Optimizing support vector machine learning for semi-arid vegetation mapping by using clustering analysis

In remote sensing communities, support vector machine (SVM) learning has recently received increasing attention. SVM learning usually requires large memory and enormous amounts of computation time on large training sets. According to SVM algorithms, the SVM classification decision function is fully determined by support vectors, which compose a subset of the training sets. In this regard, a solution to optimize SVM learning is to efficiently reduce training sets. In this paper, a data reduction method based on agglomerative hierarchical clustering is proposed to obtain smaller training sets for SVM learning. Using a multiple angle remote sensing dataset of a semi-arid region, the effectiveness of the proposed method is evaluated by classification experiments with a series of reduced training sets. The experiments show that there is no loss of SVM accuracy when the original training set is reduced to 34% using the proposed approach. Maximum likelihood classification (MLC) also is applied on the reduced training sets. The results show that MLC can also maintain the classification accuracy. This implies that the most informative data instances can be retained by this approach.     

Variable orientation within a natural population of the sandhopper Talitrus saltator (Crustacea: Amphipoda) as a response to a variable environment: The case-study of Berkoukesh beach,Tunisia

Sandy beaches are harsh environments, driving resident arthropod populations to various typical adaptations, particularly behavioural ones. Here we evaluated the effects of seasonal meteorological variability on the behaviour of Talitrus saltator on Berkoukesh beach (N-W Tunisia). The site is characterised by a Mediterranean climate, but is particularly exposed to seasonal winds and storms. The shoreline is in morphodynamic equilibrium. We tested sandhopper Talitrus saltator orientation in April, when sudden rainfall and storms are common, and in June, when as a rule the weather is warm and dry. The results were analysed with circular statistics and multiple regression models adapted to angular distributions, in order to highlight differences in orientation under the various conditions. Depending on the environmental conditions, amphipods from the same population appeared to utilise various orientation strategies as a response to different environmental constraints. The use of a range of behavioural mechanisms (sun-orientation seaward, sun-orientation landward, and phototaxis) resulted in links to the local landscape and to the animals’ life cycle. As a general conclusion, we can infer that the behavioural variability found within the same population represents a response to seasonal environmental fluctuation. Such an increase in variability is likely to develop on a beach in dynamic equilibrium, where landscape references are stable, and a variable behaviour represents a strategy for dealing with environmental fluctuations.     

土地资源体多级变粒度空间数据管理方法

结合资源体的概念和土地要素功能提出了土地资源体概念,将土地资源数据对象组织成土地利用资源体、土地权属资源体等不同类型的土地资源体.在土地资源体对象基础上,结合具体的土地资源管理业务需要,提出了土地资源体多级变粒度数据组织管理模式,对土地资源体横向按资源体、图库、图层集合、图层和地物等不同资源授权粒度,纵向按多级区域层次管理的方式进行管理.国家、省、市级别的土地资源管理以县为基本单位,以区域特征管理国家、省、市、县等逻辑关系,县级的土地资源时空数据按资源体、图库、图层集合、图层和地物等不同资源授权粒度来对数据进行管理.在具体的土地资源管理和业务实施时,可以根据实际的需要对位于不同位置、不同层次、不同资源体类型的土地资源体进行动态组合.     

Method for evaluating the degrees of land use sustainability of mountainous county and its application in Yunnan Province,China

The evaluation of sustainable land use is the key issue in the field of studying the sustainable land utilization. In general analysis, the sustainable land use is evaluated respectively from its ecological sustainability, economic sustainability and social sustainability in China and other countries in recent years. Although this evaluation is an important work, it seems insufficient and hard to comprehensively reflect the whole degree of land use sustainability. Thus, to make up this deficiency, this paper brings forward the evaluation indexes, which make it possible to quantitatively reflect the whole degree of land use sustainability, namely, the concept of ＂degrees of overall land use sustainability＂ （Dos）, and research and measurement development of the method of and calculation in Dos. Taking the evaluation of the degree of land use sustainability in county regions of Yunnan Province as the actual example for analysis, results are basically as follows：
1） The degree of land use sustainability （Dos） is the ration index to organically and systematically integrate the degree of ecological friendliness （DeF）, the degree of economic viability （Dev） and the degree of social acceptability （Dsa）, able to comprehensively reflect the whole sustainability degree of regional land use
2） Based on the value of Dos, the grading system and standard for the sustainability of land use may be established and totally divided into five grades, namely, the high-degree sustainability, middle-degree sustainability, low-degree sustainability, conditional sustainability and non-sustainability. Meanwhile, the standard for distinguishing sustainability grades has also been confirmed so as to determine the nature of sustainability degrees in different grades. This makes the possibility for the combination of nature determination with ration in research result and provides with the scientific guideline and decision-making gist for better implementation of sustainable land use strategy.
3） The pract     

国土资源数据管理初探

在分析国土资源数据及其管理特点的基础上,基于国土资源信息化和数据资源保护,将国土资源数据整体上分为资料数据、基础数据、业务数据、管理数据和元数据5类,提出了各类数据进行计算机管理的组织方法和采用的相关技术。     

基于3S的荣成湾沿岸土地覆被变化及驱动力研究

运用3S技术对最近40年来荣成湾沿岸土地覆被动态变化及驱动力进行研究.结果表明,该区海岸湿地土地覆被总面积和陆域土地覆被总面积变化不大,但其各自类型结构和分布均发生了显著调整,而且二者变化在时间上不同步.从面积上讲,前者以1981年为界,渴湖和沙地先减少后波动增加,滩涂和沼泽地先增加后波动减少;养殖池从无到有并迅速增加...     

北京精细下垫面信息引入对暴雨模拟的影响

首先根据2000年环北京实际的精细下垫面布局资料（500m分辨率）,按美国USGS陆面资料分类标准（25类）对其提供的全球30 s经纬分辨率（≈1 km）下垫面分类资料进行了更新设计.进而针对一个北京夏季暴雨过程,利用10:3.3km双向双重嵌套的MM5V3.6-Noah LSM陆气耦合模式进行24h数值对比试验,研究了北京精细下垫面信息引入对暴雨的影响.分析表明：新设计的陆面资料更真实地反映了环北京区域的下垫面结构,尤其针对北京城区面积迅增特征;同时还修正了原资料将亚洲中纬度区域落叶阔叶林下垫面类型归属为热带(或亚热带)稀疏大草原类型的问题.其在数值天气模式中的引入会对短期暴雨过程的发生发展产生重要影响.对此次暴雨主要降水中心的模拟,12h差值分布范围远达30km以上,中心值相对差异可达30%.研究发现在城市下垫面和大气相互间存在一个重要的相互影响机制,即由于城区面积的扩大会导致自然植被减少,进而会减少地表蒸发及相应局地大气水分供应、加深边界层高度并增强大气水汽混合,这不利于降水的发生发展.     

基于标准化降水蒸散指数（SPEI）的毛乌素沙地1981—2020年干旱特征研究

大气干旱是影响半干旱沙区植被建设、生态恢复及社会经济可持续发展的重要因素。基于1981—2020年毛乌素沙地10个气象站点的逐月气象资料,计算了月、季和年尺度的标准化降水蒸散指数（SPEI）,分析了该沙区近40年降水和气温的变化趋势、干旱事件及其频率的时空特征。结果表明：（1）毛乌素沙地近40年降水量和气温均呈现显著的上升趋势（P<0.05）;秋季和冬季降水量呈现显著的上升趋势（P<0.05）,四季气温均呈现显著的上升趋势（P<0.05）。（2）毛乌素沙地总体上呈现出不显著的湿润化趋势（P>0.05）,但秋季呈显著的湿润化趋势（P<0.05）;中、西部地区呈现出湿润化趋势,而东部地区则呈现干旱化趋势。（3）近40年毛乌素沙地的月尺度下干旱总频率达32.71%,各等级发生频率为轻旱>中旱>重旱>特旱,季节发生频次为冬季>夏季、秋季>春季;轻旱主要发生在毛乌素沙地的北部、中部、东南和西南部,中旱在东部、北部和西部边缘,重旱在东部、中部以及南部地区,特旱在西北部、南部和东南部区域。     

基于陆海统筹的海岸带空间功能分区——以宁波市为例

海岸带空间功能分区是优化海岸带开发与保护的基础性工作,在国土空间规划体系中具有重要作用。当前我国海陆功能分区在分区层级、分区方法等方面并不一致,导致海岸带保护与开发利用失衡。本文在梳理国内外海岸带空间功能分区研究的基础上,从陆海统筹角度出发,构建海岸带空间功能分区体系,并以宁波市为例进行验证,在优先划定生态保护区基础上,对海陆空间进行适宜性评价,根据评价结果确定功能分区。结果表明：（1）宁波市海岸带功能区中生态保护区面积占比约为60%,海陆一体发展区占比约为22.3%,海洋发展区占比约为12.5%,陆地发展区占比约为5.2%;(2)宁波市开发利用功能区空间分布与以临港产业、海洋服务业和海洋渔业为基础的海洋经济发展导向相符。海岸带空间功能分区要以生态保护为底线,以优化空间布局为导向,为优化海岸带开发与保护提供有力支撑。     

第三次国土调查城镇村内部细化调查方法研究

基于第三次国土调查城镇村内部细化调查的工作要求和数据基础,梳理了城镇村调查边界划定、城镇村土地利用框架构建、城镇村土地利用图斑转绘、城镇村土地利用类型判定、外业补充调查等城镇村内部细化调查环节;归纳了1:2000基础地理信息数据、不动产登记数据、基础性地理国情监测数据等已有调查成果在各调查环节的数据转换利用方式,为城镇...