长江口北支湿地分类及生境特征

长江口北支湿地可以划分为海岸潮滩湿地生境、河口湿地生境和人工湿地生境3大类,生境类型丰富。分析了每类湿地生境的特征,最后指出由于人类的高强度干扰,生境破碎化严重,生物多样性降低,湿地生态服务功能减弱。     

SANDRA法对北京小时强降水扰动环流场的分型研究

利用cost733class软件中的SANDRA(Simulated ANnealing and Diversified RAndomization)客观分型方法对北京地区2007～2014年暖季5～9月的小时强降水日的500 hPa扰动位势高度场进行分型研究。结果显示,所划分的4类环流形势分别在蒙古、东北—华北地区、河套地区和俄罗斯远东地区存在扰动低压区。根据4类环流形势的质心,将2007～2014年暖季所有日划归4类,计算每类小时强降水日占各自类型总天数的百分比得出蒙古扰动低压类的小时强降水日出现概率最大。统计小时强降水日的探空廓线得出,925 hPa和850 hPa的比湿中位数分别为13.01 g kg~(-1)和10.64 g kg~(-1),这2个层级上最常出现的风向是180°～225°。     

Stability of Kerogen Classification with Regard to Image Segmentation

This paper investigates the stability of an automatic system for classifying kerogen material from images of sieved rock samples. The system comprises four stages: image acquisition, background removal, segmentation, and classification of the segmented kerogen pieces as either inertinite or vitrinite. Depending upon a segmentation parameter d, called “overlap”, touching pieces of kerogen may be split differently. The aim of this study is to establish how robust the classification result is to variations of the segmentation parameter. There are two issues that pose difficulties in carrying out an experiment. First, even a trained professional may be uncertain when distinguishing between isolated pieces of inertinite and vitrinite, extracted from transmitted-light microscope images. Second, because manual labelling of large amount of data for training the system is an arduous task, we acquired the true labels (ground truth) only for the pieces obtained at overlap d=0.5. To construct ground truth for various values of d we propose here label-inheritance trees. With thus estimated ground truth, an experiment was carried out to evaluate the robustness of the system to changes in the segmentation through varying the overlap value d. The average system accuracy across values of d spanning the range from 0 to 1 was 86.5%, which is only slightly lower than the accuracy of the system at the design value of d=0.5 (89.07%).     

基于投影寻踪模型和加速遗传算法的石羊河流域水资源承载力综合评价

针对区域水资源承载力状况,采用高维降维技术——投影寻踪分类模型（PPC）,利用基于实数编码的加速遗传算法（RAGA）优化其投影方向,将多维数据指标（样本评价指标）转换到低维子空间,根据投影函数值的大小评价出样本的优劣,从而做出评价,最大限度避免了灰色关联法评判中权重矩阵取值的人为干扰,为区域水资源承载力状况评价及其它评判问题提供一条新的方法与思路。     

Stochastic gradient boosting classification trees for forest fuel types mapping through airborne laser scanning and IRS LISS-III imagery

This paper presents an application of Airborne Laser Scanning (ALS) data in conjunction with an IRS LISS-III image for mapping forest fuel types. For two study areas of 165 km² and 487 km² in Sicily (Italy), 16,761 plots of size 30-m × 30-m were distributed using a tessellation-based stratified sampling scheme. ALS metrics and spectral signatures from IRS extracted for each plot were used as predictors to classify forest fuel types observed and identified by photointerpretation and fieldwork. Following use of traditional parametric methods that produced unsatisfactory results, three non-parametric classification approaches were tested: (i) classification and regression tree (CART), (ii) the CART bagging method called Random Forests, and (iii) the CART bagging/boosting stochastic gradient boosting (SGB) approach. This contribution summarizes previous experiences using ALS data for estimating forest variables useful for fire management in general and for fuel type mapping, in particular. It summarizes characteristics of classification and regression trees, presents the pre-processing operation, the classification algorithms, and the achieved results. The results demonstrated superiority of the SGB method with overall accuracy of 84%. The most relevant ALS metric was canopy cover, defined as the percent of non-ground returns. Other relevant metrics included the spectral information from IRS and several other ALS metrics such as percentiles of the height distribution, the mean height of all returns, and the number of returns.     

A modified stochastic neighbor embedding for multi-feature dimension reduction of remote sensing images

In automated remote sensing based image analysis, it is important to consider the multiple features of a certain pixel, such as the spectral signature, morphological property, and shape feature, in both the spatial and spectral domains, to improve the classification accuracy. Therefore, it is essential to consider the complementary properties of the different features and combine them in order to obtain an accurate classification rate. In this paper, we introduce a modified stochastic neighbor embedding (MSNE) algorithm for multiple features dimension reduction (DR) under a probability preserving projection framework. For each feature, a probability distribution is constructed based on t-distributed stochastic neighbor embedding (t-SNE), and we then alternately solve t-SNE and learn the optimal combination coefficients for different features in the proposed multiple features DR optimization. Compared with conventional remote sensing image DR strategies, the suggested algorithm utilizes both the spatial and spectral features of a pixel to achieve a physically meaningful low-dimensional feature representation for the subsequent classification, by automatically learning a combination coefficient for each feature. The classification results using hyperspectral remote sensing images (HSI) show that MSNE can effectively improve RS image classification performance.     

关于土地覆被遥感监测的几点思考

针对国内外土地覆被遥感监测中存在的突出问题展开讨论,分析土地覆被分类系统的目标适应性; 总结现有分类算法的特点及存在问题,分析小尺度和大尺度监测技术的差异性和效果; 研究不同尺度土地覆被监测所解决的应用问题及尺度空间变化下的分类效果; 分析现有监测体系的分类精度及产生误差的原因和解决方法.     

Automatic interpretation of digital maps

In the past, the availability and/or the acquisition of spatial data were often the main problems of the realization of spatial applications. Meanwhile this situation has changed: on one hand, comprehensive spatial datasets already exist and on the other hand, new sensor technologies have the ability to capture fast and with high quality large amounts of spatial data. More and more responsible for the increasing accessibility of spatial data are also collaborative mapping techniques which enable users to create maps by themselves and to make them available in the internet. However, the potential of this diversity of spatial data can only hardly be utilized. Especially maps in the internet are represented very often only with graphical elements and no explicit information about the map’s scale, extension and content is available. Nevertheless, humans are able to extract this information and to interpret maps. For example, it is possible for a human to distinguish between rural and industrial areas only by looking at the objects’ geometries. Furthermore, a human can easily identify and group map objects that belong together. Also the type, scale and extension of a map can be identified under certain conditions only by looking at the objects’ geometries. All these examples can be subsumed under the term “map interpretation”. In this paper it is discussed how map interpretation can be automated and how automatic map interpretation can be used in order to support other processes. The different kinds of automatic map interpretation are discussed and two approaches are shown in detail.     

Classifying knowledge on climate change impacts, adaptation, and vulnerability in Europe for informing adaptation research and decision-making: A conceptual meta-analysis

Knowledge on climate change impacts, adaptation, and vulnerability is fragmented, because it is found in disparate case studies which use inconsistent terminology and focus on distinct aspects relevant to adaptation. While large-scale syntheses such as the Assessment Reports of the Intergovernmental Panel on Climate Change provide a high level overview and are useful for international decision-making, there is a need for systematic and flexible access to this research-based knowledge in order to aid future adaptation research and decision-making. Against this background, we present a ‘conceptual’ meta-analysis, a novel approach to meta-analyse studies on climate change impacts, adaptation, and vulnerability in Europe. The meta-analysis results in a classification scheme for relating the diverse studies. This scheme consists of (i) a classification of studies according to the type of adaptation-relevant results they produce and (ii) a hierarchical classification of the regional and thematic context of studies. The implementation of this scheme, for example in the form of a database, overcomes some of the identified gaps of current adaptation knowledge representation. We furthermore present a quantitative analysis of the classified studies that exemplifies how the developed classification scheme can be applied to get a systematic and quantitative overview of the knowledge they contain. Thus, the conceptual meta-analysis and the classification scheme represent a first step towards a systematisation of knowledge on climate change impacts, adaptation, and vulnerability and may be seen as a useful complement to qualitative literature reviews.     

Salt diapirs without well defined boundaries – a feasibility study of semi‐automatic detection

Prestack depth imaging of seismic data in complex areas such as salt structures requires extensive velocity model updating. In many cases, salt boundaries can be difficult to identify due to lack of seismic reflectivity. Traditional amplitude based segmentation methods do not properly tackle this problem, resulting in extensive manual editing. This paper presents a selection of seismic attributes that can reveal texture differences between the salt diapirs and the surrounding geology as opposed to amplitude‐sensitive attributes that are used in case of well defined boundaries. The approach consists of first extracting selected texture attributes, then using these attributes to train a classifier to estimate the probability that each pixel in the data set belongs to one of the following classes: near‐horizontal layering, highly‐dipping areas and the inside of the salt that appears more like a low amplitude area with small variations in texture. To find the border between the inside of the salt and the highly‐dipping surroundings, the posterior probability of the class salt is input to a graph‐cut algorithm that produces a smooth, continuous border. An in‐line seismic section and a timeslice from a 3D North Sea data set were employed to test the proposed approach. Comparisons between the automatically segmented salt contours and the corresponding contours as provided by an experienced interpreter showed a high degree of similarity.