基于地学知识的大尺度土地利用/土地覆盖精细化分类方法研究

人类活动对生态环境具有显著影响,大尺度土地利用/覆盖变化（Land Use/Cover Change,LUCC）作为人类活动最直接的表征,能够很好地反映这一过程,因此进行精确而迅速的大尺度土地利用/覆盖分类与提取方法研究尤为关键。全球覆盖产品GlobCover（2005/2006）数据已经具有良好的空间精度和数据准确度,但仍然存在一些分类误差。为提高地表覆被分类精度,本文以GlobCover（2005/2006）的巴西数据为例,以2005年Landsat TM/ETM影像为主要信息源,结合相应地学知识与辅助数据,利用人机交互逐栅格修改方法得到2005年土地利用数据产品。结果表明：通过对GlobCover数据和本次成果数据进行精度评价与对比分析,GlobCover数据巴西地区的总体精度为67.17%,Kappa系数为0.58,改进后产品总体精度为93.39%,Kappa系数为0.91。此外,改进后数据显示巴西常绿阔叶林面积最大,面积比例达45.67%;农地/自然植被镶嵌面积次之,比例为19.19%;封闭灌丛面积最小,比例为12.34%。农地/自然植被镶嵌和灌丛与草地2种地类的修改比例最大,其中混合像元地类比例减少3.54%,灌丛与草地比例增加3.81%。综上,改进方法可以有效地提高土地利用/覆盖分类的效率和精度,为后续大尺度LUCC产品的制作和以LUCC产品为基础的相关研究提供参考。     

土地覆盖的图像融合动态监测

近20年来,关于图像融合应用分析方法,如HIS,PCS,HPF,SFIM,SVR,Wavelet和Brovey等均有新的进展。本文主要是对不同时相的影像进行融合,如Brovey-融合法将不同时相的TM(1986年7月26日)和ETM+(2000年5月4日)的PAN波段影像进行融合,然后对其采用非监督分类和PCS分析,将两时相的土地覆盖变化区域提取出来。同时将两时相影像,用后分类法进行分类提取出变化区域。研究表明融合法具有快速、简便和准确的特点。     

Effects of RapidEye imagery’s red-edge band and vegetation indices on land cover classification in an arid region

Land cover classification (LCC) in arid regions is of great significance to the assessment, prediction, and management of land desertification. Some studies have shown that the red-edge band of RapidEye images was effective for vegetation identification and could improve LCC accuracy. However, there has been no investigation of the effects of RapidEye images’ red-edge band and vegetation indices on LCC in arid regions where there are spectrally similar land covers mixed with very high or low vegetation coverage information and bare land. This study focused on a typical inland arid desert region located in Dunhuang Basin of northwestern China. First, five feature sets including or excluding the red-edge band and vegetation indices were constructed. Then, a land cover classification system involving plant communities was developed. Finally, random forest algorithm-based models with different feature sets were utilized for LCC. The conclusions drawn were as follows: 1) the red-edge band showed slight contribution to LCC accuracy; 2) vegetation indices had a significant positive effect on LCC; 3) simultaneous addition of the red-edge band and vegetation indices achieved a significant overall accuracy improvement (3.46% from 86.67%). In general, vegetation indices had larger effect than the red-edge band, and simultaneous addition of them significantly increased the accuracy of LCC in arid regions.     

吉林西部盐碱地数字图像植被覆盖度的自动提取

植被覆盖度是生态环境变化的重要指标,也是遥感反演的关键参数。盐碱地植被覆盖度的准确测量对研究地表植被蒸腾、土壤水分蒸发及土壤退化、盐碱化等具有重要意义。过绿指数(Excess Green index,ExG)对绿色植被比较敏感,能突显植被信息,去除土壤、阴影的干扰。通过对吉林西部盐碱地玉米、高粱、绿豆、杂草、土壤数字图像特征分析,利用改进过绿指数(Modified Excess Green index,MExG)算法计算植被和土壤的MExG值;并确定区分植被和土壤的MExG阈值为40,进而计算植被覆盖度。本文采用监督分类的最大似然法对比验证MExG自动提取结果,并对两种方法计算的玉米、高粱、绿豆和杂草的覆盖度,分别进行目视判读和t检验。研究表明,MExG自动提取方法具有客观性强,处理时间短,分类精度高等优点,是计算不同植被类型覆盖度的有效方法。     

基于深度学习的高分辨率遥感影像土地覆盖自动分类方法

土地覆盖变化是全球变化研究的核心,而精准分类是开展土地覆盖变化研究的基础。高分辨率遥感卫星技术的快速发展对地表分类的速度和精度提出了双重挑战,近年来人工智能等新技术的发展为图像自动分割提供了实现途径,而以卷积神经网络为代表的深度学习方法在遥感图像分类领域也具有独特的优势。为对比深度学习模型设计对高分辨率图像分类结果的影响,本文以郑州市2019年高分1号影像作为输入,对比研究了基于UNet模型改进的4种不同深度学习网络模型在高分辨率影像土地覆盖自动分类应用中的差异,探讨了残差网络、模型损失函数、跳层连接和注意力机制模块等编码和解码设定对于分类精度的影响机制。研究发现：同时加入多尺度损失函数、跳层连接和注意力机制模块的MS-EfficientUNet模型对郑州市土地覆盖分类结果最优,基于像元评价的整体分类精度可达0.7981。通过在解码器中引入多尺度损失函数可有效提高林地、水体和其他类别的分类精度;而对编码器进行改进,加入跳层连接和注意力机制可进一步提高草地、水体和其他类别地物的分类精度。研究结果表明,深度学习技术在高分辨率遥感影像自动分类中具有潜在应用价值,但分类结果精度的进一步提高和多级别大范围的精细分类方法仍是下一步研究的重点。     

基于决策树方法的蒙古高原土地覆盖遥感分类——以蒙古国中央省为例

蒙古高原包括蒙古全部、俄罗斯南部和中国北部部分地区。蒙古高原的土地利用/覆盖格局与变化,对揭示该区域乃至整个东北亚地区的资源、环境和生态特征,促进该区域可持续发展具有重要的现实和科学意义。本文以在蒙古国中央省及其所含首都乌兰巴托市为研究区,利用空间分辨率为30 m的TM影像,采取QUEST(Quick Unbiased and Efficient Statistical Tree)决策树方法,通过图像目视解译,获取了研究区2010年土地覆盖分类数据。结果显示,草地占据研究区总面积的70.88%,其次是森林占14.83%、裸地占10.73%、农田占2.98%、水体占0.31%、建筑用地占0.27%、湿地占0.02%。通过野外实地采集的139个GPS验证点进行精度评价发现,一级土地覆盖类型的总体精度可达72.66%。针对草地的二级分类的总体精度有较明显下降,其主要是由于中蒙科学家对于草地类型分类体系的差异所造成的典型草地和荒漠草地的混分。     

江西省都昌县山地与平原植被界线提取

由于生长环境、地带性分布规律和垂直差异,山地与平原地区的不同植被类型在遥感影像上存在“同物异谱”及“异物同谱”现象,易导致土地类型的误分。为避免此类错分,在进行土地覆被类型解译之前,应首先确定平原、山地植被的边界。本文在遥感影像聚类分析、GIS空间分析及数理统计分析技术的支持下,以江西省都昌县北部地区为研究区域,基于高分一号（GF-1）遥感卫星影像及地形要素,完成了山地植被与平原植被的界线提取。实验结果显示,本研究得到的植被界线精度高达99.47%和96.28%。与单纯基于遥感影像分类得到的植被边界成果相比,精度提高了近25%和23%。研究证明,高分辨率遥感影像与地形因子结合后,计算得到的山地平原划分界线精度有明显提高,可以满足高分辨率遥感影像土地覆被类型解译研究的需要。     

Spatial assessment of forest cover and land-use changes in the Hindu-Kush mountain ranges of northern Pakistan

Anthropogenic activities and natural processes are continuously altering the mountainous environment through deforestation, forest degradation and other land-use changes. It is highly important to assess, monitor and forecast forest cover and other land-use changes for the protection and conservation of mountainous environment. The present study deals with the assessment of forest cover and other land-use changes in the mountain ranges of Dir Kohistan in northern Pakistan, using high resolution multi-temporal SPOT-5 satellite images. The SPOT-5 satellite images of years 2004, 2007, 2010 and 2013 were acquired and classified into land-cover units. In addition, forest cover and land-use change detection map was developed using the classified maps of 2004 and 2013. The classified maps were verified through random field samples and Google Earth imagery (Quick birds and SPOT-5). The results showed that during the period 2004 to 2013 the area of forest land decreased by 6.4%, however, area of range land and agriculture land have increased by 22.1% and 2.9%, respectively. Similarly, barren land increased by 1.1%, whereas, area of snow cover/glacier is significantly decreased by 21.3%. The findings from the study will be useful for forestry and landscape planning and can be utilized by the local, provincial and national forest departments; and REDD+ policy makers in Pakistan.     

基于“DEM-NDVI-土地覆盖分类”的天山博格达自然遗产地山地垂直带提取与变化分析

本文基于Landsat影像数据获取天山博格达自然遗产地土地覆盖分类,结合归一化植被指数（NDVI）和数字高程模型（DEM）构建“DEM-NDVI-土地覆盖分类”散点图分析研究区植被受海拔和坡向的水热空间变化影响的分布特征,通过概率统计分析提取博格达遗产地山地垂直带,并结合研究区的气温、降水数据和NDVI变化特征分析垂直带变化的原因。研究结果表明：① 本文利用“DEM-NDVI-土地覆盖分类”散点图,揭示了研究区1989年和2016年的NDVI值和分类类别随着海拔上升的变化特征,其中NDVI值随着海拔上升呈现“倒U形”变化,而不同分类类别在一定的海拔区间内呈现出聚集效应,且不同分类类别有明显的高程界限。② 1989年和2016年博格达遗产地山地垂直带分带上限分别为：1278 m和1185 m（温带荒漠草原带）、1784 m和1759 m（山地草原带）、2706 m和2730 m（山地针叶林带）、3272 m和3293 m（高山草甸带）、3636 m和3690 m（高山垫状植被带）。③ 博格达遗产地1989年和2016年山地垂直带受区域气温升高和降雨增加的影响有较为明显的改变,其中温带荒漠草原带最为敏感,其上限变化最大,向下收缩93 m;山地针叶林带的分布范围则向两侧扩张49 m;山地草甸带带宽基本保持不变,但整体上移了约20 m;冰雪带则受到全球气候变暖的影响向上退缩54 m。     

Spatio-temporal distribution of vegetation index and its influencing factors——a case study of the Jiaozhou Bay,China

The coastal zone is an area characterized by intense interaction between land and sea, high sensitivity to regional environmental changes, and concentrated human activities. Little research has investigated vegetation cover changes in coastal zones resulting from climate change and land-use change, with a lack of knowledge about the driving mechanism. Normalized diff erence vegetation index(NDVI) can be used as an indicator for change of the coastal environment. In this study, we analyzed the interannual changes and spatial distribution of NDVI in the coastal zone around Jiaozhou Bay in Qingdao, a coastal city undergoing rapid urbanization in northeast China. The underlying causes of NDVI variations were discussed in the context of climate change and land-use change. Results showed that the spatio-temporal distribution of NDVI displayed high spatial variability in the study area and showed a typical trend of gradually increasing from coastal to inland regions. The significant increase area of NDVI was mainly found in newly added construction land, extending along the coastline towards the inland. Land vegetation cover demonstrated a certain response relationship to sea-land climate change and land-based activities. The impact of land-based human activities was slightly greater than that of sea-land climate change for land vegetation cover. The results indicate that promoting ecological policies can build an ecological security framework of vegetation suitable for the resource characteristics of coastal cities. The framework will buf fer the negative ef fects of sea-land climate change and land-based human activities on vegetation cover and thereby achieve the balance of regional development and ecological benefits in the coastal zone.     

Land use and land cover change within the Koshi River Basin of the central Himalayas since 1990

Land change is a cause and consequence of global environmental change.Land use and land cover have changed considerably due to increasing human activities and climate change,which has become the core issue of major international research projects.This study interprets land use and land cover status and the changes within the Koshi River Basin(KRB)using Landsat remote sensing(RS)image data,and employs logistic regression model to analyze the influence of natural and socioeconomic driving forces on major land cover changes.The results showed that the areas of built-up land,bare land and forest in KRB increased from 1990 to 2015,including the largest increases in forest and the highest growth rate in construction land.Areas of glacier,grassland,sparse vegetation,shrub land,cropland,and wetland all decreased over the study period.From the perspective of driving analysis,the role of human activities in land use and land cover change is significant than climate factors.Cropland expansion is the reclamation of cropland by farmers,mainly from early deforestation.However,labor force separation,geological disasters and drought are the main factors of cropland shrinkage.The increase of forest area in India and Nepal was attributed to the government’s forest protection policies,such as Nepal’s community forestry has achieved remarkable results.The expansion and contraction of grassland were both dominated by climatic factors.The probability of grassland expansion increases with temperature and precipitation,while the probability of grassland contraction decreases with temperature and precipitation.     

国土调查遥感40年进展与挑战

运用遥感技术进行土地资源调查,摸清其数量及分布状况,长期以来都是遥感领域研究的重要内容。本文首先回顾了过去40年来遥感技术在我国国土调查中的应用情况,然后围绕高分辨率影像的特征提取、大范围影像的样本获取、多时相/多传感器影像的迁移学习以及多源异构数据融合4个方面介绍了相关进展情况;接着归纳总结了现有遥感信息提取技术在国土调查中面临的4个挑战：① 高分辨率影像分类存在如何定义、选择、挖掘高级特征的问题;② 国土调查中的遥感数据集规模庞大,存在着类间不平衡和类内多样性,为这种复杂数据集获取足够、均衡、多样化的样本集是一个巨大挑战;③ 对于多传感器/多时相影像,如何低成本、及时地实现土地利用分类是值得考虑的问题;④ 从土地覆盖到土地利用存在语义鸿沟,如何合适地引入语义信息以弥合语义鸿沟需要被考虑。最后,本文对国土调查遥感技术的未来发展方向和应用点进行了展望。     

High resolution land cover datasets integration and application based on Landsat and Globcover data from 1975 to 2010 in Siberia

Land cover is recognized as one of the fundamental terrestrial datasets required in land system change and other ecosystem related researches across the globe. The regional differentiation and spatial-temporal variation of land cover has significant impact on regional natural environment and socio-economic sustainable development. Under this context, we reconstructed the history land cover data in Siberia to provide a comparable datasets to the land cover datasets in China and abroad. In this paper, the European Space Agency(ESA) Global Land Cover Map(GlobCover), Landsat Thematic Mapper(TM), Enhanced Thematic Mapper(ETM), Multispectral Scanner(MSS) images, Google Earth images and other additional data were used to produce the land cover datasets in 1975 and 2010 in Siberia. Data evaluation show that the total user′s accuracy of land cover data in 2010 was 86.96%, which was higher than ESA GlobCover data in Siberia. The analysis on the land cover changes found that there were no big land cover changes in Siberia from 1975 to 2010 with only a few conversions between different natural forest types. The mainly changes are the conversion from deciduous needleleaf forest to deciduous broadleaf forest, deciduous needleleaf forest to mixed forest, savannas to deciduous needleleaf forest etc., indicating that the dominant driving factor of land cover changes in Siberia was natural element rather than human activities at some extent, which was very different from China. However, our purpose was not just to produce the land cover datasets at two time period or explore the driving factors of land cover changes in Siberia, we also paid attention on the significance and application of the datasets in various fields such as global climate change, geopolitics, cross-border cooperation and so on.     

基于ISO元数据扩展模型的土地覆盖遥感分类体系框架研究

由于研究主题和应用目的的不同,国内外已经存在和正在产生着越来越多的遥感数据源的土地覆盖分类体系。这不仅使得分类体系缺乏可扩展性与互操作性,而且使得不同分类体系的土地覆盖数据难以对比、交换和集成。本文借鉴ISO 19115地理信息元数据的扩展经验,设计了基于ISO元数据扩展模型的土地覆盖分类体系框架,并研究其动态扩展方法。提出一种包括核心分类、全集分类和专题应用分类的三层土地覆盖可扩展分类体系框架。其中,核心分类是从国内外主要的土地利用/覆盖分类系统中抽取的共性分类元素;全集分类收集全部可能的土地覆盖分类元素;专题应用分类通过对核心分类的继承,和对全集分类的裁剪和扩展生成。该分类框架将为土地利用/覆盖的研究和应用提供一种科学的、可比的动态分类扩展模型和方法。     

Dynamics of land use change in a mining area: a case study of Nadowli District,Ghana

In a developing country like Ghana, the study of land use and land cover change(LULCC) based on satellite imageries still remains a challenge due to cost, resolution and availability with less skilled man power. Existing researches are skewed towards the southerly part of Ghana thereby leaving the Northern sectors uncovered. The maximum likelihood classification(MLC) algorithm was employed for the LULCC between 2000 and 2014 in Nadowli: an area characterized by an upsurge in mining in the Northern belt of Ghana. A spatial-social approach was utilized combining both satellite imagery and socio economic data. Land use transition matrix, land use integrated index/degree indices was used to depict the characters of the change. A semi structured interview, pair wise ranking and key informant interviews were used to correlate the socio economic impact of the different LULC. Overall changes in the landscape showed an increase in bare ground by 19.22%, open savannah by 16.8% whereas closed savanna decreased by 50%. Land use change matrix showed increasing trends of bare ground at the expense of vegetation. The integrated land use index highlighted the bare ground and built up areas rising with a decreasing closed vegetation woodlot. Large farm size are shrinking whiles majority of the people view mining as the main socio economic activity affecting the environment and the reduction in vegetation. This study therefore provides a strategic guide and a baseline data for land use policy actors in the Northern belt of Ghana. This will aid in developing models for future land use change implications in surrounding areas where mining is on the rise.     

干旱荒漠区植被覆盖变化的遥感监测分析

多期的遥感数据可以用来分析干旱荒漠区植被的空间分布格局和变化特征。本文以1989、2000和2007年3个不同时相的Landsat TM/ETM+影像为数据源,利用线性光谱混合分析和RGB彩色合成法构建一个研究框架,对古尔班通古特沙漠西缘进行植被信息的提取和变化监测分析。在混合像元分解过程中,通过多种方法选择端元,比较...     

泛北极地区植被数据集与制图：回顾与展望

泛北极地区位于北半球高纬度地区,主要属于低温限制型生态系统,因而泛北极地区植被对全球变暖敏感。要明确泛北极地区陆地生态系统对全球变暖响应过程和机理,就需要高精度的植被类型分类数据作为基础资料。但是,目前泛北极地区植被数据的结果还不完善。为更好地认识泛北极地区植被类型分类的现状、发展历史和未来研究方向,本文综述了泛北极地区植被类型制图的数据来源、植被类型划分方法和植被类型制图研究方法。总体而言,泛北极地区的植被调查从20世纪20年代就陆续开展,目前部分区域尺度上的地表覆盖类型的结果,但具体的植被类型制图工作还存在一系列难题。主要原因包括植被野外调查实测数据较少和分布不均、植被类型分类标准不一、苔原植被群落的异质性大、制图技术和分类算法优化困难等。因此,在下一步泛北极植被类型制图工作中,需要制定标准化分类策略,规范数据获取及数据库的整理工作,并发展新的制图方法,从而促进植被类型制图研究工作。     

基于NDVI的三峡大坝岸边植被时空特征分析

三峡工程建设对生态系统中植被的破坏很明显,尤其是岸边带附近。本文基于多时相遥感图像,采用NDVI序列计算植被覆盖度,通过比较三峡大坝蓄水前后1978、1999、2006年3个时期坝区9月份岸边3km缓冲区的植被覆盖度特征、动态变化,描述了研究区各年份植被覆盖分布以及近30年的植被覆盖变化特征;同时,从面积角度定量,采用分级分析了变化大小,并应用统计学的非参数Wilcoxon秩和检验方法对不同时期、不同土地利用类型的覆盖度样本进行了检验,得到如下结论:近30年间,三峡大坝岸边带植被覆盖变化显著,1978～1999年时间段,由于大坝工程建设植被破坏程度较高,有植被覆盖的区域面积下降了3.31km²;1999年至2006年时间段,在有8km²的淹没区情况下,有植被覆盖的区域仅下降1.57km²,说明植被恢复较明显。近30年间,三峡大坝植被覆盖度整体上有增加的趋势。     

京津风沙源区生态环境时空变化的遥感监测分析

本文利用由遥感影像解译获得的土地利用数据和MODIS NDVI产品,采用空间转移矩阵、最大值合成法、均值法和一元线性回归模拟等方法,分析了2000年以来京津风沙源区生态环境变化的时空特征.结果表明:(1)2000-2005年京津风沙源区耕地开垦、林草地减少的趋势有所减缓,但区域气候变化趋于干旱,水域面积明显减少,草地退...     

土地利用与土地覆被时空动态变化分析——以岷江上游地区为例

全面、客观地反映土地动态变化有利于正确认识对土地资源的开发和利用,能为地区产业结构调整,制定可持续发展的土地管理和土地规划提供依据。多时相遥感数据已经被成功运用于研究土地变化,评估前期政策对环境和土地利用的影响^[1～5]。在遥感和GIS技术支持下,分析了岷江流域上游地区的土地利用/土地覆被状况及其1986～2000年的时空动态变化和驱动力影响。为保护该地区有限的珍贵林业资源,恢复长江上游的生态屏障作用和国土资源的有效可持续利用提供决策依据。