物候特征辅助下的随机森林宏观尺度土地覆盖分类方法研究

通过遥感技术获取大范围土地覆盖信息对于监测、理解和预测自然资源具有重要的科学意义.MODIS数据是当今宏观尺度土地覆盖研究的主要数据源.本文以河北省为研究区,应用MOD13Q1数据产品,构建MODIS NDVI时间序列,从中反演物候特征作为参与分类的主要辅助信息,并采用随机森林分类方法进行宏观尺度土地覆被分类实验,并与单决策树(CART)进行对比分析.实验结果表明,物候特征辅助下的随机森林宏观尺度土地覆被分类方法的总体精度为87.2％,Kappa系数为0.83,比CART单一决策树精度提高了17.9％;应用物候特征参与分类,使得总体精度提高2.6％;其中,旱地和建筑用地精度分别提高了6.7％和11.9％.     

基于MODIS时间序列数据的作物季相信息提取

基于MODIS NDVI时间序列数据对浙北平原单季稻区进行作物季相一致性分析。对NDVI时间序列数据进行离散傅立叶变换去除噪声,再利用土地利用现状图提取耕地区的NDVI影像图,根据时间序列曲线的最大值研究作物的季相。结果表明:水稻生长期对NDVI时间序列曲线的响应和季相一致性均较小麦和油菜好;8 d合成的数据较16 d合成的数据可以更详细地反映作物季相信息。研究证实了MODIS NDVI时间序列曲线对区域作物季相分析的意义。     

MODIS土地覆盖数据产品精度分析——以黄河源区为例

MODIS土地覆盖数据产品覆盖广、时间分辨率高,是区域土地覆盖变化监测的重要数据源。本文以中国土地资源分类系统为依据,重新归类黄河源区MODIS土地覆盖数据。利用2000年和2006年黄河源区Land-sat解译数据为参考数据,对相应的MODIS土地覆盖数据,从数量精度和形状一致性两个方面进行精度分析和适用性评价。结果表明:在形状上,加入权重的总体形状一致性皆在69%以上,其中主要地类草地的一致性达到88%以上;在数量上,加入权重的总体面积相对误差在26%以内,误差主要产生在未利用土地等地类。MODIS土地覆盖数据产品在大尺度的土地覆盖监测中仍然有重要的应用价值。     

基于AVHRR和TM数据的时间序列较高分辨率NDVI数据集重构方法

由于技术条件的限制,一个传感器很难同时具有高空间分辨率和高时间分辨率。然而,在高分辨率尺度上监测地表景观季节性变化的能力是全球的迫切需要,融合周期短、覆盖范围广与分辨率高、周期长的遥感数据是一种较好的方法。基于AVHRR时间分辨率高和TM空间分辨率高及其数据积累时间长的特点,选择若尔盖高原为研究区域,在改进ESTARFM方法的基础上,对TM NDVI和AVHRR NDVI进行融合,构建高时空分辨率的NDVI数据集。研究结果表明:该方法能有机结合AVHRR NDVI的时间变化信息与TM NDVI的空间差异信息,有效实现高时空分辨率NDVI数据集的重构,3景预测高分辨率NDVI与MODIS NDVI产品相关系数分别达到了0.89、0.91和0.85。该方法能够在时间上保留高时间分辨率数据的时间变化信息,同时在空间上反映高空间分辨率数据的空间差异信息,从而为有效构建相对高分辨率时间序列NDVI数据集提供了可能的方法。     

基于植被分区的中国植被类型分类方法

高精度的土地覆盖分类产品对定量遥感研究及遥感应用等具有非常重要的意义。目前免费的且全球覆盖的土地分类产品已有很多,但这些产品多为国外研究机构和人员所研发,由于对中国区域地形复杂、植被结构特征差异与农作物种植结构差异等没有进行充分的研究,使得这些产品用于中国区域的分类时其精度尤其是植被类型的分类精度较低。因此,生产一种针对中国区域的植被类型分类产品是非常必要的。针对中国区域地形、土壤等信息,并在借鉴现有的植被区划的基础上,发展了一种基于植被分区的中国植被类型分类方法,该分类方法以长时间序列为基础,能以较高的时间分辨率捕捉地表随时间变化的信息,从而利用地物在时间维上的差异提高分类精度,并利用该方法完成了2012年中国土地覆盖分类。此外还通过分层随机采样的方法对分类结果进行了精度评估,发现本分类产品的总体精度和Kappa系数有较大提高,其中本文产品总体精度为90.78%,Kappa系数为0.86;并通过与MODIS土地覆盖数据产品进行比较,发现该产品精度比MODIS土地覆盖数据产品在植被类型上提高了61.38%。     

基于MODIS遥感数据的宏观土地覆盖特征分类方法与精度分析研究

针对宏观土地覆盖遥感分类的现状,充分利用MODIS相对于AVHRR数据具有的多光谱和分辨率优势,提出了利用MODIS数据进行分类特征选择与提取并结合多时相特征进行宏观土地覆盖分类的分类方法,并在中国山东省进行了分类试验,得出以下结论:①不同比例下的训练样本与验证样本影响着总体分类精度;②从MODIS数据中得到的植被指数EVI、白天地表温度Tday、水体指数NDWI、纹理特征局部平稳Homogeneity等可以作为分类特征配合参与到多波段地表反射率Ref1-7遥感影像中,能明显提高分类精度,而土壤亮度指数NDSI则没有贡献;③提取的分类特征对总体分类精度贡献大小为:EVI贡献最大,提高近6个百分点,其次是Homogeneity、NDWI,均提高近4个百分点,而最少的Tday也贡献了近3个百分点;④各分类特征对不同地物类别具有不同的分离度,在提高某些类别的分离性时,有可能降低了其它类别的分离性。试验结果表明:在没有其它非遥感信息的前提下,仅利用MODIS遥感自身信息对宏观土地覆盖分类就可达到较高精度。     

基于MODIS遥感数据的宏观土地覆盖特征分类方法与精度分析研究

针对宏观土地覆盖遥感分类的现状,充分利用MODIS相对于AVHRR数据具有的多光谱和分辨率优势,提出了利用MODIS数据进行分类特征选择与提取并结合多时相特征进行宏观土地覆盖分类的分类方法,并在中国山东省进行了分类试验,得出以下结论:①不同比例下的训练样本与验证样本影响着总体分类精度;②从MODIS数据中得到的植被指数EVI、白天地表温度Tday、水体指数NDWI、纹理特征局部平稳Homogeneity等可以作为分类特征配合参与到多波段地表反射率Ref1-7遥感影像中,能明显提高分类精度,而土壤亮度指数NDSI则没有贡献;③提取的分类特征对总体分类精度贡献大小为:EVI贡献最大,提高近6个百分点,其次是Homogeneity、NDWI,均提高近4个百分点,而最少的Tday也贡献了近3个百分点;④各分类特征对不同地物类别具有不同的分离度,在提高某些类别的分离性时,有可能降低了其它类别的分离性。试验结果表明:在没有其它非遥感信息的前提下,仅利用MODIS遥感自身信息对宏观土地覆盖分类就可达到较高精度。     

在GIS支持下利用MODIS数据监测多种作物和果树种植面积

MODIS数据以其时间分辨率高、监测范围大、可免费接收、获取方便及时等优势,已经成为土地利用研究的重要信息源。以河北省38°N带为研究区,选取不同时相的MODIS数据,分别计算出NDVI,根据植被的生长过程中叶面积的变化规律,观察其NDVI的变化,建立分类规则,确定出主要植被的种植区域。在GIS软件的支持下,利用分类精度为91%的TM数据分类结果从提取区域的面积和形状两个方面对MODIS数据的分类结果进行像元尺度上的精度分析。     

MODIS NDVI与MODIS EVI的比较分析

MODIS NDVI与MODIS EVI是目前应用比较广泛的植被指数,MODIS EVI是对NDVI的发展和延续,从植被指数计算公式和合成方法两方面做了改进。具体表现在:避免了MODIS NDVI在植被高覆盖区易饱和的问题,考虑了土壤背景对植被指数的影响,对气溶胶等残留做了进一步校正,采用BRDF/CV-MVC合成方法保证了合成采用最佳像元。EVI时间序列相较于NDVI时间序列季节性更明显,能够更好地反映高植被覆盖区的季节性变化特征,并且很少有突降现象,时间序列曲线较平滑。EVI的这些优势为高覆盖植被物候特征的季节性变化监测提供了新的思路。     

基于遥感和GIS的东亚土地覆盖年际变化研究

土地覆盖的年际变化是以土地覆盖的宏观分布模式为基准，在外界驱动因子的作用下发生的年与年之间的变化，因此，为揭示东亚地区土地覆盖的年际变化特征，首先选取东亚地区时相一致的不同空间分辨率（1km和8km)的NDVI影像进行了非监督分类，并总结了东亚土地覆盖的宏观分布模式，然后以时间序列的8kmAVHRRNDVI数字影像为基础，应用跨平百分率分析方法生成每年5-9月距平百分率分级影像，并以该影像为基础分析总结了东亚土地覆盖的年际变化特征，结果显示，该方法及其揭示的现象比较客观地反映了东亚土地覆盖年际变化特征。     

Soil moisture estimation using MODIS and ground measurements in eastern China

Recent technological advances in remote sensing have shown that soil moisture can be measured by microwave remote sensing under some topographic and vegetation cover conditions. However, current microwave technology limits the spatial resolution of soil moisture data. It has been found that the Normalized Difference Vegetation Index (NDVI) and Land Surface Temperature (LST) are related to surface soil moisture; therefore, a relationship between ground observed soil moisture and satellite NDVI and LST products can be developed. Three years of 1 km NDVI and LST products from the Moderate Resolution Imaging Spectroradiometer (MODIS) have been combined with ground measured soil moisture to determine regression relationships at a 1 km scale. Results show that MODIS NDVI and LST are strongly correlated with the ground measured soil moisture, and regression relationships are land cover and soil type dependent. These regression relationships can be used to generate soil moisture estimates at moderate resolution for study area.     

河谷型城市土地利用类型及格局的热环境效应遥感分析——以兰州市为例

以河谷型城市兰州为例,采用Landsat ETM+遥感影像为基本数据源,定量反演了地表温度（LST）和植被指数（NDVI）,利用GIS空间分析方法,分析了LST和NDVI 在不同土地利用类型之间的差异以及二者之间的定量关系,并引入多样性和聚集度指数,讨论了在不同土地利用的空间组合下,LST和NDVI 的空间差异及相互关系。结果显示:LST和NDVI具有明显的相关性,中心城区LST表现出热岛效应,而NDVI则为低谷效应;土地利用斑块和类型两种尺度水平上LST和NDVI均具有明显负相关的线性关系,城市内部不同土地类型所产生的热环境效应不同;土地利用多样性越丰富、聚集度越小的区域,其温度对地表植被覆盖的敏感性越弱。     

基于数据机理的植被叶面积指数遥感反演研究

定量获取地表植被高精度时序及空间覆盖的叶面积指数（Leaf Area Index, LAI）是生态监测及农业生产应用的重要研究内容。通过使用Moderate Resolution Imaging Spectroradiometer（MODIS）植被冠层多角度观测MOD09GA数据及叶面积指数MOD15A2数据,发展了一种参数化的叶面积指数遥感反演方法并完成了必要的检验分析。研究使用基于辐射传输理论的RossThick LiSparse Reciprocal（RTLSR）核驱动模型及Scattering by Arbitrarily Inclined Leaves with Hotspot（SAILH）模型进行植被冠层辐射特征的提取,使用Anisotropic Index （ANIX）异质性指数作为指示植被冠层二向反射分布Bidirectional Reflectance Distribution Function（BRDF）的辅助特征信息,发展了基于数据机理（Data-Based Mechanistic, DBM）的植被叶面积指数建模和估算方法。通过必要的林地、农作物、草地植被实验区反演及数值分析可得知：①时间序列多角度遥感观测数据结合数据机理的叶面积指数估算方法,可实现模型参数的时序动态更新,改进叶面积指数估算结果的时序完整性及精度。②异质性指数可以用做指示植被冠层二向反射分布特征信息,可降低因观测数据几何条件差异所导致的反演结果不确定情况,同时能够补充植被时序生长过程表现的植被结构变化等动态特征。经研究实践,可将算法应用于时空尺度的叶面积指数估算,并能够为生态、农业应用提供植被的高精度遥感监测指标。     

多时相影像福州市不透水面对城市地表温度的空间分布研究

随着城市化进程的加快,城市热力场也随之发生变化,从而影响着城市区域环境、社会经济以及社会环境。由于NDVI具有季相变化的不稳定性,本研究采用两个时相TM/ETM+影像分析福州市及其周边地区不透水面对热力场的时空分布变化状况。为了获取精确的城市不透水面信息,本实验采用NDVI二元法结合2000年同区域的IKONOS影像提取不透水面信息。通过定量分析不透水面百分比、NDVI与地表温度的关系,得出不透水面百分比与城市地表温度呈线性相关,其相关系数在0.7左右;尤其30%以上的不透水面对地表热环境的空间分布影响最为突出,因此,相对于不稳定的NDVI而言,不透水面信息能更好地反映城市热环境的空间分布状况。     

Downscaling MODIS LST in the East African mountains using elevation gradient and land-cover information

Land-surface temperature (LST) is strongly affected by altitude and surface albedo. In mountain regions where steep slopes and heterogeneous land cover are predominant, LST can vary significantly within short distances. Although remote sensing currently provides opportunities for monitoring LST in inaccessible regions, the coarse resolution of some sensors may result in large uncertainties at sub-pixel scales. This study aimed to develop a simple methodology for downscaling 1 km Moderate Resolution Spectroradiometer (MODIS) LST pixels, by accounting for sub-pixel LST variation associated with altitude and land-cover spatial changes. The approach was tested in Mount Kilimanjaro, Tanzania, where changes in altitude and vegetation can take place over short distances. Daytime and night-time MODIS LST estimates were considered separately. A digital elevation model (DEM) and normalized difference vegetation index (NDVI), both at 250 m spatial resolution, were used to assess altitude and land-cover changes, respectively. Simple linear regressions and multivariate regressions were used to quantify the relationship between LST and the independent variables, altitude and NDVI. The results show that, in Kilimanjaro, altitude variation within the area covered by a 1 km MODIS LST pixel can be up to ±300 m. These altitude changes can cause sub-pixel variation of up to ±2.13°C for night-time and ±2.88°C for daytime LST. NDVI variation within 1 km pixels ranged between –0.2 and 0.2. For night-time measurements, altitude explained up to 97% of LST variation, while daytime LST was strongly affected by land cover. Using multivariate regressions, the combination of altitude and NDVI explained up to 94% of daytime LST variation in Kilimanjaro. Finally, the downscaling approach proposed in this study allowed an improved representation of the influence of landscape features on local-scale LST patterns.     

Boosted decision tree classifications of land cover over Turkey integrating MODIS,climate and topographic data

This study investigates the impact of using different combinations of Moderate Resolution Imaging Spectroradiometer (MODIS) and ancillary datasets on overall and per-class classification accuracies for nine land cover types modified from the classification system of the International Geosphere Biosphere Programme (IGBP). Twelve land cover maps were generated for Turkey using boosted decision trees (BDTs) based on the stepwise addition of 14 explanatory variables derived from a time series of 16-day MODIS composites between 2000 and 2006 (Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI) and four spectral bands) and ancillary climate and topographic data (minimum and maximum air temperature, precipitation, potential evapotranspiration, aspect, elevation, distance to sea and slope) at 500-m resolution. Evaluation of the 12 BDTs indicated that the BDT built as a function of all the MODIS and climate variables, aspect and elevation produced the highest degree of overall classification accuracy (79.8%) and kappa statistic (0.76) followed by the BDTs that additionally included distance to sea (DtS), and both DtS and slope. Based on an independent validation dataset derived from a pre-existing national forest map and Landsat images of Turkey, the highest overall accuracy (64.7%) and kappa coefficient (0.58) among the 12 land cover maps was achieved by using MODIS-derived NDVI time series only, followed by NDVI and EVI time series combined; NDVI, EVI and four MODIS spectral bands; and the combination of all MODIS and climate data, aspect, elevation and distance to sea, respectively. The largest improvements in producer's accuracies were observed for grasslands (+50%), barrenlands (+46%) and mixed forests (+39%) and in user's accuracies for grasslands (+53%), shrublands (+30%) and mixed forests (+28%), in relation to the lowest producer's accuracy. The results of this study indicate that BDTs can increase the accuracy of land cover classifications at the national scale.     

Comparative Analysis on Three Land Surface Temperature Inversion Algorithm based on Landsat 8 Data over Sanheba Basin

The Land Surface Temperature (LST) of TIRS10 / Landsat 8 remote sensing data is studied and analyzed by combining the data and related parameters of Sanheba basin,and the LST inversion algorithm are used the Radiative Transfer Equation Method (RTE),Mono\|Window algorithm (MW) and Single\|Channel Method (SC).The parameters of the MW algorithm are corrected.The LST gray scale and density segmentation graphs,the histogram of LST and the cross validation flank are used to compare the results of the LST inversion algorithm.The results show that the three kinds of algorithms are similar to the linear fitting degree of LST,and the spatial distribution is consistent.The RTE and SC algorithm are close to each other,the average error of algorithm is 0~0.05 K.the LST of MW algorithm is higher than that of the other two algorithms,the average error of algorithm is 0~1.27 K.The LST of different land cover types in this basin is compared,and the inversion results can effectively reflect the details of the surface thermal field structure according to the different land cover types.The LST values obtained by these three algorithms are compared with the MODIS LST product values.The results show that there is a significant correlation between the LST values and the MODIS LST products.In this paper,3 kinds of the LST inversion algorithms are analyzed detailed accurate on TIRS10/Landsat 8 remote sensing data,provide a reference for other thermal infrared satellite data inversion LST algorithm,but also for the subsequent LST improve the accuracy of inversion basis.     

Estimating afternoon MODIS land surface temperatures (LST) based on morning MODIS overpass,location and elevation information

The MODerate Resolution Imaging Spectroradiometer (MODIS) instrument on‐board the Terra and Aqua satellites is a critical tool for providing daily estimates of land surface temperature (LST). Terra launched in late 1999 has a morning (AM) overpass, whereas Aqua launched in early 2002 has an afternoon (PM) overpass. Generally, LST is expected, under cloudless conditions, to be warmer in the early afternoon than the morning due to the link between maximum skin temperature and solar insolation peak time, therefore the Aqua PM LST is likely to be closer to the maximum daily LST than that acquired from Terra. This letter investigated differences between the Aqua MODIS PM and Terra MODIS AM LST estimates over a range of land cover classes, locations, and dates, across Canada. The aim was to develop a simple adjustment which can be applied to Terra AM LST estimates to approximate a “synthetic” Aqua PM LST product from 2000 to mid‐2002, thereby providing a seamless afternoon MODIS LST product from 2000 to 2006. Results indicate that there are statistically significant differences between the AM and PM LST ranging from 0.3°C to 3.2°C depending on cover type, and between 1.2° and 5.0° depending on time of year. On average, over 90% of the variation observed in the PM record can be explained by the AM LST, land cover types and location.     

利用粒子群优化估计高光谱数据协方差矩阵

与传统的多光谱遥感相比,高光谱遥感具有更高的光谱分辨率,能更好地进行地物分类识别。但是,当训练样本数与数据维数相当,或小于后者时,会导致协方差矩阵近似奇异或奇异,使得经典最大似然分类失效,需要对协方差矩阵进行修正。典型的协方差阵估计方法往往只选取总体协方差、类别协方差及其相应变形中的两种形式进行组合,未考虑多种形式共同对协方差阵估计的影响。提出将PSO算法应用到协方差阵估计中,考虑所有形式的共同作用,对组合参数进行优化。最后,通过高光谱数据的分类实验证明了方法的可行性和有效性。