Land use/land cover change (LUCC) has considerable impact on ecosystem services. It is essential to quantify the spatiotemporal heterogeneity of ecosystem services from the perspective of LUCC, which will benefit regional land management and ecological protection. We analyzed land use change in the Pearl River Delta from 2000 to 2015, and we used a spatially explicit integrated modeling tool (InVEST) for quantification of ecosystem services-water yield, carbon storage, soil retention, and food supply. The results revealed increases in the areas of grassland and built-up land, and decreases in the areas of woodland, cropland, water body, and unused land during 2000 to 2015, which have caused increase in water yield and carbon storage, while decrease in soil retention and food supply. The dynamic changes of woodland, grassland, cropland, and built-up land were the main driving factors in the relationship of trade-offs and synergies among the four ecosystem services, which are ubiquitous. Those all illustrate the importance of considering ecosystem services in decision making related to land use and land management.

There has been a move towards using mixed method approaches in geospatial research to gain context in understanding health related social patterns and processes. The central premise is that official data is often too reductionist and misses' nuances that can help explain causality. One example is the geonarrative, a spatially relevant commentary or interview that can be mapped by content and/or location. While there have been several examples of geonarratives being used by researchers, there is no commonly available software that can easily transfer the associated text into spatial data. Having a standardized software platform is vital if these methods are to be used across different disciplines. This paper presents an overview of a solution, Wordmapper (WM), which is a standalone software developed to process geonarratives from a transcription and associated global positioning system (GPS) path. Apart from querying textual narrative data, Wordmapper facilitates qualitative coding which could be used to extract latent contextual information from the narratives. In order to improve interoperability, Wordmapper provides spatialized narrative data in formats, such as ESRI shape files, Keyhole Markup Language (KML), and Comma Separated Values (CSV). A case study based on five different spatial video geonarratives (SVG) collected to assess the human impacts following the 2011 Joplin, Missouri are used for illustration.

3 km2,耕地面积共减少4.9×103 km2,林草用地面积共减少16.4×103 km2。2010-2015年与2000-2010年相比,中国土地利用变化的区域空间格局基本一致,但分区变化呈现新的特征。东部建设用地持续扩张和耕地面积减少,变化速率有所下降;中部建设用地扩张和耕地面积减少速度增加;西部建设用地扩张明显加速,耕地面积增速进一步加快,林草面积减少速率增加;东北地区建设用地扩展持续缓慢,耕地面积稳中有升,水旱田转换突出,林草面积略有下降。从“十二五”期间国家实施的主体功能区布局来看,东部地区的土地利用变化特征与优化和重点开发区的国土空间格局管控要求基本吻合;中部和西部地区则面临对重点生态功能区和农产品主产区相关土地利用类型实现有效保护的严峻挑战,必须进一步加大对国土空间开发格局的有效管控。]]>

土地利用/土地覆被变化已列为“国际地圈与生物圈计划”的核心项目,在该领域的研究工作逐渐加强。本文论述了全球环境变化中的土地利用/土地覆被变化的内涵,在全球环境变化中的作用,其主要研究内容、关键问题及研究方法,并介绍了国外有关研究项目的情况。

Land use and land cover change has aroused increasing attention of scientists worldwide since1990.Recognizing the importance of this change to other global environmental change and sustainable development issues,the International Geosphere-Biosphere ProgrammeIGBP)and the HumanDimensions of Global Environmental Change ProgrammeHDP)initiated a joint core projectLand Use and Land Cover Change(LUCC)and published a Science/Research Plan for the project.To promote the national LUCC projects,the paper presents a general review on the basic concepts,background,and Progress on the metnodologies of international LUCC researches.Land use/land cover is not a new research domain but is given new meanings and research contents in the context of global environmental change.Based on the definition of land cover given bythe IGBP/HDP and other international institutions,the author proposes a new translated term ofland cover in Chinese that matches the definition closely.This will avoid misunderstanding of thedomestic LUCC projects at early stages.Land cover changes refer to conversion and modification of vegetation,changes on biodiversity,soil quality,runoff,erosion,sedimentation and land productivity.International researches onLUCC involve:1)influence of LUCC on systematic global enviromental changes like biogeochemicalcircles and climatic variation,and cumulative global environmental changes like eforestation,biodiversity reduction and land degradation;2)response of LUCC to global environmental changes;3)LUCC and sustainable development including the sustainability of different land uses.The fundamental scientific issue of LUCC research is the dynamics of land use and coverchanges,which is extremely significant to the prediction of the global environmental change in thenext 50 to 100 years.The modedling of causes-use-cover system is challenge because of its inherentcomplexity.An integrated approach to the modeling is necessary that combines:1)large-scale onsite case study approach to land use dynamics;2)direct observation and measurement of land coverchange by using remote sensing images;and 3)regional and global modeling of economic processesrelated to LUCC.

在全球环境变化研究中,以土地利用与土地覆盖动态为核心的人类–环境耦合系统研究逐渐成为土地变化科学 (LCS) 研究的新动向。基于覆盖中国21世纪初5年间隔的遥感卫星数据获取的1 km网格土地利用变化空间信息,依据近5年土地利用变化区域分异的显著特征,以及自然地理、经济发展与国家宏观政策因素综合考虑,设计针对21世纪初5年新的中国土地利用动态区划图,揭示土地利用变化的空间格局与驱动因素。总体上,21世纪初5年中国处于土地利用快速变化期,黄淮海平原、东南沿海地区与四川盆地城乡建设用地显著扩张,占用大规模优质农田,导致南方水田面积明显减少；西北绿洲农业发展与东北地区开垦导致北方旱地面积略有增加；受西部开发“生态退耕”政策的影响中西部地区林地面积显著增加,国家退耕还林还草政策成效明显,对区域土地覆盖状况的改善产生积极的影响；这一时段国土开发与区域发展战略的实施,包括“西部大开发”、“东北振兴”等国家重大政策,加之快速的经济发展是该阶段土地利用变化格局形成的主要驱动因素。

Land use and land cover change as the core of coupled human-environment systems has become a potential field of land change science (LCS) in the study of global environment change. Based on remotely sensed data of land use change with the spatial resolution of 1km ×1km on national scale among every five years, this paper designed a new dynamic regionalization according to the comprehensive characteristics of land use including regional differentiation, physical, economic, and macro-policy factors as well. Spatial pattern of land use change and its driving forces were investigated in Chia in the early 21st century. To sum up, land use pattern of this period was characterized by rapid changes in the whole country. Over the agricultural zones,e.g., Huang-Huai-Hai Plains, the southeast coastal area and Sichuan Basin, the built-up and residential areas were considerably expanded to a great proportion in the northwestern oasis agricultural zones and the northeastern zone led to a slight increase of arable land aea in the northern China. Due to the "grain for green" policy, forest area was significantly increased in the middle and western developing region,Where the vegetation coverage was substanially enlarged, likewise. This paper argued the main driving forces as the implementation of the strategy on land use and regional development, such as the "Western Development", "the Revitalization of the Northeast" policy, coupled with rapidly economic development during this period.

露天煤矿开采对区域景观格局、生态过程、生物生境等造成巨大影响,导致矿区生态系统服务功能和价值发生变化。该文以山西省平朔露天煤矿1987年、1996年、2005年和2010年遥感影像数据及矿区未来复垦计划和产业转型规划的相关资料为基础,利用生态系统服务经济价值评估方法,分析了1987-2010年煤炭开采对矿区生态系统的食物生产等生产服务价值和土壤形成与保护、水源涵养、生物多样性维持、气候调节等支持与调节服务价值的影响,并使用在缓冲算子调节下改进的灰色系统GM（1,1）模型预测2010-2020年矿区在产业转型背景下生态系统服务价值的变化。结果表明：受煤矿开采的影响,平朔矿区原地貌土地被大量损毁,导致了矿区生态系统结构受损和生态系统服务价值下降。1987-2010年,平朔矿区5项生态系统服务总价值由9 206.15万元下降到6 688.14万元,年均下降1.19%,其中1987-1996年、1996-2005年、2005-2010年3个阶段生态系统服务价值下降速率分别为15.22%、9.22%、5.61%;预测2010-2020年间,受土地复垦和产业转型升级的影响,矿区生态系统服务价值下降速度趋于缓慢,至2020年矿区5项生态系统服务总价值为6 429.81万元,年均下降0.39%。在露天煤矿开采的不同阶段,应注重通过保护性的矿产开采,科学的地貌重塑、土壤重构、植被重建等技术及生态产业的大力发展来调控矿区生态系统组成、结构和功能,从而提高矿区各项生态系统服务价值。

Open coal mining causes huge impacts on regional landscape patterns,ecological process and biological habitat. It results in changes in mining area ecosystem service functions and values. Here,we used ecosystem service value evaluation methods to analyze the production service values of food production and the support and regulation service values of soil formation and protection,water conservation,biodiversity maintenance,and climate regulation of the Shanxi Pingshuo mining area from 1987 to 2010 based on 1987,1996,2005 and 2010 remote sensing image and future reclamation planning and industry transformation planning. We used a modified gray system GM （1,1） model regulated by buffer operator to predict the changes in mining area ecosystem service values under a background of industry transformation. We found that the landform of Pingshuo mining area has been damaged heavily by coal mining,and led to ecological system structural damage and ecosystem service value decline. Pingshuo mining area’s five ecosystem service values decreased from 92 061 500 CNY to 66 881 400 CNY in 1987-2010; falling by an annual average of 1.19%. The decreased speed of ecosystem service values was 15.22%,9.22%,5.61% for 1987-1996,1996-2005 and 2005-2010. In 2020 under land reclamation and transformation of industrial deepening,the total value of the five ecosystem services will fall to 64 298 100 CNY; falling by an annual average of 0.39% from 2010-2020. Therefore,we suggest that the Pingshuo mining area should control mining area ecosystem composition,structure and function through scientific landform remolding,soil reconstruction,vegetation reconstruction and vigorous development of the ecological industry to improve mining area ecosystem service values.

为揭示东部高潜水位矿区地表水体的时空演变规律，该文以兖州煤田为研究区，在比较改进归一化差异水体指数法、单波段阈值法、谱间关系法、K-T变换4种水体提取方法的精度及优缺点基础上，采用基于阈值分割的改进的归一化差异水体指数法提取了研究区1990－2014年的水体信息并分析了其时空变化特征。研究结果表明：从1990－2009年，兖州煤田地表水域面积增加了1 696.14 hm2，且2001－2005年水域面积扩张速度较快，年均增长率达14.0%，2009－2014年水域面积减少，年均下降率为3%；煤炭开采是研究区内水域面积变化的主要驱动因子。该文实现了煤矿区地表水体变化的动态监测，并分析了其变化原因，有助于客观与定量地评估煤炭开采的生态累积效应。

随机森林方法目前已经成为遥感分类机器学习中一种有效方法,探索基于中等分辨率的Landsat卫星数据与随机森林方法相结合对复杂地形区长时间序列数据的获取及土地利用/土地覆被变化及模拟研究是非常有意义的。本文基于Landsat8OLI卫星多光谱数据,采用随机森林分类方法对青海省湟水流域复杂地形区土地利用类型进行了分类研究。针对复杂地形区域的情况,将研究区进行地理分区,根据每个分区的特点,选择相应的地形特征参数,并通过提取Landsat 8数据的光谱信息与纹理信息构建最优特征集,探索随机森林方法在复杂地形区土地利用分类的适用性。结果表明：使用Landsat8OLI数据进行随机森林分类,能较好地得到湟水流域复杂地形区域的土地利用类型结果;光谱、地形及纹理信息的结合在不同分区的表现结果不同。在脑山区光谱与地形信息结合能使随机森林分类效果最佳,总体精度达到91.33%,Kappa系数为0.886;而在浅山区与川水区综合考虑光谱、地形、纹理信息进行随机森林分类效果最佳,浅山区与川水区总体精度分别达到92.09%和87.85%,Kappa系数分别为0.902和0.859;利用随机森林算法进行优化选择纹理特征组合可以在保证分类精度的同时能够快速地提取土地利用类型信息,为复杂地形区土地利用类型的区分提供了实际可行的方法。

Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, ***, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.]]>

P<0.05）,其中总分类精度和Kappa系数均随影像分辨率的降低而先升高后降低,并于4 m分辨率处达到峰值,该结果与各类地物光谱反射率的空间尺度变化特征密切相关;而不同分类器对各空间尺度影像分类结果的影响程度差异较大（P<0.05）,其中SVM的分类精度最优,MLC次之,ANN的结果较差。此外,伴随影像空间分辨率的降低,不同土地覆被类型面积提取结果的变化规律不同,导致同类地物在不同空间尺度下的提取结果出现较大差异,表明在使用多源分辨率遥感数据进行土地监测等相关研究时,其伴随的结果误差不容忽视。]]>

基于天绘一号(TH-1,或称MS-1)卫星多光谱数据,采用随机森林分类方法(random forests classification,RFC)对位于中亚干旱区的我国新疆维吾尔族自治区阿勒泰地区北屯市及周边区域的土地覆盖进行了分类研究。针对北屯市不透水层与裸土混杂的情况,将纹理特征与植被信息构建最优组合,建立有效的RFC分类器,提高对易混淆土地覆盖类型的分类识别精度。结果表明,采用RFC的分类精度高于最大似然法分类结果,总体分类精度提高了近10%。经过优化选择的特征组合在对干旱区中小城市土地覆盖进行分类时表现良好,能得到较高精度的分类结果,可满足新疆中小城市发展规划对土地覆盖信息的需求。