Geospatial data mining for digital raster mapping

We performed an in-depth literature survey to identify the most popular data mining approaches that have been applied for raster mapping of ecological parameters through the use of Geographic Information Systems (GIS) and remotely sensed data. Popular data mining approaches included decision trees or “data mining” trees which consist of regression and classification trees, random forests, neural networks, and support vector machines. The advantages of each data mining approach as well as approaches to avoid overfitting are subsequently discussed. We also provide suggestions and examples for the mapping of problematic variables or classes, future or historical projections, and avoidance of model bias. Finally, we address the separate issues of parallel processing, error mapping, and incorporation of “no data” values into modeling processes. Given the improved availability of digital spatial products and remote sensing products, data mining approaches combined with parallel processing potentials should greatly improve the quality and extent of ecological datasets.     

Building a model-based personalised recommendation approach for tourist attractions from geotagged social media data

When travelling, people are accustomed to taking and uploading photos on social media websites, which has led to the accumulation of huge numbers of geotagged photos. Combined with multisource information (e.g. weather, transportation, or textual information), these geotagged photos could help us in constructing user preference profiles at a high level of detail. Therefore, using these geotagged photos, we built a personalised recommendation system to provide attraction recommendations that match a user's preferences. Specifically, we retrieved a geotagged photo collection from the public API for Flickr (Flickr.com) and fetched a large amount of other contextual information to rebuild a user's travel history. We then created a model-based recommendation method with a two-stage architecture that consists of candidate generation (the matching process) and candidate ranking. In the matching process, we used a support vector machine model that was modified for multiclass classification to generate the candidate list. In addition, we used a gradient boosting regression tree to score each candidate and rerank the list. Finally, we evaluated our recommendation results with respect to accuracy and ranking ability. Compared with widely used memory-based methods, our proposed method performs significantly better in the cold-start situation and when mining ‘long-tail’ data.     

Classifier ensembles for land cover mapping using multitemporal SAR imagery

SAR data are almost independent from weather conditions, and thus are well suited for mapping of seasonally changing variables such as land cover. In regard to recent and upcoming missions, multitemporal and multi-frequency approaches become even more attractive. In the present study, classifier ensembles (i.e., boosted decision tree and random forests) are applied to multi-temporal C-band SAR data, from different study sites and years. A detailed accuracy assessment shows that classifier ensembles, in particularly random forests, outperform standard approaches like a single decision tree and a conventional maximum likelihood classifier by more than 10% independently from the site and year. They reach up to almost 84% of overall accuracy in rural areas with large plots. Visual interpretation confirms the statistical accuracy assessment and reveals that also typical random noise is considerably reduced. In addition the results demonstrate that random forests are less sensitive to the number of training samples and perform well even with only a small number. Random forests are computationally highly efficient and are hence considered very well suited for land cover classifications of future multifrequency and multitemporal stacks of SAR imagery.     

刺参染色体制备的初步研究

为探索取材容易、结果稳定可靠的刺参染色体制备方法,分别以刺参(Apostichopus japortfcus)胚胎和成体为材料对刺参染色体制片方法进行了研究.结果表明,以原肠后期胚胎为材料采用常规的热滴片法,细胞有丝分裂指数最高,获得分裂相效果最好;以成体呼吸树、成体肠组织为材料时,也能获得中期分裂相染色体,但存在着细...     

典型深街谷内树木空间配置对行人呼吸高度处气流的影响

为揭示树木的不同空间配植方案对行人呼吸高度气流的影响,本文将树木视为均匀多孔介质,通过附加源项法从空气动力学角度用CFD模拟了H/W=2的典型深街谷几何内4种树木配植情景,实验表明,不同空间配置下树木对街谷内行人呼吸高度处局地气流的影响强弱在空间分布模式上差异悬殊：① 均匀种植的树木对街谷内行人呼吸高度的气流起到阻碍作用,不均匀种植则有效提升街谷的整体流速。4种空间配植方案下树木对气流的影响程度不同,阻碍作用从大到小的顺序为均匀间距8 m（Spa8m）>均匀间距6 m（Spa6m）>均匀间距20 m（Spa20m）>不均匀配植（Non-uniform）;对应的平均气流增强指标顺序为$\bar{D}_{spa8}$（-19.31%）<$\bar{D}_{spa6}$（-16.14%）<$\bar{D}_{spa20}$（-10.73%）<$\bar{D}_{non-uniform}$（1.25%）。② 对比不均匀和均匀的种植方案,不均匀植树的街谷内部行人呼吸高度的气流流速比其对照案例（均匀植树Spa8m方案）整体增强了106.49%。街谷中部不种树,在街谷两端配置树木并预留足够的自由空间的不均匀植树方案,能够让角涡渗入街谷中部,促使街谷内部的垂直漩涡和两端的水平角涡运动,增强湍流和垂直交换,有效减少了街道两端“风口效应”和街道中部“风影效应”的区域,改善了整个街谷行人呼吸平面的风环境。④ 合理空间配置的树木能够改善街谷内部的行人风环境。街谷内行人呼吸高度处的气流对局地条件很敏感,树木的局部配置（空间簇集、密度）将引起强烈的空间变化。在既有城市建筑布局条件下,如何通过谨慎的景观设计,利用树木等城市绿化措施有效地改善城市的行人风环境,缓解污染扩散、疾病传播等问题,本文的方法可提供一定的参考。     

基于随机森林特征选择的城市绿化乔木树种分类

城市绿化在改善空气、水和土壤质量,吸收和减少二氧化碳及各种污染物,缓解城市热岛和减少雨水径流等方面发挥着重要作用。及时准确地获取树种信息是城市规划与绿化管理的先决条件,对进一步改善城市生态环境也具有重要意义。基于遥感技术,使用高空间分辨率的WorldView-2卫星影像,采用光谱、纹理、指数以及几何等多种特征相结合的面向对象方法,并通过随机森林进行特征选择,对福州大学旗山校区北部的榕树、杧果、香樟、重阳木、羊蹄甲、垂叶榕以及木棉7种主要绿化乔木进行树种分类。实地验证结果表明：通过特征选择可以减少或规避数据冗余以及休斯效应的产生,该方法可以提高现有同类型树种分类的精度,当淘汰全部特征的20%,利用34个特征（包括15个光谱特征、6个纹理特征、8个指数特征和5个几何特征）进行分类时,总精度最高,可达74.95%,Kappa系数为0.67。其中,光谱平均值的特征重要性最高,而各波段的标准差的重要性较低。WorldView-2卫星影像的4个新增波段,特别是黄光和红边波段及其构建的指数特征重要性较高,也说明这些波段在植被遥感,特别是树种分类中极具应用前景。     

近20年京津唐地区不透水面变化的遥感监测

不透水面是衡量城市化程度的重要指标之一,对京津唐城市群的不透水面进行深入研究,可以量化城市群扩张过程及其影响,对该区域多城市协调发展及规划布局具有重要意义。本文结合高分辨遥感影像、生长季及落叶季的Landsat TM遥感影像和夜间灯光数据等,采用分类和回归树（Classification and rRegression Tree, CART）算法,构建了适于京津唐地区不透水面盖度提取的技术方案,获取了京津唐地区1995-2016年共5期地表不透水面盖度专题信息,并分析了地表不透水面的时空演变规律,结论为：① 适于京津唐地区不透水面盖度提取的CART算法的最佳输入变量组合为：生长季和落叶季的Landsat TM图像以及对应的夜间灯光数据;其次为生长季Landsat TM遥感图像和夜间灯光数据组合方案。利用该组合方案,ISP估算输出结果的交叉验证精度R值可以达到约0.85,可以满足地表不透水面纵向对比分析的需要。② 从地表不透水面总面积数量值来看,1995-2016年京津唐主体城市区域整体上呈增长趋势,其中2011-2016年地表不透水面积增加愈加明显;③ 从地表不透水面盖度值的高低来看,1995-2016年京津唐中、高盖度不透水面的占比都是在不断增长的,低盖度不透水面占比存在少量下降现象,且京、津、唐3城市的主体城区各阶段变化差异较大,反映出了各城市扩张具有各自不同的时空演变特征。     

气温变化对西峰黄土高原地温与梨树发育期的影响

用西北地区140站1961-2000年的气温资料和西峰黄土高原1971-2005年5,10,15,20cm地温和1984-2005年梨树发育期资料,分析了西北地区春季、夏季、秋季、冬季和年气温的变化事实,再用相关计算和典型年份对比,分析了地温的时间变化规律及其对梨树发育期的影响。结果表明,西北地区20世纪60年代冬季增温,其余降温,70年代均降温,80年代冬季增温,其余降温,90年代均增温,冬季的最明显。西峰10cm地温各季节呈持续升高的趋势,春季增温最明显为0.058℃/a,变幅也最大,冬季增温幅度次之为0.039℃/a,再是秋季为0.032℃/a,夏季增温幅度最小为0.029℃/a,上升趋势均通过0.05和0.01的信度检验。冬季、春季地温与梨树的各发育期均为负相关,即地温高,发育期早,地温低,发育期迟。冬季地温与梨树发育期相关最显著的是叶变始期和开花始期,相关系数为-0.41～-0.52,信度为0.05,春季地温与之相关最显著的是开花始期,相关系数为-0.68～-0.69,信度达0.001。春季地温对梨树发育期的影响具有明显的持续性和滞后性,冬季地温对梨树发育期影响有阶段性,春季地温对梨树发育期的影响比冬季的明显。     

Modelling and observation of hedgerow transpiration effect on water balance components at the hillslope scale in Brittany

Vegetation has a major influence on the water and energy balance of the earth's surface. In the last century, human activities have modified land use, inducing a consequent change in albedo and potential evapotranspiration. Linear vegetation structures (hedgerows, shelterbelts, open woodland, etc) were particularly abundant but have declined considerably over the past several decades. In this context, it is important to quantify their effect on water and energy balance both on a global scale (climate change and weather prediction) and on a local scale (soil column, hillslope and watershed). The main objective of this study was to quantify the effect of hedgerows on the water cycle by evaluating spatial and temporal variations of water balance components of a hillslope crossed by a hedgerow. Water flow simulation was performed using Hydrus‐2D to emphasize the importance of transpiration in the water balance and to evaluate water extraction from groundwater. Model validation was performed by comparing simulated and observed soil matrix potentials and groundwater levels. Hedgerow transpiration was calculated from sap flow measurements of four trees. Water balance components calculated with a one‐dimensional water balance equation were compared with simulations. Simulation runs with and without tree root uptake underlined the effect of hedgerow transpiration, increasing capillary rise and decreasing drainage. Results demonstrated that the spatial and temporal variability of water balance components was related to the hedgerow presence as well as to the meteorological context. The relations between transpiration, groundwater proximity and soil‐water availability determined the way in which water balance components were affected. Increased capillary rise and decreased drainage near hedges were related to the high transpiration of trees identified in this study. Transpiration reached twice the potential evapotranspiration when groundwater level and precipitation amounts were high. Water balance analysis showed that transpiration was a substantial component, representing 40% of total water output. These results may offer support for improving hydrological models by including the effect of land use and land cover on hydrological processes. Copyright © 2012 John Wiley & Sons, Ltd.     

地图数据库中的结构化河网及其自动建立

本文提出了一种基于河段的结构化河网,讨论了这种结构化河网的自动建立过程,主要包括两个结构索引即线索树结构索引及层次结构索引的自动产生;根据包含以上两个索引的结构化河网,提供了若干检索函数,作为地图数据库中结构处理时结构信息的提取手段。