基于ETM+遥感数据的滨海湿地信息提取研究

以江苏省典型滨海湿地为研究对象,利用2005年5月份的Landsat7 ETM+图像数据,在湿地特征及其遥感图像表征分析的基础上,逐步提高湿地信息的提取精度,通过对多光谱遥感图像特征向量的分析,总结出一些湿地信息提取的规则和方法。在滨海湿地光谱特征分析的基础上,首先对研究区的图像进行了非监督分类,进而利用湿地的光谱相应特征、纹理特征、主成分变换、归一化差异水体指数等特征和相应的知识规则,得到用于优化分类的知识规则,采用分层分类的方法对非监督分类的结果进行了优化,从而使提取结果的精度较原来有了很大程度的提高。     

基于对象和DEM的湿地信息提取——以洪河沼泽湿地为例

湿地资源遥感信息提取并满足一定的分类精度和效率,是湿地研究的关键问题之一。利用高分辨率的SPOT5影像数据,通过对研究区分别进行基于像素的监督分类和基于对象的分类,进行典型沼泽湿地专题信息提取,同时将面向对象分类与DEM辅助数据进行信息复合,探寻提升分类精度的方法。结果表明,基于对象和辅助数据DEM的信息提取,可以有效地改善遥感图像的分类精度。     

基于对象和DEM的湿地信息提取——以洪河沼泽湿地为例

湿地资源遥感信息提取并满足一定的分类精度和效率,是湿地研究的关键问题之一。利用高分辨率的SPOT5影像数据,通过对研究区分别进行基于像素的监督分类和基于对象的分类,进行典型沼泽湿地专题信息提取,同时将面向对象分类与DEM辅助数据进行信息复合,探寻提升分类精度的方法。结果表明,基于对象和辅助数据DEM的信息提取,可以有效地改善遥感图像的分类精度。     

基于决策树方法的淡水沼泽湿地信息提取——以三江平原东北部为例

湿地是生态系统的重要组成部分,及时、准确地获得湿地基础信息,对湿地的动态监测、保护与可持续利用及其它领域的研究具有重要意义。以三江平原东北部沼泽湿地为例,利用分类回归树(Classification and Regression Tree,CART)算法从训练样本数据集中挖掘分类规则,集成遥感影像的光谱特征、纹理特征和地学辅助数据建立研究区湿地信息提取的决策树模型。用实测的GPS样本点对分类结果进行精度验证,并与最大似然监督分类方法(Maximum Likelihood Classification,MLC)进行对比。结果表明,基于CART的决策树分类结果的总精度和Kappa系数分别为82.65%和0.7935,分类精度较MLC监督分类方法有明显提高,是内陆淡水沼泽湿地信息提取的有效手段。     

基于ALOS影像的盐城海滨湿地遥感信息分类方法研究

盐城海滨湿地类型丰富多样,湿地植物覆被类型之间的生态交错带十分明显,如何更为准确地获得海滨湿地覆盖信息,对湿地研究具有重要价值和意义。以ALOS影像为数据源,江苏盐城海滨湿地核心区为试验区,开展湿地信息遥感分类研究。在对研究区进行非监督分类,分析其限制分类精度原因基础上,针对研究区域的特点提出适合的分类精度改进方法。以非监督分类后的结果为模板,借助分区分层分类方法的思想,通过分析遥感影像光谱信息、纹理信息、主成分变换信息,得到知识规则,以基于知识规则修改的方法对芦苇、米草和盐蒿3种植被交错带进行修正。然后以基于GIS规则的方法对剩余区域进行修正。通过GPS数据进行精度检验,分类精度达到92.6829%,Kappa系数为0.9098。实验证明基于GIS规则和知识规则的分区分层分类法是提高海滨湿地遥感分类精度的有效方法。     

基于分层分析的ASTER 影像土地利用/ 覆盖遥感监测研究

以龙海市为实验区, 利用ASTER 遥感数据, 在研究区典型地物光谱特征系统分析的基础上,进行基于分层分类思想的地物分类提取方法研究。首先将影像划分为独立的子区( 水体、植被覆盖区和非植被覆盖区域) 以避免分类过程中光谱的互相影响; 然后在每个独立的子区基础上根据各类地物的不同光谱特征和空间特征, 对各类地物进行逐层掩模、分层提取。结果表明该方法优于传统的监督和非监督分类效果。     

结合自动分区与分层分析的多光谱遥感图像地物分类方法

结合分区与分层的思想,针对多光谱遥感图像,提出一种新的分类方法。在地物光谱分析基础上实现遥感影像的自动分区,然后运用多光谱图像主成份变换前后的地物光谱特征实现地物的分层提取。该分类方法在大庆部分地区地物分类中得到了应用,结果表明,该方法比常规的监督分类在分类精度上有了明显提高。     

基于遥感案例推理的海岸带养殖信息提取

目前基于目视解释或光谱分类的养殖信息提取效率低,难以克服由于地物混杂带来的“椒盐”噪声现象且难以融合地学知识。针对养殖信息提取中存在的问题,首先在分析现有养殖信息提取方法和案例推理CBR(Case\|Based Reasoning)用于遥感图像处理的基础上,提出基于遥感案例推理的海岸带养殖信息提取的研究思路;其次,结合养殖区域的空间特征和属性特征,构建案例的表达模型以及CBR相似性推理模型;最后,对不属于案例构建区的粤西沙田镇进行养殖信息提取的CBR实验,精度达到84.56%。对比CBR方法和传统监督分类方法可知,CBR方法是实现海岸带养殖信息快速准确提取的一种有效手段。     

基于光谱理论的遥感信息提取方法的研究

以东昌府区为例,根据区内各种地物不同的光谱特征,利用遥感光谱分析方法,基于ERDAS IMAGINE平台对东昌府区内各种地物分别用监督分类和非监督分类两种方法进行信息提取,对两种方法进行比较,选择效果比较好的一种对东昌府区遥感信息进行提取研究,并对提取结果进行分析。研究表明,基于光谱理论的遥感信息监督分类提取方法在对东昌府区进行信息提取时更为精确。     

土地覆盖遥感专题信息的分层提取方法及其应用

重点讨论了土地覆盖遥感专题信息的分层提取方法,即根据各类目标的不同特征,采取相应的信息提取方法,分别建立专题信息层,最后把各专题层合并得到整体分类图;在此方案实施过程中,对各类目标开展了野外遥感调查和特征系统分析,并对样本区进行了ＧＰＳ定位,以获取空间辅助信息,提高提取精度;分层提取方法充分考虑到各类目标的不同特点,从而避免了通常分类方法中,单纯利用光谱特征所造成的地物混分现象     

基于多季相Sentinel-2影像的白洋淀湿地信息提取

白洋淀湿地是华北平原上重要的浅水湖泊湿地,对雄安新区绿色发展具有重要的生态价值。对白洋淀高度异质化的景观格局进行分类,能够为白洋淀湿地资源的遥感监测提供指导意义。针对湿地季节变化的特点,对白洋淀每个季节选取一期具有代表性的Sentinel-2影像,采用分类与回归树（CART）、支持向量机（SVM）、随机森林（RF）3种常用的机器学习分类器对15种季相组合实验方案进行分类,分析不同季相遥感影像及其组合对白洋淀湿地信息提取的优劣。结果表明：相较于使用单一季相影像分类,多季相影像的组合能够显著提高分类精度,春&夏季相组合能够得到最优的分类效果,相对单季影像总体分类精度提高了10.9%~25.5%,Kappa系数提高了0.09~0.29;SVM分类器的分类表现较为稳定,能够得到最高的平均分类精度,CART分类器在处理高维特征的能力不如随机森林和SVM;不同特征类型对湿地信息提取的贡献度从高到底依次是红边光谱特征、传统光谱特征、缨帽变换特征、主成分分析特征、纹理特征。实验成果能为湿地信息的遥感识别提供依据。     

Understanding urban wetland dynamics: cross-scale detection and analysis of remote sensing

This study aimed to detect and understand remotely sensed urban wetland dynamics as a sensitive indicator of the combined effects of human disturbances and climate impacts in the course of global change. To address this objective, the study developed technical approaches to detect and interpret wetland changes across spatial scales in complex urban landscapes. Using a series of Satellite Pour l’Observation de la Terre (SPOT) images covering 1992–2010, the study was conducted in the Kansas City metropolitan area of the USA, which has experienced significant urban sprawl in recent decades. As a fine-tuning of the traditional supervised image classification, a knowledge-based classification algorithm was developed to identify fine-scale, hidden wetlands that cannot be appropriately detected based on their spectral differentiability. The analyses of wetland change were implemented at the metropolitan, watershed, and sub-watershed scales as well as being based on the size of surface water bodies in order to reveal real pictures of urban wetland change trends in relation to major driving factors. The results of the study indicated that the knowledge-based classification approach improved the detection capability and accuracy of urban wetlands by fine-tuning the traditional classification results. The cross-scale analysis of detected land covers revealed that wetland dynamics varied in trend and magnitude from metropolitan, watersheds, to sub-watershed scales. The study found that increased precipitation swelled wetlands, which inflated the findings of remotely sensed wetland cover and related trend interpretation. During an 18 year study period, human development activities in the study area resulted in a large increase in impervious surfaces, which was mainly at the expense of farmland/grassland areas and some small wetlands in all urban watersheds. In contrast, increased precipitation in the region swelled large wetlands in particular. This mixed picture of urban wetland dynamics, associated with the analysis of underlying driving factors, provides a new baseline for relevant urban planning, management, and research in a global change perspective.     

遥感监测东北地区典型湖泊湿地变化的方法研究

湖泊湿地生态脆弱,易受环境因子的影响。近十年来,东北地区湖泊湿地的时空格局发生了显著变化。如何简单、有效地提取湿地变化范围进而确定其变化类型是湿地变化检测中最需要解决的问题。基于2006~2016年30 m空间分辨率的Landsat-TM/OLI影像数据,水体、植被和土壤等生态因子的动态变化率被用于提取东北地区湖泊湿地变化范围;多维特征数据集的湿地分类方案确定湿地的变化类型。另外,湿地变化检测类型分为转出类型（湿地减少）,转入类型（湿地增加）和湿地间转换类型（湿地相对稳定）。最终基于动态变化率计算方法,松嫩平原湿地、兴凯湖湿地和呼伦湖湖泊湿地变化结果的正检率均高于90%。同时,利用年内多时相数据和综合多维生态指数共同表征地表的状态变化,实验区的湖泊湿地分类结果的整体分类精度和 Kappa 系数分别达到 84.31%和0.788。湖泊湿地变化检测方法具有很好的检测精度,可以代表研究区湖泊湿地类型的实际变化,是湿地资源调查与遥感监测技术研究的有益补充,为进一步深化与拓宽地表生态质量评价及其动态变化检测的方法研究提供理论基础。     

Comparison of three satellite sensors at three spatial scales to predict larval mosquito presence in Connecticut wetlands

Satellite imagery can be used to identify suitable habitat for mosquitoes in areas inaccessible or lacking sufficient ground-based information about the environment but current applications are limited by the spatial and spectral resolution of the sensors. Here, models used to compare prediction of the presence of Anopheles punctipennis larvae in Connecticut wetlands were built using stepwise logistic regression and compared by Akaike's Information Criterion (AIC). Vegetation indices were extracted from three satellite sensor scenes (Hyperion, ASTER and Landsat-TM) at three scales (pixel, wetland perimeter, and wetland area). The best models were developed using ASTER (ROC = 0.80, p = 0.01, AIC 65.37) and Hyperion (ROC = 0.81, p < 0.01, AIC 66.40) at the wetland area level. The Disease Water Stress Index (DWSI), a measure of leaf water content, and Normalized Difference Vegetation Index (NDVI) were significant in many of the models. This comparison of satellite based models demonstrates higher spatial and spectral resolution of ASTER and Hyperion resulted in more parsimonious models than Landsat-TM models. The need for continued research and development into sensors with increased spatial and spectral resolution and the development of mosquito specific indices is discussed.     

面向滨海湿地的全色/多光谱影像融合方法与应用分析——以杭州湾（1999~2018年）为例

影像融合在滨海湿地遥感监测中具有重要作用,然而滨海湿地区域多以水体、植物等为主,地物复杂多变,导致现有融合方法易产生光谱畸变且鲁棒性往往较差,难以满足滨海湿地的长时序动态监测需求。为此,提出基于空—谱质量评价的全色/多光谱影像融合方法SSQI_ PANSHARP,所提融合模型以融合影像的空—谱质量评价为导向,集成多种融合方法在空间增强和光谱保真方面的互补优势,满足滨海湿地长时序遥感监测对融合方法鲁棒性的需求。以杭州湾滨海湿地为研究区域,利用1999~2018年Landsat-7、Landsat-8卫星20年影像数据,从定性、定量以及滨海湿地典型地物光谱指数NDVI、NDWI等多方面,对提出方法进行充分验证,并在此基础上均匀抽取相近季度3期数据,对杭州湾滨海湿地近20年间土地覆盖类型,进行宏观长时序动态监测分析。研究结果表明,SSQI_PANSHARP方法在滨海湿地区域中的光谱保真度、空间结构信息增强效果表现较好,且鲁棒性强,适合于滨海湿地的长时序监测需求。监测结果显示,杭州湾南岸滨海湿地2010年后建筑用地比例上升,区域内池塘水田明显增加,农田绿地有所下降。     

Mapping an inland wetland complex using hyperspectral imagery

The goal is to determine the extent to which heterogeneous inland wetland vegetation communities and their dominant species, as well as adjacent upland vegetation types, can be mapped using 4‐m hyperspectral Compact Airborne Spectrographic Imager (CASI) data. Two classification algorithms, the maximum‐likelihood classifier (MLC) and the spectral angle mapper (SAM), are applied to CASI data acquired over an inland wetland complex located in southern Ontario, Canada. Application of the MLC algorithm to all bands of the CASI data produced better classification results than use of the SAM. Using the MLC, 10 classes were identified with an overall accuracy of 92%. This approach permitted differentiation between areas of shrub‐dominated vegetation communities, floating aquatic communities, emergent aquatics and shallow open water. In the SAM classification, 11 image‐derived spectral endmembers were generated. Wetland classes identified were shrub‐dominated wetlands, floating aquatic vegetation communities, shallow open water and moderately turbid shallow open water. Upland vegetation types were accurately mapped with both algorithms. Reasons why the SAM did not perform as well as the MLC in this complex environment are suggested. It is concluded that high‐resolution hyperspectral data can provide information needed by wetland managers about inland wetland plant communities and their dominant species.     

A spectral library for a semi-arid wetland and its application to studies of wetland degradation using hyperspectral and multispectral data

Semi-arid wetland areas in Central Spain are especially sensitive ecosystems and are considered to be one of the most important areas for the migration and wintering of waterfowl in Europe. Many of these wetland areas are saline or sub saline and are subjected to natural (seasonal) as well as human induced changes. Factors causing changes that significantly alter or modify the ecological function of these wetlands are considered to be degradation processes. The use of hyperspectral and multispectral data together with ground spectra and field studies has a great potential for monitoring wetland conditions. In this work spectral and analytical information concerning soil, vegetation and land use, contained in a site specific spectral library, is linked with the spectral characteristics of components from an anthropogenic influenced wetland area in La Mancha Alta. This information forms the basis for determining and selecting end members from hyperspectral data (DAIS 7915), which are then extrapolated to lower spatial and spectral resolution multispectral Landsat ETM+ and TM data. A spectral unmixing is carried out to obtain a multitemporal analysis for evaluating wetland degradation. Results show that the approach is successful in determining rapid surface change due to anthropogenic influences. Spectral unmixing results present an increase of salt-affected soil and a redistribution of saline pasture. This is further supported with a post classification change detection assessment and ground data confirm that principal causes are changes in wetland use together with water regulation of the Cigüela river.     

Nontidal wetland mapping in South Carolina using airborne multispectral scanner data

High resolution multispectral scanner (MSS) imagery of Savannah River nontidal wetlands were analyzed to identify 1) useful spectral bands for discriminating among National Wetland Inventory classes, 2) where the classes cluster in n-dimensional feature space, and 3) what wetland classification accuracies can be expected. Spectral measurements in the green (0.55–0.60 μm), red (0.65–0.70 μm), and near-infrared wavelengths (0.70–0.79 μm and 0.92–1.10 μm) provided the most useful information. Emergent marsh (both persistent and nonpersistent), scrub-shrub, mixed deciduous swamp forest, and mixed deciduous upland forest were found to cluster in somewhat predictable regions of 2- and 3-dimensional feature space. The overall classification accuracy of the Steel Creek delta study area was 83% and was assessed by comparing the remote sensing derived thematic map with 1325 linear meters of transects sampled in situ. These results suggest that high resolution aircraft MSS data can provide detailed vegetation type information for mapping both thermally affected and rejuvenating nontidal wetland in the South Carolina Savannah River Swamp System.