Urban sprawl has been identified as one of the most negative effects of global population growth on the environment and biodiversity. Frequent monitoring of urban sprawl is needed to limit the impact of this ongoing phenomenon. This paper proposes precise monitoring of building construction using an object-based classification methodology applied to Spot 5 images with a 2.5 m resolution. An application at a regional scale on Reunion Island in the Indian Ocean shows that this building extraction methodology has limitations in the production of reference urban maps because of difficulties in defining the shape and the number of buildings compared to classical photo-interpretation of aerial photography. However, these results are of great value for planning in urban sprawl areas where up-to-date information is lacking because of the rapid pace of house construction and residential development.

This study is the result of investigating the land use/cover surrounding Conakry city and its two neighboring cities from the past to the present periods which are herein after referred to as this egion and the impact of numerous changes during that time. These changes have become a major concern for the Guinean government and scientific community. Using map interpretation with integration of remote sensing, GIS technology and a GIS method we investigated the land use/cover and a population dynamism model with the aims of promoting a sustainable recovery and future judicious utilization. We found out that these three cities are on the verge of being unified, as a result of the expansion of urban residential areas and the changing economic realities causing significant influences on this land use/cover change. The pattern of land cover 59years ago presented a landscape relatively pristine, while that in the present period presents a landscape that is markedly in a degrading decline. During the past 59years, land use/cover has been influenced by key factors that revolve around socio-economic development, climatic patterns, topography manipulation, and policy implementation influences. The level of degradation of the land use/cover has increased and will oblige the political, scientific and local communities to take note of the environmental changes and set up urgent, rigorous and coherent policies for the rational development and management of the land use/cover resources of this region. That can be part of a model for other countries to reclaim the past sustainable environment.

Based on the principles of sustainable development, land use planning often requires the compromise between economic development and environmental conservation while advocating social justice. Given that ideas, values, and attitudes vary among the stakeholders involved, land use planning inevitably incurs a variety of conflicts. The conflicts in land use planning can be described from the perspective of the conflicts among land use types and the conflicts among stakeholders. Accordingly, land use planning can be conceived as the process of dealing with conflicts among different land use types through resolving the conflicts among stakeholders. This study centers around two important issues in land use planning: land use allocation and specific land use proposal deliberation. A Conflict Resolution Framework was proposed based on GIS and Multi-criteria Decision Analysis techniques. A Consensus Building Model was established to address the conflicts among different stakeholders with competing interests in the process of land use allocation. A Spatial Conflict Resolution Strategy was developed to help stakeholders and planners formulate specific land use proposals through an iterative modification process. The both models were tested and evaluated in the context of Lantau, Island Hong Kong. Moreover, the challenges of this research and future work are also covered in this paper.

Natural resources management is indispensable in ensuring environmental sustainability and reducing the risk associated with climate change and increasing demand for ecological goods and services. Natural resources planners need to have at their disposal tools that can objectively help in prioritizing land use allocation. Traditional application of land use change model based on economic model, trend analysis, and or scenario analysis present some challenges of data availability and reliability necessary for implementation of the models. However, with the advent of information technology, GIS and remote sensing, biophysical data known for having influence on land use allocation can easily be accessed. The current study explores the application of GIS-Multi-criteria analysis in modeling future land use scenarios for resources planning and management using easy to construct biophysical parameters known for influencing future land use allocation. The decision problems in this study are to find the best spatial allocation of land to future agriculture and forest development, which are considered to present critical land use change in the study area. The afforestation scenarios are meant to offset the pressure on the native forest resources due to the increased demand for fuel and timber and also to contribute to the environmental protection and the agricultural land use scenarios are meant to increase productivity and ensure environmental protection. The land use scenarios did not consider hen in the future the land use pattern may develop. The analyses of scenarios indicate that afforestation extent in the basin can be increased from 4.6% to 42.9% of the total basin area. However, the afforestation extent of 42.9% may be considered unrealistic, since in practice, it may not be possible to realize up to 42.9% afforestation, nevertheless, the spatial pattern of the afforestation may provide crucial insight into spatial afforestation policies and it future consequences. The agricultural land use can increase from 6.2% to 53.7% of the basin area. The agricultural land use expansion can be realised since the expansion of farm land is primarily the main option to achieve food production increase in the near future. The findings indicate potential use of the methodology in land use planning.

随着城市化、工业化、机动化进程的加快,大气污染已成为我国最严重的环境问题之一,对公众健康和生态环境造成了诸多负面影响.土地利用回归,即Land-use Regression(LUR)模型是目前模拟城市尺度大气污染时空分异的常用方法之一,其在欧洲和北美得到广泛的应用,而在国内,相关研究却不多.本文在整理国内外文献的基础上,从构建LUR模型的主要步骤入手,包括监测数据获取、模型自变量生成、模型构建、模型检验和回归映射等方面,对LUR模型在大气污染时空分异研究中的进展进行归纳总结,进而展望了未来的研究重点与方向,即突出时空分异、扩展模型变量类别和改进模型构建方法.本文旨在普及LUR模型在我国的应用,为人口暴露、流行病学研究和健康风险评价等提供方法论基础.

为了评估土地利用变化和人为热对区域气象环境产生的影响，同时针对WRF模式对城市土地利用和人为热刻画不够准确的现状，以上海为例，选用GLC2009对WRF中上海地区原有数据进行修正。通过楼层信息将上海市分为三类（商业区、高强度区、低强度区），同时重新估算了人为热通量和人为热释放日变化系数。利用WRF／UCM对2010年8月11-17日的一次高温过程进行了模拟试验。与观测资料的对比表明：新的土地利用数据较真实地反映了上海地区下垫面的变化，尤其是大规模建设导致的城市功能区变化；使用新的土地利用和人为热数据，温度和比湿模拟的平均偏差分别改善了1．95℃和0．713g／kg；高温范围和比湿对土地利用的改变最敏感，高温强度对人为热最敏感。

在遥感和GIS技术的支持下,运用WEKA的J48决策树算法和监督分类的最大似然法对肥东县3期ETM+影像进行分类,提取土地利用信息,构建了土地利用类型转换矩阵,从主地利用类型的数量、结构和程度3个方面对肥东县土地利用变化进行分析.研究表明,前一种分类方法的精度较高;肥东县2000年～2011年建设用地面积呈上升趋势且变化最大,耕地、林地、草地、水域、未利用地均呈减少趋势,土地利用变化速度和综合程度越来越快.

本文利用凉城县2009年07月20日获取的ALOS多光谱数据和2009年07月09日获取的Landsat5 TM数据,进行影像预处理,计算归一化植被指数,以DEM、坡度及NDVI作为辅助数据,结合这些辅助特征值建立决策树分类提取规则,对凉城县土地利用现状进行分类研究。结果显示：总体分类精度达73.67%,kapaa系数0.696 4。为提高地类的分类准确性将分类结果进行分类后处理,其中裸地面积最大49.71%,林地、耕地、草地总面积为37.77%,其它地类总面积为12.52%,得到与研究区实际土地利用面积相符的地类面积。

土地利用分类精度直接决定土地利用／土地覆被变化相关研究的准确性，而基于决策树的遥感影像分类是近年来提高土地利用分类精度的重要方法。QUEST决策树在影像解译和空间表达方面，运算速度和分类精度均优于普通CART等决策树方法。本文以云南丽江地区为例，应用QUEST决策树分类方法，对该地区的LandsatTM5影像图进行分类，同时将地形因素、植被指数作为地学辅助数据的因子添加到分类波段中，进行不同特征融合，来处理目标类别间的非线性关系，该方法在处理图像理解知识方面具有更大的灵活性；同时与普通决策树分类法的遥感影像分类的结果相比较，Kappa系数值从原来的0．789提高到0．849。在地形复杂的山地地区，针对TM影像数据，选择基于QUEST决策树分类能够有效提高土地利用分类结果精度。

针对面向对象土地利用分类存在特征维数过高的问题,提出了一种结合Relief F和粒子群优化算法（particle swarm optimization,PSO）的混合特征选择方法,即首先利用Relief F作为特征预选器滤除相关性小的特征,然后以PSO作为搜索算法,以支持向量机（support vector machine,SVM）的分类精度作为评估函数在剩余特征中选择出最优特征子集。该文以吉林省长春市部分区域为研究区,采用Landsat8遥感影像为数据源,首先对其进行多尺度分割,然后提取影像对象的光谱、纹理、形状和空间关系特征,利用提出的混合特征选择方法选取最优特征子集,最后使用SVM分类器对研究区进行土地利用分类,总体分类精度和Kappa系数分别为85.88%和0.8036,与基于4种其他特征选择方法的土地利用分类结果进行比较,基于Relief F和PSO的混合特征选择方法利用最少的特征获得最高的分类精度,能够有效地用于面向对象土地利用分类。

土地利用变化是反映人类活动程度的重要因子，分析土地利用时空变化规律，是揭示人类活动程度的有效方式。在遥感和地理信息系统技术的支持下，采用人机交互图像处理方法获取北洛河流域1976年、1998年和2010年土地利用数据；从土地利用变化速度、转移方向和土地利用程度方面，全面分析1976年以来北洛河流域人类活动作用下的土地利用时空变化规律。结果表明：①1976．1998年和1998-2010年间北洛河流域综合土地利用动态度从0．61增加到6．66；耕地和草地面积减少，减小速度分别从2．00％和2．69％增加到26．20％和23．33％，林地和城乡工矿居民用地面积增加，前者增加速度从5．93％增到59．68％，后者增加速度从6．59％减小到3．52％。②两个时段土地利用类型转移方向都呈现出耕地和草地主要转化为林地，少部分耕地转化为城乡工矿居民用地的特点；③流域各县土地利用程度综合变化指数从-2-1之间，扩大为．27～4之间。证明流域内人类活动对自然环境的影响逐渐增大；主要表现为耕地、草地、林地和城乡工矿居民用地的相互转化；影响区域主要分布在流域上游吴旗县、富县、甘泉、黄陵县和洛川县；而人类活动作用导致的林地面积增大程度远远大于耕地和草地面积减小和城乡工矿居民用地面积增加程度。