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.     

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.     

Advances in understanding of the mechanism for generation of earthquake thermal precursors detected by satellites

Stresses building up during an earthquake preparation phase also manifest themselves in the form of a so called increased land surface temperature (LST) leading to a thermal precursor prior to the earthquake event. This phenomenon has now been validated by our observations of short-term thermal anomalies detected by infrared satellite sensors for several recent past earthquakes around the world. The rise in infrared radiance temperature was seen to vary between 5 and 12 °C for different earthquakes. We discuss in this paper different explanations for the generation of such anomalies that have been offered. Emission of gases due to the opening and closure of micropores upon induced stresses and also the participation of ground water have been propounded as a possible cause for generation of thermal anomalies. Seismo-ionosphere coupling, by which gases like radon move to the earth–atmosphere interface and cause air ionization thus bringing about a change in air temperature, relative humidity, etc., has been put forth by some workers. A mechanism of low frequency electromagnetic emission was tested and experimented by scientists with rock masses in stressed conditions as those that exist at tectonic locations. The workers proposed the positive hole pair theory, which received support from several scientific groups. Positive holes (sites of electron deficiency) are activated in stressed rocks from pre-existing yet dormant positive hole pairs (PHPs) and their recombination at rock–air interface leads to a LST rise. A combination of remote sensing detection of rock mechanics behavior with a perception of chemistry and geophysics has been applied to propose the remote sensing rock mechanics theory. Remote sensing detections of such anomalies confirm so far proposed lab theories for such a hotly debated field as earthquake precursor study by providing unbiased observations with consistency in time and space distribution.     

乡镇土地利用规划管理信息系统设计与实现

针对当前乡镇土地利用规划中存在的问题,运用GIS的数据管理和空间分析等功能,结合规划区域的实际状况,开发了一个面向乡镇的土地利用规划管理信息系统,提高了土地管理的工作效率和信息化水平,能够实现乡镇土地的合理利用。     

贵州省国土资源信息化建设模式研究

本文在深入调研贵州省国土资源信息化建设现状基础上,回顾了发展历程,系统总结了贵州省在推进国土资源信息化建设方面的主要思路和做法,阐述了建设现状和取得的主要成效,以贵州省国土资源信息化建设模式为借鉴,提出了几个值得深入思考和探讨的问题。     

单窗算法的大气参数估计方法

根据地表热辐射传导方程,提出了一个简单可行且精度较高的专门用于从TM6数据中演算地表温度的方法——单窗算法.这一算法把大气和地表状态对地表热传导的影响直接包括在演算公式中.该方法需要两个大气参数进行地表温度的演算,即大气平均作用温度和大气透射率.本文论述这两个大气参数的估计方法:根据大气水分含量或地表附近空气湿度来估计大气透射率;通过分析标准大气剖面资料,尤其是大气水分和气温随高程的变化规律,根据地表温度推算大气平均作用温度.     

深化土地制度改革的广域视角和深度思维

在改革成为社会各界持续热议并正发力推进的今天,改革思维和视角的重塑与再造意义非凡。全球一体化的大势正推进着文化融合走向深入,洋为中用、中西合璧等观点正深度影响着我国改革进程,尤其是土地制度改革。笔者认为,只有立足文化基因的视角,明白"洋如何为洋用"才能做好"洋为中用",切实做到"大我"和"小我"的理性认知,公平和效率的均衡协调、底线和红线的表里融合理应成为我国土地制度改革的主论调和基本准则。     

基于移动GIS的土地执法动态巡查系统建设

目前土地执法巡查工作存在着作业方式落后、信息化程度低、巡查效率低和巡查人员不易监督的问题。针对这些问题,通过分析土地执法巡查的业务需求和移动GIS技术的特点提出构建基于移动GIS的土地执法动态巡查系统,在此基础上完成系统总体架构设计和功能设计,分析系统实现的移动GIS技术、数据库引擎技术、Web Services技术和基于时间维的GIS管理技术,重点阐述移动GIS技术在系统中的应用,最后完成系统开发。系统的使用改善了执法巡查现状,提高了巡查效率。     

Analysis of urban built-up areas and surface urban heat island using downscaled MODIS derived land surface temperature data

Regional scale urban built-up areas and surface urban heat islands (SUHI) are important for urban planning and policy formation. Owing to coarse spatial resolution (1000 m), it is difficult to use Moderate Resolution Imaging Spectroradiometer (MODIS) Land surface temperature (LST) products for mapping urban areas and visualization, and SUHI-related studies. To overcome this problem, the present study downscaled MODIS (1000 m resolution)-derived LST to 250 m resolution to map and visualize the urban areas and identify the basic components of SUHI over 12 districts of Punjab, India. The results are compared through visual interpretation and statistical procedure based on similarity analysis. The increased entropy value in the downscaled LST signifies higher information content. The temperature variation within the built-up and its environs is due to difference in land use and is depicted better in the downscaled LST. The SUHI intensity analysis of four cities (Ludhiana, Patiala, Moga and Vatinda) indicates that mean temperature in urban built-up core is higher (38.87 °C) as compared to suburban (35.85 °C) and rural (32.41 °C) areas. The downscaling techniques demonstrated in this paper enhance the usage of open-source wide swath MODIS LST for continuous monitoring of SUHI and urban area mapping, visualisation and analysis at regional scale. Such initiatives are useful for the scientific community and the decision-makers.     

第二次土地调查若干问题探讨

第二次土地调查的目的是全面查清全国土地利用状况,掌握真实的土地基础数据,如何保证调查的质量?文章以江阴市为例进行探讨。