Study on the Submarine Slope Stability of the Deep Channel in the Caofeidian Harbor

Objective The greatest advantage of the Caofeidian Harbor is its deep channel facing the Bohai Bay. The deep channel is a natural port hub for shipping of the Caofeidian Habor. The construction of the Caofeidian Harbor has impacted the hydrodynamic environment and the sediments movement, which has attracted much attention about the geomorphic evolution, slope stability and the evolution trend after submarine slope destruction. Insight from this study might be significant for the future development of the Caofeidian Habor, including planning, operation and maintenance.

Seismic stratigraphy of the Qiongdongnan deep sea channel system,northwest South China Sea

Based on more than 4000 km 2D seismic data and seismic stratigraphic analysis, we discussed the extent and formation mechanism of the Qiongdongnan deep sea channel. The Qiongdongnan deep sea channel is a large incised channel which extends from the east boundary of the Yinggehai Basin, through the whole Qiongdongnan and the Xisha trough, and terminates in the western part of the northwest subbasin of South China Sea. It is more than 570 km long and 4–8 km wide. The chaotic (or continuous) middle (or high) amplitude, middle (or high) continuity seismic facies of the channel reflect the different lithological distribution of the channel. The channel formed as a complex result of global sea level drop during early Pliocene, large scale of sediment supply to the Yinggehai Basin, inversion event of the Red River strike-slip fault, and tilted direction of the Qiongdongnan Basin. The large scale of sediment supply from Red River caused the shelf break of the Yinggehai Basin to move torwards the S and SE direction and developed large scale of prograding wedge from the Miocene, and the inversion of the Red River strike-slip fault induced the sediment slump which formed the Qiongdongnan deep sea channel.

融合累积分布函数和通道注意力机制的DeepLabV3+图像分割算法

为了解决DeepLabV3+在语义分割时未充分利用主干的低级特征,以及大倍数上采样造成有效特征缺失的问题,提出一种累积分布通道注意力DeepLabV3+(CDCA-DLV3+)模型。首先,基于累积分布函数和通道注意力提出了累积分布通道注意力(CDCA);然后,利用CDCA获取主干部分有效的低级特征;最后,采用特征金字塔网络(FPN)进行特征融合和逐步上采样,从而避免大倍数上采样所造成的特征损失。CDCA-DLV3+模型在Pascal VOC2012验证集与Cityscapes数据集上的平均交并比(mIoU)分别为80.09%和80.11%,相较于DeepLabV3+模型分别提升1.24和1.02个百分点。实验结果表明,所提模型分割结果更加精确。

Sedimentary characteristics comparison and genesis analysis of the deepwater channel in the hydrate enrichment zones on the north slope of the South China Sea

Natural gas hydrate(NGH) is one of the important clean energy at present and even in the future. The study of its sedimentary environment and minerogenetic condition has long been a hot issue that has received much concern from geologists all over the world. China has successfully obtained the samples of NGH in Shenhu and Dongsha sea areas in 2007, 2013 and 2015, respectively. From this, the continental slope north of the South China Sea becomes an important test site for the study of NGH sedimentary genesis and minerogenetic condition. NGH has been found in Shenhu, Dongsha and Qiongdongnan areas within the continental slope north of South China Sea,at different depths of water, with different sedimentary characteristics, gas genesis, and minerogenetic conditions.Using a seismic sedimentology theory, combining seismic facies results of each facies, sedimentary facies and evolution of each area are documented in turn establishing a sedimentary model by considering palaeogeomorphology, sea level change and tectonic movement. The channel system and MTD(Mass Transport Deposition) system among these three areas were compared focusing on the developing position, appearance and controlling factors. Relative location among three areas is firstly defined that Dongsha area in a nearprovenance steep upper slope, Shenhu area in a normal gentle slope and Qiongdongnan area in an awayprovenance flat plain. Besides, their channel systems are classified into erosional, erosional-aggradational and aggradational channel, and MTD systems into headwall domain, translational domain and toe domain.

Sedimentary processes in Zenisu deep-sea channel revealed by side-scan imagery

Side-scan sonar data collected by Cruises 99-09 Leg 2 and 00-06 Leg 1 of R/V Yokosuka were used to reveal the sedimentary processes in Zenisu deep-sea channel. The middle and lower segments of the channel are rich in turbidite and other debrite deposits. By high-resolution imaging, three sedimentary processes were distinguished with distinct acoustic features. 1. Slumps and slides occur with contrasting backscatter, rough surface textures, blockings, and acoustic shadows at headwalls. They are very extensive and often in lobate form downslope. 2. Debris flow has uniform, general medium backscatter, sometimes showing marbling/lineation in lobate form. 3. Turbidity current is characterized by low backscatter confined to the channel as acoustic signal is attenuated. Regional tectonics must be the dominating factor that controls deposition pattern in this area.

Channel Estimation with an Interpolation Trained Deep Neural Network

This paper proposes a deep learning-based channel estimation method for orthogonal frequency-division multiplexing (OFDM) systems. The existing OFDM receiver has low estimation accuracy when estimating channel state information (CSI) with fewer pilots. To tackle the problem, in this paper, a deep learning model is first trained by the interpolated channel frequency responses (CFRs) and then used to denoise the CFR estimated by least square (LS) estimation. The proposed deep neural network (DNN) can also be trained in a short time because it only learns the CFR and the network structure is simple. According to the simulation results, the performance of the DNN estimator can be compared with the minimum mean-square error (MMSE) estimator. Furthermore, the DNN approach is more robust than conventional methods when fewer pilots are used. In summary, deep learning is a promising tool for channel estimation in wireless communications.

Geologic-Geophysical Indicators of the Deep Structure of Zones of Geothermal Anomalies for Allocation of Channels of the Deep Heat and Mass Transfer

On the basis of the analysis of field thermogeochemical data along abnormal zones of a thermal stream in the Bukhara-Khiva, oil-and-gas region of the Turan (Tegermen, Chagakul, Shimoly Alat, Beshtepa) was succeeded to obtain important data on a deep structure of sites. Data of gas-chemical and geothermal observations show about confinedness of abnormal concentration of methane to zones of the increased values of the temperature field the measured values of temperatures (Tegermen Square and others). On geoelectric section mines 2-D of inversion of the MT-field depth of 4000 m are lower, among very high-resistance the chemogenic and carbonate deposits of the Paleozoic is traced the subvertical carrying-out abnormal zone. This zone is identified as the channel of a deep heat and mass transfer with which hydrocarbon (HC) deposits are connected. It is shown that electro-investigation when using a geophysical complex can and has to become “advancing” at exploration by oil and gas.

基于A-BiLSTM和CNN的文本分类

为解决单一神经网络不能获取准确全局文本信息的问题,提出一种基于A-BiLSTM双通道和优化CNN的文本分类模型。A-BiLSTM双通道层使用注意力机制关注对文本分类贡献值较大的部分,并用BiLSTM提取文本中上下文语义信息;A-BiLSTM双通道层中将两者输出的特征信息融合,得到高级语义;A-BiLSTM双通道层后,使用优化CNN的强学习能力提取关键局部特征,得到最终文本特征表示。分类器输出文本信息的类别。实验结果表明,该模型分类效果优于其它对比模型,具有良好的泛化能力。

基于并行反向投影的图像超分辨率

基于反向投影的残差特征提取与融合,可有效提升深度网络的特征提取能力,从而有益于改善图像的超分辨率重构性能.在此基础上提出了一种改进的采用并行反向投影策略的图像超分辨率深度网络,通过并行增强处于不同频段的高频特征,得到超分辨率性能的进一步提升.具体进行浅层特征提取后,网络经过多级的双路并行的反向投影特征增强模块.每一级模块中包含两个通路,分别采用顺序相反的上下采样,可同时得到处于不同频段的残差特征信息.通过对多级残差特征的融合,图像的高频特征得到不断的增强.同时网络引入了多尺度特征提取与通道注意力机制,以改进特征表达和学习能力.在多个公开的数据集上的大量实验结果表明,该方法可以有效提升超分辨率性能,并且在减少模型复杂度方面有一定的成效.

MCJ-UNet:一种双/多通道联合InSAR相位解缠网络

干涉合成孔径雷达(InSAR)可实现地表高程的高效获取,在地形测绘中应用广泛。双/多通道InSAR技术可借助不同通道(基线、频点)的高程模糊度差异,解决相位欠采样问题,完成高程陡变区域的干涉相位解缠,实现InSAR技术在测绘困难区域的有效应用。该文即面向高效高精度相位解缠需求,利用深度学习这一有力工具,结合不同通道的相位特征及相互约束关系,提出了一种双/多通道联合干涉相位解缠网络:Multi-Channel-Joint-UNet(MCJ-UNet)。该网络的构建以双通道(双频、双基线)InSAR为基本观测构型,并可实现向多通道构型的扩展,其构建的核心思路主要包括3点:首先,将干涉相位解缠中的模糊数估计问题转化为语义分割问题,并采用UNet网络完成分割处理;其次,引入挤压激励模块(SE)动态调整信息权重,以增强网络不同通道对其所需信息的感知能力;最后,利用多通道联合约束下的相位残差优化损失函数,实现网络调谐。此外,为避免语义分割结果的边缘细节误差对解缠效果的影响,该文还提出了一种基于多通道联合约束的解缠误差自修正方法,以保证解缠质量。模拟地形仿真数据、真实地形仿真数据以及TerraSAR-X实测数据验证了所提方法的有效性。

基于注意力机制引导深度残差网络的RIS辅助通信信道估计

用可重构智能表面(Reconfigurable Intelligent Surface, RIS)增强无线覆盖和信道容量是未来通信网络的候选方案之一。为估计RIS辅助的多用户(Multi User, MU)通信系统上行链路的信道状态信息,提出一种基于注意力机制的深度残差网络,构建了包含稀疏块、特征增强块、注意力引导块和重构块的网络结构,隐式地学习残差噪声,利用注意力机制加强对特定信道噪声特征的提取。仿真结果表明,该方法的估计精度略低于线性最小均方误差(Linear Minimum Mean Square Error, LMMSE)估计,在高信噪比时比常规深度残差去噪网络的估计精度更高。

双通道深度图像先验降噪模型

相对于采用固定网络参数值的有监督深度降噪模型而言,无监督的深度图像先验(Deep Image Prior,DIP)降噪模型更具灵活性和实用性.然而,DIP模型的降噪效果远低于有监督降噪模型(尤其是在处理人工合成噪声图像时).为进一步提升DIP降噪模型的降噪效果,本文提出了双通道深度图像先验降噪模型.该降噪模型由噪声图像预处理、在线迭代训练和图像融合3个模块组成.首先,利用BM3D和FFDNet两种经典降噪方法对给定的噪声图像进行预处理,得到2张初步降噪图像,然后,将原DIP单通道逼近目标图像架构拓展为双通道工作模式.其中,第一通道以FFDNet初步降噪图像和噪声图像为双目标图像,第二通道则以BM3D预处理图像和噪声图像为双目标图像.在此基础上,按照标准的DIP在线训练方式让DIP网络输出图像在两个通道上分别逼近各自的目标图像,同时依据基于边缘能量定义的伪有参考图像质量评价值适时终止迭代过程,从而获得2张中间生成图像.最后,使用结构化图块分解融合算法将两张中间生成图像融合并作为最终的降噪后图像.实验数据表明,在合成噪声图像上,本文提出的双通道深度图像先验降噪模型在各个噪声水平上显著优于原DIP及其他无监督降噪模型(提升了约2.2 dB),甚至逼近和超过了新近提出的主流有监督降噪模型,这充分表明了本文提出的改进策略的有效性;在真实噪声图像上,本文提出的降噪模型优于排名第二的对比降噪方法约2 dB,展现出其在实际应用场景下独有的优势.

基于改进图像超分辨卷积网络的矿井OFDM信道估计研究

针对煤矿井下环境恶劣,传统信道估计算法存在准确度低的问题,提出一种改进图像超分辨卷积网络(Super Resolution Convolutional Network,SRCNN)进行信道估计。在改进SRCNN模型中,将导频处的估计值作为输入,改进SRCNN模型取代了传统信道估计算法中的插值过程,降低了复杂度,并加入注意力机制ECA模块提高通道特征的学习,实现对煤矿井下环境更准确的信道估计。仿真结果表明:改进SRCNN模型的信道估计算法优于传统的信道估计算法,与SRCNN模型的信道估计相比,其估计精度提升了1个数量级。

基于多模态数据融合的改进中尺度涡检测模型

提出一种基于多模态数据融合的改进中尺度涡检测模型。该模型以海平面高度数据为基础,首次将融合表层海温数据扩展为融合多深度层海温数据;将海温数据的深度层作为通道,嵌入通道注意力机制,使得模型能够关注于海水温度数据中最具有区分度的深度层;模型在编码及解码过程中采用残差学习单元,在加深网络深度的同时,更好地拟合激活函数,缓解训练问题,以提高模型的检测准确率。以中国南海部分海域为例开展实验验证,结果表明该中尺度涡检测模型准确率达到93.62%,模型具备有效性和可靠性。

基于高效通道注意力的多阶段图像去雨网络

针对现有图像去雨算法不能更好地保留图像背景细节的问题,提出一种基于高效通道注意力的多阶段图像去雨网络。首先,网络使用3×3卷积提取雨图的浅层特征并传递给高效通道注意力模块,为不同的特征通道分配不同的权重;然后,传递给3个并行阶段,在前2个阶段中,使用编码-解码器进行多尺度特征提取,减少雨纹信息丢失,其中使用Transformer模块抑制无用信息传递;最后,在第3个阶段使用初始分辨率模块代替编码-解码器,从而保留输出图像的精细特征。实验结果表明,所提算法在Rain800、Rain12、Rain100L和Rain100H公开测试集上的结构相似性分别为0.830、0.968、0.960和0.944,峰值信噪比分别为27.33 dB、35.27 dB、36.79 dB和28.94 dB。所提算法相比于经典和新颖的图像去雨算法,在去除雨纹和恢复背景细节上具有更好的效果。

中新世以来上印度扇水道-堤岸体系几何学特征及演化

以中新世以来上印度扇水道-堤岸体系为研究对象,利用高精度二维地震资料开展地震精细解释与几何学分析,刻画水道-堤岸体系几何学特征及时空演化过程,探讨中新世以来上印度扇发育演化主要期次及特征。结果表明,中新世以来上印度扇水道-堤岸体系可划分为中新世、上新世及更新世至今三大期次,整体表现出“单期水道-侧向迁移-扁长型”到“多期水道-垂向叠置-厚窄型”的演化特征。深入探讨中新世以来上印度扇水道-堤岸体系的几何学特征及演化可为重力流水道的沉积构型样式研究提供新的例证,并为深海油气勘探开发提供参考。

融合注意力机制与线激光辅助的输送带缺陷检测网络

针对输送带缺陷种类繁多、缺陷特征像素占比小以及传统算法检测精度低的问题,采用随机仿射变换,扩充样本数据集;分析各通道间的关联关系及其贡献值对模型特征提取的影响,提出了一种通道关联加权注意力机制,利用关联卷积及全连接方式计算通道关联度及贡献权值,调整相应通道信息占比,提升模型检测精度;分析了上采样以及卷积块对输出特征图大小的影响,改进原特征金字塔特征卷积块及上采样结构,提高算法对小目标的特征提取以及缺陷检测能力;最后在输送带缺陷数据集上进行测试。结果表明:改进算法模型能对输送带典型的异物插入、破损、撕裂等缺陷特征进行有效识别,识别精准度可达99.7%,召回率大于99.5%,平均精度均值达到99.5%。

基于深层神经网络的信道编码类型盲识别

为了解决当前识别算法只能识别一种或者两种码字类型以及人工提取特征复杂的问题,提出了两种基于深层神经网络模型的信道编码类型识别器,即卷积神经网络(convolutional neural network,CNN)识别器和递归CNN(recursive CNN,RCNN)识别器,用于识别接收数据中不同类型的信道码字。将待识别的软解调序列作为自然语言处理中文本分类问题的句子向量进行处理,输入到预先训练好的深层神经网络识别器中进行识别,并分析了字长度对识别准确率的影响,得出了最合适的字长度。实验结果表明,两种识别器都能够有效识别接收数据中多种类型的信道编码,且在信噪比为3 dB时CNN识别器的识别准确率能够达到99%以上,而RCNN识别器在1 dB时就能够达到99%以上的识别准确率。

基于自适应p持续的移动自组网信道接入和资源分配算法

针对基于p持续的移动自组网(MANET)信道接入和资源分配问题,提出一种具有低复杂度的自适应信道接入和资源分配算法。首先,考虑到自组网无中心分布式组网特点,以每个节点的信道利用率最大化为目标建立优化问题;其次将该问题建模为马尔可夫决策过程并定义状态、动作和奖励函数;最后基于策略梯度训练网络参数,联合优化竞争概率、优先级增长因子以及通信节点数量。仿真实验结果表明,所提算法可以显著提高p-持续载波侦听多址接入(CSMA)协议的性能,与固定竞争概率和p值预定义的方案相比,所提算法的信道利用率提高了45%和17%;此外,当节点数量小于35时,所提算法优于固定接入节点数量的方案。同时,在节点数据包到达率较高时,所提算法可以充分利用信道,减少时隙资源浪费。

基于模型驱动深度学习的OTFS信道估计

针对单输入单输出(SISO)的正交时频空间(OTFS)调制系统,该文利用一种模型驱动深度学习算法进行OTFS信道估计。该方案首先将去噪近似消息传递(DAMP)算法进行深度展开,利用去噪卷积神经网络代替传统的去噪器,对含噪的时延多普勒信道进行去噪估计,然后提供了状态演化方程来预测可学习去噪近似消息传递(LDAMP)算法的理论归一化均方误差性能。仿真结果表明,相比于其他估计方案,该方案不仅在低信噪比条件下具有优越的性能表现,而且还具有非常好的鲁棒性,在信道路径总数不变时,增加OTFS 2维网格点数量,可以有效提升信道估计精确度。