A-FPN算法及其在遥感图像船舶检测中的应用

光学遥感图像船舶检测主要面临两个挑战:光学遥感图像背景复杂,船舶检测易受海浪、云雾及陆地建筑等多方面干扰;遥感图像分辨率低,船舶目标小,对于其分类与定位带来很大困难;针对上述问题,在FPN的基础上,提出一种融入显著性特征的卷积神经网络模型A-FPN (Attention-Based Feature Pyramid Networks)。首先,利用卷积提取图像特征金字塔;然后,利用顶层金字塔逐级构建显著特征层,抑制背景信息,通过金字塔顶层的细粒度特征提高浅层特征的表达能力,构建自上而下的多级显著特征映射结构;最后利用Softmax分类器进行多层级船舶检测。A-FPN模型利用显著性机制引导不同感受下的特征进行融合,提高了模型的分辨能力,对遥感图像处理领域具有重要应用价值。实验阶段,利用公开的遥感目标检测数据集NWPU VHR-10中的船舶样本进行测试,准确率为92.8%,表明A-FPN模型适用于遥感图像船舶检测。     

激光跟踪仪在核电站主管道安装中的应用

目前,核电站的主管道焊接越来越多的采用了自动焊技术,这有利于提高焊接质量效率,还可以压缩建设成本。然而,主管道自动焊对焊缝的限差较现有工艺要求更高,高精度的测量是实现主管道自动焊的必要条件之一。本文针对主管道自动焊管口组队高精度的技术要求,提出采用激光跟踪仪对主管道自动焊相关的设备进行更为精密的三维工业测量,通过理论技术评定测量精度,然后选择测量仪器和编制具体的测量方案,最终保证了主管道自动焊精确组对的实现。     

复杂地形景区三维导览图的设计与实现

为满足复杂地形景区对三维地图导览的需求,构建更为清晰的三维地图模型,提供良好的三维导览地图设计方案显得尤为重要。为了更好地与卫星影像进行贴合,DEM数据的采样密度要与卫星影像的分辨率一致。本文通过对比当下常用的四种空间插值方法的适用范围与运用特点,设置相关阈值及权重,直观比较了四种插值方法产生的插值结果,选择更适合复杂景区DEM插值的插值方法并对其进行精度提升,以此得到符合精度要求的DEM数据。最后利用相应地区的卫星影像进行地图投影及影像贴图,两种数据结合构建复杂景区的三维地图模型,给游客带来更为精确直观的定位信息和空间要素信息。     

Retrieving volume FeO and TiO_2 abundances of lunar regolith with CE-2 CELMS data using BPNN method

The volume FeO and TiO_2 abundances(FTAs) of lunar regolith can be more important for understanding the geological evolution of the Moon compared to the optical and gamma-ray results. In this paper, the volume FTAs are retrieved with microwave sounder(CELMS) data from the Chang'E-2 satellite using the back propagation neural network(BPNN) method. Firstly, a three-layered BPNN network with five-dimensional input is constructed by taking nonlinearity into account. Then, the brightness temperature(TB) and surface slope are set as the inputs and the volume FTAs are set as the outputs of the BPNN network.Thereafter, the BPNN network is trained with the corresponding parameters collected from Apollo, Luna,and Surveyor missions. Finally, the volume FTAs are retrieved with the trained BPNN network using the four-channel TBderived from the CELMS data and the surface slope estimated from Lunar Orbiter Laser Altimeter(LOLA) data. The rationality of the retrieved FTAs is verified by comparing with the Clementine UV-VIS results and Lunar Prospector(LP) GRS results. The retrieved volume FTAs enable us to re-evaluate the geological features of the lunar surface. Several important results are as follows. Firstly, very-low-Ti(1.5 wt.%) basalts are the most spatially abundant, and the surfaces with TiO_2 5 wt.% constitute less than 10% of the maria. Also, two linear relationships occur between the FeO abundance(FA) and the TiO_2 abundance before and after the threshold, 16 wt.% for FA. Secondly, a new perspective on mare volcanism is derived with the volume FTAs in several important mare basins, although this conclusion should be verified with more sources of data. Thirdly, FTAs in the lunar regolith change with depth to the uppermost surface,and the change is complex over the lunar surface. Finally, the distribution of volume FTAs hints that the highlands crust is probably homogeneous, at least in terms of the microwave thermophysical parameters.     

A natural language processing and geospatial clustering framework for harvesting local place names from geotagged housing advertisements

Local place names are frequently used by residents living in a geographic region. Such place names may not be recorded in existing gazetteers, due to their vernacular nature, relative insignificance to a gazetteer covering a large area (e.g. the entire world), recent establishment (e.g. the name of a newly-opened shopping center) or other reasons. While not always recorded, local place names play important roles in many applications, from supporting public participation in urban planning to locating victims in disaster response. In this paper, we propose a computational framework for harvesting local place names from geotagged housing advertisements. We make use of those advertisements posted on local-oriented websites, such as Craigslist, where local place names are often mentioned. The proposed framework consists of two stages: natural language processing (NLP) and geospatial clustering. The NLP stage examines the textual content of housing advertisements and extracts place name candidates. The geospatial stage focuses on the coordinates associated with the extracted place name candidates and performs multiscale geospatial clustering to filter out the non-place names. We evaluate our framework by comparing its performance with those of six baselines. We also compare our result with four existing gazetteers to demonstrate the not-yet-recorded local place names discovered by our framework.     

铜藻(Sargassum horneri)在营养限制胁迫后对NH4-N的超补偿吸收研究

以经济马尾藻铜藻(Sargassum horneri)为研究材料,研究了其在营养限制胁迫后对NH_4-N的超补偿吸收情况。实验分营养限制和恢复营养两个阶段进行,每个阶段均设置饥饿处理组、饱和处理组和正常对照组。铜藻在低营养限制胁迫(饥饿)下培养10天后,恢复营养盐培养3天,分别采用次溴酸盐氧化法和锌镉还原法测定培养液中的NH_4-N和NO_3-N的浓度。本文研究发现,饥饿处理组中铜藻吸收氨氮的速率远高于正常对照组和饱和处理组,在恢复培养第一天时,饥饿处理组对NH_4-N的吸收速率最高为14.94μmol/(g·h),与正常对照组及饱和处理组间差异显著。在恢复培养的后两天,三个处理组中铜藻对NH_4-N的吸收速率差异慢慢变小,直至最后几乎相同。三组对NO_3-N没有表现出较高的吸收,最高仅为6.15μmol/(g·h),结果表明:氮源包括NH_4-N和NO_3-N时,铜藻优先选择吸收NH_4-N。实验后称重测定生长速率:对照组、饥饿处理组和饱和组生长率(SGR)分别为8.48%、8.86%、8.01%,ANOVA方差分析表明,三者存在显著差异(P=0.0320.05),从而证实了铜藻也存在超补偿生长的现象。     

Assessment of alternative adsorption models and global sensitivity analysis to characterize hexavalent chromium loss from soil to surface runoff

We investigate our ability to assess transfer of hexavalent chromium, Cr(VI), from the soil to surface runoff by considering the effect of coupling diverse adsorption models with a two‐layer solute transfer model. Our analyses are grounded on a set of two experiments associated with soils characterized by diverse particle size distributions. Our study is motivated by the observation that Cr(VI) is receiving much attention for the assessment of environmental risks due to its high solubility, mobility, and toxicological significance. Adsorption of Cr(VI) is considered to be at equilibrium in the mixing layer under our experimental conditions. Four adsorption models, that is, the Langmuir, Freundlich, Temkin, and linear models, constitute our set of alternative (competing) mathematical formulations. Experimental results reveal that the soil samples characterized by the finest grain sizes are associated with the highest release of Cr(VI) to runoff. We compare the relative abilities of the four models to interpret experimental results through maximum likelihood model calibration and four model identification criteria (i.e., the Akaike information criteria [AIC and AIC_C] and the Bayesian and Kashyap information criteria). Our study results enable us to rank the tested models on the basis of a set of posterior weights assigned to each of them. A classical variance‐based global sensitivity analysis is then performed to assess the relative importance of the uncertain parameters associated with each of the models considered, within subregions of the parameter space. In this context, the modelling strategy resulting from coupling the Langmuir isotherm with a two‐layer solute transfer model is then evaluated as the most skilful for the overall interpretation of both sets of experiments. Our results document that (a) the depth of the mixing layer is the most influential factor for all models tested, with the exception of the Freundlich isotherm, and (b) the total sensitivity of the adsorption parameters varies in time, with a trend to increase as time progresses for all of the models. These results suggest that adsorption has a significant effect on the uncertainty associated with the release of Cr(VI) from the soil to the surface runoff component.     

面向稀疏散布数据集的时空Kriging优化

时空Kriging法通过将变异函数向时空域进行扩展得到时空变异函数,有效地利用时空邻近的采样点综合进行插值,由于时空稀疏散布数据集具有单一时刻下样本点数量少以及时空分布不规律的特点,难以满足使用时空Kriging插值法的基本条件,导致插值精度不高,据此本文提出了优化方法：通过多时段叠置拟合空间变异函数的方法,综合利用时空邻域内的采样点以解决单一时刻下空间邻域内数量不足情况;控制时间变异对空间变异函数拟合的误差影响;采用积合式模型构建时空变异函数进行插值。最后使用Argo海温数据进行插值实验,在相同条件下与时空Kriging法以及时空权重法的交叉验证结果对比得出,该方法在保证拟合所需采样点数量要求的同时,有效削减了一般时空Kriging法中时间变异对空间变异函数拟合结果的干扰,插值结果的绝对误差均值从0.5降低至0.2以内,稳定性进一步增强,改善了时空Kriging法在稀疏散布数据条件下精度上的不足。     

利用短期静态PPP结果反演海潮负荷位移

采用香港11个GPS测站的观测资料进行1 h、2 h、3 h和4h静态PPP解算，获得4组PPP坐标序列，利用调和分析求取11个测站处8个主要分潮的负荷位移参数（振幅和相位），将其与海潮模型计算的负荷位移参数进行对比，并比较分析PPP反演值与海潮模型值改正海潮负荷信号的效果。结果表明，垂直和水平方向上，不同PPP结果反演8个分潮的负荷位移分别具有约5 mm和7 mm的差异；PPP反演8个分潮垂向负荷位移优于全球海潮模型，但水平方向上的反演效果稍弱。     

Capsizing Probability of Dead Ship Stability in Beam Wind and Wave for Damaged Ship

The International Maritime Organization has developed the second-generation intact stability criteria. Thus, damage stability criteria can be established in the future. In order to identity the capsizing probability of damaged ship under dead ship condition, this paper investigates two methods that can be used to research the capsizing probability in time domain, which mainly focus on the nonlinear righting lever GZ curve solution. One method subjects the influence of damaged tanks on the hull shape down to the wind and wave, and the other method is consistent with the real-time calculation of the GZ curve. On the basis of one degree of freedom rolling equation, the solution is Monte Carlo method, and a damaged fishery bureau vessel is taken as a sample ship. In addition, the results of the time-domain capsizing probability under different loading conditions are compared and analyzed. The relation of GM and heeling angle with the capsizing probability is investigated, and its possible reason is analyzed. On the basis of combining the time-domain flooding process with the capsizing probability calculation, this research aims to lay the foundation for the study of capsizing probability in time domain under dead ship condition, as well as provide technical support for capsizing mechanism of dead ship stability and damage stability criteria establishment in waves.