Detecting regional dominant movement patterns in trajectory data with a convolutional neural network     

Can Yang  Győző Gidófalvi 《International journal of geographical information science》2020,34(5):996-1021

  相似文献   

基于深度学习理论的无人机影像分类     

阳成 《北京测绘》2020,(4):481-484

针对无人机影像深度学习分类方法缺乏现状,本文利用深度学习理论卷积神经网络方法对无人机影像进行了分类。该法首先抽取无人机影像作为训练集和检验集,然后建立一个2个卷积层-池化层的卷积神经网络模型进行深度学习,通过设定参数并运行模型实现无人机影像分类。实验表明,本文提出的方法可完成较复杂地区无人机影像分类,其分类精度与支持向量机方法相当,为无人机遥感影像分类提供了一个崭新的技术视点。  相似文献   

Modelling the Shimokita deep coalbed biosphere over deep geological time: Starvation,stimulation, material balance and population models     

Stephen A. Bowden  Abdalla Y. Mohamed  Ayad N. F. Edilbi  Yu-Shih Lin  Yuki Morono  Kai-Uwe Hinrichs  Fumio Inagaki 《Basin Research》2020,32(5):804-829

Basin models can simulate geological, geochemical and geophysical processes and potentially also the deep biosphere, starting from a burial curve, assuming a thermal history and utilizing other experimentally obtained data. Here, we apply basin modelling techniques to model cell abundances within the deep coalbed biosphere off Shimokita Peninsula, Japan, drilled during Integrated Ocean Drilling Program Expedition 337. Two approaches were used to simulate the deep coalbed biosphere: (a) In the first approach, the deep biosphere was modelled using a material balance approach that treats the deep biosphere as a carbon reservoir, in which fluxes are governed by temperature-controlled metabolic processes that retain carbon via cell-growth and cell-repair and pass it back via cell-damaging reactions. (b) In the second approach, the deep biosphere was modelled as a microbial community with a temperature-controlled growth ratio and carrying capacity (a limit on the size of the deep biosphere) modulated by diagenetic-processes. In all cases, the biosphere in the coalbeds and adjacent habitat are best modelled as a carbon-limited community undergoing starvation because labile sedimentary organic matter is no longer present and petroleum generation is yet to occur. This state of starvation was represented by the conversion of organic carbon to authigenic carbonate and the formation of kerogen. The potential for the biosphere to be stimulated by the generation of carbon-dioxide from the coal during its transition from brown to sub-bituminous coal was evaluated and a net thickness of 20 m of lignite was found sufficient to support an order of magnitude greater number of cells within a low-total organic carbon (TOC) horizon. By comparison, the stimulation of microbial populations in a coalbed or high-TOC horizon would be harder to detect because the increase in population size would be proportionally very small.  相似文献   

基于YOLOv3深度学习的海雾气象条件下海上船只实时检测     

王飞  刘梦婷  刘雪芹  秦志亮  马本俊  郑毅 《海洋科学》2020,44(8):197-204

海雾气象条件下船只高精度检测识别面临较大困难，传统的目标识别、定位方法效果差强人意。作者围绕海雾气象条件下不同类型船只的实时检测问题，提出一种基于YOLOv3深度学习的实时海上船只检测新思路。首先构建清晰图片和模糊图片（海雾、雨）的判别方法，实现图片清晰度分类处理；其次为提高海雾气象条件下海上船只的实时检测精度，消除海雾遮挡对目标识别的影响，运用暗通道先验去雾方法对含有海雾的图像实行去雾；最后基于YOLOv3深度学习算法对精细处理后的图像进行船只实时检测。实验结果表明该方法能够在海雾气象条件下高效、准确地检测到船只，对海上复杂环境条件下的船只实时检测研究具有一定的理论指导意义。  相似文献   

基于机器学习的海洋环境预报订正方法研究     

许立兵  王安喜  汪纯阳  陈悦  陈昱文  周峥  陈幸荣  邢建勇  刘克威  黄小猛 《海洋通报》2020,39(6):695-704

结合中尺度数值模式 WRF 预报数据和 ERA5 再分析资料，利用机器学习方法对 WRF 预报场的风场、温度、气压进行预报订正。采用 ERA5 作为真值，与原始 WRF 预报相比，利用随机森林模型可以将预报结果整体均方根误差降低 44%以 上，利用深度神经网络模型可以将预报结果整体均方根误差降低 34%以上。通过随机森林模型实验得到不同输入特征对预报要素的影响程度，分析了关键的预报订正因子。  相似文献   

星站差分与PPP技术在深远海调查中的位置服务精度分析     

周东旭  唐秋华  张化疑  梁冠辉  厉峰 《海洋通报》2020,39(2):215-222

利用在全球不同海域的船载GNSS进出港数据,以事后动态处理技术(PPK)的坐标计算值为评价基准,分析了Veripos星站差分系统和事后动态精密单点定位技术(PPP)在不同运动状态下的位置服务精度。结果表明,Veripos与PPP在低动态下的平面与高程位置服务精度可优于6.2 cm和14.9 cm,在常规动态下平均精度优于20 cm;PPP与Veripos坐标分量平均互差小于15 cm,标准差小于23 cm,在深远海调查中PPP技术可作为星站差分系统的有效补充和特殊情况下的位置服务替代。  相似文献   

红外卫星云图和相关向量机的有眼热带气旋客观定强模型   总被引：1，自引：1，他引：0  

戴李杰  张长江  薛利成  马雷鸣  鲁小琴 《遥感学报》2018,22(4):581-590

热带气旋TC(Tropical Cyclone)是全球影响最严重的自然灾害之一。TC强度和路径的准确预报,对于减轻其带来的灾害影响至关重要。本文基于静止红外卫星云图和相关向量机RVM(Relevance Vector Machine)构建有眼TC客观定强模型。首先,利用高斯平滑对红外卫星云图进行去噪;然后,利用基于测地活动轮廓GAC(Geodesic Active Contour)模型的偏微分方程PDE(Partial Differential Equation)法对有眼TC的眼壁进行分割,提取眼壁的亮温梯度信息,计算眼壁亮温梯度的最大值及梯度数据不同概率时的均值,从而构造与TC强度密切相关的特征因子;最后,利用RVM构建单特征因子、多特征因子与近地面最大中心风速的客观定强模型,研究不同特征维度对TC客观定强误差的影响。实验结果表明,在单特征因子的模型定强中,95%概率眼壁亮温梯度均值的定强误差最小,相比利用单特征因子所构建的定强模型,多特征因子的模型定强误差更小,即多特征因子中包含更多与TC强度相关的特征信息。在多特征因子的模型定强中,二特征因子优于三特征因子模型,说明应当合理选择特征因子维数,并非越多越好。本文所用RVM模型具有良好的高维非线性处理能力,能对TC强度进行有效估计。  相似文献   

Evaluation of effectiveness of three fuzzy systems and three texture extraction methods for building damage detection from post-event LiDAR data     

Milad Janalipour 《International Journal of Digital Earth》2018,11(12):1241-1268

Building damage maps after disasters can help us to better manage the rescue operations. Researchers have used Light Detection and Ranging (LiDAR) data for extracting the building damage maps. For producing building damage maps from LiDAR data in a rapid manner, it is necessary to understand the effectiveness of features and classifiers. However, there is no comprehensive study on the performance of features and classifiers in identifying damaged areas. In this study, the effectiveness of three texture extraction methods and three fuzzy systems for producing the building damage maps was investigated. In the proposed method, at first, a pre-processing stage was utilized to apply essential processes on post-event LiDAR data. Second, textural features were extracted from the pre-processed LiDAR data. Third, fuzzy inference systems were generated to make a relation between the extracted textural features of buildings and their damage extents. The proposed method was tested across three areas over the 2010 Haiti earthquake. Three building damage maps with overall accuracies of 75.0%, 78.1% and 61.4% were achieved. Based on outcomes, the fuzzy inference systems were stronger than random forest, bagging, boosting and support vector machine classifiers for detecting damaged buildings.  相似文献   

Mapping fractional landscape soils and vegetation components from Hyperion satellite imagery using an unsupervised machine-learning workflow     

Michael J. Friedel  Massimo Buscema  Luiz Eduardo Vicente  Fabio Iwashita  Andréa Koga-Vicente 《International Journal of Digital Earth》2018,11(7):670-690

An unsupervised machine-learning workflow is proposed for estimating fractional landscape soils and vegetation components from remotely sensed hyperspectral imagery. The workflow is applied to EO-1 Hyperion satellite imagery collected near Ibirací, Minas Gerais, Brazil. The proposed workflow includes subset feature selection, learning, and estimation algorithms. Network training with landscape feature class realizations provide a hypersurface from which to estimate mixtures of soil (e.g. 0.5 exceedance for pixels: 75% clay-rich Nitisols, 15% iron-rich Latosols, and 1% quartz-rich Arenosols) and vegetation (e.g. 0.5 exceedance for pixels: 4% Aspen-like trees, 7% Blackberry-like trees, 0% live grass, and 2% dead grass). The process correctly maps forests and iron-rich Latosols as being coincident with existing drainages, and correctly classifies the clay-rich Nitisols and grasses on the intervening hills. These classifications are independently corroborated visually (Google Earth) and quantitatively (random soil samples and crossplots of field spectra). Some mapping challenges are the underestimation of forest fractions and overestimation of soil fractions where steep valley shadows exist, and the under representation of classified grass in some dry areas of the Hyperion image. These preliminary results provide impetus for future hyperspectral studies involving airborne and satellite sensors with higher signal-to-noise and smaller footprints.  相似文献   

The effects of visual realism,spatial abilities,and competition on performance in map-based route learning in men     

Arzu Çöltekin  Rebecca Francelet  Kai-Florian Richter  John Thoresen  Sara Irina Fabrikant 《制图学和地理信息科学》2018,45(4):339-353

We report on how visual realism might influence map-based route learning performance in a controlled laboratory experiment with 104 male participants in a competitive context. Using animations of a dot moving through routes of interest, we find that participants recall the routes more accurately with abstract road maps than with more realistic satellite maps. We also find that, irrespective of visual realism, participants with higher spatial abilities (high-spatial participants) are more accurate in memorizing map-based routes than participants with lower spatial abilities (low-spatial participants). On the other hand, added visual realism limits high-spatial participants in their route recall speed, while it seems not to influence the recall speed of low-spatial participants. Competition affects participants’ overall confidence positively, but does not affect their route recall performance neither in terms of accuracy nor speed. With this study, we provide further empirical evidence demonstrating that it is important to choose the appropriate map type considering task characteristics and spatial abilities. While satellite maps might be perceived as more fun to use, or visually more attractive than road maps, they also require more cognitive resources for many map-based tasks, which is true even for high-spatial users.  相似文献