基于光谱角分类器遥感影像的自动分类和精度分析研究

遥感影像是地球表面一定区域景观和覆盖的客观记录和形象显示。选择黑河弱水流域作为自动分类的典型研究区,利用该区域的Landsat 7ETM+遥感影像结合地面实况调查数据,寻找土地利用/覆盖类型自动分类的训练样本,运用光谱角分类方法对ETM+图像进行自动分类。通过分类图像与地面真实样本数据对比分析,获得适用于荒漠地表遥感影像自动分类的可行性方法,并且进一步讨论了混淆矩阵计算的分类误差,研究了以Kappa分析为基础的精度评价。     

Alteration mineral mapping using masking and Crosta technique for mineral exploration in mid-vegetated areas: a case study in Areletuobie,Xinjiang (China)

Thematic Mapper (TM) and Enhanced Thematic Mapper (ETM)+ data have been successfully employed in the field of mineral exploration to identify key minerals over arid and semi-arid terrains. However, redundant vegetation and cloud may seriously interfere with the discrimination of the minerals with diagnostic features. Therefore, in this study, we use masking technique to eliminate the negative influence of vegetation and cloud and Crosta technique to identify the diagnostic features of hydroxyl-minerals, carbonate-minerals and iron oxides. Then the anomalies were endowed with special colours and overlapped with the remote-sensing and geochemical data, overlaying images as remote-sensing anomalies. The mineral exploration work was carried through by synthetic analysis of the remote-sensing images, geochemical data and structures. Finally, areas with high correlation between the occurrence of hydrothermal alteration and presence of main faults and geochemical anomalies were considered as mineral exploration targets worthy of further detailed exploration programmes.     

Comparison of multi-temporal ASTER images for hydrothermal alteration mapping using a fractal-aided SAM method

The shortwave infrared (SWIR) spectral bands of four multi-temporal images acquired by the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) on NASA’s Terra platform were analysed for evaluating the effects of acquisition properties and atmospheric pre-processing levels on the resulting hydrothermal alteration maps a using the fractal-aided Spectral Angle Mapper (SAM) method. Three ASTER level-1B products covering the Sar Cheshmeh area in Iran were used for hydrothermal alteration mapping. These images were converted to surface reflectance using the Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes (FLAASH) method. The low reflectance of band 5 of the level-1B products was compensated for by using the spectra of collected rock samples. Level-2 (AST2B05S) SWIR ASTER images that had already been processed were also used. Reference spectra of the main hydrothermal alteration types were extracted for each product. The threshold angles were determined using the real value–area (RV–A) fractal technique. Then, SAM classification was carried out to map hydrothermal alteration for every product. It is concluded that the level-1B products that had been converted to reflectances have a better spectral contrast than the AST2B05S product. Summer images with lower tilt angle and higher solar elevation should be used to increase the accuracy of the image classification and minimize the effect of vegetation on the spectra of index minerals. By comparing the resulting hydrothermal alteration maps with known alteration types using a confusion matrix, it was shown that the application of the RV–A fractal technique to produce less biased threshold angles increases the accuracy of SAM classification.     

Thermal anomalies associated with faults: a case study of the Jinhua–Quzhou basin of Zhejiang Province,China

Faults provide the path for geothermal natural convection and partially influence the ground surface thermal environment. The land surface temperatures (LSTs) near a fault are higher than in other areas and can indicate the strike trend of an underground fault. However, these anomalies of higher LSTs are not located accurately in the fault centre but near it with some offset, and these LST data may include other thermal information that needs to be eliminated prior to analysis. In this study, LSTs were retrieved from Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper Plus (ETM+) thermal infrared (TIR) images and enhanced with land cover classification and elimination. The spatial patterns of the enhanced images were compared with geophysical prospecting tectonic profiles and with regional geological tectonic maps, revealing the spatial correspondence between the thermal anomalies and the faults. The results indicated that the thermal anomalies are located near the faults and are consistent with the faults' dip planes.     

Combined use of ASTER and ALI data for hydrothermal alteration mapping in the northwestern part of the Kerman magmatic arc,Iran

The study area is located in the Kerman magmatic arc in southern Iran, which is known for its world-class porphyry-type deposits. The Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) and Advanced Land Imager (ALI) visible–near-infrared to shortwave-infrared bands were used to investigate the spectral discrimination of hydrothermally altered rocks based on their mineral assemblages. Band ratioing, directed principal component analysis (DPCA), and the Spectral Angle Mapper (SAM) were applied on ASTER and ALI data for separating ferric iron-poor from ferric iron-rich phyllic alteration zones. The individual principal component images through DPCA could detect specific alteration zones dominated by minerals such as iron oxides, sericite, kaolinite, chlorite, and epidote. The phyllic zone associated with copper mineralization is generally rich in iron oxide minerals at the surface, which can be especially detected by ALI. The altered areas were sampled and studied using X-ray diffraction analysis, spectral measurements, chemical analysis, and thin-section studies. The results of this analysis have shown that more than 90% of the known copper mineralization falls within the ASTER/ALI-mapped alteration areas. These data can be useful for mapping alteration minerals related to porphyry deposits in other regions with similar geological settings.     

基于SAM与SVM的高光谱遥感蚀变信息提取

高光谱遥感技术的发展,提高了遥感技术的定量化水平,要求人们从光谱维去理解地物在空间维的变换。提出了一种光谱角匹配技术（Spectral Angle Mapper,SAM）与支持向量机（Support Vector Machine,SVM）相结合的高光谱遥感蚀变信息提取模型,在光谱维提取地表的蚀变信息。鉴于SAM算法仅考虑波谱矢量方向,忽略辐射亮度大小的缺点,利用SVM算法对SAM的提取结果进行二次分类,利用网格搜索法并结合分类精度评估进行参数寻优。通过AVIRIS高光谱数据实验证明,提取的蚀变信息分类精度为78.172 6%,Kappa系数为0.712 5。该模型计算方便,对于解决光谱维的地物分类及相似矿物的蚀变信息提取具有一定的实际意义。     

Mineral imaging with Landsat Thematic Mapper data for hydrothermal alteration mapping in heavily vegetated terrane

A mineral imaging methodology, which involves processing of Landsat Thematic Mapper (TM) images and integration of ground data, is tested in the Baguio district of the Philippines to map hydrothermally altered zones in heavily vegetated terranes. Based on published reflectance spectra, two band ratio images are created and input into principal components analysis to map each predominant hydrothermal alteration mineral into separate mineral images. Digitized map data of known hydrothermal alteration zones are used for identifying training pixels for the known alteration zones. The mineral images and the training pixels are used in a supervised classification to map hydrothermally altered zones; classification accuracy reaches 69%. Inclusion of an image of a digital elevation model improves the classification accuracy to 82%. The mineral imaging methodology proved more successful in remote mapping of known hydrothermally altered zones in the Baguio district than remote mapping of limonitic and clay alteration using previously developed techniques.     

Integration and analysis of airborne geophysical and ETM+ data for exploration of porphyry type deposits in the Central Iranian Volcanic Belt using fuzzy classification

Previous studies have shown that there are altered areas that do not show anomalies in geophysical data but anomalies can be seen in processed Thematic Mapper images and vice versa. In order to map the altered areas associated with porphyry type copper deposits, the airborne geophysical data, i.e. radiometry and magnetometry and Landsat Enhanced Thematic Mapper (ETM+) data (hydroxyle and iron oxide images) of an area located in the Central Iranian Volcanic Belt have been integrated and analysed using fuzzy classification. Sar Cheshmeh and Darrehzar areas with known mineralization and alteration were chosen as training areas. After defining the training areas (Sar Cheshmeh and Darrehzar), the entire region was classified into altered and unaltered areas. Field observation and sampling confirmed a high classification accuracy. This analysis was found to be useful for exploration of porphyry type deposits in the Central Iranian Volcanic-Sedimentary Belt, where most parts of this belt are surveyed using airborne geophysics.     

Evaluation of geophysics and spaceborne multispectral data for alteration mapping in the Sar Cheshmeh mining area,Iran

The Sar Cheshmeh porphyry copper deposit is located in the Central Iranian Volcanic-Sedimentary Belt (CIVSB). The hydrothermal alteration zones are well developed within and around the porphyry stock. Given the poor soil and vegetation cover in this area, we evaluated the usefulness of multispectral remote sensing data derived from Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) and Enhanced Thematic Mapper Plus (ETM⁺) images and airborne magnetic–radiometric data for hydrothermal alteration mapping at a local scale. Principal component analysis (PCA), band ratios and the spectral angle mapper (SAM) technique were applied to the multispectral data sets to map hydrothermally altered rocks. PCA and band ratios were also applied to the airborne geophysical data. The overall results showed that the multispectral remote sensing data sets resulted in more accurate hydrothermal alteration mapping and lithological discrimination in the study area as compared with the airborne geophysical data. The radiometric data are also useful in enhancing areas with potassic alteration.     

高寒山区矿化蚀变信息提取的应用研究

从遥感影像中准确地提取矿化蚀变信息有着重要的理论和现实意义。本文中,作者利用ETM+多光谱数据,针对新疆西天山地区特殊的高寒山区特点,提出了一种改进的光谱角分类法——定量光谱角分类法来进行矿化蚀变信息提取。通过试验研究表明,该方法能够有效地提取矿化蚀变信息,具有一定的理论参考价值。     

A Landsat-based study of black rock coatings proximal to base metal smelters,Sudbury, Ontario,Canada

Past emission of metal-bearing particulate matter, sulphur dioxide (SO₂), and sulphuric acid by base metal smelters in the Sudbury region led to widespread loss of vegetation, contamination of soils, and formation of black coatings on rock surfaces. These black coatings formed through the incorporation of smelter-borne particulate matter into the partly dissolved uppermost layers of siliceous minerals on exposed rock, and are characterized by high heavy-metal content. This study involved assessment of the reflectance properties of black coatings in the Sudbury region, and determination of the geographic distribution of coatings through supervised classification of reflectance data derived from a Landsat Enhanced Thematic Mapper Plus (ETM+) image. Classifications involved the use of the Spectral Angle Mapper (SAM), Maximum Likelihood, and Feedforward Backpropagation Neural Network algorithms. The reflectance spectra of black coatings in the Sudbury region are relatively flat and featureless, and are characterized by reflectance values less than ~13% across the visible, near-infrared, and short-wave infrared. Spectral properties are similar to those of magnetite, a spinel-group mineral known to be present in Sudbury coatings. The presence of carbon-rich soot particles may be an important influence on the reflectance properties of coatings. SAM classification results are characterized by the widespread mislabelling of uncoated urban and open-pit sites as mantled by black coatings, and neural network results problematically mislabel some uncoated wetland sites as coated. Results generated by the Maximum Likelihood algorithm most usefully depict the distribution of exposed black coatings in the Sudbury region. The mapping of black coatings using remote-sensing methods can provide useful information on the spatial character of environmental degradation in the vicinity of smelters, and should be helpful in the monitoring of environmental recovery where emissions have been reduced or eliminated.     

Land‐cover classification in the Andes of southern Ecuador using Landsat ETM+ data as a basis for SVAT modelling

A land‐cover classification is needed to deduce surface boundary conditions for a soil–vegetation–atmosphere transfer (SVAT) scheme that is operated by a geoecological research unit working in the Andes of southern Ecuador. Landsat Enhanced Thematic Mapper Plus (ETM+) data are used to classify distinct vegetation types in the tropical mountain forest. Besides a hard classification, a soft classification technique is applied. Dempster–Shafer evidence theory is used to analyse the quality of the spectral training sites and a modified linear spectral unmixing technique is selected to produce abundancies of the spectral endmembers. The hard classification provides very good results, with a Kappa value of 0.86. The Dempster–Shafer ambiguity underlines the good quality of the training sites and the probability guided spectral unmixing is chosen for the determination of plant functional types for the land model. A similar model run with a spatial distribution of land cover from both the hard and the soft classification processes clearly points to more realistic model results by using the land surface based on the probability guided spectral unmixing technique.     

Geospatial variability in the egg raft distribution and abundance of Culex pipiens and Culex restuans in Urbana‐Champaign,Illinois

The aim of this study was to determine whether areas of high Culex pipiens and Culex restuans abundance in an urban environment, based on fixed oviposition surveillance sites, corresponded to remotely sensed data. A land use land cover (LULC) classification, based on Landsat‐7 Enhanced Thematic Mapper Plus (ETM+) data acquired in July 2003 and Landsat‐5 TM data from July 1991, was compared to the abundance of Culex egg rafts in Urbana‐Champaign, East‐Central Illinois. We performed a maximum likelihood, unsupervised classification and generated three land cover classifications: urban, non‐urban and water. Ground coordinates of the Culex surveillance sites were overlaid onto LULC maps with 10 m² grid cells. The grid was stratified based on levels of drainage: 0 = poorly drained and 1 = well‐drained. Total LULC change from 1991 to 2003 in the Urbana‐Champaign study site was relatively low, at 12.1%. The most frequent LULC category was maintained urban. The egg raft rate was significantly higher in urban LULC habitats. Remote stratification of the urban land cover using QuickBird visible and near‐infrared (NIR) data revealed that high‐density canopy coverage was most frequently associated with high Culex abundance in oviposition traps. We demonstrate that optical remote sensing can identify land use parameters associated with high Culex oviposition.     

Remote sensing of temperature variations around major power plants as point sources of heat

Variations in land surface temperature (LST) around major point sources of heat were studied using the Tampa Bay region as a case study. LST in the Tampa Bay region, FL, USA, was retrieved from Landsat Thematic Mapper (TM) 6 and Enhanced Thematic Mapper Plus (ETM+) 6 high-gain thermal bands. The TM6 image data were obtained on 29 January (winter season) and 3 April 2007 (spring season). The ETM+6 data were obtained on 11 April 2007 (spring season). Spatial profiles of LST around four major fossil-fuelled power plants (FFPPs) were considered in this study. Temperatures were found to be highest at power plants and to decay to an average background temperature within 1.2–2.0 km from the FFPPs. The average background temperatures obtained in January and April were 17°C and 29°C, respectively. Results indicate that LST in close proximity to the FFPPs could be up to 10°C hotter than the surrounding areas. These findings suggest that FFPPs are significant heat sources and populations living within 1–2 km from an FFPP might be at significantly higher risk of heat-related illnesses and mortality.     

Circa 2014 African land-cover maps compatible with FROM-GLC and GLC2000 classification schemes based on multi-seasonal Landsat data

A new African land-cover data set has been developed using multi-seasonal Landsat Operational Land Imager (OLI) imagery mainly acquired around 2014, supplemented by Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper Plus (ETM+). Each path/row location was covered by five images, including one in the growing season of vegetation and the others in four meteorological seasons (i.e. spring, summer, autumn, and winter), choosing the image with the least cloud coverage. The data set has two classification schemes, i.e. Finer Resolution Observation and Monitoring – Global Land Cover (FROM-GLC) and Global Land Cover 2000 (GLC2000), providing greater flexibility in product comparisons and applications. Random forest was used as the classifier in this project. Overall accuracies were 71% and 67% for the maps in the FROM-GLC classification scheme at level 1 and level 2, respectively, and 70% for the map in the GLC2000 classification scheme. The newly developed African land-cover map achieved a greater improvement in accuracy compared to previous products in the FROM-GLC project. Multi-seasonal imagery helped increase the mapping accuracy by better differentiating vegetation types with similar spectral features in one specific season and identifying vegetation with a shorter growing season. Night light data with 1 km resolution was used to identify the potential area of impervious surfaces to avoid overestimating the distribution of impervious surfaces without decreasing the spatial resolution. Stacking multi-seasonal mapping results could adequately minimize the disturbance of cloud and shade.     

A satellite remote sensing technique for geological structure horizon mapping

A satellite remote sensing technique is demonstrated for generating near surface geological structure data. This technique enables the screening of large areas and targeting of seismic acquisition during hydrocarbon exploration. This is of particular advantage in terrains where surveying is logistically difficult. Landsat Thematic Mapper (TM) data and a high resolution digital elevation model (DEM), are used to identify the map outcropping horizons. These are used to reconstruct the near surface structure. The technique is applied in Central Yeman which is characterized by a 'layer-cake' stratigraphic section and low dipping terrain. The results are validated using two-dimensional seismic data. The near surface map images faults and structure not apparent in the raw data. Comparison with the structure map generated from two-dimensional seismic data indicates very good structural and fault correlation. The near surface map successfully highlights areas of potential closure at reservoir depths.     

Landsat ETM+ imaging for mineral potential mapping: application to Avaj area,Qazvin, Iran

The Avaj area is located in the northwestern part of Iran, on the boundary between the Orumieh-Dokhtar and Sanandaj-Sirjan geological zones. It corresponds to two different geological sub-zones:Abe-Garm, to the north, which is related to the volcanic belt of Orumieh-Dokhtar; and the Razan sub-zone, to the south, which is related to the Sanandaj-Sirjan zone. Lithological aspects of different rock units indicate the presence of four distinct volcanic groups of andesite, basalt, tuff, and dacite. The present research utilizes various Landsat Enhanced Thematic Mapper Plus (ETM+) image-processing techniques, including false colour composite images, colour composite ratio images, and standard principal component (PC) image analysis on six bands and colour composite selective PC images, filtering and supervised classification. Nonetheless, colour composite selective images may be the most reliable method for enhancement of areas with hydrothermal alteration. All the techniques used clearly show the pervasive alteration of kaolinite-argillite in the area. These alterations are mainly related to the andesite, and tuffs have the same trend as fault directions.     

Land‐cover classification in the Brazilian Amazon with the integration of Landsat ETM+ and Radarsat data

Land‐cover classification with remotely sensed data in moist tropical regions is a challenge due to the complex biophysical conditions. This paper explores techniques to improve land‐cover classification accuracy through a comparative analysis of different combinations of spectral signatures and textures from Landsat Enhanced Thematic Mapper Plus (ETM+) and Radarsat data. A wavelet‐merging technique was used to integrate Landsat ETM+ multispectral and panchromatic data or Radarsat data. Grey‐level co‐occurrence matrix (GLCM) textures based on Landsat ETM+ panchromatic or Radarsat data and different sizes of moving windows were examined. A maximum‐likelihood classifier was used to implement image classification for different combinations. This research indicates the important role of textures in improving land‐cover classification accuracies in Amazonian environments. The incorporation of data fusion and textures increases classification accuracy by approximately 5.8–6.9% compared to Landsat ETM+ data, but data fusion of Landsat ETM+ multispectral and panchromatic data or Radarsat data cannot effectively improve land‐cover classification accuracies.     

Extreme‐learning‐machine‐based land cover classification

The extreme learning machine (ELM), a single hidden layer neural network based supervised classifier is used for remote sensing classifications. In comparison to the backpropagation neural network, which requires the setting of several user‐defined parameters and may produce local minima, the ELM requires setting of one parameter, and produces a unique solution for a set of randomly assigned weights. Two datasets, one multispectral and another hyperspectral, were used for classification. Accuracies of 89.0% and 91.1% are achieved with this classifier using multispectral and hyperspectral data, respectively. Results suggest that the ELM provides a classification accuracy comparable to a backpropagation neural network with both datasets. The computational cost using the ELM classifier (1.25 s with Enhanced Thematic Mapper (ETM+) and 0.675 s with Digital Airborne Imaging Spectrometer (DAIS) data) is very small in comparison to the backpropagation neural network.     

Geological applications of Landsat Enhanced Thematic Mapper (ETM) data and Geographic Information System (GIS): Mapping and structural interpretation in south-west Iran,Zagros Structural Belt

Arabia-Eurasia convergence is achieved in north-west Zagros by a combination of shortening on NW-SE-trending folds and thrusts, mainly in the Zagros Structural Belt, and by right-lateral strike-slip on the NW-SE-trending Main Recent Fault. Structural patterns are often used as indicators of major features on the surface. In the present study, Landsat Enhanced Thematic Mapper (ETM) data from 9 November 2002 was digitally processed to enhance the structural patterns. The contrast stretching of ETM band 4 was found to be the best in displaying lineaments and folds for the area, hence was further processed by using directional filters and generating different combinations of false colour composites (FCCs). Finally, a structural map of the study area (Dezful-Brojerd) was prepared using the processed ETM images. This study indicates that the Landsat ETM data are useful for locating and interpretation of the structural features in the Zagros Structural Belt. Examination of the Landsat ETM 2002 images combined with field visits revealed that the area is highly active and structurally is in a dynamic state due to compressional forces. However the density of the structural features on the imagery calibrated to several field visit data shows that the south and south-east of the study area are not as tectonically active. This may be due to presence of thick evaporite sequence of Gachsaran Formation on the Landsat image.