Classifying airborne LiDAR point clouds via deep features learned by a multi-scale convolutional neural network

Point cloud classification plays a critical role in many applications of airborne light detection and ranging (LiDAR) data. In this paper, we present a deep feature-based method for accurately classifying multiple ground objects from airborne LiDAR point clouds. With several selected attributes of LiDAR point clouds, our method first creates a group of multi-scale contextual images for each point in the data using interpolation. Taking the contextual images as inputs, a multi-scale convolutional neural network (MCNN) is then designed and trained to learn the deep features of LiDAR points across various scales. A softmax regression classifier (SRC) is finally employed to generate classification results of the data with a combination of the deep features learned from various scales. Compared with most of traditional classification methods, which often require users to manually define a group of complex discriminant rules or extract a set of classification features, the proposed method has the ability to automatically learn the deep features and generate more accurate classification results. The performance of our method is evaluated qualitatively and quantitatively using the International Society for Photogrammetry and Remote Sensing benchmark dataset, and the experimental results indicate that our method can effectively distinguish eight types of ground objects, including low vegetation, impervious surface, car, fence/hedge, roof, facade, shrub and tree, and achieves a higher accuracy than other existing methods.     

PREDICTIVE ABILITY OF REGRESSION MODELS.PART Ⅱ:SELECTION OF THE BEST PREDICTIVE PLS MODEL

A procedure called GOLPE is suggested in order to detect those variables which increase the predictivityof PLS models.The procedure is based on evaluating the predictive power of a number of PLS modelsbuilt by different combinations of variables selected according to a factorial design strategy.Examplesare given of the efficiency of this variable selection procedure,which shows how these predictive PLSmodels are better than those obtained by all variables and better than the corresponding ordinaryregression models.     

新疆河流年径流量对夏季0C层高度变化的响应

According to climate features and river runoff conditions, Xinjiang could be divided into three research areas: The Altay-Tacheng region, the Tianshan Mountain region and the northern slope of the Kunlun Mountains. Utilizing daily observations from 12 sounding stations and the annual runoff dataset from 34 hydrographical stations in Xinjiang for the period 1960-2002, the variance of the summertime 0℃ level height and the changing trends of river runoff are analyzed both qualitatively and quantitatively, through trend contrast of curves processed by a 5-point smoothing procedure and linear correlation. The variance of the summertime 0℃ level height in Xinjiang correlates well with that of the annual river runoff,especially since the early 1990s, but it differs from region to region, with both the average height of the 0℃ level and runoff quantity significantly increasing over time in the Altay-Tacheng and Tianshan Mountain regions but decreasing on the northern slope of the Kunlun Mountains. The correlation holds for the whole of Xinjiang as well as the three individual regions, with a 0.01 significance level. This indicates that in recent years, climate change in Xinjiang has affected not only the surface layer but also the upper levels of the atmosphere, and this raising and lowering of the summertime 0℃ level has a direct impact on the warming and wetting process in Xinjiang and the amount of river runoff. Warming due to climate change increases the height of the 0℃ level, but also speeds up, ice-snow melting in mountain regions, which in turn increases river runoff, leading to a season of plentiful water instead of the more normal low flow period.     

The response of annual runoff to the height change of the summertime 0℃ level over Xinjiang

According to climate features and river runoff conditions, Xinjiang could be divided into three research areas: The Altay-Tacheng region, the Tianshan Mountain region and the northern slope of the Kunlun Mountains. Utilizing daily observations from 12 sounding stations and the annual runoff dataset from 34 hydrographical stations in Xinjiang for the period 1960–2002, the variance of the summertime 0℃ level height and the changing trends of river runoff are analyzed both qualitatively and quantitatively, through trend contrast of curves processed by a 5-point smoothing procedure and linear correlation. The variance of the summertime 0℃ level height in Xinjiang correlates well with that of the annual river runoff, especially since the early 1990s, but it differs from region to region, with both the average height of the 0℃ level and runoff quantity significantly increasing over time in the Altay- Tacheng and Tianshan Mountain regions but decreasing on the northern slope of the Kunlun Mountains. The correlation holds for the whole of Xinjiang as well as the three individual regions, with a 0.01 significance level. This indicates that in recent years, climate change in Xinjiang has affected not only the surface layer but also the upper levels of the atmosphere, and this raising and lowering of the summertime 0℃ level has a direct impact on the warming and wetting process in Xinjiang and the amount of river runoff. Warming due to climate change increases the height of the 0℃ level, but also speeds up, ice-snow melting in mountain regions, which in turn increases river runoff, leading to a season of plentiful water instead of the more normal low flow period.     

海岸带地区SPOT卫星影像大气校正方法比较及精度验证

为获得反演海岸带地区地表真实反射率的最佳大气校正方法,分别利用DOS、6S及FLAASH三种模型对SPOT卫星影像进行大气校正,对比分析校正前后影像的典型地物光谱曲线及NDVI指数的变化情况,并对结果进行精度验证。研究表明:三种大气校正模型均能有效去除大气对遥感影像的影响,获取较为准确的地表反射率信息;对比河流、水库、海水、植被、城镇、裸地等六种典型地物校正前后的光谱曲线,与DOS及6S模型相比,FLAASH模型校正结果中各地物反射率差别较大、特征明显,能较好的还原地表真实情况;NDVI指数检验显示,FLAASH模型对地物NDVI响应更强烈,在地物光谱响应特征分析等方面具有更强的优势,是三种模型中最适宜海岸带地区SPOT影像的大气反演方法。研究方法及结论可为同类研究提供参考与借鉴。     

湖南省传统聚落景观基因的空间特征

湖南省有着悠久的历史文化和优越的自然地理环境,是全国传统聚落相对集中和保存较为完好的省区之一.本文以国家和湖南省政府正式公布的30 个历史文化名村名镇为研究对象,结合传统聚落景观基因理论,建立了包括建筑特征、文化特征、环境特征、聚落布局特征4 大类共14 项指标的传统聚落景观基因识别指标体系;根据要素提取法、图案分析法、结构提取法、含义提取法等景观基因提取方法,建立了湖南省传统聚落景观基因的识别流程,并进行了传统聚落景观基因的识别与提取.在此基础上,从建筑基因的特征、选址布局基因的特征、图腾文化基因的特征3 个角度分析了该省传统聚落景观基因的空间特征.本文对湖南省传统聚落的保护与合理、可持续开发利用具有参考意义,对开展全国其他省份传统聚落的相关研究同样具有借鉴意义.     

LATENT FEATURES WITH MAXIMAL CORRELATION BETWEEN TWO EQUAL SETS OF VARIABLES

If in two data tables X and Y objects are characterized by the same variables(measured at differentoccasions),then looking for common latent features should be more appropriate than choosing latentfeatures in X and Y separately(e.g.as in canonical correlation or PLS).The procedure to be proposedhere is a slight modification of the method of linear characteristics(according to De Groot and Li)bydisclaiming the assumption of equal inner-block covariance matrices.In order to find weights defining alatent feature with maximal correlation between X and Y,a system of non-linear equations has to besolved.The procedure is applied to the investigation of heavy metal concentrations in different humantissues.     

Digital map conflation: a review of the process and a proposal for classification

This article is centred on analysing the state of the art of the conflation processes applied to geospatial databases (GDBs) from heterogeneous sources. The term conflation is used to describe the procedure for the integration of these different data, and conflation methods play an important role in systems for updating GDBs, derivation of new cartographic products, densification of digital elevation models, automatic features extraction and so on. In this article we define extensively each conflation process, its evaluation measures and its main application problems and present a classification of all conflation processes. Finally, we introduce a bibliography which the reader may find useful to further explore the field. It tries to serve as a starting point and direct the reader to characteristic research in this area.     

Synthesis of seismic surface waves

Summary. The reflection method is used to produce complete sets of Rayleigh wave dispersion curves in a given phase velocity—frequency window for horizontally stratified media, including modes of very high numerical order, and theoretical surface wave seismograms are then synthesized.
The difficulties encountered when attempting to complete large numbers of dispersion curves are discussed. Particular problems arise from models with a low-velocity zone, when curves in a certain portion of the dispersion diagram split into two families, the crustal and the channel modes. The reflection method provides a convenient framework in which to examine this phenomenon heuristically and so devise a method to overcome the difficulties.
Seismograms are produced by mode summation and it is found that body-wave behaviour, as well as surface-wave features can be synthesized. The effect of truncating the mode series at a number comparable with the number of modes used in previous studies is examined. It is found that although the S -coda at longer ranges is not adversely affected, the arrivals attributable to body-waves are severely distorted. This must call into question the validity of synthetic seismograms generated by summation of only a few modes.     

基于多重分割关联子的高分辨率遥感场景分类

高分辨率遥感影像提供了丰富的外观信息和空间结构信息,广泛应用于土地利用分类当中,源于文章领域的视觉词袋（Bag-of-Visual-Words,BoVW）模型现已成功应用于图像分类领域。传统的BoVW模型忽略了特征之间的空间布局信息和像素一致性信息,提出多重分割关联子特征,融合图像的外观信息、空间布局信息和像素一致性信息,实验表明该方法能够获取优于许多经典的遥感图像特征的性能。     

The response of annual runoff to the height change of the summertime 0°C level over Xinjiang

According to climate features and river runoff conditions, Xinjiang could be divided into three research areas: The Altay-Tacheng region, the Tianshan Mountain region and the northern slope of the Kunlun Mountains. Utilizing daily observations from 12 sounding stations and the annual runoff dataset from 34 hydrographical stations in Xinjiang for the period 1960–2002, the variance of the summertime 0°C level height and the changing trends of river runoff are analyzed both qualitatively and quantitatively, through trend contrast of curves processed by a 5-point smoothing procedure and linear correlation. The variance of the summertime 0°C level height in Xinjiang correlates well with that of the annual river runoff, especially since the early 1990s, but it differs from region to region, with both the average height of the 0°C level and runoff quantity significantly increasing over time in the Altay-Tacheng and Tianshan Mountain regions but decreasing on the northern slope of the Kunlun Mountains. The correlation holds for the whole of Xinjiang as well as the three individual regions, with a 0.01 significance level. This indicates that in recent years, climate change in Xinjiang has affected not only the surface layer but also the upper levels of the atmosphere, and this raising and lowering of the summertime 0°C level has a direct impact on the warming and wetting process in Xinjiang and the amount of river runoff. Warming due to climate change increases the height of the 0°C level, but also speeds up, ice-snow melting in mountain regions, which in turn increases river runoff, leading to a season of plentiful water instead of the more normal low flow period.     

Locating some types of random errors in Digital Terrain Models

The increasing use of Geographical Information System applications has generated a strong interest in the assessment of data quality. As an example of quantitative raster data, we analysed errors in Digital Terrain Models (DTM). Errors might be classified as systematic (strongly dependent on the production methodology) and random. The present work attempts to locate some types of randomly distributed, weakly spatially correlated errors by applying a new methodology based on Principal Components Analysis. The Principal Components approach presented is very different from the typical scheme used in image processing. A prototype implementation has been conducted using MATLAB, and the overall procedure has been numerically tested using a Monte Carlo approach. A DTM of Stockholm, with integer-valued heights varying from 0 to 59 m has been used as a testbed.The model was contaminated by adding randomly located errors, distributed uniformly within 4 m and 4m. The procedure has been applied using both spike shaped (isolated errors) and pyramid-like errors. The preliminary results show that for the former, roughly half of the errors have been located with a Type I error probability of 4.6 per cent on average, checking up to 1 per cent of the dataset. The associated Type II error of the larger errors (of exactly 4m or 4 m) drops from an initial value of 1.21 per cent down to 0.63 per cent. By checking another 1 per cent of the dataset, such error drops to 0.34 per cent implying that about 71 per cent of the 4m errors have been located; Type I error was below 11.27 per cent. The results for pyramid-like errors are slightly worse, with a Type I error of 25.80 per cent on average for the first 1 per cent effort, and a Type II error drop from an initial value of 0.81 per cent down to 0.65 per cent. The procedure can be applied both for error detection during the DTM generation and by end users. It might also be used for other types of quantitative raster data.     

柴达木盆地雅丹地貌区风况数据集

为了明确柴达木盆地雅丹地貌发育的风况特征,对盆地中南部鲸背状雅丹区和西北部长垄状雅丹区的风况分别进行了长期的野外实地观测。对实测的风速风向数据按照罗盘16方位分风速段统计分析,计算输沙势,得到柴达木盆地雅丹地貌区风况数据集。该数据集包括两个数据文件：（1）盆地中南部的鲸背状雅丹区风况数据（WinReg_WhaleBackYardang_QB）;（2）盆地西北部的长垄状雅丹区风况数据（WinReg_LongRidgeYardang_QB）。每个数据文件均包含3个工作表,分别为观测周期内的原始风速风向记录,各月份、季节、年度的风频和输沙势。本数据集存储为.xls格式,压缩后的数据量为2.73 MB。本数据集不仅可准确阐释柴达木盆地雅丹地貌发育的风况特征,也为进一步研究雅丹地貌的发育演化模式奠定了基础。本数据集的相关研究成果发表在《中国沙漠》2013年33卷第5期和《Journal of Arid Land》2019年11卷第5期。     

Methods for estimating missing data on migrants in the 1991 British census

"This paper discusses the use of suppression to protect data in the Special Migration Statistics, a dataset produced from the 1991 [British] Census, and argues that this procedure prevents accurate analysis of the data. A computer program is described that uses a series of methods to ?recover' data which were suppressed, and to estimate those parts of the data which cannot be recovered.... The program has been used to recover and estimate data successfully, and results include sample tables of migrants between types of districts by ethnicity."     

Data-driven approach to characterize urban vitality: how spatiotemporal context dynamically defines Seoul’s nighttime

ABSTRACT

This study takes a data-driven approach to define urban nighttime by examining the spatiotemporal dynamics of urban vitality. Using micro-scale spatiotemporal analysis, this paper empirically provides a comprehensive, yet granular, picture of collective human behaviors in cities. Using Seoul, South Korea as a case study site, it prioritizes the spatiotemporal context in order to mitigate uncertain contextual effects inherent in such forms of data-driven analysis. Instead of leaving the data re-grouping up to researcher’s arbitrary decision, this paper employs a functional principal component analysis (FPCA) to systematically transform a set of discrete data to a continuous functional form. This paper applies FPCA on 24-hour-based dataset of pedestrian traffic in Seoul in order to make a data-driven extraction of principal components that characterize the city’s unique patterns of urban vitality. Extracting principal components allows for less statistically obvious phenomena to be measured that would have otherwise been hidden within the data. This approach proved successful in capturing nighttime vitality patterns that are eclipsed by the overwhelming trend of daytime patterns. Additionally, this paper compares differences between regions and seasons to examine what the differences can tell about the definition of nighttime.     

Deep seismic reflectors in the Campos basin, offshore Brazil

Summary. Some deep crustal features underlying the Campos basin are best recognized in a few reflection seismic sections that have been reprocessed recently to 10 s two-way traveltime. A prominent climbing-to-the-basin reflector is interpreted as the Moho, and a relatively steep fracture zone is, probably, the first example so far of an extensional fault crossing the whole crust and offsetting the Moho. Further constraints on the deep structure of the basin are provided by estimating the thinning of the crust from shallow seismic data and gravity modelling, and by cross-plotting backstripped subsidence curves against curves predicted by the lithospheric stretching model.     

An application of problem and product ontologies for the revision of beach nourishments

An ontological approach in GIS serves as a framework for the conceptualization of processes in the real world. In this paper, we examine an application in coastal change in the Netherlands, whereby beaches are subject to artificial nourishment to offset the effect of severe erosion. The use of ontologies helps to define two scenarios: S_I determined by the regulations from the Ministry for Public Works; S_II grounded on the abilities from an existing spatial dataset. A comparison between S_I and S_II shows that 72.8% of the objects suitable and unsuitable for nourishment are correctly classified. A higher overlap is found in areas where actual beach nourishments were carried out. Inaccuracies in attributes influence the determination of the objects. A sensitivity analysis applied to altitude illustrates a significant increase of objects suitable for nourishment for both scenarios, when altitude is decreased within the lower limit of the root mean square error for the 95% confidence interval. Moreover, the sensitivity of altitude shows that artificial boundaries for beach nourishment objects are not reasonable and consequently should be treated as vague objects.     

Exploring multi-criteria decision strategies in GIS with linguistic quantifiers: an extension of the analytical network process using ordered weighted averaging operators

Many real-world spatial planning and management problems give rise to a geographical information system (GIS)-based multi-criteria decision-making. Analytical network process (ANP) provides a comprehensive methodology for representing complex multi-criteria decision-making problems as a network of criteria and alternatives, where feedback and interdependence relationships may exist within and between all the criteria and alternatives. Experts’ experiences are used to estimate relative magnitudes of tangible and intangible factors through paired comparisons in order to make rational and consistent decisions. However, the GIS-based ANP, an adoption of weighted linear aggregation rule, typically employed a high trade-off decision strategy and neglected other decision strategies. This paper develops a novel GIS-based multi-criteria evaluation (MCE) procedure by extending the ANP using fuzzy quantifiers-guided ordered weighted averaging (OWA) operators. This extension, which generalizes the aggregation process used in the ANP, would provide a generic powerful decision-making tool that allows decision-makers to define a decision strategy on a continuum between pessimistic (risk-averse) and optimistic (risk-taking) strategies. By changing the linguistic quantifiers, the GIS-based ANP–OWA can generate a wide range of decision strategies taking into accounts the level of risk the decision-makers wish to assume in their MCE. A land-use suitability analysis in a region of Saudi Arabia is presented to demonstrate the application of the proposed procedure.     

Lichenometric Dating of Rock Surfaces in the Northern Cascade Range,USA

This study presents a growth curve developed from direct and indirect growth rates of Rhizocarpon geographicum lichens from study sites on Mounts Baker, Rainier, Adams, and Hood in the northern Cascade Range of the western USA. Our observations of direct growth rates are based on 31 measurements of 11 lichens growing on different surfaces. This direct growth rate dataset is complemented by indirect growth rates based on measurements of the largest lichen observed on 20 different surfaces over 24–33‐yr periods. The direct and indirect datasets produce statistically indistinguishable mean radial growth rates of 0.48 and 0.50 mm yr^?1, respectively. Statistical analysis of zero and first order fits of our growth rate data suggests that lichen growth is best characterized by the average of our mean growth rate (zero order) models at 0.49 mm yr^?1. Our revised growth curve for the study area extends the applicable range for dating rock surface in the study area to the seventeenth century, approximately 175 years longer than previous calibrated curves.