Spatially constrained regionalization with multilayer perceptron

In this article, multilayer perceptron (MLP) network models with spatial constraints are proposed for regionalization of geostatistical point data based on multivariate homogeneity measures. The study focuses on non‐stationarity and autocorrelation in spatial data. Supervised MLP machine learning algorithms with spatial constraints have been implemented and tested on a point dataset. MLP spatially weighted classification models and an MLP contiguity‐constrained classification model are developed to conduct spatially constrained regionalization. The proposed methods have been tested with an attribute‐rich point dataset of geological surveys in Ukraine. The experiments show that consideration of the spatial effects, such as the use of spatial attributes and their respective whitening, improve the output of regionalization. It is also shown that spatial sorting used to preserve spatial contiguity leads to improved regionalization performance.     

基于决策树的我国农业数据挖掘分析

决策树是用于分类的常用建模方法。首先对分类的概念和决策树方法分别进行了总体介绍,在此基础上对我国30个省市自治区的乡村劳动力、耕地面积以及农业总产值信息数据进行了挖掘分析,在运用决策树对数据进行分类过程中对连续数据采用聚类分析的方法进行离散化处理,从而避免了原始经验分类方法的主观性。最后,通过上述决策树分类方法,生成我国农业情况的决策树,获得相关空间分类规则,并对其进行分析说明。结果表明,决策树分类方法适合我国农业情况。     

一种空间交叉异常显著性判别的非参数检验方法

空间异常探测旨在从海量空间数据中挖掘不符合普适性规律、表现出“与众不同”特性的空间实体集合,对于揭示地理现象的特殊发展规律具有重要价值。现有研究在空间异常度量方面取得了重要进展,但多缺乏对空间异常模式显著性的统计判别,且是针对单一类别数据,没有顾及多类别数据间的相互影响。为此,本文基于空间随机过程的思想,针对两种类别空间点数据,提出了一种空间交叉异常显著性判别的非参数检验方法。首先,针对基本数据集实体,采用约束Delaunay三角网,构建合理、稳定的空间邻近域;然后,统计落在基本数据集实体空间参考邻域半径范围内的参考数据集实体的数目,度量初始异常度;进而,采用α-Shape法构建支撑域,以空间随机过程为基础构建零模型,采用蒙特卡洛模拟检验空间异常的显著性;最后,采用生存距离对异常模式的稳定性进行评价分析。通过试验分析与比较发现,该方法能够有效识别具有统计显著性的空间交叉异常。     

Important considerations about space‐time data: Modeling,scrutiny, and ratification

Space‐time data are becoming more abundant as time goes by, with hands‐on interest in them becoming more prevalent. These data have a very sensitive ordering in space and time, one that the simplest of recording errors can scramble. These data are also complex, containing both spatial and temporal autocorrelation coupled with their interaction. One goal of many researchers is to disentangle and account for these autocorrelation components in a parsimonious way. This article presents three competing model specifications to achieve this end. In addition, it outlines seven best practices for vetting space‐time datasets. This article cites a publicly available corrupt (containing at least errors of omission) rabies dataset to illustrate how a large volume of potentially valuable data can be rendered meaningless. In addition, it exemplifies postulated contentions about the United States National Cancer Institute Surveillance, Epidemiology, and End Results Program’s 1969–2018 population‐by‐county dataset, a collection of population counts held in high esteem. One major empirical finding is that this particular dataset exhibits traits that may merit remedial revisions action. A key conceptual finding is a suggested set of best practices for space‐time data proofreading. These two findings contribute to an ultimate goal of a large collection of certified open access space‐time datasets supporting repeatable and replicable scientific analyses.     

基于信息熵的遥感影像特征离散化方法

利用信息熵方法对遥感影像的光谱特征进行离散化,根据信息熵的准则函数,寻找断点,对属性进行区间分割,以提高数据处理效率。并用决策树方法对多光谱遥感影像进行分类,通过对比离散化前后的分类效果分析离散化对多光谱遥感影像分类的影响,实验结果证明了该方法的有效性。     

Assessing reference dataset representativeness through confidence metrics based on information density

Land cover maps obtained from classification of remotely sensed imagery provide valuable information in numerous environmental monitoring and modeling tasks. However, many uncertainties and errors can directly or indirectly affect the quality of derived maps. This work focuses on one key aspect of the supervised classification process of remotely sensed imagery: the quality of the reference dataset used to develop a classifier. More specifically, the representative power of the reference dataset is assessed by contrasting it with the full dataset (e.g. entire image) needing classification. Our method is applicable in several ways: training or testing datasets (extracted from the reference dataset) can be compared with the full dataset. The proposed method moves beyond spatial sampling schemes (e.g. grid, cluster) and operates in the multidimensional feature space (e.g. spectral bands) and uses spatial statistics to compare information density of data to be classified with data used in the reference process. The working hypothesis is that higher information density, not in general but with respect to the entire classified image, expresses higher confidence in obtained results. Presented experiments establish a close link between confidence metrics and classification accuracy for a variety of image classifiers namely maximum likelihood, decision tree, Backpropagation Neural Network and Support Vector Machine. A sensitivity analysis demonstrates that spatially-continuous reference datasets (e.g. a square window) have the potential to provide similar classification confidence as typically-used spatially-random datasets. This is an important finding considering the higher acquisition costs for randomly distributed datasets. Furthermore, the method produces confidence maps that allow spatially-explicit comparison of confidence metrics within a given image for identification of over- and under-represented image portions. The current method is presented for individual image classification but, with sufficient evaluation from the remote sensing community it has the potential to become a standard for reference dataset reporting and thus allowing users to assess representativeness of reference datasets in a consistent manner across different classification tasks.     

Automatic Update of Road Attributes by Mining GPS Tracks

Despite advances in cartography, mapping is still a costly process which involves a substantial amount of manual work. This article presents a method for automatically deriving road attributes by analyzing and mining movement trajectories (e.g. GPS tracks). We have investigated the automatic extraction of eight road attributes: directionality, speed limit, number of lanes, access, average speed, congestion, importance, and geometric offset; and we have developed a supervised classification method (decision tree) to infer them. The extraction of most of these attributes has not been investigated previously. We have implemented our method in a software prototype and we automatically update the OpenStreetMap (OSM) dataset of the Netherlands, increasing its level of completeness. The validation of the classification shows variable levels of accuracy, e.g. whether a road is a one‐ or a two‐way road is classified with an accuracy of 99%, and the accuracy for the speed limit is 69%. When taking into account speed limits that are one step away (e.g. 60 km/h instead of the classified 50 km/h) the classification increases to 95%, which might be acceptable in some use‐cases. We mitigate this with a hierarchical code list of attributes.     

Integrated Framework for the Simulation of Biological Invasions in a Heterogeneous Landscape

In the integrated framework presented in this article, a geographical information system serves as a shell to integrate spatial, dynamic and stochastic perspectives of biological invasions in a coherent workflow. A decision tree model stratifies the landscape with respect to spatial susceptibility and builds the spatial biophysical structure for the simulation of species invasion. A dynamic diffusion model evaluates the temporal changes of species to provide the dynamic parameters for the simulation. A simulation model derived from percolation theory simulates species invasion by combining spatial and dynamic information, and explicitly representing spatio‐temporal patterns of invasions within the GIS‐percolation environment. The simulation illustrates the great influence of spatial structure and connectivity of landscape on the diffusion of the species.     

尺度驱动的空间聚类理论

空间聚类是探索性空间数据分析的有力手段,不仅可以直接用于发现地理现象的分布格局与分布特征,亦可以为其他空间数据分析任务提供重要的预处理步骤。空间聚类有望成为大数据认知的突破口。空间聚类研究虽然已经引起了广泛关注,但是依然面临两大最根本的困境:"无中生有"和"无从理解"。"无中生有"指的是:绝大多数方法,即使针对不包含聚类结构的数据集,仍然会发现聚类;"无从理解"指的是:即使同一种聚类方法,采用不同的聚类参数就会获得千变万化的聚类结果,而这些结果的含义不明确。造成上述困境的根本原因在于:尺度没有在聚类模型中被当作重要参数而恰当地体现。为此,笔者受到人类视觉多尺度认知原理的启发,根据多尺度表达的"自然法则",建立了一套尺度驱动的空间聚类理论。首先将尺度定量化建模为聚类模型的参数,然后将空间聚类的尺度依赖性建模为一种假设检验问题,最后通过控制尺度参数以自动获得统计显著的多尺度聚类结果。在该理论指导下,可以构建适用不同应用需求的多尺度空间聚类模型,一方面降低了空间聚类过程中的主观性,另一方面有利于对空间聚类模式进行全面而深入的分析。     

基于Weka平台的C4.5算法在影像分类中的应用

遥感图像分类是从复杂的地物类型中提取有效类别信息的过程。在研究区地物类型较为复杂的情况下,借助计算机对遥感数据进行类别预测可以提高分类效率和准确率。本文基于Weka平台,利用决策树C4.5算法构造分类模型,进而对未知类别数据进行预测。实验分析表明,基于Weka平台利用决策树C4.5算法对遥感图像分类是可行且有效的,且分类精度较高。     

结合UPSCALING技术与对象多特征的土地利用覆盖信息提取研究

应用SPOT融合数据,以北京密云地区为例,提出了整合Upscaling技术与对象多特征方法的新思路,通过基于半变异函数的 空间变异特征分析,建立了面向对象多特征与多分辨率数据集的多尺度分类决策树,并对自动分类效率进行了初步探讨。     

基于专家知识的决策树分类

基于ENVI运用专家知识的决策树分类、监督分类、非监督分类手段来实现对于Landsat TM影像和快鸟影像数据的图像分类处理,简单介绍了决策树的建立过程,以及如何进行预处理、分类后处理、精度评价。通过3种分类方式的比较,基于专家知识的决策树分类法具有分类判别规则十分灵活、分类决策树看起来很直观、分类条件清晰、分类效果好、运算效率高等特点。实验中,其分类方式的缺陷表现为分类过多、过于复杂,可能会产生错误的速度加快;决策树判别规则复杂,树形分枝多导致用户难以识别、理解、应用。     

Inference and analysis across spatial supports in the big data era: Uncertain point observations and geographic contexts

The ways in which geographic information are produced have expanded rapidly over recent decades. These advances have provided new opportunities for geographical information science and spatial analysis—allowing the tools and theories to be expanded to new domain areas and providing the impetus for theory and methodological development. In this light, old problems of inference and analysis are rediscovered and need to be reinterpreted, and new ones are made apparent. This article describes a new typology of geographical analysis problems that relates to uncertainties in the relationship between individual‐level data, represented as point features, and the geographic context(s) that they are associated with. We describe how uncertainty in context linkage (uncertain geographic context problem) is also related to, but distinct from, uncertainty in point‐event locations (uncertain point observation problem) and how these issues can impact spatial analysis. A case study analysis of a geosocial dataset demonstrates how alternative conclusions can result from failure to account for these sources of uncertainty. Sources of point observation uncertainties common in many forms of user‐generated and big spatial data are outlined and methods for dealing with them are reviewed and discussed.     

Using Thermal Remote Sensing in Environmental Studies

Thermovision is a relatively new method of remote sensing with applications in areas such as military operations, residential monitoring, technological process control and emergency management. Surprisingly, it has not seen much application in environmental studies. The article presents a method of using thermovision for topoclimatic studies. The method is based on the spatial distribution of land surface temperature (LST). The LST distribution indicates the amount of solar energy reaching the Earth surface and depends primarily on terrain shape and land cover types. By analyzing the LST distribution, one can determine spatial topoclimatic variability. The LST derived topoclimatic classification was compared with the theoretical topoclimatic classification based on heat balance. New classes of topoclimates were created and some of the existing types were diversified into more detailed subtypes. The analysis of selected lowland areas in north‐western Poland revealed that both land cover and terrain shape characteristics had a significant impact on the LST distribution, contrary to the expectation of land cover characteristics being more important than terrain shape. The article demonstrates the possibilities of using thermovision in environmental research and presents a new method of topoclimate delimitation based on thermal remote sensing data and geographical information systems (GIS) techniques comparing. The LST classification method with conventional methods based on DEM and land cover analysis.     

Discovering Spatial Interaction Communities from Mobile Phone Data

In the age of Big Data, the widespread use of location‐awareness technologies has made it possible to collect spatio‐temporal interaction data for analyzing flow patterns in both physical space and cyberspace. This research attempts to explore and interpret patterns embedded in the network of phone‐call interaction and the network of phone‐users’ movements, by considering the geographical context of mobile phone cells. We adopt an agglomerative clustering algorithm based on a Newman‐Girvan modularity metric and propose an alternative modularity function incorporating a gravity model to discover the clustering structures of spatial‐interaction communities using a mobile phone dataset from one week in a city in China. The results verify the distance decay effect and spatial continuity that control the process of partitioning phone‐call interaction, which indicates that people tend to communicate within a spatial‐proximity community. Furthermore, we discover that a high correlation exists between phone‐users’ movements in physical space and phone‐call interaction in cyberspace. Our approach presents a combined qualitative‐quantitative framework to identify clusters and interaction patterns, and explains how geographical context influences communities of callers and receivers. The findings of this empirical study are valuable for urban structure studies as well as for the detection of communities in spatial networks.     

通过训练样本采样处理改善小宗作物遥感识别精度

训练样本质量是决定农作物遥感识别精度的关键因素,虽然高空间分辨率卫星的发展有效地解决了农作物遥感识别过程中的混合像元问题,但是当区域内不同作物种植面积差异较大时,训练集中不同类别样本数量往往相差较大,这样的不均衡数据集影响分类器的训练,导致少数类别的识别精度不理想。为研究作物遥感识别过程中的不均衡样本问题,本文基于GF-2号卫星数据,首先挖掘了地物的光谱信息、纹理信息,用特征递归消除RFE (Recursive Feature Elimination)方法进行特征优选,然后从数据处理的角度采用了5种采样算法对不均衡训练集进行处理,最后使用采样后的均衡数据集训练分类器,对比数据采样前后决策树与Adaboost(Adaptive Boosting)两种分类器的识别结果,发现:(1)经过采样处理后两种分类算法明显提升了小宗作物的分类精度;(2)经过ADASYS (Adaptive synthetic sampling)采样处理后,分类器性能提升最多,决策树的Kappa系数提高了14.32%,Adaboost的Kappa系数提高了10.23%,达到最高值0.9336;(3)过采样的处理效果优于欠采样,过采样对分类器的性能提升更多。综上所述,选择合适的采样方法和分类方法是提高不均衡数据集遥感分类精度的有效途径。     

决策树分类法及其在遥感图像处理中的应用

首先阐述了决策树分类器的结构与理论基础,并就决策树算法的发展趋势进行了归纳总结。然后结合遥感图像分类的特点,探讨了决策树分类法的实现方法和关键问题。在此基础上,以徐州市TM影像为数据进行了分类试验。试验说明了决策树分类法在遥感图像处理中的具体实现过程,并且试验结果表明该方法在依据感兴趣区类别进行图像分类时效果较好。     

一种干旱半干旱地区决策树分类方法

以内蒙古自治区伊金霍洛旗为研究区,利用Landsat TM影像,对干旱半干旱地区土地利用信息进行提取。在ENVI软件的支持下,分析了影像的光谱特征及NDVI,NDBI,NDWI特征变量,并运用灰度共生矩阵对影像进行纹理特征提取,得到熵纹理特征图像,确定各类地物的阈值,运用决策树分类法对影像进行分类。结果表明,结合光谱特征和纹理特征的决策树分类方法,提取干旱半干旱地区土地利用信息可行且准确性较高。     

Integrated compression of vehicle spatio‐temporal trajectories under the road stroke network constraint

With fast growth of all kinds of trajectory datasets, how to effectively manage the trajectory data of moving objects has received a lot of attention. This study proposes a spatio‐temporal data integrated compression method of vehicle trajectories based on stroke paths coding compression under the road stroke network constraint. The road stroke network is first constructed according to the principle of continuous coherence in Gestalt psychology, and then two types of Huffman tree—a road strokes Huffman tree and a stroke paths Huffman tree—are built, based respectively on the importance function of road strokes and vehicle visiting frequency of stroke paths. After the vehicle trajectories are map matched to the spatial paths in the road network, the Huffman codes of the road strokes and stroke paths are used to compress the trajectory spatial paths. An opening window algorithm is used to simplify the trajectory temporal data depicted on a time–distance polyline by setting the maximum allowable speed difference as the threshold. Through analysis of the relative spatio‐temporal relationship between the preceding and latter feature tracking points, the spatio‐temporal data of the feature tracking points are all converted to binary codes together, accordingly achieving integrated compression of trajectory spatio‐temporal data. A series of comparative experiments between the proposed method and representative state‐of‐the‐art methods are carried out on a real massive taxi trajectory dataset from five aspects, and the experimental results indicate that our method has the highest compression ratio. Meanwhile, this method also has favorable performance in other aspects: compression and decompression time overhead, storage space overhead, and historical dataset training time overhead.     

TM classification using local spectral variability

A classification method which takes into account not only spectral but also spatial features for LANDSAT‐4 and 5 Thematic Mapper (TM) data is proposed. In accordance with improvement of Instantaneous Field of View (IFOV), spatial information such as textural, contextual, etc. is also increased so that some treatments of such information is highly required. One of the simplest spatial features is local spectral variability such as standard deviation, variability constant, variance, etc. in small cells such as 2x2,3x3 pixels. Such information can be used together with conventional spectral features in an unified way, for the traditional classifier such as a pixel‐wise Maximum Likelihood Decision Rule (MLDR). From the experiments, there was a substantial improvement in overall classification accuracy for TM forestry data. The probability of correct classification (PCC) for the new clearcut and the alpine meadow classes increased by 7% to 97% correct. The confusion between alpine meadow and new clearcut was reduced from 9% to 3%.