基于交通轨迹数据的三维动态噪声地图

噪声信息具有空间传播和随距离衰减变化的特征,采用三维动态可视化形式表达噪声地图可以体现该特征。本文针对噪声的空间分布与强度变化提出一种噪声地图表达的方法,基于Bertin符号参量分析,以具有高度可变的方柱并配以深浅变化的颜色作为噪声符号,动态传递噪声信息。为进行多尺度地图展示,在不同地图等级下设有相应细节层次的符号尺寸和定位排列方式。噪声地图以Web端Mapbox为展示平台,基于交通噪声模型和GPS轨迹数据,对上海黄浦区某区域一时间段内的噪声情况进行模拟表达,实现噪声数据的立体动态化显示。三维动态的表达扩展了噪声数据的表现维度,多维度、多参量的立体动态符号不仅可准确刻画噪声的分布,而且从视觉观感上提高了受众的兴趣度和专注度,这为研究噪声的热点分布、传递趋势等空间规律提供了可视化参考。     

使用长短期记忆人工神经网络进行花岗岩变形破坏阶段的判别

判别岩石所处的变形破坏阶段是分析岩石变化过程的重要基础。由于室内试验视频数据具有很好的等时距分布特征,可以使用基于长短期记忆的神经网络（LSTM-NN）模型判别外荷作用下岩石的变形破坏阶段。本文根据花岗岩室内单轴压缩试验所得应力-应变曲线和试验视频图像中裂隙的分布情况,将岩石变形破坏过程分成岩石压密阶段、弹性变形阶段、裂隙扩展阶段、整体破坏阶段,在提取不同阶段不同组分主要数字特征参数（面积）基础上,建立了基于LSTM-NN模型的岩石变形破坏阶段分类网络,分析了模型主要参数（学习率和最大周期等）对分类准确性的影响,使用所建模型对岩石所处变形破坏阶段进行了判别。结果表明,在LSTM-NN模型参数中,学习率和最大周期对变形破坏阶段判别准确率的影响较大,二者分别为0.005和200时的判别准确率达到最高;对于整个变形破坏阶段来说,LSTM-NN模型对裂隙扩展阶段预测的判别效果最好、对整体破坏阶段预测的判别效果最差;对于花岗岩中不同组分来说,LSTM-NN模型对变形破坏阶段预测准确性高低的顺序是裂隙、黑云母、长石、石英。     

超参数对GRU-CNN混合深度学习弹性阻抗反演影响研究

CNN-GRU混合深度学习反演弹性阻抗取得了较好的反演效果.但是,基于深度学习的叠前反演参数众多,包括内部深度学习网络可学习参数和外部超参数等,目前超参数选取对网络性能及计算速度影响尚缺乏系统性研究,这直接影响到了该方法的进一步推广应用.因此,本文在混合深度学习反演弹性阻抗基础上,探讨学习率、Ep-och、batch_size、正则化参数及参与网络训练的测井个数等5个超参数对网络性能及计算速度的影响,为深度学习地震反演超参数选取提供依据.研究结果可为三维大面积深度学习反演提供一个可行的质控手段,对于推动深度学习方法在石油物探中广泛应用具有一定意义.     

北斗三号系统进展及性能预测: 试验验证数据分析

网络实时动态测量(real-time kinematic, RTK)技术可为大范围区域用户提供实时高精度的定位服务,然而目前该技术对卫星导航定位(satellite navigation and positioning,SNAP)基准站网密度要求较高。为了满足稀疏大尺度SNAP基准站网区域的高精度定位服务需求,提出了一种基于虚拟大气约束（virtual atmosphere constrait, VAC）的网络RTK服务方法,首先构建非组合双差观测值模型,快速解算并固定SNAP基准站基线模糊度;然后提取基线大气延迟,分别建立斜路径电离层和天顶对流层误差模型;最后将内插的大气延迟及其精度信息作为虚拟观测值,提升终端RTK的定位性能。采用中国西北的SNAP基准站网数据(平均站间距为205.1 km)和网内外6个流动站数据进行RTK验证,结果表明,所提方法可以满足大尺度参考网下用户的高精度定位需求,相比传统的虚拟基准站技术,VAC服务模式下的终端定位精度、初始化速度平均分别提升61.64%和9.96%,该模式下测试终端固定解水平和高程方向的平均均方根分别为1.19 cm、2.73 cm;采用多次初始化进行验证,平均88.78%的时段在2个历元内即可完成初始化;VAC服务模式对大尺度SNAP基准站网内外用户均具有较好的适应性。     

基于Web的地下管网溯源分析算法研究

利用.NetCore的并行运算机制,实现基于Web的高性能地下管网的溯源分析功能.实践证明当某点管网数据监测出现异常时,能够快速分析所有可能流经该点源头管网信息,并在地图上动态展示分析结果,达到快速定位查询管网源头的区域管理目的.     

基于BP神经网络与数学形态学的彩色地质图面要素信息智能提取

地质图是一个区域地质研究的重要成果,也是前人留下的宝贵资料,更融合了地质专家的丰富知识。本研究的目的是通过新的思路将彩色地质图信息提取出来,使其结果能直接进行数据分析,并用于决策和分析。以机器学习为指导,在分析半结构化（栅格）地质图特征的基础上,根据图例信息,提出一种彩色地质图信息提取新思路,对彩色地质图进行分层信息提取,并结合数学形态学和多层前向反馈式神经网络,探索半结构化数据转换为结构数据的有效技术方法。利用图像信息提取技术将半结构化地质图转化为结构化数据,可用于成矿预测等研究。这一变化将改变传统地质数据的结构,地质研究的信息基础和来源将会增加,对于获取更多的数据源和信息源,进一步开展地质分析研究具有重要意义。     

基坑支护结构水平变形预测的遗传神经网络方法

采用遗传算法和误差反向传播算法相结合的混合算法来训练前馈人工神经网络,先用遗传学习算法进行全局训练,再用BP算法进行精确训练。就遗传算法过程中的选择、变异进行了探索,提出了用BP网络训练产生变异的遗传算法。作为实例,将该方法应用于预测基坑支护结构水平变形中。结果表明,该方法有收敛速度较快、预测精度高等优点。     

利用ERS-2 SAR图像纹理分析方法揭示长白山天池火山近代喷发物空间分布特征

简单介绍了SAR图像的纹理特征以及正交小波变换纹理提取方法。论述了SAR图像的纹理特征参与分类的重要性。以长白山天池火山为例,通过对ERS2SAR图像进行纹理分析,提取了SAR图像两个层次的尺度变化、时频局部化和方向性纹理特征。并将SAR纹理特征与TM图像及DEM进行复合,利用多源信息各自的优势,进行了BP神经元网络分类,从较大范围对长白山天池火山735±15aB.P.大喷发的喷发物空间分布进行评价。获取了长白山天池火山近代喷发物的空间分布及规模。这对长白山天池火山未来喷发危险性初步评价、火山地质制图及火山灾害预测有重要意义。     

Metrics to assess how longitudinal channel network connectivity and in‐stream Atlantic salmon habitats are impacted by hydropower regulation

Habitat fragmentation in channel networks and riverine ecosystems is increasing globally due to the construction of barriers and river regulation. The resulting divergence from the natural state poses a threat to ecosystem integrity. Consequently, a trade‐off is required between the conservation of biodiversity in channel networks and socio‐economic factors including power generation, potable water supplies, fisheries, and tourism. Many of Scotland's rivers are regulated for hydropower generation but also support populations of Atlantic salmon (Salmo salar L.) that have high economic and conservation value. This paper investigates the use of connectivity metrics and weightings to assess the impact of river barriers (impoundments) associated with hydropower regulation on natural longitudinal channel connectivity for Atlantic salmon. We applied 2 different weighting approaches in the connectivity models that accounted for spatial variability in habitat quality for spawning and fry production and contrasted these models with a more traditional approach using wetted area. Assessments of habitat loss using the habitat quality weighted models contrasted with those using the less biologically relevant wetted area. This highlights the importance of including relevant ecological and hydrogeomorphic information in assessing regulation impacts on natural channel connectivity. Specifically, we highlight scenarios where losing a smaller area of productive habitat can have a larger impact on Atlantic salmon than losing a greater area of less suitable habitat. It is recommended that future channel connectivity assessments should attempt to include biologically relevant weightings, rather than relying on simpler metrics like wetted area which can produce misleading assessments of barrier impacts.     

Assessment of flow paths and confluences for saltwater intrusion in a deltaic river network

Saltwater intrusion is a serious issue in estuarine deltas all over the world due to rapid urban sprawl and water shortage. Therefore, detecting the major flow paths or locations at risk of saltwater intrusion in estuarine ecosystems is important for mitigating saltwater intrusion. In this paper, we introduce a centrality index, the betweenness centrality (BC), to address this problem. Using the BC as the weighted attribute of the river network, we identify the critical confluences for saltwater intrusion and detect the preferential flow paths for saltwater intrusion through the least‐cost‐path algorithm from a graph theory approach. Moreover, we analyse the responses of the BC values of confluences calculated in the river network to salinity. Our results show that the major flow paths and critical confluences for saltwater intrusion in a deltaic river network can be represented by the least cost paths and the BC values of confluences, respectively. In addition, a significant positive correlation between the BC values of confluences and salinity is determined in the Pearl River Delta. Changes in the salinity can produce significant variation in the BC values of confluences. Therefore, freshwater can be diverted into these major flow paths and critical confluences to improve river network management under saltwater intrusion. Copyright © 2015 John Wiley & Sons, Ltd.