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%。     

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。     

基于空谱融合与AlexNet算法的滨海湿地植被分类研究

为提高遥感影像融合质量,提升资源一号(ZY-1 02D)高光谱遥感影像滨海湿地植被分类精度,提出将ZY-1 02D高光谱影像与空间分辨率为10 m的哨兵2号(Sentinel-2)影像进行Brovey融合,并通过搭建AlexNet卷积神经网络对ZY-1 02D高光谱影像和Brovey融合影像的滨海湿地植被进行分类,与支持向量机、随机森林和BP神经网络分类算法进行精度对比。研究结果表明:经Brovey融合后,AlexNet、支持向量机、随机森林和BP神经网络算法的植被分类总体精度分别提高15.60%、7.00%、14.80%和10.00%,Kappa系数提高了21.35%、9.93%、18.97%、12.85%;基于Brovey影像融合与AlexNet算法的植被分类精度最高,总体精度为92.40%,Kappa系数为89.42%。空谱融合配合AlexNet卷积神经网络有效解决了高光谱遥感影像在滨海湿地植被分类应用中精度较低的问题,为滨海湿地植被资源动态监测提供技术和方法支撑。     

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。     

联合Bi-LSTM和注意力加强多尺度卷积的黄河三角洲湿地高光谱图像分类方法研究

近年来,面向黄河口的监测需求日益增大,如黄河入海流路改道至清水沟路以来,在新老河道的交汇处存在着丰富的地物类别,对于这些地物类别的检测识别研究有助于掌握生态环境状态,对于黄河口的湿地保护以及国家改善环境的战略支持具有重要意义。因此,本文提出一种新的湿地高光谱图像分类方法,分双路分别提取图像的空谱特征并融合分类。光谱维采用分组预处理的双向长短期记忆网络(Bi-LSTM)有效学习光谱特征;空间维采用注意力加强的多尺度卷积网络有效增强所提取的空谱特征,使得分类结果更具准确性。本文实验应用覆盖黄河入海口新老河道交界处的成像光谱仪(Compact High Resolution Imaging Spectrometer,CHRIS)所采集的数据和黄河三角洲自然保护区滨海湿地高分5号传感器(GF-5)所采集的高光谱图像开展。结果表明:分组与双向长短期记忆网络(Bi-LSTM)的有效结合显著提升了网络性能,同其他监督分类方法相比提升约3%~8%,此外注意力机制的加入同比增加约3%,在使用1%的极少训练集下数据集CHRIS和GF-5的总体分类精度分别达到92.3%和86.11%。     

海岸带高光谱影像分类技术研究

以海岸带地物分类研究为重要对象,针对传统海岸带区域地物及海水等目标分类技术的局限性,通过分析海岸带地物的光谱特征以及在高光谱数据中的表征,研究高光谱成像技术在海岸带遥感应用中的有效性。实验结果表明相对传统的遥感影像分类技术,高光谱海岸带分类显得更为精细,也展示了高光谱技术在海洋遥感中的巨大应用前景?     

不同极化方式SAR与TM融合影像滨海湿地分类精度比较

以覆盖黄河口湿地区域的Radarsat-2 SAR全极化影像和Landsat-5 TM影像为例,将4种极化方式的SAR影像与TM影像分别进行融合,采用支持向量机对融合结果进行滨海湿地典型地物土地覆盖分类,并对分类结果进行比较评价,分析不同极化方式的SAR影像与TM影像融合结果在滨海湿地地区的分类能力。实验结果表明:采用与SAR影像融合的方法能够提高TM影像的分类精度,其中HV极化方式的SAR影像与TM影像的融合结果分类精度最高,最适用于滨海湿地土地覆盖分类研究。     

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。     

Microbial Biomass and Organic Nutrients in the Deep-Sea Sediments of the Central Indian Ocean Basin

In order to assess the impact of deep-sea mining on the in situ benthic life, we measured the microbial standing stock and concentration of organic nutrients in the deep-sea sediments of the Central Indian Ocean Basin in the Indian pioneer area. Sediments were collected using box core and grab samples during September 1996. The total bacterial numbers ranged from 10 10 -10 11 cells per g -1 dry weight sediment. There was a marginal decrease in the number of bacteria from surface to 30 cm depth, though the subsurface section registered a higher number than did the surface. The highest numbers were encountered at depths of 4-8 cm. The retrievable number of bacteria were two orders less in comparison with the direct total counts of bacteria. An almost homogeneous distribution of bacteria, total organic carbon, living biomass, and lipids throughout the depth of cores indicates active microbial and benthic processes in the deep sea sediments. On the other hand, a uniform distribution of total counts of bacteria, carbohydrates, and total organic carbon in all the cores indicates their stable nature and suggests that they can serve as useful parameters for long-term monitoring of the area after the benthic disturbance. Further studies on temporal variability in this region would not only verify the observed norms of distribution of these variables but would also help to understand restabilization processes after the simulated benthic disturbance.     

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。     

Geoacoustic Inversion via Genetic Algorithm and Its Application to Manganese Sediment Identification

An acoustic inversion method using a wide-band signal and two near field receivers is proposed and applied to multiple layered seabed models including a manganese sediment. The inversion problem can be formulated into a probabilistic model comprised of signals, a forward model, and additive noise. The forward model simulates wide-band signals, such as chirp signals, and is chosen to be the source-waveletconvolution plane wave modeling method. The wavelet matching technique, using weighted least-squares fitting, estimates the sediment sound-speed and thickness on which determination of the possible numerical ranges for a priori uniform distribution is based. The genetic algorithm is applied to a global optimization problem to find a maximum a posteriori solution for determined a priori search space. Here the object function is defined by an L 2 norm of the difference between measured and modeled signals. Not only the marginal pdf but also its statistics are calculated by numerical evaluation of integrals using the samples selected during importance sampling process of the genetic algorithm.     

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.     

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.     

Phylogenetic diversity and phenotypic characterization of cultivable bacterioplankton isolated from polar oceans

A set of 27 marine planktonic bacteria isolated from the polar regions was characterized by 16S rDNA sequencing and physiological and biochemical testing. More than half of these bacteria were positive for caseinase, gelatinase and 13-glucosidase, and could utilize glucose, maltose or malic acid as carbon source for cell growth. Twelve isolates expressed nitrate reduction activities. Except for one antarctic isolate BSwlO175 belonging to Actinobacteria phylum, these isolates were classified as γ-Proteobacteria, suggesting that γ-Proteobacteria dominated in cultivable marine bacterioplankton at both poles. Genus Pseudoalteromonas was the predominant group in the Chukchi Sea and the Bering Sea, and genus ShewaneUa dominated in cultivable bacterioplankton in the Prydz Bay. With sequence similarities above 97%, genus Psychrobacter was found at both poles. These 27 isolates were psychrotolerant, and significant 16S rDNA sequence similarities were found not only between arctic and antarctic marine bacteria （ 〉 99% ）, but also between polar marine bacteria and bacteria from other aquatic environments （ ≥ 98.8% ）, including temperate ocean, deep sea, pond and lake, suggesting that in the polar oceans less temperature-sensitive bacteria may be cosmopolitan and have a bipolar, even global, distribution at the species level.     

Deep-Sea Sediment Compression Curves: Some Controlling Factors, Spurious Overconsolidation, Predictions, and Geophysical Reproduction

Oedometer tests have been carried out on 70 undisturbed surficial clays (at approximately 250 mm below the mudline), mostly collected by free-fall corers from sites widely scattered throughout the deep-sea North Atlantic. Acoustic measurements were also made, initially on contiguous samples and ultimately on the same sample using a geophysically instrumented oedometer which also collected electrical resistivity data. Apart from those quiescent areas below the carbonate compensation depth, such as north of the West Indies where very fine clays exist, most of the samples are silty clays whose geotechnical-geophysical properties are dependent on the type of clay minerals present (and their ability to take in moisture), the sand-size fraction, and the quantity of carbonate present. Thus the pure clays have high compressibilities which decrease on the addition of coarse particles, while the converse is true for the acoustic parameters, these increasing with the sand fraction. Using the notion of the intrinsic compression line for all samples, and comparison to it of the measured compression curves, it is clear that, contrary to some previously held ideas, most deep-sea clays are normally consolidated; the addition of carbonate has the effect of creating an open, stronger sediment skeleton. Interestingly, where information is available, the variation with depth of a sample's acoustic velocity follows the void ratio pressure relationship of the compression curve. This allows the construction of an in-situ sediment compression curve using the in-situ geophysical observations.