排序方式: 共有56条查询结果,搜索用时 125 毫秒
41.
In this study, the self-organizing map (SOM), which is an unsupervised clustering algorithm, and a supervised proportional learning vector quantization (PLVQ), are employed to develop a combined method of seafloor classification using multibeam sonar backscatter data. The PLVQ is a generalized learning vector quantization based on the proportional learning law (PLL). The proposed method was evaluated in an area where there are four types of sediments. The results show that the performance of the proposed method is better than the SOM and a statistical classification method. 相似文献
42.
43.
本文研究基于SOM(Self-Organizing Feature Map)神经网络学习模型的高分辨率遥感影像道路网自动提取算法。首先利用数学形态学提取遥感图像道路的初始道路区域信息,自动对原始图像进行分区并确定神经元初始权值,用SOM网络学习模型对神经元进行训练学习,经迭代获取道路网中心点位置,最后运用"中心点四邻域跟踪判别法"跟踪连接形成道路中心线。实验表明,该方法在高分辨率遥感影像道路网的提取上有较好的效果,特别在主干道路网的提取上效果更佳,对噪声干扰具有良好的鲁棒性。 相似文献
44.
本文综合利用2015—2020年地面气象观测资料、欧洲中心ERA5再分析资料及大气环境监测数据,分析了汾渭平原东部运城市污染物浓度的变化特征以及与天气形势和气象要素的关系。结果表明:①2015—2020年期间运城市PM2.5、PM10、SO2、NO2、CO 5种污染物年平均浓度呈下降趋势,而O3浓度呈上升趋势;②冬季和夏季空气质量相对较差,首要污染物分别是PM2.5和O3,边界层高度的变化与近地层风向风速、污染物浓度的关系密切,冬季(夏季)PM2.5(O3)污染较重时边界层高度较低(较高),以东北风(东南风)为主,风速偏小(偏大);③最后利用自组织映射神经网络(SOM)算法分别对冬夏925 hPa位势高度场进行天气分型并开展不同天气形势下污染物浓度与气象要素的变化对比研究,发现冬季污染时以静稳天气为主,低层弱东北风将污染物输送至运城市,而夏季O3污染较重时受热低压形势控制,利于O3前体物汇合,太阳辐射较强时O3浓度较高。 相似文献
45.
46.
ABSTRACTA database of 88 superficial sediment samples, distributed in space and time, was collected from the Sidi Chahed Dam (northeast of Meknes city, Morocco) and from four other reference stations (in the same region) located in supposedly uncontaminated environments. Analyses were focused on the physico-chemical characteristics and concentrations of heavy metals (Fe, Mn, As, Cu, Zn, Pb, Cr, Cd). The database was processed by advanced statistical analysis techniques. The method of classification by self-organizing maps (SOM) was used, permitting understanding and visualization of the spatial and temporal distribution of samples. Principal component analysis (PCA) and SOM hierarchical classification (SOM-HC) were used to validate the classification and detect seasonal variations in heavy metal concentrations. Dependencies between different metal tracers were considered and their spatio-temporal distribution is shown, together with the ranking of clusters, according to their pollution levels. Thus, autumn samples were the only ones with high concentrations of As, compared to the four reference stations. This is due to leaching of bare soil by the first stormy rains of autumn. In winter and spring samples, the concentrations of tracers Mn, Zn, Cu, Pb, Cd and Cr were relatively high compared to those of the reference stations. Summer sample concentrations were most comparable with the reference stations, probably due to the scarcity of rainfall and runoff in this season.
Editor Z.W. Kundzewicz Associate editor E. Gargouri 相似文献
47.
Forest structure at stand level plays a key role for sustainable forest management, since the biodiversity, productivity, growth and stability of the forest can be positively influenced by managing its structural diversity. In contrast to field-based measurements, remote sensing techniques offer a cost-efficient opportunity to collect area-wide information about forest stand structure with high spatial and temporal resolution. Especially Interferometric Synthetic Aperture Radar (InSAR), which facilitates worldwide acquisition of 3d information independent from weather conditions and illumination, is convenient to capture forest stand structure. This study purposes an unsupervised two-stage clustering approach for forest structure classification based on height information derived from interferometric X-band SAR data which was performed in complex temperate forest stands of Traunstein forest (South Germany). In particular, a four dimensional input data set composed of first-order height statistics was non-linearly projected on a two-dimensional Self-Organizing Map, spatially ordered according to similarity (based on the Euclidean distance) in the first stage and classified using the k-means algorithm in the second stage. The study demonstrated that X-band InSAR data exhibits considerable capabilities for forest structure classification. Moreover, the unsupervised classification approach achieved meaningful and reasonable results by means of comparison to aerial imagery and LiDAR data. 相似文献
48.
Similarity between catchments in a region can be determined depending on catchment properties. This helps to understand the response behavior of the similar catchments more appropriately. Catchment classification plays a major role in the process of hydrological prediction in the case of ungauged catchments. The following categorization was carried out for 32 catchments of India. Principal Component Analysis (PCA) along with K-means clustering, was applied as linear classification; and Self-Organizing Map (SOM) and Kernel Principal Component Analysis (KPCA) were implemented as nonlinear classification methods on catchment attributes and daily streamflow time series. The classification established on streamflow signatures was taken as the reference classification. Results obtained from PCA, SOM, and KPCA were compared with results of the reference classification. The absence of discordant catchments from the clusters of SOM, based on catchment attributes, suggests homogeneity among SOM-derived clusters. Similarity index scores are 0.48 and 0.47, 0.46 and 0.42 ?for first, second, third and fourth clusters of SOM respectively with that of the reference classification technique. Nonlinear techniques with high similarity index values outperformed standard techniques. This study demonstrated the ability of classification based on catchment attributes to classify ungauged catchments. 相似文献
49.
C. Natali G. Bianchini L. Vittori Antisari M. Natale U. Tessari 《Chemie der Erde / Geochemistry》2018,78(4):490-499
Carbon and nitrogen elemental (C-N, wt%) and isotopic (δ13C-δ15N, ‰) investigation has been carried out on alluvial and deltaic soils from the Padanian plain (northern Italy), an area interested by intensive agricultural activities, to refine previous inferences on depositional facies, pedogenetic processes and anthropogenic influences. Soil analysis, carried out by EA-IRMS, have been focused on inorganic and organic fractions properly speciated by a thermally-based method, whereas further insights on the organic matter constituents have been obtained by sequential fractionation. The bulk EA-IRMS analyses reveal a remarkable compositional heterogeneity of the investigated soils (TC 0.89 to 11.93?wt%, TN 0.01 to 0.78?wt%, δ13CTC -1.2 to -28.2‰, δ15N -1.2 to 10.0‰) that has to be explained as an integration between inorganic and organic pools. The latter have been subdivided in Non-Extractable Organic Matter (NEOM, δ13C -16.3 to -28.6‰) and in extractable fractions as Fulvic (FA, δ13C -24.7 to -27.5‰, δ15N 0.6 to 5.7‰) and Humic (HA, δ13C -24.6 to -27.0‰, δ15N 1.0 to 9.7‰) Acids, which have been used to infer soil dynamics and Soil Organic Matter (SOM) stability processes. Results indicate that SOM at depth of 100?cm was generally affected by microbial reworking, with the exception of clayey and peaty deposits in which biological activity seems inhibited. Peaty and clayey soils display an organic fraction loss of ca. 20% toward the surface, suggesting deterioration possibly induced by intensive agricultural activities. These latter may be the cause of the ubiquitous losses of organic fraction throughout the investigated area over the last seventy years, evaluated by the comparison with historical data on corresponding topsoils. The obtained insights are very important because these soils are carbon (and nitrogen) sinks that are vulnerable and can be degraded, loosing agricultural productivity and potentially contributing to greenhouse gases fluxes. 相似文献
50.
基于SOM神经网络的城市土地覆盖遥感分类研究 总被引:1,自引:0,他引:1
土地覆盖及其变化的研究作为区域及全球环境变化研究所需的极为重要的地表参数,是遥感应用分析的主要内容之一。以往所采用的遥感分类方法主要针对侧重于土地社会属性的土地利用类型的分类研究且很难获得理想的精度。本文在非监督的自组织映射神经网络的基础上进行了一定的改进,构建了有监督的神经网络模型,以湖南省长沙市主城区的土地自然属性为侧重点,对其土地覆盖进行分类。实验结果表明:利用本文所使用的方法得到的分类结果,其总体精度和Kappa系数均高于传统的分类方法得出来的分类结果。 相似文献