于SSH數(shù)據(jù)識別的中尺度渦進(jìn)行對比,結(jié)果表明兩種數(shù)據(jù)源識別的中尺度渦在統(tǒng)計(jì)特征上具有明顯的差異性;此外,本文探討了研究海域中尺度渦與金槍魚的空間相關(guān)性分析,結(jié)果表明大眼金槍魚與氣旋渦分布呈正相關(guān)性,黃鰭金槍魚與反氣旋渦呈現(xiàn)一定的相關(guān)性。通過上述內(nèi)容的研究,論文取得了一定的研究成果,具體有:(1)首次構(gòu)建了基于SAR影像的中尺度渦訓(xùn)練數(shù)據(jù)集,為中尺度渦自動(dòng)識別方法研究提供了數(shù)據(jù)基礎(chǔ);(2)提出了簡單有效的中尺度渦自動(dòng)識別模型,實(shí)現(xiàn)了中尺度渦完全自動(dòng)化的高精準(zhǔn)度識別;(3)為高動(dòng)態(tài)中尺度渦的自動(dòng)識別提供了新理論新方法。同時(shí),也為其他海洋現(xiàn)象的自動(dòng)識別提供技術(shù)參考。
[Abstract]:At this stage, human beings have entered the period of large-scale exploitation and utilization of the ocean, and the ocean has become the main battle field for all countries in the world. Relying on high and new marine science and technology and deepening the comprehensive understanding of the ocean, it is the core of realizing rational control, efficient development and sustainable development of the ocean. Mesoscale vortices exist widely as important oceanic phenomena. In the ocean and the marginal sea of the world, more than 90% of the kinetic energy of the ocean is carried, and the irregular spiral structure continues to rotate at high speed and horizontal movement, and changes the vertical and horizontal distribution of energy and matter in the ocean. The dynamic changes in the space and time of the matter and energy in the ocean have a profound influence on the climate and ecology. Therefore, the mesoscale is realized. The dynamic monitoring and spatio-temporal characteristics analysis of the vortex not only contribute to the study of ocean climate change and the distribution of marine ecological resources, but also play an important role in the practical application of deep-sea fishing and ocean fishing. The automatic recognition of mesoscale vortices is an important means to realize dynamic monitoring and analysis of spatiotemporal dynamic changes. The remote, non contact and rapid acquisition of marine phenomena and information of marine environment elements provides an irreplaceable data source for the study of mesoscale vortex automatic recognition. Mesoscale eddy recognition based on marine remote sensing data has become a hot spot. The main research methods can be divided into physical characteristics based on the geometric characteristics of flow field and two kinds of methods. However, the existing physical feature recognition method has introduced a large number of subjective factors in the artificial design process, which leads to the low accuracy of the mesoscale vortex recognition. At the same time, compared with the land remote sensing, the ocean remote sensing images have significant weak characteristics, and the main purpose is to show low spectral contrast and high dynamic ocean elements. The uncertainty of characteristic expression intensifies the existing problem of low precision based on the artificial design feature recognition method. In addition, the characteristics of the geometric feature recognition method based on the flow field are not generalized by the characteristics of the expert setting threshold. In particular, the mesoscale vortex is formed by the interaction of various marine elements in the specific sea area, showing the difference with the spatial difference. The high dynamic characteristics of the closed form and its geometric and physical characteristics are highly dynamic with the injection or dissipation of energy during the movement. The recognition method based on a single threshold can not meet the requirement of the high dynamic mesoscale vortex automatic recognition, which greatly restricts the progress of the mesoscale eddy research. Quasi recognition is the research goal. Aiming at the limitation of the existing methods for the automatic recognition of high dynamic mesoscale vortices, combined with the idea of deep learning, a mesoscale vortex automatic recognition model based on feature learning is proposed. The main research contents are as follows: (1) the construction of the mesoscale eddy training data set.SAR satellite based on SAR images is all day and all day The high resolution observational advantage provides the necessary data basis for the refinement of mesoscale vortices. In this paper, the ESA-2 and Envisat SAR images of 2005-2010 years, 5 N-25 degrees N, 108 degree E-125 E are provided by ESA. Based on artificial visual method, the mesoscale vortices are manually annotated with the external rectangle, and the data expansion is used. In order to improve the size of the training data set and increase the diversity of the training dataset, (2) research on the automatic recognition model of mesoscale vortex based on feature learning. The key to the automatic recognition is to obtain and express the high level characteristic of the mesoscale vortex. This paper is based on the present condition of the small scale of the training data set of the scale vortex in the SAR image, from the model frame Starting with the two aspects of the model parameter initialization, the multi-layer network model Deep Eddy suitable for the high dynamic mesoscale vortex automatic recognition is constructed. Through the multi-layer network model of Deep Eddy, the essential characteristics of the mesoscale vortex are abstracted and expressed, and the automatic accurate identification of the mesoscale vortices is realized. The experiment shows the optimum of the Deep Eddy model. The accuracy of scale vortex recognition reaches 96.88%. (3), which proposes a robust mesoscale vortex automatic recognition model for shape and scale. The mesoscale vortices have serious geometric and spatial scale differences, which significantly affect the accuracy of their automatic recognition. The acquisition of multi-scale spatial features is the accuracy of reducing the accuracy of geometric and spatial scale differences. The key of this paper is to improve the multi-layer network model of the mesoscale vortex automatic recognition based on the spatial Pyramid model. It is recorded as Deep Eddy+ to extract and express the multi-scale spatial features of the mesoscale vortex. The experiment shows that the accuracy of the mesoscale vortex recognition of the Deep Eddy+ model is obviously better than the Deep Eddy model under the same model parameters setting. The accuracy of the mesoscale vortex recognition accuracy of the Deep Eddy+ model is an empirical analysis of the 98.47%. (4) mesoscale eddy automatic identification model. The Deep Eddy+ model is used to automatically identify the SAR images obtained in the study area, and the spatial and temporal characteristics of the mesoscale vortices are analyzed according to the automatic recognition results, and the SSH data based on the SSH data are also analyzed. The results show that the mesoscale vortices identified by the two sources have obvious differences in statistical characteristics. In addition, the spatial correlation analysis of the mesoscale vortices and tuna in the study area is discussed. The results show that the large Eye Tuna has a positive correlation with the cyclone distribution, and the yellowfin tuna and the anti gas vortex are in a positive correlation. A certain correlation is presented. Through the study of the above content, some research results have been obtained. (1) the data set of mesoscale vortex training based on SAR image is first constructed, which provides a data basis for the study of the mesoscale eddy automatic recognition method. (2) a simple and effective mesoscale eddy automatic identification model is proposed to realize the middle ruler. The high precision recognition of the complete automation of the degree vortices (3) provides a new theory and new method for the automatic recognition of the high dynamic mesoscale vortices. At the same time, it also provides a technical reference for the automatic identification of other marine phenomena.
【學(xué)位授予單位】：上海海洋大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2017
【分類號】：S951.4

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 李熙泰;張鐘哲;王喜風(fēng);;馬里亞納海溝東西兩側(cè)海域中尺度渦的海面高度計(jì)觀測研究[J];大連海洋大學(xué)學(xué)報(bào);2013年01期

相關(guān)會議論文 前4條

1 黃興輝;宋海斌;拜陽;劉伯然;陳江欣;;利用地震海洋學(xué)方法估算南海中尺度渦的地轉(zhuǎn)流速[A];中國科學(xué)院地質(zhì)與地球物理研究所2013年度（第13屆）學(xué)術(shù)論文匯編——油氣資源研究室[C];2014年

2 金寶剛;張韌;王桂華;;呂宋海峽以東中尺度渦變化規(guī)律研究[A];“海洋動(dòng)力過程與天氣、氣候變化”聯(lián)合學(xué)術(shù)年會論文摘要集[C];2009年

3 林緬;姬莉莉;;深水環(huán)境下低頻聲波傳播特性之探討[A];中國力學(xué)大會——2013論文摘要集[C];2013年

4 劉磊;費(fèi)建芳;程小平;黃小剛;馬占宏;;海溫及海浪對臺風(fēng)眼墻中尺度渦的影響[A];創(chuàng)新驅(qū)動(dòng)發(fā)展 提高氣象災(zāi)害防御能力——S13熱帶海洋氣象[C];2013年

相關(guān)重要報(bào)紙文章 前1條

1 本報(bào)記者 李果;難定位的殘�。褐锌圃涸斀庑l(wèi)星監(jiān)測浮標(biāo)[N];21世紀(jì)經(jīng)濟(jì)報(bào)道;2014年

相關(guān)博士學(xué)位論文 前9條

1 張正光;中尺度渦[D];中國海洋大學(xué);2014年

2 王世紅;反向動(dòng)能級串的全球分布特征，，各向異性特征及其在渦平衡過程中的作用[D];中國科學(xué)院研究生院(海洋研究所);2016年

3 董迪;基于衛(wèi)星遙感和現(xiàn)場觀測的黑潮延伸區(qū)中尺度渦旋研究[D];中國科學(xué)院大學(xué)(中國科學(xué)院遙感與數(shù)字地球研究所);2017年

4 杜艷玲;基于海洋遙感影像的中尺度渦自動(dòng)識別及與漁場動(dòng)態(tài)關(guān)系研究[D];上海海洋大學(xué);2017年

5 何忠杰;西北太平洋副熱帶逆流區(qū)及其鄰近海域中尺度渦研究[D];中國海洋大學(xué);2007年

6 王桂華;南海中尺度渦的運(yùn)動(dòng)規(guī)律探討[D];中國海洋大學(xué);2004年

7 陳更新;南海中尺度渦的時(shí)空特征研究[D];中國科學(xué)院研究生院（海洋研究所）;2010年

8 高勁松;南海北部中尺度渦及北部灣環(huán)流結(jié)構(gòu)與生成機(jī)制研究[D];中國海洋大學(xué);2013年

9 王大奎;南海中尺度渦渦動(dòng)動(dòng)能和渦致熱量輸運(yùn)特征的數(shù)值模擬研究[D];中國海洋大學(xué);2011年

相關(guān)碩士學(xué)位論文 前10條

1 垞永燦;北太平洋中尺度渦統(tǒng)計(jì)分析[D];國家海洋局第一海洋研究所;2015年

2 劉麗娜;基于高度計(jì)數(shù)據(jù)與數(shù)值模式的中尺度渦探測方法研究[D];中國石油大學(xué)(華東);2014年

3 趙越;中尺度渦環(huán)境下聲傳播分析[D];中國海洋大學(xué);2015年

4 崔鳳娟;南海中尺度渦的識別及統(tǒng)計(jì)特征分析[D];中國海洋大學(xué);2015年

5 程建婷;臺灣以東中尺度渦的探測及其對黑潮入侵東海路徑的影響[D];中國科學(xué)院研究生院(海洋研究所);2016年

6 趙福;南海北部中尺度渦的數(shù)值模擬及個(gè)例預(yù)報(bào)研究[D];國家海洋環(huán)境預(yù)報(bào)中心;2017年

7 林鵬飛;南海和西北太平洋中尺度渦的統(tǒng)計(jì)特征分析[D];中國科學(xué)院研究生院（海洋研究所）;2005年

8 畢經(jīng)武;基于多源遙感數(shù)據(jù)的太平洋中尺度渦克里金提取方法研究[D];山東師范大學(xué);2015年

9 鄭聰聰;北太平洋中尺度渦現(xiàn)象分析[D];中國科學(xué)院研究生院（海洋研究所）;2013年

10 劉聰;中尺度渦對北太平洋副熱帶西部模態(tài)水的影響初探[D];中國海洋大學(xué);2014年

本文編號：1898916