基于光谱-空间联合Transformer模型的黄河三角洲湿地高光谱影像分类

黄河三角洲湿地地物类型在光谱曲线上差异较小,且在空间上分布零散,呈破碎化特性。现有的分类方法受限于局部感受野难以捕捉到图像的长距离依赖关系,导致在黄河三角洲湿地高光谱影像中分类精度不理想,针对此问题,本文提出了一种光谱-空间联合Transformer模型。光谱和空间支路分别以光谱向量和空间邻域为输入,基于自注意力机制提取全局光谱和空间特征,在两个支路引入多阶特征交互层,实现浅层边缘信息和深层语义信息的融合,最后采用自适应相加的方式将两路特征融合,送入分类器实现最终分类。本文在黄河三角洲湿地高分五号GF-5和CHRIS两幅高光谱影像上验证方法的有效性,实验结果表明,该方法显著提高了湿地分类的精度,在选用3%的样本训练条件下总体精度分别达到了90.90%和94.17%,优于其他分类方法。研究结果可实现黄河三角洲湿地地物类型的高精度分类,为湿地的保护提供技术支持。     

基于地物光谱可分性的CHRIS 高光谱影像波段选择及其分类应用

本文以黄河口湿地为研究区,应用覆盖该区域的CHRIS高光谱遥感影像,提出了一种基于地物光谱可分性的滨海湿地高光谱影像波段选择方法。该方法利用研究区的7种典型地物的110余条现场实测地物光谱曲线,通过分析比对地物两两之间的光谱可分度,确定地物类型之间的光谱可分区间,基于此选取CHRIS高光谱影像的地物分类特征波段,应用三种经典的监督分类方法(支持向量机法SVM、人工神经网络法ANN和光谱角制图法SAM)开展利用全波段的和利用本文方法选择特征波段的分类对比实验。结果表明:(1)基于光谱可分性特征波段的方法较全波段分类精度有所提高,其中ANN分类精度最高,为82.52%,较全波段分类精度提高了约为5.1%;(2)芦苇、水体、黄河水和裸滩4种地物的识别能力高,生产者精度都在80%以上;(3)碱蓬的用户精度提升最为明显,约在7%。     

基于光谱特征空间的监督分类中包络线去除效能评价

对覆盖黄河口滨海湿地的PROBA CHRIS高光谱遥感影像进行包络线去除变换,采用6种常用的基于光谱特征空间的监督分类算法对变换前后的影像数据进行滨海湿地典型地物分类,通过目视对比分析和定量分析相结合的方法分析比较变换前后的分类结果,评价包络线去除方法对该类算法影响的效果和能力。结果表明,包络线去除方法能够提高部分监督分类算法针对滨海湿地典型植被类型的区分和识别能力;但由于滨海湿地内具有面积较大的裸滩和浑浊水体,这两类地物在影像中的光谱特征相近,而包络线去除方法并不能解决二者的误分问题,因此并不能提高该类算法针对CHRIS高光谱遥感影像的总体分类精度。     

黄河口湿地典型地物类型高光谱分类方法

黄河口湿地地物类型具有复杂多样的特点,本文将线性光谱混合分析模型与归一化植被指数(NDVI)和归一化水体指数(NDWI)相结合,建立了一种新的滨海湿地遥感影像分类方法;开展了基于CHRIS高光谱影像的黄河口湿地芦苇、柽柳、碱蓬、大米草、潮滩和水体6种典型地物分类实验,整体分类精度为77.33%,Kappa 系数为 0.71,与经典的最大似然分类(MLC)方法相比较,整体分类精度提高1.6%,Kappa 系数提高0.02,尤其是芦苇、碱蓬、大米草和潮滩的分类精度明显提高。     

联合光谱和纹理特征的滨海湿地高光谱深度学习分类—以黄河三角洲湿地为例

本文基于CHRIS高光谱遥感影像，发展了一种结合地物光谱特征和多纹理空间特征信息，采用双全链接的8层深度卷积神经网络分类算法对滨海湿地高光谱影像进行遥感地物分类，并在黄河口滨海湿地进行了应用。结果表明：1）基于测试样本数据，联合光谱特征和K-L变换的纹理特征信息，采用DCNN模型方法展现了高的分类精度，精度高达99%；2）利用光谱特征和全纹理特征的精度比仅使用光谱特征和光谱特征联合K-L变换后纹理特征的分类精度低。利用K-L变换后的光谱特征和纹理特征的DCNN分类精度达到99.38%，相比于使用全纹理特征信息的精度提高了4.15%；3）基于验证图像，发展的DCNN分类方法精度优于其他算法，DCNN方法总体分类精度为84.64%，Kappa系数为0.80；4）相比于浅层分类方法，本文发展的DCNN模型分类算法保证了所有地物类型的分类精度更加均衡，保持了主要地物类型的分类精度几乎不变，同时提高了滩涂和农田的精度。基于DCNN模型，潮滩和农田的分类精度分别达到79.26%和56.72%。比其它浅层分类方法提高了2.51%和10.6%。     

基于双路图卷积的黄河三角洲湿地地物分类研究

黄河三角洲湿地地物精确分类对湿地资源的保护、开发和利用具有重要意义。目前的湿地分类算法大多存在着全局信息利用不足,地物类型边界不易区分等问题,导致分类精度不高。针对此问题,本文提出了基于双路图卷积的黄河三角洲湿地地物分类算法,包括图结构数据构建模块、特征提取与融合模块两部分。图结构数据构建模块,设计欧式图表示光谱值之间的绝对差异,衡量不同地物类型,设计余弦图表达不同像素光谱波形之间的差异,用以区分不同的地物边界;特征提取与融合模块,利用图卷积聚合全局信息,对欧式图利用双层图卷积进行特征提取,对余弦图使用图U-Net网络进行特征提取,之后将两个特征融合,得到同时具有光谱值绝对差异和光谱波形差异的融合特征,最后进行分类。在CHRIS和GF5两个数据集的实验结果表明,本文所提算法在黄河三角洲湿地地物分类中取得了具有竞争力的分类结果。     

基于决策级数据融合的CHRIS 高光谱图像分类方法研究

本文选取8种常用的遥感图像监督分类方法,综合利用多数投票方法与先验分类概率信息,设计了3组决策级融合分类策略,在应用地物丰富的黄河口湿地CHRIS高光谱图像数据进行分类实验的基础上,开展了不同融合策略决策分类结果的比较研究,分析了融合策略对高光谱图像总体分类精度以及不同地物分类精度的影响。结果表明:(1)3组决策级融合策略总体分类精度均大于85%,Kappa系数都优于0.77,较8种单分类器均有提高,表明决策级融合是利用已有分类器资源、提升高光谱图像分类精度的一种途径;(2)策略3的分类表现最好,即维持最小虚警率的前提下降低错分可以提高分类精度,其中芦苇、滩涂地物同时保持了很高的生产者精度和用户精度,均接近90%,水体在保持较高用户精度的情形下生产者精度有大幅提升,增幅达11%;(3)每组策略综合考虑生产者精度和用户精度的情形下分类精度最高,较仅考虑生产者精度或用户精度的情形提升了1~2个百分点,表明设计算法时应同时考虑减少错分和漏分的情况。     

基于主成分分析和决策级融合的高光谱图像分类方法研究

为了评价主成分分析方法和决策级数据融合方法对高光谱图像地物分类结果的影响,作者利用各分类器和主成分分量的优势,提出了两组地物分类结果的决策级融合策略,利用8种常用监督分类方法对高光谱原始图像和PCA变换后不同分量组合图分类得到的结果进行决策级融合,并应用覆盖黄河入海口新老河道交界处的CHRIS/PROBA高光谱图像开展实验研究。结果表明:直接采用每类地物分类精度最高的、空穴和缝隙采用总体分类精度最高的融合策略,在综合考虑生产者精度和用户精度的情形下,仅使用最大似然法、支持向量机和人工神经网络3种分类方法,按照分类精度从高到低的顺序进行的融合分类效果最好,总体分类精度为87.82%。与8种监督分类方法中效果最好的最大似然法相比,精度提高了2.7个百分点,同时明显减少了错分现象,尤其是对于分布面积较小的翅碱蓬和柽柳,滩涂被误分为翅碱蓬、芦苇被误分为柽柳的现象大大降低。     

条带消除对于高光谱图像分类效果的影响——以CHRIS/PROBA图像为例

以CHRIS/PROBA高光谱图像数据为例,使用非监督分类的ISODATA和监督分类的最大似然法、支持向量机等3种经典的图像分类算法,对消条带前后的图像分别开展分类实验,并对分类结果做了分析。实验结果表明,消条带处理可以较好地改善高光谱图像分类结果的目视效果,能够消除不同类别斑块边缘因条带而产生的"毛刺"现象,这对地物斑块的形状及几何分布敏感的研究(如景观生态学)至关重要;但消条带处理对于提高分类精度的效果并不显著,精度提高最大值不到2%。     

典型高光谱图像端元提取算法在黄河口湿地应用评价研究

端元提取是混合像元分解的基础,也是高光谱遥感的研究热点。对于特定区域的高光谱图像应该使用哪种端元提取算法,需要对各种端元提取算法进行客观地评价。作者针对黄河口湿地CHRIS高光谱图像,使用了重建图像与原图像的均方根误差、有效端元数量两个指数对PPI、N-FINDR、VCA、OSP、IEA和SISAL六种典型的端元提取算法进行了评价。结果表明,SISAL算法重建误差最小,仅有其他算法误差的10%~28%;OSP算法识别了具有物理意义的6种有效端元,多于其他算法识别的地物类型,而SISAL算法识别的端元缺乏物理意义。     

Assessing the Validity of Seismo-Acoustic Predictor Equations for Obtaining Seabed and Sub-Surface Sediment Physical Properties

The interdependence between the seismo-acoustic properties of a marine sediment and its geotechnical/physical parameters has been known for many years, and it has been postulated that this should allow the extraction of geotechnical information from seismic data. Though in the literature many correlations have been published for the surficial layer, there is a lack of information for greater sediment depths. In this article, a desktop study on a synthetic seafloor model illustrates how the application of published near-surface prediction equations to subsurface sediments (up to several tens of meters burial depth) can lead to spurious predictions. To test this further, acoustic and geotechnical properties were measured on a number of sediment core samples, some of which were subjected to loading in acoustically-equipped consolidation cells (oedometers) to simulate greater burial depth conditions. For low effective pressures (representing small burial depths extending to around 10 meters subsurface), the general applicability of established relationships was confirmed: the prediction of porosity, bulk density, and mean grain size from acoustic velocity and impedance appears generally possible for the investigated sedimentary environments. As effective pressure increases through, the observed relationships deviate more and more from the established ones for the near-surface area. For the samples tested in this study, in some instances increasing pressure even resulted in decreasing velocities. There are several possible explanations for this abnormal behavior, including the presence of gas, overconsolidation, or bimodal grain size distribution. The results indicate that an appropriate depth correction must be introduced into the published prediction equations in order to obtain reliable estimates of physical sediment properties for greater subsurface depths.     

A Review of Some Environmental Issues Affecting Marine Mining

This article reviews information recently available from existing marine and coastal mining for responses to environmental issues affecting marine mining at different depths. It is particularly but not exclusively concerned with those issues affecting seabed biodiversity impact and recovery. Much information has been gathered in the past 10 years from shallow mining operations for construction aggregate, diamonds, and gold, from coastal mines discharging tailings to shallow and deep water, and from experimental deep mining tests. The responses to issues identified are summarized in a series of eight tables intended to facilitate site-specific consideration. Since impacts can spread widely in the surface mixing layer SML, and can affect the biologically productive euphotic zone, the main issues considered arise from the depth of mining relative to the SML of the sea. Where mining is below the SML, the issue is whether it is environmentally better to bring the extraction products to the surface vessel for processing (and waste discharge), or to process the extraction products as much as possible on the seabed. Responses to the issues need to be sitespecific, and dependent on adequate preoperational environmental impact and recovery prediction. For deep tailings disposal from a surface vessel, there are four important environmental unknowns: (1) the possible growth of "marine snow" (bacterial flocs) utilizing the enormous quantities of fine tailings particles (hundreds or thousands of metric tons per day) as nuclei for growth, (2) the possibility that local keystone plankton and nekton species may migrate diurnally down to and beyond the depth of deep discharge and hence be subjected to tailings impact at depth, (3) the burrow-up capability of deep benthos and their ability to survive high rates of tailings deposition, and (4) the pattern and rate of dispersion of a tailings density current through the deep water column from discharge point to seabed. Actions to obtain relevant information in general and site-specifically are suggested.     

Increased Particle Fluxes at the INDEX Site Attributable to Simulated Benthic Disturbance

Particle fluxes were measured 7 m above the sea bottom during the predisturbance, disturbance, and postdisturbance periods by using time series sediment traps attached to seven deep-sea moorings deployed in the INDEX experiment site in the Central Indian Basin. The predisturbance particle fluxes varied between 22.3 to 55.1 mg m -2 day -1 . Increased and variable particle fluxes were recorded by the sediment traps during the disturbance period. The increase observed was 0.5 to 4 times more than the background predisturbance fluxes. The increases in particle fluxes (~4 times) recorded by the sediment trap located in the southwestern direction (DMS-1) were the greatest, which could be the result of preferential movement of resuspended particles generated during the deep-sea benthic disturbance along the general current direction prevailing in this area during the experimental period. Also, the traps located closer to the disturbance area recorded greater fluxes than did the traps far away, across the Deep Sea Sediment Resuspension System path. This variability in recorded particle fluxes by the traps around the disturbance area clearly indicates that physical characteristics such as grain size and density of the resuspended particles produced during the disturbance had an important effect on particle movement. The postdisturbance measurements during ~5 days showed a reduction in particle fluxes of ~50%, indicating rapid particle settlement.     

海上大直径钢管桩打桩过程中桩周土强度弱化研究

海上大直径钢管桩打桩过程中,桩周土体受到强烈扰动而发生强度弱化,掌握桩周土体强度弱化规律对于准确预测打桩过程、保证工程安全具有重要意义。为研究土体强度弱化规律,开展了环剪试验模拟打桩对桩周土体的扰动,测试土体强度随剪切速率的变化规律,建立了描述土体强度弱化规律的拟合公式,引入到打桩分析软件中。研究结果表明：土体的强度折减程度不仅与土体本身的性质有关还受到土体的埋深和剪切速率的影响,埋深越深土体强度折减程度越低,剪切速率越高土体强度折减越高,在打桩分析中可采用这里推荐的线性折减方法来模拟不同深度处土体强度的折减规律。     

Determination of In Situ Sediment Shear Strength from Advanced Piston Corer Pullout Forces

The advanced piston corer (APC) has been used by the Ocean Drilling Program since 1985 for recovering soft sediments from the ocean floor. The pullout force measured on extracting the core barrel from the sediment is shown to correlate with the average shear strength of the sediment core measured in the ship's laboratory. A simple rule of thumb is derived relating the shear strength of the sediment to the pullout force. Multiple APC holes at individual sites allow the consistency of the pullout measurements to be assessed. The effects of different operational procedures during APC coring are also explored. Although generally applicable, the correlation between pullout force and laboratory measurements of shear strength breaks down for some APC holes, possibly because of the disturbance of some sediment types during the APC coring process. A better understanding of the physical process of APC coring, and its effect on the properties of the sediment both inside and immediately outside the core barrel, would indicate what confidence can be put on the measurement of pullout force as a way of evaluating the in situ shear strength of deep sea sediments.     

Interannual Sea Level Variations and Annual Tides in the Northwestern Pacific

Specific properties of the interannual sea level variations and annual tides in the Northwestern Pacific were studied. Several tide stations were monitored. The monthly mean sea level for the year of 1995 was analyzed at each tide station. A seismic event in 1995, some tectonic activity around the subject area, and the Kuroshio (the oceanic western boundary current) may possibly contaminate results which would have occurred from the astronomical annual tide alone.     

《Acta Oceanologica Sinica》Vol. 33(2014) contents

<正>~~     

INFORMATION FOR AUTHORS

<正>Acta Oceanologica Sinica(AOS)is a comprehensive academic journal edited by the Editorial Committee of Acta Oceanologica Sinica and is designed to provide a forum for important research papers of the marine scientific community which reflect the information on a worldwide basis.The journal publishes scholarly papers on marine science and technology,including physics,chemistry,biology,