基于深度学习的镜下矿石矿物的智能识别实验研究   总被引：1，自引：3，他引：1  

徐述腾  周永章 《岩石学报》2018,34(11):3244-3252

矿石矿物鉴定的智能化是智能地质学和智能矿床学的基础技术之一。计算机视觉技术和深度学习理论使矿石矿物鉴定的智能化成为可能。本研究基于深度学习系统Tensor Flow,以吉林夹皮沟金矿和河北石湖金矿的黄铁矿、黄铜矿、方铅矿、闪锌矿等硫化物矿物为例,设计有针对性的Unet卷积神经网络模型,有效自动提取矿相显微镜下矿石矿物的深层特征信息,实现镜下矿石矿物智能识别与分类。实验显示,模型在训练过程中,随着训练次数的增加,模型精度在不断增大,损失函数不断减小;经过3000个批处理之后,模型精度和损失函数基本趋于稳定。训练出的模型对测试集中的显微镜镜下矿石矿物照片的识别成功率均高于90%,说明实验所建立的模型,具有很好的图像特征提取能力,能完成镜下矿石矿物智能识别的任务。  相似文献   

亚实性肺腺癌能谱CT虚拟平扫效果的研究          下载免费PDF全文

韩仙俊  贺文  陈疆红  赵丽琴  刘佳宝  曹佳鑫 《CT理论与应用研究》2019,28(1):81-90

目的:评价能谱CT虚拟平扫与常规CT扫描对亚实性肺腺癌密度(CT值)的一致性;增强扫描对亚实性肺腺癌侵袭性判断的价值。方法:46例患者胸部CT平扫首次发现肺部亚实性结节患者行能谱CT增强扫描,符合条件39例患者共45个经病理证实为肺腺癌及其癌前病变入组。在工作站获取虚拟平扫图像,比较病灶、周围正常肺组织及椎旁肌各组能谱数据感兴趣区的平均HU值有无差异及其相关性;根据预后及侵袭性分为癌前病变及微浸润性腺癌组、浸润性腺癌组并比较两者的差异。结果:病灶、周围肺组织及椎旁肌的普通平扫与虚拟平扫CT净增值之间无显著差异,且两者具有高度相关性。HU净增值及碘浓度在癌前病变及微浸润性腺癌组、浸润性腺癌组之间无显著差异,增强扫描在鉴别肺腺癌浸润性方面无阳性结果。结论:应用能谱CT虚拟平扫HU值与普通平扫无统计学差异并显著相关,增强扫描对鉴别肺腺癌浸润性方面无阳性结果。  相似文献   

机器学习在地震紧急预警系统震级预估中的应用          下载免费PDF全文

胡安冬  张海明 《地球物理学报》2020,63(7):2617-2626

地震预警是地震减灾工作的重要途径,而震级预估是整个地震紧急预警系统中重要且较为困难的一个环节.目前,世界上多个国家和地区都已建立了各自的地震预警系统,并且形成了特征频率(τ_p和τ_c等)相关和特征振幅(Pd等)相关的两类震级紧急预警的方法,但各有局限性.本文在已有的方法和理论基础上,运用机器学习算法,将日本KIK和KNET台网从2015年至2017年所记录到的843条地震目录,55426条记录作为全数据集,设计、训练出一套用于常见震级范围的机器学习震级预估模型.与已有方法的预估结果相比,机器学习方法不仅使预估的整体误差和方差下降,同时多台联合评估单一地震事件的截面方差也更低.本研究的结果显示了机器学习算法在震级紧急预估问题上具有较广阔的应用前景,同时也为较为复杂的深度学习类算法框架下端到端模型提供了实践基础和研究可能.  相似文献   

中低纬电离层F层峰高和厚度的变化特征分析   总被引：3，自引：0，他引：3       下载免费PDF全文

王宁  郭立新  赵振维  丁宗华  林乐科 《地球物理学报》2017,60(4):1268-1275

电离层F层参数对电离层空间天气研究与电波传播应用具有重要意义,以往工作主要针对电离层f_0F_2、TEC等参数.本文利用我国中纬地区的兰州、中低纬过渡区的昆明、低纬地区的海口三个观测站的电离层垂直探测数据,分析了电离层峰高h_mF_2、F层虚高h’F和定性表征的厚度h_mF_2—h’F的周日、季节、太阳活动变化特征.研究表明:(1)兰州h_mF_2在太阳活动高年和低年的数值接近,海口在太阳活动高年白天的h_mF_2比低年白天高20~30 km.(2)在海口和昆明,h_mF_2最大值多出现在中午时段,兰州站的最大值出现在夜间.(3)海口的h_mF_2在01-3LT期间出现很强的"午夜衰落"现象,此后迅速增大.(4)利用h_mF_2-h'F来表征电离层的厚度时,其季节和周日变化特征与常用的B_0存在相似之处,但未出现清晨与午后凹陷等现象.这些结果对于提高我国电离层变化特性的认识和模式化研究水平具有重要的科学意义.  相似文献   

GPU ray casting method for visualizing 3D pipelines in a virtual globe     

Zhaocong Wu  Jie Shao  Guohui Deng 《International Journal of Digital Earth》2019,12(4):428-441

Pipelines are an important part of urban infrastructure development. As part of a virtual globe (VG), the high-efficiency and high-quality visualization of 3D large-scale and high-density urban pipelines is of great importance. This paper proposes a GPU-based pipeline ray casting method for the visualization of urban-scale pipelines in the framework of a VG. The method involves the initial partitioning of the pipeline data into tiles, based on the relationship between the pipeline layer scale and the discrete global grid system (DGGSs). The pipeline centerline in each tile is then segmented and encoded, and a coarser pipeline bounding volume is subsequently constructed using a geometry shader. Finally, the fine 3D pipeline is rendered using a pixel shader. The results of the experimental implementation of the proposed method show that it satisfies the requirements for the multiscale visualization of pipelines in a VG. Moreover, compared with the traditional polygon-based method, the method facilitates a 20% increase in rendering frame rate for the same pixel level accuracy display effect. It also enables the visualization of the thickness of the 3D pipeline without any obvious effect on the rendering efficiency.  相似文献   

Volcano video data characterized and classified using computer vision and machine learning algorithms     

《地学前缘(英文版)》2020,11(5):1789-1803

Video cameras are common at volcano observatories,but their utility is often limited during periods of crisis due to the large data volume from continuous acquisition and time requirements for manual analysis.For cameras to serve as effective monitoring tools,video frames must be synthesized into relevant time series signals and further analyzed to classify and characterize observable activity.In this study,we use computer vision and machine learning algorithms to identify periods of volcanic activity and quantify plume rise velocities from video observations.Data were collected at Villarrica Volcano,Chile from two visible band cameras located～17 km from the vent that recorded at 0.1 and 30 frames per second between February and April 2015.Over these two months,Villarrica exhibited a diverse range of eruptive activity,including a paroxysmal eruption on 3 March.Prior to and after the eruption,activity included nighttime incandescence,dark and light emissions,inactivity,and periods of cloud cover.We quantify the color and spatial extent of plume emissions using a blob detection algorithm,whose outputs are fed into a trained artificial neural network that categorizes the observable activity into five classes.Activity shifts from primarily nighttime incandescence to ash emissions following the 3 March paroxysm,which likely relates to the reemergence of the buried lava lake.Time periods exhibiting plume emissions are further analyzed using a row and column projection algorithm that identifies plume onsets and calculates apparent plume horizontal and vertical rise velocities.Plume onsets are episodic,occurring with an average period of～50 s and suggests a puffing style of degassing,which is commonly observed at Villarrica.However,the lack of clear acoustic transients in the accompanying infrasound record suggests puffing may be controlled by atmospheric effects rather than a degassing regime at the vent.Methods presented here offer a generalized toolset for volcano monitors to classify and track emission statistics at a variety of volcanoes to better monitor periods of unrest and ultimately forecast major eruptions.  相似文献   

Maintaining accurate,current, rural road network data: An extraction and updating routine using RapidEye,participatory GIS and deep learning     

《International Journal of Applied Earth Observation and Geoinformation》2020

Accurate and current road network data is fundamental to land management and emergency response, yet challenging to produce for unpaved roads in rural and forested regions using traditional cartographic approaches. Automatic extraction of roads from satellite imagery using deep learning is a promising alternative gaining increasing attention, however most efforts have focused on urban paved roads and used very high spatial resolution imagery, which is less frequently available for rural regions. Additionally, road extraction routines still struggle to produce a fully-connected, vectorized road network. In this study covering a large forested area in Western Canada, we developed and evaluated a routine to automatically extract unpaved road pixels using a convolutional neural network (CNN), and then used the CNN outputs to update a pre-existing government road network and evaluate if and how it would change. To cover the large spatial extent mapped in this study, we trained the routine using moderately high-resolution satellite imagery from the RapidEye constellation and a ground-truth dataset collected with smartphones by organizations already operating and driving in the region. Performance of the road extraction was comparable to results achieved by others using very high-resolution imagery; recall accuracy was 89–97%, and precision was 85–91%. Using our approach to update the pre-existing road network would result in both removals and additions to the network, totalling over 1250 km, or about 20 % of the roads previously in the network. We discuss how road density estimates in the study area would change using this updated network, and situate these changes within the context of ongoing efforts to conserve grizzly bears, which are listed as a Threatened species in the region. This study demonstrates the potential of remote sensing to maintain current and accurate rural road networks in dynamic forest landscapes where new road construction is prevalent, yet roads are also frequently de-activated, reclaimed or otherwise not maintained.  相似文献   

Evaluations and comparisons of rule-based and machine-learning-based methods to retrieve satellite-based vegetation phenology using MODIS and USA National Phenology Network data     

《International Journal of Applied Earth Observation and Geoinformation》2020

Vegetation phenology is a sensitive indicator that reflects the vegetation–atmosphere interactions and vegetation processes under global atmospheric changes. Fast-developing remote sensing technologies that monitor the land surface at high spatial and temporal resolutions have been widely used in vegetation phenology retrieval and analysis at a large scale. While researchers have developed many phenology retrieving methods based on remote sensing data, the relationships and differences among the phenology retrieving methods are unclear, and there is a lack of evaluation and comparison with the field phenology recoding data. In this study, we evaluated and compared eight phenology retrieving methods using Moderate Resolution Imaging Spectroradiometer (MODIS) and the USA National Phenology Network data from across North America. The studied phenology retrieving methods included six commonly used rule-based methods (i.e., amplitude threshold, the first-order derivative, the second-order derivative, the third-order derivative, the relative change curvature, and the curvature change rate) and two newly developed machine learning methods (i.e., neural network and random forest). At the large scale, the start of the season (SOS) values, derived by all methods, had similar spatial distributions; however, the retrieved values had large uncertainties in each pixel, and the end of the season (EOS) inverted values were largely different among methods. At the site scale, the SOS and EOS values extracted by the rule-based methods all had significant positive correlations with the field phenology observations. Among the rule-based methods, the amplitude threshold method performed the best. The machine learning methods outperformed the rule-based methods in terms of retrieving the SOS when assessed using the field observations. Our study highlighted that there were large differences among the methods in retrieving the vegetation phenology from satellite data and that researchers must be cautious in selecting an appropriate method for analyzing the satellite-retrieved phenology. Our results also demonstrated the importance of field phenology observations and the usefulness of the machine learning methods in understanding the satellite-based land surface phenology. These findings provide a valuable reference for the future development of global and regional phenology products.  相似文献   

数码城市GIS之虚拟旅游   总被引：1，自引：0，他引：1  

兰小机  仇菊香 《国土资源信息化》2009,(1):6-7,32

本文从数码城市GIS入手,介绍了当前比较流行的虚拟旅游。首先,介绍了虚拟旅游的定义和特点,然后介绍了虚拟旅游的类型和国内虚拟旅游网站的发展现状,在此基础上,最后提出了虚拟旅游的发展展望。  相似文献   

地震仪表系统中电磁干扰识别与排除方法研究     

姜丹  邹彤  陈志高  郭唐永 《大地测量与地球动力学》2009,29(Z1):128-130

针对地震仪表系统受电磁干扰易发生误报警的情况,提出运用有限状态机来实现电磁干扰识别及排除。运用该方法 可有效地降低系统的误报警率,提高系统的可靠性。  相似文献