三峡库区岩性智能分类研究

三峡库区岩体上方覆盖着厚实的土壤和茂密的植被,是高植被覆盖区,岩性信息弱,因此岩性识别和分类困难,没有成熟的方法可循。针对三峡库区进行岩性分析,选择三峡库区巴东城区作为研究区域,采用2000年5月成像的ETM+遥感影像,构造纹理、光谱、植被覆盖等17个分类因子,将遥感影像与地质图叠加,选取1 101个样本点,采用决策树C4.5算法,挖掘出三峡库区巴东县处岩性的解译规则和知识,决策树的学习精度为96.6%,剪枝后精度为95.9%,规则提取的精度为93.1%,提取的规则置信度很高,并基于知识驱动和规则匹配实现了岩性的智能分类,分类精度较高为90.11%;将分类结果与IsoData方法、K-Means方法、马氏距离法、最大似然法、最小距离法、平行六面体方法等6种方法的分类结果进行比较,试验结果证明,决策树方法的分类结果最好,精度明显高于其他6种方法。     

基于PCA+RBF的多光谱卫星遥感影像分类

多光谱卫星遥感影像具有波段多,信息量大的特点,传统的分类方法难以达到比较高的精度.这里首先采用主成份分析对多波段遥感图像进行降维,再采用训练后的RBF(radial basis function)神经网络做图像的监督分类.通过对ETM 的遥感数据进行实验,结果表明,这种分类方法的分类精度,明显优于最大似然法、最小距离法等传统的分类方法.同时,与基于像元的RBF神经网络法相比,也有一定的优势.     

利用粗糙集理论进行遥感分类信息提取

以辽宁省双台子河口湿地为研究对象,以Landsat 8和HJ-1-A/HJ-1-B的多时相遥感影像为数据源,根据研究区现状,将研究区分为旱地、芦苇、水田、碱蓬、混合植被、水面、滩涂、居民点、养殖塘九个类型.利用时间序列的归一化植被指数提取植被与非植被的分类阈值,采用粗糙集理论和多时相遥感影像,对植被和非植被分别进行分类规则的获取,建立了研究区决策树分类模型.为了进行精度评价,利用相同的训练点又进行了同样基于像元的最大似然法分类.最后利用混淆矩阵对上述两种方法进行了精度评估,基于粗糙集的决策树分类法与最大似然法总体分类精度分别为93.70%和91.62%,Kappa系数分别为0.92和0.90,两项指标值基于粗糙集理论法均比最大似然法有所提高.这为构建决策树分类模型进行湿地地表分类信息提取提供了一条新的研究思路.     

面向对象的喀斯特地区石漠化遥感信息提取研究——以贵州省大方地区为例

针对现有基于像素的监督和非监督分类方法在地质环境复杂、地形起伏较大、阴影明显的喀斯特石漠化地区难以满足石漠化信息提取精度要求的问题,采用基于纹理特征数据和地形数据辅助面向对象方法进行喀斯特地区石漠化信息的提取。该方法首先依据石漠化分布在TM/ETM+影像面积大小不均匀的特征,利用纹理和地形因子计算最优分割参数进行多尺度分割;然后根据植被覆盖率、岩石裸露率以及坡度因子构建石漠化分级指标;最后参照石漠化分级标准、光谱信息以及纹理特征等建立的分类规则提取喀斯特地区石漠化信息。选取贵州省石漠化严重的大方县时序TM/ETM+影像进行石漠化信息提取试验,结果表明:与基于像素的监督分类和非监督分类方法相比,基于面向对象的分类可以有效地减少因复杂地形导致石漠化信息提取结果"椒盐化"现象,提取精度明显优于基于像素的监督分类和非监督分类方法。      

ETM影像小波变换数据融合在土地利用中的分类研究

在ERDAS软件支持下,对ETM遥感影像数据的TM1—TM5,TM7与其全色波段TM8进行小波变换融合,对融合后的影像采用混合分类方法进行土地利用分类。并对其分类结果进行评价,总体精度达到95.43%,研究结果表明此方法可行有效。     

若尔盖高原地物遥感分类

各种物质在遥感数据中都有其特征的波谱吸收峰。因此通过波谱识别就可以大大减少以往遥感分类方法中的漏分及混分现象。为了解决若尔盖高原地物遥感分类问题,首次对本区ETM多光谱融合数据采用了地物波谱角分类法进行地物识别。分类步骤:遥感数据定标→选择训练区样本→MNF变换减维去噪处理→利用纯净像元指数(PPI)进行样本提纯→利用n-D散度法进行样本重组→波谱角分类(SAM).其分类结果表明,类别精度评价总精度为0.806,kappa系数为0.785.其精度均符合1:5万比例尺的土地详查工作的技术要求。      

运用LANDSAT ETM+和ASTER数据进行岩性分类

本文评价了运用ASTER和LANDSAT ETM+数据进行岩性制图的性能。分别利用ASTER数据不同波段区图像及其组合,以及ETM+数据进行岩性分类,并探讨了将ASTER和ETM+数据叠加在一起进行了岩性分类; 利用现有地质图对所有分类结果进行了定量评价。结果表明,ASTER数据不同波段的岩性识别能力不同,并且较ETM+数据能更准确地识别岩性。更重要的是,把ASTER与ETM+数据结合在一起进行岩性分类,可获得比用任一数据单独分类更高的分类精度,表明二者的光谱特征具有一定的互补性。     

基于遥感信息提取技术的泰国铜金矿成矿预测

以泰国铜金热液型矿区为例,根据地质异常理论、典型铜金矿成矿模式,利用ETM+遥感影像、地质图、矿产地质数据库等多元地学数据,结合GIS技术,提取研究区地质(地层、构造)、遥感(羟基、铁染蚀变信息和线环构造)等致矿信息,采用证据权法对该区铜金矿进行成矿预测,并结合研究区主要控矿地质要素,圈定研究区铜金找矿有利地段,为该地区的找矿工作提供参考。     

基于光谱—空间特征的ASTER影像岩性分类研究——以甘肃北山白峡尼山地区为例

遥感岩性制图是地质填图中的重要工作,基于光谱特征的岩性分类易受到色调、纹理等因素影响导致精度不佳。前人进行岩性自动分类研究多关注影像的光谱特征,而忽略空间特征,笔者等基于甘肃北山白峡尼山地区ASTER影像,将支持向量机、极限学习机两种机器学习分类方法与基于空间特征的快速漂移算法相结合进行岩性分类。结果表明支持向量机分类总体精度为89. 17%;极限学习机不但具有需调节参数少的优势,且分类精度和速度均优于支持向量机,分类总体精度达96. 70%;利用快速漂移算法提取的影像空间特征可有效减少错分区,提升岩性分类效果。研究证实将基于光谱特征的极限学习机和基于空间特征的快速漂移算法结合的岩性分类方法具有客观、高效、高精度等优势,可为后续地质填图和找矿勘查工作提供可靠数据支撑,在遥感岩性分类领域具有较高的推广价值。     

基于光谱—空间特征的ASTER影像岩性分类研究——以甘肃北山白峡尼山地区为例

遥感岩性制图是地质填图中的重要工作,基于光谱特征的岩性分类易受到色调、纹理等因素影响导致精度不佳。前人进行岩性自动分类研究多关注影像的光谱特征,而忽略空间特征,笔者等基于甘肃北山白峡尼山地区ASTER影像,将支持向量机、极限学习机两种机器学习分类方法与基于空间特征的快速漂移算法相结合进行岩性分类。结果表明支持向量机分类总体精度为89.17%;极限学习机不但具有需调节参数少的优势,且分类精度和速度均优于支持向量机,分类总体精度达96.70%;利用快速漂移算法提取的影像空间特征可有效减少错分区,提升岩性分类效果。研究证实将基于光谱特征的极限学习机和基于空间特征的快速漂移算法结合的岩性分类方法具有客观、高效、高精度等优势,可为后续地质填图和找矿勘查工作提供可靠数据支撑,在遥感岩性分类领域具有较高的推广价值。     

利用证据权法实现滑坡易发性区划

依托“5.12”特大地震的抗震救灾工作,以汶川地震12个极重灾县市为研究对象,在1:5万滑坡详细调查、编录和遥感影像解译的基础上,利用DEM数据,ETM影像及基础地质数据,使用证据权法完成了研究区滑坡易发性评价因子的提取与制图以及相关性统计分析,实现了1:5万的滑坡易发性区划。     

Identification and mapping of some soil types using field spectrometry and spectral mixture analyses: a case study of North Sinai, Egypt

This study examines linear spectral unmixing technique for mapping the surface soil types using field spectroscopy data as the reference spectra. The investigated area is located in North Sinai, Egypt. The study employed data from the Landsat 7 ETM+ satellite sensor with improved spatial and spectral resolution. Mixed remotely sensed image pixels may lead to inaccurate classification results in most conventional image classification algorithms. Spectral unmixing may solve this problem by resolving those into separate components. Four soil type end-members were identified with minimum noise fraction and pixel purity index analyses. The identified soil types are calcareous soils, dry sabkhas, wet sabkhas, and sand dunes. Soil end-member reference spectra were collected in the field using an ASD FieldSpec Pro spectrometer. Constrained sum-to-one and non-negativity linear spectral unmixing model was applied and the soil types map was produced. The results showed that linear spectral unmixing model can be a useful tool for mapping soil types from ETM+ images.     

Utilization of supervised classification in structural and lithological mapping of Wadi Al-Marwah Area,NW Arabian Shield,Saudi Arabia

Wadi Al-Marwah area is located in the northwestern part of the Arabian Shield, Saudi Arabia. It is mainly covered by Precambrian igneous and sedimentary rock units. This area was not subjected to previous detailed lithological or structural mapping. This study aims to apply supervised classification technique of remotely sensed digital satellite data of Landsat 7 for detailed lithological and structural mapping of the area. The fusion between multispectral Enhanced Thematic Mapper (ETM)+ data and high-resolution panchromatic ETM+ band-8 produced a color composite fused image for the study area, scale 1:50,000. The structural lineaments of the study area were extracted and interpreted from the digital imageries data. Little discrepancies or improvements were detected when combining the supervised classification results with the Landsat ratios or principal component analysis. These highlighted the benefits of multispectral classification, especially in terms of lithologic discrimination. The overall results of image processing techniques, applied in this work, were excellent and succeeded in the performance of a more detailed and accurate lithological and structural maps (scale 1:50,000) than the previous published maps for the investigated area.     

遥感解译在内蒙古额济纳旗地区1：5万地质填图中的应用

遥感技术是地质填图工作的重要辅助技术方法。针对内蒙古额济纳旗地区的荒漠戈壁地貌景观特点,在地质填图中选取国产资源三号卫星遥感数据和ETM+遥感数据作为遥感解译的数据源,并分别对获取的遥感数据进行数据融合、几何校正（或精校正）、图像校正和镶嵌等数据处理。鉴于测区植被不发育,地表多以基岩和戈壁滩为主,资源三号遥感图像颜色单调。特将校正的资源三号图像与ETM+图像进行图像融合,融合后的图像既具有ETM+图像的丰富色彩信息,又保证了资源三号卫星图像的高空间分辨率,便于实施人机交互地质矿产信息提取。根据遥感影像特征,建立了地层、侵入体和构造的解译标志,提取了与岩性和构造相关的各类信息,结合地质资料进行综合判别解译,提高了地质填图工作的准确性,为荒漠戈壁地貌区的地质填图提供了技术支持。     

通过遥感对矿产资源开采中环境影响的研究--以阜新煤矿和排山楼金矿为例

阜新地区地处华北地台,富含煤和金矿床.呈东西向分布的太古宙和元古宙变质地层在华力西期、印支期和燕山期的变形和岩浆活动中发生隆起.金矿赋存于隆起的前寒武纪变质岩石中.成煤期为晚石炭-早二叠纪、早中侏罗纪、晚侏罗-早白垩纪.阜新煤矿和排山楼金矿是辽宁省的主要煤、金产地.
由于开采物中的有用物质只占很小的比例,因此提取有用物质的方式不可避免地要破坏当地的环境.矿山开采的每一步骤都对环境产生着负面影响.应用遥感资料进行矿山管理,是采用基于地表物体光谱反射的可视近红外(VNIR)遥感和短波红外(SWIR)遥感,以及基于物体热发光的热红外(TIR)遥感,利用不同的地表光谱反射,将相似的物体区分、分类、填图,并进行土地资源分析.野外工作包括在阜新煤矿和排山楼金矿确定岩石蚀变类型,采集标本,构造测量,对矿山环境进行数码拍照.陆地卫星MSS、TM和ETM+数据是分析研究的基础.应用ERDAS IMAGING软件处理卫星数据.并用ERDAS MapSheets和ViewFinder软件划图.应用各种图像处理技术进行图像增强和物体分辨.从卫星图像上直接测量排山楼金矿和阜新煤矿露天采场的多边形周长和面积.从卫星图像上可以看出,阜新煤矿从1980年到2000年环境的恶化.矿山开采产生的废矿堆不仅对矿区造成破坏,由于它们邻近市区,也通过视觉污染和噪音污染构成了潜在的环境污染源.开采活动对环境影响的另一个方面就是地面下沉,这是由地下开采造成的.它对地表的影响是明显的.本研究的重点是煤矿开采造成的地面下沉.与金矿脉的开采不同,煤矿的开采要移去数米厚的整个煤层.其结果不可避免地导致上覆地层的垮塌.排山楼金矿和阜新煤矿的另一个环境污染源来自矿石的处理(提纯和浓缩).金矿和煤矿都采用重力分离和浮选的方法.排山楼金矿目前采用先进的氰化-碳吸附选矿方法.作为补救措施,现在对用于浮选的化学剂的选择不仅要考虑其效益,而且要将其对环境的损害降到最低.尾矿处理也是影响环境的一个重要问题.阜新煤矿和排山楼金矿通常将尾矿倾倒地附近的人工坑内.这些区域虽然不至于对景观造成严重破坏,但很难在其表面恢复植被.而且,从该区域排出的水含有强酸和有毒的金属离子,一旦流入自然水系,将给水生生物造成大面积损害.堆放尾矿的区域一旦干燥,将产生另一个环境问题——粉尘污染.基于这些发现,提出如下建议：
（ 1）采矿过程中环境不断恶化的事实说明,两个矿山在控制露天开采方面仍有不足.虽然移动矿体上覆岩石或盖层是矿山开采的必要前提,但矿产资源的采掘必须对自然的保护给予更多的重视.应更加注重盖层的回填,植被、湿地、沼泽的恢复,控制溢出物,合理利用废物.
（2）地方政府应参与地区内矿产资源开发项目的立项、审批工作.政府在法律框架内干预、控制矿山开采行为中的环境和土地利用问题.     

A Comparative Study of Landsat‐7 and Landsat‐8 Data Using Image Processing Methods for Hydrothermal Alteration Mapping

Comparing spaceborne satellite images of Landsat‐8 Operational Land Imager (OLI) and Landsat‐7 Enhanced Thematic Mapper plus (ETM+) was undertaken to investigate the relative accuracy of mapping hydrothermal alteration minerals. The study investigated the northern part of Rabor, which contains copper mineralization occurrences, and is located in the Kerman Cenozoic magmatic assemblage (KCMA), Iran. Image processing methods of band ratio, principal component analysis (PCA), and spectral angle mapper (SAM) were used to map the distribution of hydrothermally altered rocks associated with the porphyry copper mineralization. The band ratio combination of both sensors for mapping altered areas showed similar outcomes. PCA exposed variations in the spatial distribution of hydroxyl‐bearing minerals. The representation of hydrothermal areas using OLI data was more satisfactory than when using ETM+ data. SAM analysis found similar results for mapping hydroxyl‐bearing zones. Verification of the results came through ground investigation and laboratory studies. Rock samples (n = 56) were collected to validate results using thin sections, X‐ray diffraction (XRD) and spectral analyses. Field observations and laboratory analysis revealed that phyllic and propylitic alterations dominate the alteration zones in the study area. Argillic and iron oxides/hydroxides alterations were observed to a lesser degree. The results indicate that alteration maps prepared by OLI data using PCA for visual interpretation are more suitable than those of ETM+ due to a higher radiometric resolution and lower interference between vegetation and altered areas. As the spectral bandwidth of ETM+ band 7 covers absorption feature of propylitic alteration, better mapping of propylitic alterations is achieved using ETM+ data.     

Investigating the application of pixel-level and product-level image fusion approaches for monitoring surface water changes

The aim of this paper was to investigate the suitability of the pixel-level and product-level image fusion approaches to detect surface water changes. In doing so, firstly, the principal component analysis technique was applied to Landsat TM 2010 multispectral image to generate the PC components. Several pixel-level image fusion techniques were then performed to merge the Landsat ETM+ 2000 panchromatic with the PC1PC2PC3 band combination of Landsat TM 2010 imagery to highlight the surface water changes between the two images. The suitability of the resulting fused images for surface water change detection was evaluated quantitatively and visually. Finally, the support vector machine (SVM) technique was applied to the qualified fused images to map the highlighted changes. Furthermore, a product level fusion (PLF) approach based on various satellite-derived indices was employed to detect the surface water changes between ETM+ 2000 and TM 2010 images. The accuracy of the resulting change maps was assessed based on a reference change map produced using visual interpretation. The results demonstrated the effectiveness of the proposed approaches for surface water change detection, especially using the Gram Schmidt-SVM, PLF-NDWI, and PLF-NDVI methods which improved the accuracy of change detection over 99.70 %.     

Mapping Proterozoic unconformity-related uranium deposits in the Rockhole area, Northern Territory, Australia using landsat ETM+

The Rockhole area, Northern Territory, Australia, hosts a number of Proterozoic unconformity-related uranium deposits. The geology of the area features within Paleoproterozoic rocks of the Pine Creek Orogen, near the unconformity with overlying platform cover sandstone of the Paleo- to Mesoproterozoic McArthur Basin. Landsat Enhanced Thematic Mapper plus (ETM+) data was used in the Rockhole area to assist in mapping geological structures and lithology, and to identify anomalous concentrations of ferrous minerals, the product of alteration, which can be indicators of buried uranium mineralization. Several image-processing procedures were applied to the ETM+ data to identify, isolate and enhance mineralogical information as simple and complex false color composites. ETM+ 754 shown as red green and blue respectively was the best simple image. Overall, complex images based on Principal Component Analysis proved to be the most useful products. Sandstone, shale and siltstone, the target lithologies, Koolpin Formation, the target stratigraphic unit, and bleaching pattern due to the removal of iron(II) compounds, the target alteration pattern, were confidently mapped to provide information required by the mineral emplacement model, which ultimately identified areas of likely uranium mineralization. Thus the contrasting behavior of the two principle oxidation states of uranium and iron can be utilized to map/delineate bleached alteration zones associated with economic concentrations of uranium using multispectral sensors like Landsat or better hyperspectral sensors.