基于超像元词包特征和主动学习的高分遥感影像变化检测     

杨进一  徐伟铭  王成军  翁谦 《地球信息科学学报》2019,21(10):1594-1607

为解决高分辨率遥感影像变化检测中存在底层特征缺乏语义信息、像元级的检测结果存在“椒盐”现象以及监督分类中样本标注自动化程度较低,本文提出一种基于超像元词包特征和主动学习的变化检测方法。首先采用熵率分割算法获取叠加影像的超像元对象;其次提取两期影像像元点对间的邻近相关影像特征（相关度、斜率和截距）和顾及邻域的纹理变化强度特征（均值、方差、同质性和相异性）,经线性组合作为像元点对的底层特征;然后基于像元点对底层特征利用BOW模型构建超像元词包特征,并采用一种改进标注策略的主动学习方法从无标记样本池中优选信息量较大的样本,且自动标注样本类别;最后训练分类器模型完成变化检测。通过选用2组不同地区的GF-2影像和Worldview-Ⅱ影像作为数据源进行实验,实验结果中2组数据集的F1分数分别为0.8714、0.8554,正确率分别为0.9148、0.9022,漏检率分别为0.1681、0.1868,误检率分别为0.0852、0.0978。结果表明,该法能有效识别变化区域、提高变化检测精度。此外,传统主动学习方法与改进标注策略的主动学习方法的学习曲线对比显示,改进的标注策略可在较低精度损失下,有效提高样本标注自动化程度。  相似文献   

基于GPS和水准数据的微粒群算法联合反演祁连山北缘断裂三维滑动速率     

刘杰 《大地测量与地球动力学》2019,39(9):906-909

将微粒群算法与位错理论模型相结合，采用中国地壳运动观测网络提供的青藏高原地区2001~2004年GPS测量数据和2000~2006年水准测量数据，通过常规定权和附有相对权比的方法对祁连山北缘断裂的三维滑动速率进行联合反演，并与蚁群算法反演结果进行对比。结果表明，微粒群算法收敛速度快、稳定性高，结合经典位错理论模型，是一种可以有效求解断层三维滑动速率反演问题的优化算法，在大地测量反演领域极具应用潜力。  相似文献   

气候变化对西藏湖泊变迁的影响(1973—2017)   总被引：1，自引：0，他引：1  

闫立娟 《地球学报》2020,41(4):493-503

西藏湖泊众多,其水位和面积变化对气候波动有敏感记录。本文运用RS和GIS技术,以1973—1977年、1989—1992年、1999—2001年、2008—2010年和2017年5期遥感影像为底图矢量化了西藏所有湖泊边界,建立了湖泊空间数据库。以湖泊空间数据为基础,分析了1973—2017年西藏湖泊面积动态变化特征,结论如下:从20世纪70年代至2017年,西藏湖泊总面积持续增加,共增长了47.23%;从20世纪70年代至90年代,研究区北部和中部湖泊呈萎缩的趋势,其余地区呈扩张的趋势;从2000年至2017年,西藏湖泊呈持续扩张的趋势。另外,笔者分析了研究区年平均气温、年降雨量和年蒸发量的变化特征。1981—2017年,西藏气候向暖湿方向发展,主要表现为气温升高、降雨量增加和蒸发量减少。气候变化对不同地区不同时期湖泊变迁影响显著:(1)西藏北部和中部湖泊主要以冰川、冰雪融水和地表径流为主要补给源。20世纪70年代至90年代,气温和降雨量波动较小,引起这些地区湖泊萎缩的主要原因为冰川和冰雪融水补给的减少。(2)从20世纪90年代至2017年,气温和降雨量增加、蒸发量减少,导致研究区湖泊呈现全面扩张的趋势。  相似文献   

Gully erosion spatial modelling: Role of machine learning algorithms in selection of the best controlling factors and modelling process     

《地学前缘(英文版)》2020,11(6):2207-2219

This investigation assessed the efficacy of 10 widely used machine learning algorithms (MLA) comprising the least absolute shrinkage and selection operator (LASSO), generalized linear model (GLM), stepwise generalized linear model (SGLM), elastic net (ENET), partial least square (PLS), ridge regression, support vector machine (SVM), classification and regression trees (CART), bagged CART, and random forest (RF) for gully erosion susceptibility mapping (GESM) in Iran. The location of 462 previously existing gully erosion sites were mapped through widespread field investigations, of which 70% (323) and 30% (139) of observations were arbitrarily divided for algorithm calibration and validation. Twelve controlling factors for gully erosion, namely, soil texture, annual mean rainfall, digital elevation model (DEM), drainage density, slope, lithology, topographic wetness index (TWI), distance from rivers, aspect, distance from roads, plan curvature, and profile curvature were ranked in terms of their importance using each MLA. The MLA were compared using a training dataset for gully erosion and statistical measures such as RMSE (root mean square error), MAE (mean absolute error), and R-squared. Based on the comparisons among MLA, the RF algorithm exhibited the minimum RMSE and MAE and the maximum value of R-squared, and was therefore selected as the best model. The variable importance evaluation using the RF model revealed that distance from rivers had the highest significance in influencing the occurrence of gully erosion whereas plan curvature had the least importance. According to the GESM generated using RF, most of the study area is predicted to have a low (53.72%) or moderate (29.65%) susceptibility to gully erosion, whereas only a small area is identified to have a high (12.56%) or very high (4.07%) susceptibility. The outcome generated by RF model is validated using the ROC (Receiver Operating Characteristics) curve approach, which returned an area under the curve (AUC) of 0.985, proving the excellent forecasting ability of the model. The GESM prepared using the RF algorithm can aid decision-makers in targeting remedial actions for minimizing the damage caused by gully erosion.  相似文献   

遥感技术在“6·17”丹巴堵江泥石流灾害链灾区应急救援抢险决策中的应用     

唐尧  王立娟  赵娟  张成信 《中国地质调查》2020,7(5):114-122

2020年6月17日,四川丹巴县半扇门镇梅龙沟发生泥石流,阻断小金川河,形成堰塞湖,造成重大财产损失与人员伤亡。为掌握第一手灾情,辅助开展应急救援,以国产高分二号卫星数据为主要数据源,结合无人机航空摄影数据和灾后现场调查等资料,开展了“6·17”丹巴堵江泥石流灾害链灾区应急调查与分析。研究认为: 灾区影响人口约6.5万人; 国网丹巴县供电公司应急救援队与小金县联通通信应急抢险救援队距离最近,半扇门中学等5所学校可作为临时安置避难场所备选; 受影响矿山企业6家、重要水库1座、水电站1座; 泥石流沟总体呈NW—SE向展布,掩没面积约14.27万m²; 堰塞湖湖面面积约1.03 km²,淹没区约49.8万m²,路基路面全毁路段约2.1 km,下游疑似灾害隐患点9处,因灾受损民居25处、桥梁5处; 优选了2条灾后通达性较好的通往泥石流重灾区的救援生命线。借助遥感技术深入分析泥石流灾害链影响人口等灾情先期研判、灾情灾损应急调查及应急救援生命通道优选,对我国西南山区类似条件地质灾害隐患点的应急抢险救援、防灾减灾工作具有重要的指导意义。  相似文献   

Estimation of Grassland Production in Central and Eastern Mongolia from 2006 to 2015 via Remote Sensing     

LI Ge  WANG Juanle  WANG Yanjie  WEI Haishuo 《资源与生态学报(英文版)》2019,10(6):676-684

Mongolia is an important part of the Belt and Road Initiative “China-Mongolia-Russia Economic Corridor” and a region that has been severely affected by global climate change. Changes in grassland production have had a profound impact on the sustainable development of the region. Our study explored an optimal model for estimating grassland production in Mongolia and discovered its temporal and spatial distributions. Three estimation models were established using a statistical analysis method based on EVI, MSAVI, NDVI, and PsnNet from Moderate Resolution Imaging Spectroradiometer (MODIS) remote sensing data and measured data. A model evaluation and accuracy comparison showed that an exponential model based on MSAVI was the best simulation (model accuracy 78%). This was selected to estimate the grassland production in central and eastern Mongolia from 2006 to 2015. The results show that the grassland production in the study area had a significantly fluctuating trend for the decade study; a slight overall increasing trend was observed. For the first five years, the grassland production decreased slowly, whereas in the latter five years, significant fluctuations were observed. The grassland production (per unit yield) gradually increased from the southwest to northeast. In most provinces of the study area, the production was above 1000 kg ha ^-1, with the largest production in Hentiy, at 3944.35 kg ha ^-1. The grassland production (total yield) varied greatly among the provinces, with Kent showing the highest production, 2341.76×10 ⁴ t. Results also indicate that the trend in grassland production along the China-Mongolia railway was generally consistent with that of the six provinces studied.  相似文献   

基于最大球算法定量表征土体空间孔隙网络     

解朝阳  张巍  姚东方  王坚  朱雨辰 《工程地质学报》2020,28(1):60-68

孔隙网络控制着土体渗流、排水固结与基质吸力等重要工程性质。本文介绍了多孔介质孔隙网络最大球建模基本原理与算法。以显微CT扫描振捣干法生成的南京粉砂试样为例,采用最大球算法建立了试样三维重构模型表征单元体(REV)的空间孔隙网络球棍模型,计算得到了样品REV尺度的孔隙网络参数,统计发现,孔隙半径、喉道半径、孔隙配位数、孔隙截面形状因子、喉道截面形状因子与喉道长度等孔隙参数均近似服从正态分布,孔隙体积近似服从衰减型指数分布。孔隙与喉道半径分别分布在100μm与65μm以内,两者数学期望分别为40. 0μm与18. 0μm;配位数分布在25以内,数学期望为5. 1;孔隙与喉道截面形状因子分别分布在0. 01~0. 04与0. 01~0. 05的区间内,两者数学期望分别为0. 019与0. 033;喉道长度分布在100~800μm以内,数学期望为292. 22μm。同时发现,样品中体积小于1. 5×10^7μm^3的小孔隙数量超过90%。本方法可应用于土体细观孔隙结构的定量表征。  相似文献   

基于CUDA的地震相干体并行算法   总被引：1，自引：0，他引：1  

张全 《地质与勘探》2020,56(1):147-153

相干体技术在地震勘探资料解释方面得到了广泛的应用,由于相干体技术处理的对象是三维地震数据体,所以算法运算时间较长。为了缩短解释周期,本文充分发挥GPU并行计算优势,对C3相干体算法进行并行化分析。从硬盘读取数据到GPU上计算相干值并写入硬盘的整个过程进行分析,剔除了冗余数据的读取,完成了C3相干体算法的并行化设计与实现。最后分别对串行算法与并行算法进行性能测试,结果表明本文设计的并行算法在保证精度的前提下达到了16倍左右的加速比,对加快地震资料解释具有重要意义。  相似文献   

The spatial local accuracy of land cover datasets over the Qiangtang Plateau,High Asia     

Liu  Qionghuan  Zhang  Yili  Liu  Linshan  Li  Lanhui  Qi  Wei 《地理学报(英文版)》2019,29(11):1841-1858

We analyzed the spatial local accuracy of land cover (LC) datasets for the Qiangtang Plateau, High Asia, incorporating 923 field sampling points and seven LC compilations including the International Geosphere Biosphere Programme Data and Information System (IGBPDIS), Global Land cover mapping at 30 m resolution (GlobeLand30), MODIS Land Cover Type product (MCD12Q1), Climate Change Initiative Land Cover (CCI-LC), Global Land Cover 2000 (GLC2000), University of Maryland (UMD), and GlobCover 2009 (Glob-Cover). We initially compared resultant similarities and differences in both area and spatial patterns and analyzed inherent relationships with data sources. We then applied a geographically weighted regression (GWR) approach to predict local accuracy variation. The results of this study reveal that distinct differences, even inverse time series trends, in LC data between CCI-LC and MCD12Q1 were present between 2001 and 2015, with the exception of category areal discordance between the seven datasets. We also show a series of evident discrepancies amongst the LC datasets sampled here in terms of spatial patterns, that is, high spatial congruence is mainly seen in the homogeneous southeastern region of the study area while a low degree of spatial congruence is widely distributed across heterogeneous northwestern and northeastern regions. The overall combined spatial accuracy of the seven LC datasets considered here is less than 70%, and the GlobeLand30 and CCI-LC datasets exhibit higher local accuracy than their counterparts, yielding maximum overall accuracy (OA) values of 77.39% and 61.43%, respectively. Finally, 5.63% of this area is characterized by both high assessment and accuracy (HH) values, mainly located in central and eastern regions of the Qiangtang Plateau, while most low accuracy regions are found in northern, northeastern, and western regions.

  相似文献   

基于正交匹配追踪的声层析方法   总被引：2，自引：0，他引：2  

李倩倩  史娟  李整林  罗宇  阳凡林  张凯 《海洋学报(英文版)》2019,38(11):149-157

声速剖面的变化会对声传播产生较大的影响，经验正交函数模型经常用来实现对声速剖面数据的简化描述。然而在内波、湍流等海水不均匀性存在时，这种正则化操作会造成声速重构精度的大幅降低。本文利用字典学习生成声速剖面的非正交原子，在稀疏编码时采用正交匹配追踪（OMP，Orthogonal Matching Pursuit）算法，更新字典则使用KSVD （Kernel Singular Value Decomposition）的字典更新算法。由于字典学习不需要强制使用正交条件，对于训练数据更加灵活，从而可以使用少数的原子组合达到更高的重构精度。利用一次浅海声学实验多次测量的声速剖面研究了海水声速剖面的经验正交函数表示和字典学习，研究表明：相比于正交函数表示，学习字典可以利用少数原子（甚至一个原子）更好的解释声速剖面扰动。字典学习可以提高声速剖面的稀疏性，从而提高声速剖面的反演精度。  相似文献