基于改进CGAN的海冰SAR-to-Optical影像转换

遥感海冰监测是当前研究热点,通过条件生成对抗网络 （CGAN） 将海冰SAR影像转换成光学影像,可获得全天时全天候且形象直观的监测数据,但该方法得到的转换结果存在影像模糊、纹理弱化和颜色失真等问题。本文针对以上问题设计了改进的CGAN网络,综合当前的改进方式,新模型在网络结构上加入了空洞空间金字塔模块并设计了加入交叉特征融合模块的跳跃连接,使用结构相似性和L1范数联合损失函数。本文选取东波弗特海地区5景Sentinel-1影像和7景Sentinel-2影像开展实验,实验结果表明,改进CGAN转换的影像具有更好的视觉效果,峰值信噪比 （PSNR） 提高了 3.4 dB,结构相似性 （SSIM） 提高了 0.11,均方根误差（RMSE） 降低了13%,并且经过转换后的影像比SAR影像海冰分类结果准确度提高了7.33%。     

湘南晚泥盆世佘田桥期碳酸盐块状流沉积特征

湘南晚泥盆世佘田桥期表现为东西两侧高而中部低陷的古地理面貌。两侧为碳酸盐台地,中间为深水台盆。在台盆、台地之间斜坡地带和台盆边缘,堆积了类型繁多的碳酸盐块状流沉积物。它们由两类在成因和分布上有密切联系的沉积体系组成,一类为重力崩落或滑移体系,包括岩崩、滑动和滑塌沉积,另一类为重力流体系,包括碎屑流、浊流和颗粒流沉积。在层序上它们虽作有规律的组合层序,但并不是完整的类型,而出现较大的变异性。已发现的组合层序有①滑塌沉积—碎屑流沉积,②碎屑流—高密度浊流—低密度浊流沉积,③变密度颗粒流—浊流沉积。它们沿近南北向的台盆的两侧边缘呈条带状分布,东侧位于临武香花岭至桂阳莲塘一带,重力流厚度可达150m左右,西侧位于道县虎岩坝至双牌县城一带,重力流厚只30—50m,反映了台盆边缘两侧构造活动强度不一致,东侧强,西侧弱。     

河南灵宝小秦岭金矿带矿化特征及富集规律研究

本文简述了河南灵宝小秦岭金矿带矿化特征，提出了全区金矿化富集的层位性、分带性、主从性、方向性及似等距性，同时探讨了工业矿脉内金矿化的若干局部富集规律。     

RecNet: a deep neural network for personalized POI recommendation in location-based social networks

How to exploit various features of users and points of interest (POIs) for accurate POI recommendation is important in location-based social networks (LBSNs). In this paper, a novel POI recommendation framework, named RecNet, is proposed, which is developed based on a deep neural network (DNN) to incorporate various features in LBSNs and learn their joint influence on user behavior. More specifically, co-visiting, geographical and categorical influences in LBSNs are exploited to alleviate the data sparsity issue in POI recommendation and are converted to feature vector representations of POIs and users via feature embedding. Moreover, the embedded POIs and users are fed into a DNN pairwise to adaptively learn high-order interactions between features. Our method is evaluated on two publicly available LBSNs datasets and experimental results show that RecNet outperforms state-of-the-art algorithms for POI recommendation.     

基于盐湖资源的硝酸熔盐储能材料性能研究

太阳能光热发电是可再生能源发展的主要方向。作为太阳能光热发电的核心技术,熔融盐以热容量大、粘度低、蒸汽压低、使用温度范围宽等诸多独特的性能优势,成为光热发电储能的首选。相比之下,硝酸熔盐具有优良的传热和流体流动等特性,使其在光热储热系统中的性能优势较为突出。我国盐湖地区具备太阳能光热发电的发展空间和优势,丰富的无机盐资源可以降低相关相变储能材料的生产成本,有利于推进太阳能的规模化发展、能源结构的调整优化。据此,立足于盐湖资源的开发利用,以硝酸盐系列传热蓄热介质的工业应用为背景,针对产业化的二元硝酸盐熔盐做了更深入的系统研究;在此基础上,通过添加硝酸镁,制备了低熔点的三元熔盐储能材料;并将碳纳米管引入到硝酸盐体系,进一步提升了其导热性能。这不仅为硝酸熔盐储热材料的制备提供了理论基础,也为其在光热发电的应用打开了更多的可能性。     

评价生物气生成量、生成期的碳同位素平衡法及其应用

生物气的生成期对其成藏有至关重要的制约作用,但目前国内外尚缺少可信、有效方法来对此进行评价。针对这一难题,考虑到无论生物气的生成机理如何,转化前的有机质和转化后的残余有机质及产物的13C、12C的总量应该守恒,本文探索并建立了评价生物气生成量的碳同位素平衡法,并利用松辽盆地的实际分析数据,对这一评价方法（模型）进行了标定和应用。结果表明:Ⅰ、Ⅱ、Ⅲ型有机质累计产生物成因甲烷气的量分别约为193.94 ml/g、175.64 ml/g、161.71 ml/g。区内源岩生物气的生成量约为385.4×1012 m3;生物气的主要生成期在嫩江组沉积末期之前;区内生物气的可能资源量介于11.40×1011～24.8×1011 m3之间。     

一种由粗到精的光学与SAR遥感图像配准算法

由于光学遥感图像和SAR图像具有明显的非线性强度差异,且SAR图像存在斑点噪声,使得其配准存在较大难度。为此,本文结合基于特征和基于区域图像配准方法的优点,并组合为混合模型,提出一种由粗到精的自动配准算法。以光学遥感图像和SAR图像分别为参考图像和待配准图像,先以基于特征点的SAR-SIFT完成粗配准,再以基于区域的ROEWA-HOG完成精配准。① 采用SAR-SIFT算法进行特征点检测和特征匹配来计算图像的仿射变换模型,以消除参考图像和待配准图像之间明显的旋转、尺度和平移差异,至此完成图像粗配准;② 在此基础上利用分块Harris角点检测在参考图像上获得特征点,并根据特征点确定待配准图像上的同名点搜索区域;③ 计算图像的ROEWA梯度,构造以特征点为中心的模板区域内的HOG特征向量,以SSD作为相似性测度搜索待配准图像上的同名点,完成高精度的图像配准;④ 进行图像配准实验,对配准结果进行目视检查和精度评估。经过多组光学与SAR图像配准实验,验证本文算法能够结合基于特征和基于区域的图像配准方法的优点,较好地抵抗光学与SAR图像之间的非线性强度、旋转、尺度、平移差异和SAR图像的噪声影响,并逐步提高配准精度,最终配准精度达到1个像素左右,实现了光学与SAR图像的高精度自动配准,能够满足光学与SAR图像后续综合应用。     

基于空间相似性的面实体匹配算法研究

同一地物在不同来源的地图上通常存在着差异,其识别或匹配对于不同数据源的地图编制来说很关键。面状地物要素在很多地图表示中都占有很大的比例。基于人眼综合已有信息来识别同名实体的思想,本文提出了基于空间相似性的面实体匹配算法。该算法将面实体作为一个整体看待,采用加权平均法来综合面实体的位置、形状、大小等特征的相似度,进而根据获得的总相似度大小确定匹配实体。算法在确定位置相似度时选择形状中心点对面实体进行惟一标识;采用形状描述函数来计算形状相似度,不容易受各种干扰而影响精度,避免了形状信息的丢失;面实体的大小通过其覆盖面积来度量。实验结果表明该方法具有良好的稳定性和可靠性。     

Sinkhole hazard assessment in Minnesota using a decision tree model

An understanding of what influences sinkhole formation and the ability to accurately predict sinkhole hazards is critical to environmental management efforts in the karst lands of southeastern Minnesota. Based on the distribution of distances to the nearest sinkhole, sinkhole density, bedrock geology and depth to bedrock in southeastern Minnesota and northwestern Iowa, a decision tree model has been developed to construct maps of sinkhole probability in Minnesota. The decision tree model was converted as cartographic models and implemented in ArcGIS to create a preliminary sinkhole probability map in Goodhue, Wabasha, Olmsted, Fillmore, and Mower Counties. This model quantifies bedrock geology, depth to bedrock, sinkhole density, and neighborhood effects in southeastern Minnesota but excludes potential controlling factors such as structural control, topographic settings, human activities and land-use. The sinkhole probability map needs to be verified and updated as more sinkholes are mapped and more information about sinkhole formation is obtained.     

Spatial operations in a GIS-based karst feature database

This paper presents the spatial implementation of the karst feature database (KFD) of Minnesota in a GIS environment. ESRI’s ArcInfo and ArcView GIS packages were used to analyze and manipulate the spatial operations of the KFD of Minnesota. Spatial operations were classified into three data manipulation categories: single layer operation, multiple layer operation, and other spatial transformation in the KFD. Most of the spatial operations discussed in this paper can be conducted using ArcInfo, ArcView, and ArcGIS. A set of strategies and rules were proposed and used to build the spatial operational module in the KFD to make the spatial operations more efficient and topographically correct.