Mediterranean forest mapping using hyper-spectral satellite imagery

Mediterranean forests are characterized by spatiotemporal heterogeneity that is associated with Mediterranean climate, floristic biodiversity and topographic variability. Satellite remote sensing can be an effective tool for characterizing and monitoring forest vegetation distribution within these fragmented Mediterranean landscapes. The heterogeneity of Mediterranean vegetation, however, often exceeds the resolution typical of most satellite sensors. Hyper-spectral remote sensing technology demonstrates the capacity for accurate vegetation identification. The objective of this research is to determine to what extent forest types can be discriminated using different image analysis techniques and spectral band combinations of Hyperion satellite imagery. This research mapped forest types using a pixel-based Spectral Angle Mapper (SAM), nearest neighbour and membership function classifiers of the object-oriented classification. Hyperion classification was done after reducing Hyperion data using nine selected band combinations. Results indicate that the selection of band combination while reducing the Hyperion dataset improves classification results for both the overall and the individual forest type accuracy, in particular for the selected optimum Hyperion band combination. One shortcoming is that the performance of the best selected band combination was superior in terms of both overall and individual forest type accuracy when applying the membership classifier of the object-oriented method compared to SAM and nearest neighbour classifiers. However, all techniques seemed to suffer from a number of problems, such as spectral similarity among forest types, overall low energy response of the Hyperion sensor, Hyperion medium spatial resolution and spatiotemporal and spectral heterogeneity of the Mediterranean ecosystem at multiple scales.     

一种基于光谱角和光谱距离自动加权融合分类方法

高分辨率遥感影像分类一直是业内研究的热点之一,考虑到影像地物光谱角和光谱距离在分类中具有较好的互补性,提出了一种基于光谱角和光谱距离自动加权融合的分类方法,对传统多分类器分类的融合策略进行改进,能够在训练阶段根据样本自动地调整好各分类器对各类别进行分类的权重系数,使得融合后的分类结果更加科学和准确。QuickBird影像的分类实验表明,方法的分类精度明显优于单纯的光谱角或距离法,可广泛用于各种高分辨率影像的分类识别。     

吉林西部多时相遥感数据分类方案的构建及应用

为了深化遥感监测方法在生态环境调查中的应用,本文以吉林西部为试验区,设计了一种多时相遥感数据分类方案。该方案以物候信息为主,结合地物特征变量(植被、水体和土地信息)构建的多维特征空间数据集用于土地覆被分类。该遥感分类方案提取了9种地表覆被类型,结果表明:地表植被季节变化信息和土地利用信息的引入能明显改善土地覆被的分类精度;与基于原始波段的分类方案相比,多时相遥感数据分类方案的分类精度最好,总体分类精度为95.50%,Kappa系数为95.04%。     

Land-cover classification and analysis of change using machine-learning classifiers and multi-temporal remote sensing imagery

Frequent human activity and rapid urbanization have led to an assortment of environmental issues. Monitoring land-cover change is critical to efficient environmental management and urban planning. The current study had two objectives. The first was to compare pixel-based random forest (RF) and decision tree (DT) classifier methods and a support vector machine (SVM) algorithm both in pixel-based and object-based approaches for classification of land-cover in a heterogeneous landscape for 2010. The second was to examine spatio-temporal land-cover change over the last two decades (1990–2010) using Landsat data. This study found that the object-based SVM classifier is the most accurate with an overall classification accuracy of 93.54% and a kappa value of 0.88. A post-classification change detection algorithm was used to determine the trend of change between land-cover classes. The most significant change from 1990 to 2010 was caused by the expansion of built-up areas. In addition to the net changes, the rate of annual change for each phenomenon was calculated to obtain a better understanding of the process of change. Between 1990 and 2010, an average of 4.53% of lands turned to the built-up annually and there was an annual decrease of about 0.81% in natural land. If the current trend of change continues, regardless of the actions of sustainable development, drastic declines in natural areas will ensue. The results of this study can be a valuable baseline for land-cover managers in the region to better understand the current situation and adopt appropriate strategies for management of land-cover.     

Derivation of vegetation density and land-use type pattern in mountain regions of Jordan using multi-seasonal SPOT images

The mountainous region represents the most important agricultural and biodiversity haven in Jordan. The objective of this study is to characterize the seasonal pattern of land use and vegetation using multi-temporal SPOT images. Multi-temporal SPOT images were analyzed to characterize the land use and cropping pattern in the mountain regions of Jordan. The images were radiometrically corrected using invariant objects located on the image, and a linear inter-calibration method was used to calibrate the other images. A hybrid classification approach was used in the classification; the spectral signatures of the land-use classes were derived in an iterative procedure using the ISODATA and field survey data. Then, the maximum likelihood classification was applied on all images to classify the class signatures into thematic land-use types. The hybrid classification approach gives more accurate classification accuracy especially for the multi-seasonal image classification. The overall accuracy of the multi-temporal data set was achieved with 87.9%, while classification accuracy for single-date classifications were 61.3, 76.8, 72.2, and 65.5 for months of October, February, April, and June, respectively. In addition, the scene combinations that were derived from February and April were classified the land-use types almost as well as those combinations including more scenes. Regarding the classification details, the multi-temporal images enable higher level of classification for land-use types such as Anderson level 2, and produce accurate boundaries for the different cropping and farming systems.     

喀斯特地区遥感影像解译新算法——支持向量机算法

现行的遥感影像解译方法有监督分类和非监督分类。在监督分类中有平行算法,最小距离算法、最大似然算法等,而支持向量机是监督分类中的一种新的算法。本研究选择贵阳市花溪区小碧乡局部地区为研究对象,采用SPOT数据,分别运用最大似然算法和支持向量机算法对研究区遥感影像进行解译。通过建立混淆矩阵,来计算分类精度和Kappa系数。结果表明:支持向量机具有分类精度高,分类图斑完整等优点;但在时间的消耗上,支持向量机算法要比最大似然算法长。对于这两种算法而言,都存在地物光谱特征明显相异的地物易于区别,光谱相似的地物容易造成错分的现象,然而支持向量机分类精度要比最大似然分类精度高一些。支持向量机对样本数量具有敏感性,样本数量过多将导致运算时间过长。因此在实际运用中应根据实际情况,选择适合的算法。      

Hyperspectral satellite data analysis for pure pixels extraction and evaluation of advanced classifier algorithms for LULC classification

The study was carried out for Indian capital city Delhi using Hyperion sensor onboard EO-1 satellite of NASA. After MODTRAN-4 based atmospheric correction, MNF, PPI and n-D visualizer were applied and endmembers of 11 LCLU classes were derived which were employed in classification of LULC. To incur better classification accuracy, a comparative study was also carried out to evaluate the potential of three classifier algorithms namely Random Forest (RF), Support Vector Machines (SVM) and Spectral Angle Mapper (SAM). The results of this study reemphasize the utility of satellite borne hyperspectral data to extract endmembers and also to delineate the potential of random forest as expert classifier to assess land cover with higher classification accuracy that outperformed the SVM by 19% and SAM by 27% in overall accuracy. This research work contributes positively to the issue of land cover classification through exploration of hyperspectral endmembers. The comparison of classification algorithms’ performance is valuable for decision makers to choose better classifier for more accurate information extraction.     

Experimental comparison of support vector machines with random forests for hyperspectral image land cover classification

The performances of regular support vector machines and random forests are experimentally compared for hyperspectral imaging land cover classification. Special characteristics of hyperspectral imaging dataset present diverse processing problems to be resolved under robust mathematical formalisms such as image classification. As a result, pixel purity index algorithm is used to obtain endmember spectral responses from Indiana pine hyperspectral image dataset. The generalized reduced gradient optimization algorithm is thereafter executed on the research data to estimate fractional abundances in the hyperspectral image and thereby obtain the numeric values for land cover classification. The Waikato environment for knowledge analysis (WEKA) data mining framework is selected as a tool to carry out the classification process by using support vector machines and random forests classifiers. Results show that performance of support vector machines is comparable to that of random forests. This study makes a positive contribution to the problem of land cover classification by exploring generalized reduced gradient method, support vector machines, and random forests to improve producer accuracy and overall classification accuracy. The performance comparison of these classifiers is valuable for a decision maker to consider tradeoffs in method accuracy versus method complexity.     

Study of land surface temperature and spectral emissivity using multi-sensor satellite data

In this study, an attempt has been made to estimate land surface temperatures (LST) and spectral emissivities over a hard rock terrain using multi-sensor satellite data. The study area, of about 6000 km², is a part of Singhbhum-Orissa craton situated in the eastern part of India. TIR data from ASTER, MODIS and Landsat ETM+ have been used in the present study. Telatemp Model AG-42D Portable Infrared Thermometer was used for ground measurements to validate the results derived from satellite (MODIS/ASTER) data. LSTs derived using Landsat ETM+ data of two different dates have been compared with the satellite data (ASTER and MODIS) of those two dates. Various techniques, viz., temperature and emissivity separation (TES) algorithm, gray body adjustment approach in TES algorithm, Split-Window algorithms and Single Channel algorithm along with NDVI based emissivity approach have been used. LSTs derived from bands 31 and 32 of MODIS data using Split-Window algorithms with higher viewing angle (50°) (LST1 and LST2) are found to have closer agreement with ground temperature measurements (ground LST) over waterbody, Dalma forest and Simlipal forest, than that derived from ASTER data (TES with AST 13). However, over agriculture land, there is some uncertainty and difference between the measured and the estimated LSTs for both validation dates for all the derived LSTs. LST obtained using Single Channel algorithm with NDVI based emissivity method in channel 13 of ASTER data has yielded closer agreement with ground measurements recorded over vegetation and mixed lands of low spectral contrast. LST results obtained with TIR band 6 of Landsat ETM+ using Single Channel algorithm show close agreement over Dalma forest, Simlipal forest and waterbody with LSTs obtained using MODIS and ASTER data for a different date. Comparison of LSTs shows good agreement with ground measurements in thermally homogeneous area. However, results in agriculture area with less homogeneity show difference of LST up to 2°C. The results of the present study indicate that continuous monitoring of LST and emissivity can be undertaken with the aid of multi-sensor satellite data over a thermally homogeneous region.     

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.     

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。      

Landslide susceptibility assessment using object mapping units,decision tree,and support vector machine models in the Three Gorges of China

Due to the particular geographical location and complex geological conditions, the Three Gorges of China suffer from many landslide hazards that often result in tragic loss of life and economic devastation. To reduce the casualty and damages, an effective and accurate method of assessing landslide susceptibility is necessary. Object-based data mining methods were applied to a case study of landslide susceptibility assessment on the Guojiaba Town of the Three Gorges. The study area was partitioned into object mapping units derived from 30 m resolution Landsat TM images using multi-resolution segmentation algorithm based on the landslide factors of engineering rock group, homogeneity, and reservoir water level. Landslide locations were determined by interpretation of Landsat TM images and extensive field surveys. Eleven primary landslide-related factors were extracted from the topographic and geologic maps, and satellite images. Those factors were selected as independent variables using significance testing and correlation coefficient analysis, including slope, profile curvature, engineering rock group, slope structure, distance from faults, land cover, tasseled cap transformation wetness index, reservoir water level, homogeneity, and first and second principal components of the images. Decision tree and support vector machine (SVM) models with the optimal parameters were trained and then used to map landslide susceptibility, respectively. The analytical results were validated by comparing them with known landslides using the success rate and prediction rate curves and classification accuracy. The object-based SVM model has the highest correct rate of 89.36 % and a kappa coefficient of 0.8286 and outperforms the pixel-based SVM, object-based C5.0, and pixel-based SVM models.     

基于遥感数据的全球及区域土地覆盖制图--现状、战略和趋势

土地利用／土地覆盖变化研究是近年来全球变化研究的焦点之一。全球和区域尺度的土地覆盖特征对全球环境状况的评估、模拟未来全球环境的情景有重要的作用。2000年在Internat ionalJournalofRemoteSensing杂志上出版了题为"GlobalandRegionalLandCoverCharacterizat ion from Remotely Sensed Data"的专辑。在此基础上,介绍、总结了国际上利用遥感影像进行全球和区域等大尺度土地覆盖研究的新进展。分别从数据源与制图的时空尺度、制图方法（数据预处理、分类、精度评估）等方面进行了介绍,并对现今的两个全球土地覆盖数据库进行了比较分析。     

AIRS红外高光谱资料反演大气水汽廓线研究进展

随着卫星遥感关键技术的突破,卫星光谱分辨率达到了分辨大气成分单个谱线的水平,研究人员开始了大量通道同时反演大气廓线和多种微量成分的研究.针对AIRS(Atmospheric Infrared Sounder)就红外高光谱资料反演大气水汽廓线的研究进展进行了评述,从训练数据、通道信息的提取及降维、反演算法和反演精度改进4个方面对反演晴空大气水汽廓线的研究现状进行了分析与讨论.AIRS资料反演大气水汽廓线的训练数据通常选用威斯康星大学提供的全球晴空反演训练样本集CIMSS (Cooperative Institute for Meteorological Satellite Studies,University of WisconsinMadison)和SARTA(Stand-Alone Radiative Transfer Algorithm)辐射传输模式模拟的亮温辐射值.归纳总结了2种通道信息的提取及降维方法:一是采用有效的方法来完成光谱信息压缩,对常用的主成分分析和独立分量分析方法进行了对比,认为独立分量分析更为可行.二是通道选择,即保留部分含有较多大气廓线信息量的通道,达到降维目的.在进行通道选择时要注意针对不同地区气候类型、下垫面、季节以及即时天气条件,选择不同的通道组合.介绍了3种反演算法:特征向量统计法、牛顿非线性迭代法和神经网络法.对比发现特征向量统计法简单易行,但精度不够理想;牛顿非线性迭代法精度虽高但计算耗时长,因此不适合业务使用;神经网络计算速度快、精度也能达到要求,具有很好的前景.对目前的几种样本分类方法及附加因子进行了对比分析,对反演算法精度的改进提出了一些有益的设想.最后对晴空辐射订正及云天大气水汽廓线反演进行了简要介绍,提出了该领域未来的一些研究方向.     

3种经典机器学习算法在火山岩测井岩性识别中的对比

岩性识别一直是火山岩油气勘探中的重要课题,基于测井数据的岩性识别也逐渐成为火山岩研究的需要,大数据背景下的机器学习算法为测井岩性识别提供了一个新方向。为提高某研究区火山岩岩性识别符合率,本文采用K近邻、支持向量机和自适应增强3种经典机器学习算法,对研究区内的粗面岩、非致密粗面岩、辉绿岩、辉长岩、玄武岩和非致密玄武岩等6类中基性火山岩进行岩性识别。从常规测井系列中优选对研究区岩性敏感的自然伽马、声波时差、补偿中子、深侧向电阻率和补偿密度等5种测井参数作为岩性识别模型的输入向量,从研究区内5口有岩心样品或薄片鉴定资料的目标层中选取测井数据点1 440个,其中960个作为训练样本,其余480个作为测试样本。以识别符合率和时间作为评价指标,对3种算法的识别结果进行对比分析,实验表明：自适应增强算法的分类准确率最高,6类岩性平均识别符合率达到82.10%;支持向量机算法表现良好,平均识别符合率为81.04%;K近邻算法平均识别符合率为76.04%。     

基于极限学习机的GF-2影像分类

遥感图像分类是提取图像有效信息过程中重要的一部分,为了探寻最优的分类方法,许多机器学习算法逐步应用于遥感分类中。极限学习机（extreme learning machine,ELM）以其高效、快速和良好的泛化性能在模式识别领域得到广泛应用。本文采用训练速度快、运算量小的极限学习机算法与支持向量机（support vector machines,SVM）算法和最大似然法进行分类对比,对高分辨率遥感图像进行分类,分析极限学习机算法对于遥感图像分类的准确度等性能。选取吉林省长春市部分区域的GF-2遥感数据,将融合后的影像设置为原始数据,利用3种方法进行分类。研究结果表明,极限学习机算法分类图像总体分类精度达到85%以上,kappa系数达到0.718,与其他分类方法相比分类准确度较高,且极限学习机运行时间比支持向量机运行时间约短2 480 s,约为支持向量机运行时间的1/8,因此具有良好的性能和实用价值。     

Conditional curvilinear stochastic simulation using pixel-based algorithms

In geology, structures displaying differing local directions of continuity are widespread, a typical example being a flusial depositional system. Conventional pixel-based geostatistical algorithms, may fail to reproduce such curvilinear structures. Conversely, object-based algorithms can reproduce curvilinear shapes but are difficult to condition to dense local data. Local depositional directions as obtained from dipmeter data. 3D seismic data, and geological interpretation represent critical information. An improved pixel-based geostatistical algorithm is proposed to account for such directional information. Case studies demonstrate the potential and limitations of the algorithm.     

基于ASTER数据遥感影像的决策树分类

以黑龙江省北安市为研究区域,尝试利用ASTER视反射率值进行便利、准确的土地利用分类研究。对ASTER数据进行波段相关分析,确定最佳组合波段;然后重点分析转换为视反射率值的影像特征和光谱特征,从中提取各种典型地物的光谱曲线; 并依据提取的光谱曲线建立基于地物反射率值大小关系或阈值的决策树模型,对研究区不同地物类型进行分类,并对结果进行精度评价。应用效果表明,该方法简单有效,但对于混合光谱容易错分。     

Strength of ensemble learning in multiclass classification of rockburst intensity

Rockbust is a violent expulsion of rock due to the extreme release of strain energy stored in surrounding rock mass, leading to considerable damages to underground strucures and equipment, and threatening workers' safety. As the operational depth of engineering projects increases, a larger number of factors influence the mechanism of rockburst. Therefore, accurate classification of rockburst intensity cannot be achieved based on conventional criteria. It is urgent to develop new models with high accuracy and ease to implement in practice. This study proposed an ensemble machine learning method by aggregating seven individual classifiers including back propagation neural network, support vector machine, decision tree, k-nearest neighbours, logistic regression, multiple linear regression and Naïve Bayes. In addition, we proposed nine data imputation methods to replace the missing values in the compiled database including 188 rockburst instances. Five-fold cross validation and the beetle antennae search algorithm are used to tune hyperparameters and voting weights of the individual classifiers. The results show that the rockburst classification accuracy obtained by the classifier ensemble has increased by 15.4% compared with the best individual classifier on the test set. The predictor importance obtained by the classifier ensemble shows that the elastic energy index is the most sensitive input variable for rockburst intensity classification. This robust ensemble method can be extended to solve other classification problems in underground engineering projects.     

Assessment of the reliability of supervised classifications of Landsat-7, ASTER,and SPOT-5 multispectral data in rock unit discriminations of Jabal Daf-Wadi Fatima area,Saudi Arabia

Multispectral, multiresolution remotely sensed data were processed to emphasize geological interpretation of Jabal Daf-Wadi Fatima area. The investigated area is situated in the central western part of Saudi Arabia and geologically consists of igneous and metamorphosed rocks overlain by sedimentary sequence belonging to the Arabian-Nubian Shield. Three sets of digital satellite data, Landsat-7 ETM+, ASTER, and SPOT-5, were used in this study. The application of image processing techniques enables to identify and delineate the lithologic units and the structural features of the study area. The results of this study indicate that the confusion matrix of the three maximum likelihood supervised classifications of the three datasets shows that the Landsat ETM+ bands scored the best degree of average and overall accuracy (77 and 78%, respectively). This classification distinguishes most of the rock units for mapping in the investigated area. The supervised classification of ASTER and SPOT bands has lower degrees of accuracy than the classified Landsat data. The supervised classification of SPOT bands has a degree of average and overall accuracy of 66 and 67%, respectively, but it is the best for distinguishing the spectral signatures of the different members of Fatima Formation (lower, middle, and upper members). The statistical analyses of the confusion matrices of classifications and the interpretation of the produced classified thematic maps revealed that the classification accuracy does not necessary depend on the spatial resolution of satellite data. The data of the highest spatial resolution such as SPOT data are also very useful in emphasizing and classifying the rock units of a small outcrop area. The detailed geological map of Jabal Daf-Wadi Fatima area is interpreted in this work from supervised classified images of different resolutions as well as the structure map of this area. This study shows that it is preferable to use the supervised classifications of multiresolution data for rock unit discrimination in detailed field mapping.