Land use/land cover classification using time series Landsat 8 images in a heavily urbanized area

It is of great significance to timely, accurately, and effectively monitor land use/cover in city regions for the reasonable development and utilization of urban land resources. The remotely sensed dynamic monitoring of Land use/land cover (LULC) in rapidly developing city regions has increasingly depended on remote-sensing data at high temporal and spatial resolutions. However, due to the influence of revisiting periods and weather, it is difficult to acquire enough time-series images with high quality at both high temporal and spatial resolution from the same sensor. In this paper we used the temporal-spatial fusion model ESTARFM (Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model) to blend Landsat8 and MODIS data and obtain time-series Landsat8 images. Then, land cover information is extracted using an object-based classification method. In this study, the proposed method is validated by a case study of the Changsha City. The results show that the overall accuracy and Kappa coefficient were 94.38% and 0.88, respectively, and the user/producer accuracies of vegetation types were all over 85%. Our approach provides an accurate and efficient technical method for the effective extraction of land use/cover information in the highly heterogeneous regions.     

Assessment of the impact of dimensionality reduction methods on information classes and classifiers for hyperspectral image classification by multiple classifier system

Identification of the appropriate combination of classifier and dimensionality reduction method has been a recurring task for various hyperspectral image classification scenarios. Image classification by multiple classifier system has been evolving as a promising method for enhancing accuracy and reliability of image classification. Because of the diversity in generalization capabilities of various dimensionality reduction methods, the classifier optimal to the problem and hence the accuracy of image classification varies considerably. The impact of including multiple dimensionality reduction methods in the MCS architecture for the supervised classification of a hyperspectral image for land cover classification has been assessed in this study. Multi-source airborne hyperspectral images acquired over five different sites covering a range of land cover categories have been classified by a multiple classifier system and compared against the classification results obtained from support vector machines (SVM). The MCS offers acceptable classification results across the images or sites when there are multiple dimensionality reduction methods in addition to different classifiers. Apart from offering acceptable classification results, the MCS indicates about 5% increase in the overall accuracy when compared to the SVM classifier across the hyperspectral images and sites. Results indicate the presence of dimensionality reduction method specific empirical preferences by land cover categories for certain classifiers thereby demanding the design of MCS to support adaptive selection of classifiers and dimensionality reduction methods for hyperspectral image classification.     

Development and testing of a statistical texture model for land cover classification of the Black Sea region with MODIS imagery

A statistical model is proposed for analysis of the texture of land cover types for global and regional land cover classification by using texture features extracted by multiresolution image analysis techniques. It consists of four novel indices representing second-order texture, which are calculated after wavelet decomposition of an image and after texture extraction by a new approach that makes use of a four-pixel texture unit. The model was applied to four satellite images of the Black Sea region, obtained by Terra/MODIS and Aqua/MODIS at different spatial resolution. In single texture classification experiments, we used 15 subimages (50 × 50 pixels) of the selected classes of land covers that are present in the satellite images studied. These subimages were subjected to one-level and two-level decompositions by using orthonormal spline and Gabor-like spline wavelets. The texture indices were calculated and used as feature vectors in the supervised classification system with neural networks. The testing of the model was based on the use of two kinds of widely accepted statistical texture quantities: five texture features determined by the co-occurrence matrix (angular second moment, contrast, correlation, inverse difference moment, entropy), and four statistical texture features determined after the wavelet transformation (mean, standard deviation, energy, entropy). The supervised neural network classification was performed and the discrimination ability of the proposed texture indices was found comparable with that for the sets of five GLCM texture features and four wavelet-based texture features. The results obtained from the neural network classifier showed that the proposed texture model yielded an accuracy of 92.86% on average after orthonormal wavelet decomposition and 100% after Gabor-like wavelet decomposition for texture classification of the examined land cover types on satellite images.     

An optimal selection of probability distribution functions for unsupervised land cover classification of PALSAR-2 data

Different types of classification techniques are available in the literature for the classification of Synthetic Aperture Radar (SAR) data into various land cover classes. Various SAR images are available for land cover classification such as ALOS PALSAR (PALSAR-1, PALSAR-2), RADARSAT and ENVISAT. In this paper, we have attempted to explore probability distribution function (pdf) based land cover classification using PALSAR-2 data. Over 20 different statistical distribution functions are analyzed for different classes based on statistical parameters. Probability distribution functions are selected based on Chi-squared goodness of fit test for each individual class. A decision tree based classifier is developed for classification based on the selected pdf functions and its statistical parameters. The proposed classification approach has an accuracy of 83.93%.     

Is the phenology-based algorithm for mapping deciduous rubber plantations applicable in an emerging region of northern Laos?

Updated information of rubber plantations is essential for assessing socioeconomic and environmental impacts, especially in the emerging region of northern tropics. Here, a phenological method was modified to detect rubber plantations using Landsat Operational Land Imager (OLI) imagery in Phongsaly Province of northern Laos, where it begun a rubber boom in the mid-2000s due to geo-economic cooperation. It highlighted the landscape and pixel differences of deciduous rubber plantations in the tri-temporal phases (i.e., pre-defoliation, defoliation, and foliation) during the dry season due to phenological changes. Six commonly used vegetation indices (VIs), including the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Land Surface Water Index (LSWI), Atmospherically Resistant Vegetation Index (ARVI), Normalized Burn Ratio (NBR and NBR2) derived from OLI imagery during 2013–2016 were compared to determine the most suitable VI for discriminating the phenological differences of rubber plantations from natural forests. Then, the Differences of Normalized Burn Ratio (DNBR) was applied to generate the 30 m map of rubber plantations in 2016, by combining two masks of Landsat-derived forest and suitable elevation for rubber trees cultivation. The resultant map of rubber plantations had a classification accuracy of 93.7% and the Kappa coefficient of 0.848. Our study demonstrated the usefulness of the Landsat-derived tri-temporal phenological DNBR approach in an emerging region of northern Laos, despite requiring more scenes compared with single- and double temporal window methods.     

Assessment of the sensitivity of vegetation to El-Niño/Southern Oscillation events over China

This research explores the sensitivity of vegetation in China to El-Niño/Southern Oscillation (ENSO) events from 1982 to 2006. The ENSO events are defined by the Multivariate ENSO Index (MEI), and variation in vegetation cover is captured by the Advanced Very High Resolution Radiometer (AVHRR) Normalized Difference Vegetation Index (NDVI). Pearson’s χ2 test was used to identify the areas where the variation in vegetation was sensitive to El Niño and La Niña events. The difference in the sensitivity of various ecosystems was investigated using the Moderate Resolution Imaging Spectroradiometer (MODIS) land cover product in 2000. Composite NDVI graphs during El Niño, La Niña and non-ENSO years were also produced to investigate the ENSO relationship with the six vegetation ecosystems during El Niño, La Niña and normal phases. The results show that most of the ENSO-sensitive land in China is only affected by one of the two phases of ENSO events, and the area of El Niño-sensitive vegetation is much larger than that of La Niña-sensitive vegetation. North China and the Hengduan Mountains are the two cores of the El Niño-sensitive areas, while the La Niña-sensitive areas are mainly distributed in the central, northwest and northeast regions of China. The sensitivity of vegetation varies across ecosystems: grassland and shrubland had the largest share of El Niño-sensitive areas, and sparse vegetation and savanna were the most sensitive to La Niña events. Overall, the impacts of El Niño events on vegetation in China had regular seasonal variation, while the impacts of La Niña events had regular zonal distribution.     

A robust object-based shadow detection method for cloud-free high resolution satellite images over urban areas and water bodies

Unwanted contrast in high resolution satellite images such as shadow areas directly affects the result of further processing in urban remote sensing images. Detecting and finding the precise position of shadows is critical in different remote sensing processing chains such as change detection, image classification and digital elevation model generation from stereo images. The spectral similarity between shadow areas, water bodies, and some dark asphalt roads makes the development of robust shadow detection algorithms challenging. In addition, most of the existing methods work on pixel-level and neglect the contextual information contained in neighboring pixels. In this paper, a new object-based shadow detection framework is introduced. In the proposed method a pixel-level shadow mask is built by extending established thresholding methods with a new C₄ index which enables to solve the ambiguity of shadow and water bodies. Then the pixel-based results are further processed in an object-based majority analysis to detect the final shadow objects. Four different high resolution satellite images are used to validate this new approach. The result shows the superiority of the proposed method over some state-of-the-art shadow detection method with an average of 96% in F-measure.     

Built-up land mapping capabilities of the ASTER and Landsat ETM+ sensors in coastal areas of southeastern China

Worldwide urbanization has accelerated expansion of urban built-up lands and resulted in substantial negative impacts on the global environments. Precisely measuring the urban sprawl is becoming an increasing need. Among the satellite-based earth observation systems, the Landsat and ASTER data are most suitable for mesoscale measurements of urban changes. Nevertheless, to date the difference in the capability of mapping built-up land between the two sensors is not clear. Therefore, this study compared the performances of the Landsat-7 ETM+ and ASTER sensors for built-up land mapping in the coastal areas of southeastern China. The comparison was implemented on three date-coincident image pairs and achieved by using three approaches, including per-band-based, index-based, and classification-based comparisons. The index used is the Index-based Built-up Index (IBI), while the classification algorithm employed is the Support Vector Machine (SVM). Results show that in the study areas, ETM+ and ASTER have an overall similar performance in built-up land mapping but also differ in several aspects. The IBI values determined from ASTER were consistently higher than from ETM+ by up to 45.54% according to percentage difference. The ASTER also estimates more built-up land area than ETM+ by 5.9–6.3% estimated with the IBI-based approach or 3.9–6.1% with the SVM classification. The differences in the spectral response functions and spatial resolution between relative spectral bands of the two sensors are attributed to these different performances.     

Application of SVM on satellite images to detect hotspots in Jharia coal field region of India

The present paper deals with the application of Support Vector Machine (SVM) and image analysis techniques on NOAA/AVHRR satellite image to detect hotspots on the Jharia coal field region of India. One of the major advantages of using these satellite data is that the data are free with very good temporal resolution; while, one drawback is that these have low spatial resolution (i.e., approximately 1.1 km at nadir). Therefore, it is important to do research by applying some efficient optimization techniques along with the image analysis techniques to rectify these drawbacks and use satellite images for efficient hotspot detection and monitoring. For this purpose, SVM and multi-threshold techniques are explored for hotspot detection. The multi-threshold algorithm is developed to remove the cloud coverage from the land coverage. This algorithm also highlights the hotspots or fire spots in the suspected regions. SVM has the advantage over multi-thresholding technique that it can learn patterns from the examples and therefore is used to optimize the performance by removing the false points which are highlighted in the threshold technique. Both approaches can be used separately or in combination depending on the size of the image. The RBF (Radial Basis Function) kernel is used in training of three sets of inputs: brightness temperature of channel 3, Normalized Difference Vegetation Index (NDVI) and Global Environment Monitoring Index (GEMI), respectively. This makes a classified image in the output that highlights the hotspot and non-hotspot pixels. The performance of the SVM is also compared with the performance obtained from the neural networks and SVM appears to detect hotspots more accurately (greater than 91% classification accuracy) with lesser false alarm rate. The results obtained are found to be in good agreement with the ground based observations of the hotspots. This type of work will be quite helpful in the near future to develop a hotspots monitoring system using these operational satellites data.     

Non-linear methods in remotely sensed multispectral data classification

The aim of this research is to develop an effective approach being able to deal with the stochastic nature of remote sensing data. In order to achieve this objective it is necessary to structure the methodological knowledge in the area of data mining and reveal the most suitable methods for the prediction and decision support based on large amounts of multispectral data. The idea is to establish a framework by decomposing the task into functionality objectives and to allow the end-user to experiment with a set of classification methods and select the best methods for specific applications. As a first step, we compare our results from Bayesian classification based on non-parametric probability density estimates of the data to the results obtained from other classification methods. Tree scenarios are considered, making use of a small benchmark dataset, a larger dataset from Corine land cover project for Bulgaria and analyzing different features and feature selection methods. We show that the theoretically optimal Bayesian classification can also achieve optimal classification in practice and provides a realistic interpretation of the world where land cover classes intergrade gradually.     

Selection of classification techniques for land use/land cover change investigation

The concerns over land use/land cover (LULC) change have emerged on the global stage due to the realisation that changes occurring on the land surface also influence climate, ecosystem and its services. As a result, the importance of accurate mapping of LULC and its changes over time is on the increase. Landsat satellite is a major data source for regional to global LULC analysis. The main objective of this study focuses on the comparison of three classification tools for Landsat images, which are maximum likelihood classification (MLC), support vector machine and artificial neural network (ANN), in order to select the best method among them. The classifiers algorithms are well optimized for the gamma, penalty, degree of polynomial in case of SVM, while for ANN minimum output activation threshold and RMSE are taken into account. The overall analysis shows that the ANN is superior to the kernel based SVM (linear, radial based, sigmoid and polynomial) and MLC. The best tool (ANN) is then applied on detecting the LULC change over part of Walnut Creek, Iowa. The change analysis of the multi temporal images indicates an increase in urban areas and a major shift in the agricultural practices.     

Using land use change trajectories to quantify the effects of urbanization on urban heat island

This paper proposed a quantitative method of land use change trajectory, which means the succession among different land use types across time, to examine the effects of urbanization on an urban heat island (UHI). To accomplish this, multi-temporal images from Landsat 5 Thematic Mapper (TM) and Landsat 7 Enhanced Thematic Mapper Plus (ETM+) of Xiamen City in China from 1987 to 2007 were selected. First, the land use change trajectories were extracted based on the classified images from different years. Then the land surface temperatures (LST) were retrieved and the magnitudes of the UHI were evaluated using the UHI intensity (UHII) indicator. Finally, the indices of the contribution to UHI intensity (CUHII) were constructed and calculated to quantify the effects of each land use change trajectory on the UHI during urbanization. The results demonstrated that the land use change trajectories and CUHII are effective and useful in quantifying the effects of urbanization on UHI. In Xiamen City, a total of 2218 land use change trajectories were identified and 530 of them were the existing urban or urbanization trajectories. The UHII presents a trend of continuous increase from 0.83 °C in 1987 to 2.14 °C in 2007. With respect to the effects of urban growth on UHI, the contribution of existing urban area to UHI decreased during urbanization. Prior to 2007, the existing urban area of trajectory NO. 44444 had the most significant effect on UHI with the greatest CUHII, while the value has decreased from 55.00% in 1987 to 13.03% in 2007 because of the addition of new urbanized area. In 2007, the greatest CUHII was replaced by a trajectory from farmland to built-up area (NO. 22224) with the CUHII of 21.98%, followed by the existing urban area of trajectory NO. 44444 with the CUHII of 13.03%. These results provide not only a new methodology to assess the environmental effects of urbanization, but also decision-supports for the planning and management of cities.     

A simplified data assimilation method for reconstructing time-series MODIS NDVI data

The Normalized Difference Vegetation Index (NDVI) is an important vegetation index, widely applied in research on global environmental and climatic change. However, noise induced by cloud contamination and atmospheric variability impedes the analysis and application of NDVI data. In this work, a simplified data assimilation method is proposed to reconstruct high-quality time-series MODIS NDVI data. We extracted 16-Day L3 Global 1 km SIN Grid NDVI data sets for western China from MODIS vegetation index (VI) products (MOD13A2) for the period 2003–2006. NDVI data in the first three years (2003–2005) were used to generate the background field of NDVI based on a simple three-point smoothing technique, which captures annual features of vegetation change. NDVI data for 2006 were used to test our method. For every time step, the quality assurance (QA) flags of the MODIS VI products were adopted to empirically determine the weight between the background field and NDVI observations. Ultimately, more reliable NDVI data can be produced. The results indicate that the newly developed method is robust and effective in reconstructing high-quality MODIS NDVI time-series.     

An improved land cover classification using polarization signatures for PALSAR 2 data

Land cover classification in mixed land cover scenarios is challenging with PolSAR data. Polarimetric decomposition techniques are most popular methods for PolSAR data classification in recent times. These techniques focus on identification of dominant scattering phenomena and hence result in sub-optimal classification in mixed land cover scenarios. Alternatively, polarization signatures (PSs) are good illustrations of SAR target responses as they depict a detailed physical information from target backscatter. Researchers have successfully utilized SAR PSs for land cover (LC) classification. Some reports suggested utilizing correlation between observed PSs and standard target PSs as features for LC classification. This paper presents a study on improved utilization of PSs for optimal LC classification in mixed class scenarios. First, PS based SAR features are derived using fully polarimetric SAR data. The features represent a degree of similarity between observed and standard PSs. The derived features are termed as polarization signatures correlation features or PSCFs. The novel PSCFs are analyzed, evaluated and compared with decomposition based features for the purpose of LC classification. Classification performance indicators highlight potential of PSCFs for mixed LC classification problems. Therefore, further an adaptive and optimal LC class boundary estimation approach for LC classification is proposed and developed. Observed PSs and reference LC class PS statistics are used to build empirical models between classification performance indicators and LC class boundaries. The empirical models are optimized using the evolutionary genetic algorithm to maximize classification performance. A decision tree is constructed based on the optimal class boundaries to prepare LC classification. The proposed classification approach is compared with some recent popular classifiers and comparison suggests that the proposed approach provides satisfactory results for mixed LC classification scenarios.     

Satellite remotely-sensed land surface parameters and their climatic effects for three metropolitan regions

By using both high-resolution orthoimagery and medium-resolution Landsat satellite imagery with other geospatial information, several land surface parameters including impervious surfaces and land surface temperatures for three geographically distinct urban areas in the United States – Seattle, Washington, Tampa Bay, Florida, and Las Vegas, Nevada, are obtained. Percent impervious surface is used to quantitatively define the spatial extent and development density of urban land use. Land surface temperatures were retrieved by using a single band algorithm that processes both thermal infrared satellite data and total atmospheric water vapor content. Land surface temperatures were analyzed for different land use and land cover categories in the three regions. The heterogeneity of urban land surface and associated spatial extents were shown to influence surface thermal conditions because of the removal of vegetative cover, the introduction of non-transpiring surfaces, and the reduction in evaporation over urban impervious surfaces. Fifty years of in situ climate data were integrated to assess regional climatic conditions. The spatial structure of surface heating influenced by landscape characteristics has a profound influence on regional climate conditions, especially through urban heat island effects.     

基于多重分形参数的高光谱数据特征提取

针对单一分形维数不能表征高光谱数据光谱局部吸收特征的问题,提出了基于光谱概率测度的多重分形参数特征提取方法.基于光谱信息度量进行光谱概率测度的计算,基于配分函数法估计得到尺度函数;通过对尺度函数求导计算出Holder指数,并对尺度函数勒让德Legendre变换计算出多重分形谱;从多重分形谱和Holder指数之间的函数关系提取表征多重分形谱形态的4个多重分形谱参数作为光谱特征参数;并应用于基于最小距离准则的航空推扫式高光谱成像仪(PHI,Prush-broom Hyperspectral Imager)图像监督分类.结果证明:利用基于光谱概率测度的多重分形参数特征提取方法提取的光谱特征参数进行分类得到的总体分类正确率达94.789%,分类精度明显高于利用信息量维数和多重分形谱特征提取方法进行分类的结果,证明了基于光谱概率测度的多重分形参数特征提取方法提取的多重分形参数的有效性和可靠性.     

Using the MIR bands in vegetation indices for the estimation of grassland biophysical parameters from satellite remote sensing in the Alps region of Trentino (Italy)

Development of new methods for estimating biophysical parameters can be considered one of the most important targets for the improvement of grassland parameters estimation at full canopy cover. In fact, accurate assessment methods of biophysical characteristics of vegetation are needed in order to avoid the uncertainties of carbon terrestrial sinks.

Remote sensing is a valid tool for scaling up ecosystem measurements towards landscape levels serving a wide range of applications, many of them being related to carbon-cycle models. The aim of this study was to test the suitability of satellite platform sensors in estimating grassland biophysical parameters such as LAI, biomass, phytomass, and Green herbage ratio (GR). Also, we wanted to compare some of the most common NIR and red/green-based vegetation indices with ones that also make use of the MIR band, in relation to their ability to predict grassland biophysical parameters.

Ground-truth measurements were taken on July 2003 and 2004 on the Monte Bondone plateau (Italian Alps, Trento district) in grasslands varying in land use and management intensities. From satellite platforms, an IRS-1C-LISS III image (18/07/2003; 25 m resolution in the visible-NIR and 70 m resolution in the MIR) and a SPOT 5 image (27/07/2004, 10 m resolution in the visible-NIR and MIR) were used.

LAI, biomass, and phytomass measurements showed logarithmic relationships with the investigated NIR and red/green-based indices. GreenNDVI showed the highest R² values (0.59, IRS 2003; 0.60, SPOT 2004). Index saturation occurred above approximately 100–150 g m⁻² of biomass (LAI 1.5–2). On the other hand, GR relationships were shown to be linear. MIR-based indices performed better than NIR and red/green-based ones in estimating biophysical variables, with no saturation effect. Biomass showed a linear regression with Canopy Index (MIR/green ratio) and with the Normalised Canopy Index (NCI) calculated as a normalised difference between MIR and green bands (IRS: R² = 0.91 and 0.90, respectively. SPOT: R² = 0.63 and 0.64). Similar correlations could also be found for LAI and phytomass, and GR predictability was shown to be higher than NDVI and GreenNDVI. According to these results obtained in the investigated areas, phytomass, biomass, LAI, and GR are linearly correlated with the investigated MIR band indices and as a result, these parameters could be estimated from the adopted satellite platforms with limited saturation problems.     

基于无监督学习和粒子滤波的非视距信号检测

全球卫星导航系统(GNSS)是目前应用最广泛的定位技术,研究城市峡谷中的定位问题时,由于高楼大厦的阻塞,仍存在非视距传播导致的性能退化问题。为此,提出了无监督学习粒子滤波(UL-PF)算法。在卫星信号分类阶段,使用核k-means聚类的无监督学习分类方法,在定位阶段,使用通过聚类算法优化的粒子滤波方法。所提算法考虑了采样粒子在状态空间分布中的内在相似性,探索在每个聚类中选择一个粒子作为重要粒子,利用时间序列相关技术提高重采样粒子集的多样性。实验表明：在城市场景中,所提算法的平均定位精度从传统算法的15 m提高到约5 m,收敛时间从500 s缩短到200 s左右。     

Modeling urban heat islands in heterogeneous land surface and its correlation with impervious surface area by using night-time ASTER satellite data in highly urbanizing city,Delhi-India

The present study is an assessment and identification of urban heat island (UHI) in the environment of one of the fastest urbanizing city of India, Delhi Metropolis, employing satellite image of ASTER and Landsat 7 ETM+ in the thermal infrared region 3–14 μm. Temporal (2001 and 2005) ASTER datasets were used to analyze the spatial structure of the thermal urban environment subsequently urban heat island (UHI) in relation to the urban surface characteristics and land use/land cover (LULC). The study involves derivation of parameters governing the surface heat fluxes, constructing statistics of ASTER thermal infrared images along with validation through intensive in situ measurements. The average images reveal spatial and temporal variations of land surface temperature (LST) of night-time and distinct microclimatic patterns. Central Business District (CBD) of Delhi, (Connaught Place, a high density built up area), and commercial/industrial areas display heat islands condition with a temperature greater than 4 °C compared to the suburbs. The small increase in surface temperature at city level is mainly attributed to cumulative impact of human activities, changes in LULC pattern and vegetation density. In this study the methodology takes into account spatially-relative surface temperatures and impervious surface fraction value to measure surface UHI intensity between the urban land cover and rural surroundings. Both the spatial and temporal variation in surface temperature associated with impervious surface area (ISA) has been evaluated to assess the effect of urbanization on the local climate.