Surface roughness signatures of summer arctic snow-covered sea ice in X-band dual-polarimetric SAR

ABSTRACT

Surface roughness of sea ice is primary information for understanding sea ice dynamics and air–ice–ocean interactions. Synthetic aperture radar (SAR) is a powerful tool for investigating sea ice surface roughness owing to the high sensitivity of its signal to surface structures. In this study, we explored the surface roughness signatures of the summer Arctic snow-covered first-year sea ice in X-band dual-polarimetric SAR in terms of the root mean square (RMS) height. Two ice campaigns were conducted for the first-year sea ice with dry snow cover in the marginal ice zone of the Chukchi Sea in August 2017 and August 2018, from which high-resolution (4 cm) digital surface models (DSMs) of the sea ice were derived with the help of a terrestrial laser scanner to obtain the in situ RMS height. X-band dual-polarimetric (HH and VV) SAR data (3 m spatial resolution) were obtained for the 2017 campaign, at a high incidence angle (49.5°) of TerraSAR-X, and for the 2018 campaign, at a mid-incidence angle (36.1°) of TanDEM-X 1–2 days after the acquisition of the DSMs. The sea ice drifted during the time between the SAR and DSM acquisitions. As it is difficult to directly co-register the DSM to SAR owing to the difference in spatial resolution, the two datasets were geometrically matched using unmanned aerial vehicle (4 cm resolution) and helicopter-borne (30 cm resolution) photographs acquired as part of the ice campaigns. A total of five dual-polarimetric SAR features―backscattering coefficients at HH and VV polarizations, co-polarization ratio, co-polarization phase difference, and co-polarization correlation coefficient ―were computed from the dual-polarimetric SAR data and compared to the RMS height of the sea ice, which showed macroscale surface roughness. All the SAR features obtained at the high incidence angle were statistically weakly correlated with the RMS height of the sea ice, possibly influenced by the low backscattering close to the noise level that is attributed to the high incidence angle. The SAR features at the mid-incidence angle showed a statistically significant correlation with the RMS height of the sea ice, with Spearman’s correlation coefficient being higher than 0.7, except for the co-polarization ratio. Among the intensity-based and polarimetry-based SAR features, HH-polarized backscattering and co-polarization phase difference were analyzed to be the most sensitive to the macroscale RMS height of the sea ice. Our results show that the X-band dual-polarimetric SAR at mid-incidence angle exhibits potential for estimation of the macroscale surface roughness of the first-year sea ice with dry snow cover in summer.     

Fusion of RADARSAT-2 and multispectral optical remote sensing data for LULC extraction in a tropical agricultural area

In this study, we investigated the performance of different fusion and classification techniques for land cover mapping in Hilir Perak, Peninsula Malaysia using RADAR and Landsat-8 images in a predominantly agricultural area. The fusion methods used are Brovey Transform, Wavelet Transform, Ehlers and Layer Stacking and their results classified into seven different land cover classes which include (1) pixel-based classifiers (spectral angle mapper (SAM), maximum likelihood (ML), support vector machine (SVM)) and (2) Object-based (rule-based and standard nearest neighbour (NN)) classifiers. The result shows that pixel-based classification achieved maximum accuracy of the optical data classification using SVM in Landsat-8 with 74.96% accuracy compared to SAM and ML. For multisource data classification, the highest overall accuracy recorded for layer stacking (SVM) was 79.78%, Ehlers fusion (SVM) with 45.57%, Brovey fusion (SVM) with 63.70% and Wavelet fusion (SVM) 61.16%. And for object-based classifiers, the overall classification accuracy is 95.35% for rule-based and 76.33% for NN classifier, respectively. Based on the analysis of their performances, object-based and the rule-based classifiers produced the best classification accuracy from the fused images.     

Evaluating SAR polarization modes at L-band for forest classification purposes in Eastern Amazon,Brazil

Single, interferometric dual, and quad-polarization mode data were evaluated for the characterization and classification of seven land use classes in an area with shifting cultivation practices located in the Eastern Amazon (Brazil). The Advanced Land-Observing Satellite (ALOS) Phased Array L-band Synthetic Aperture Radar (PALSAR) data were acquired during a six month interval. A clear-sky Landsat-5/TM image acquired at the same period was used as additional ground reference and as ancillary input data in the classification scheme. We evaluated backscattering intensity, polarimetric features, interferometric coherence and texture parameters for classification purposes using support vector machines (SVM) and feature selection. Results showed that the forest classes were characterized by low temporal backscattering intensity variability, low coherence and high entropy. Quad polarization mode performed better than dual and single polarizations but overall accuracies remain low and were affected by precipitation events on the date and prior SAR date acquisition. Misclassifications were reduced by integrating Landsat data and an overall accuracy of 85% was attained. The integration of Landsat to both quad and dual polarization modes showed similarity at the 5% significance level. SVM was not affected by SAR dimensionality and feature selection technique reveals that co-polarized channels as well as SAR derived parameters such as Alpha-Entropy decomposition were important ranked features after Landsat’ near-infrared and green bands. We show that in absence of Landsat data, polarimetric features extracted from quad-polarization L-band increase classification accuracies when compared to single and dual polarization alone. We argue that the joint analysis of SAR and their derived parameters with optical data performs even better and thus encourage the further development of joint techniques under the Reducing Emissions from Deforestation and Degradation (REDD) mechanism.     

噪声抑制的多极化SAR海冰图像分割

合成孔径雷达(SAR)海冰图像分割对全球气候研究和保证船舶航行安全具有重要意义。现有的基于区域的马尔可夫随机场(MRF)多极化SAR分割方法,由于受相干斑噪声影响,其区域划分不尽合理,不能有效完成分割。因此,提出一种噪声抑制的多极化SAR海冰图像分割算法,首先在极化总功率图上引入降低噪声的滤波算法,合理划分初始区域,其次考虑区域之间的差异度,从而实现多极化SAR海冰图像的准确分割。以RADARSAT-2和SIR-C获得的全极化海冰图像为实验数据进行验证,结果表明:和其他较先进算法相比,本文算法优势明显,既能高效保持图像连通性,又能增强图像的细节信息,具有更高的分割精度。     

带有区域分裂自适应细化过程的SAR海冰图像分割

受海冰自身特性、成像系统特性和环境因素的影响,合成孔径雷达SAR海冰图像具有非平稳、尺度依赖的空间结构,现有的单马尔可夫随机场MRF模型分割方法只能较好地适应非平稳性,对海冰场景的多尺度结构考虑仍然是全局的。为此,本文提出了一种区域分裂过程与二叉树分层结构自适应更新相结合的单MRF图像分割方法。首先利用单MRF模型的全局迭代权值完成初始区域合并,同时以二叉树形式保护合并过程的记录。所设计的分层合并算法可保证二叉树结构的节点数与场景中的对象尺度具有正相关性。随后的细化分裂并不产生新的区域,只是返回到初始配置。依据场景中不同区域对象的尺度,自适应地调整空间语境模型中的尺度权值,实现区域更新。实验表明,该方法有效提高了带有多尺度结构SAR海冰场景的分割精度。     

A systematic comparison of different object-based classification techniques using high spatial resolution imagery in agricultural environments

Geographic Object-Based Image Analysis (GEOBIA) is becoming more prevalent in remote sensing classification, especially for high-resolution imagery. Many supervised classification approaches are applied to objects rather than pixels, and several studies have been conducted to evaluate the performance of such supervised classification techniques in GEOBIA. However, these studies did not systematically investigate all relevant factors affecting the classification (segmentation scale, training set size, feature selection and mixed objects). In this study, statistical methods and visual inspection were used to compare these factors systematically in two agricultural case studies in China. The results indicate that Random Forest (RF) and Support Vector Machines (SVM) are highly suitable for GEOBIA classifications in agricultural areas and confirm the expected general tendency, namely that the overall accuracies decline with increasing segmentation scale. All other investigated methods except for RF and SVM are more prone to obtain a lower accuracy due to the broken objects at fine scales. In contrast to some previous studies, the RF classifiers yielded the best results and the k-nearest neighbor classifier were the worst results, in most cases. Likewise, the RF and Decision Tree classifiers are the most robust with or without feature selection. The results of training sample analyses indicated that the RF and adaboost. M1 possess a superior generalization capability, except when dealing with small training sample sizes. Furthermore, the classification accuracies were directly related to the homogeneity/heterogeneity of the segmented objects for all classifiers. Finally, it was suggested that RF should be considered in most cases for agricultural mapping.     

日光温室的纹理特征分层提取

针对高分辨率影像上日光温室的信息提取问题,该文提出了利用支持向量机、最近邻算法结合纹理特征在不同层上分别提取连片日光温室和独栋日光温室的方法。实验表明:纹理特征能提高分类精度,在大尺度的层上,分类精度提升幅度较大,但在小尺度的层上,分类精度提升幅度会比较小;并不是参与运算特征数越多,分类精度越高,多数情况下光谱+纹理组合的分类精度最高;提取连片日光温室的最优方案是支持向量机和光谱+形状+纹理(7像素×7像素),总精度为92.86%,Kappa系数为0.90,而提取独栋日光温室最优方案为SVM和光谱+纹理(11像素×11像素),总精度为88.39%,Kappa系数为0.86。     

A new Likelihood Ratio for supervised classification of fully polarimetric SAR data: An application for sea ice type mapping

One of the potential applications of polarimetric Synthetic Aperture Radar (SAR) data is the classification of land cover, such as forest canopies, vegetation, sea ice types, and urban areas. In contrast to single or dual polarized SAR systems, full polarimetric SAR systems provide more information about the physical and geometrical properties of the imaged area. This paper proposes a new Bayes risk function which can be minimized to obtain a Likelihood Ratio (LR) for the supervised classification of polarimetric SAR data. The derived Bayes risk function is based on the complex Wishart distribution. Furthermore, a new spatial criterion is incorporated with the LR classification process to produce more homogeneous classes. The application for Arctic sea ice mapping shows that the LR and the proposed spatial criterion are able to provide promising classification results. Comparison with classification results based on the Wishart classifier, the Wishart Likelihood Ratio Test Statistic (WLRTS) proposed by Conradsen et al. (2003) and the Expectation Maximization with Probabilistic Label Relaxation (EMPLR) algorithm are presented. High overall classification accuracy of selected study areas which reaches 97.8% using the LR is obtained. Combining the derived spatial criterion with the LR can improve the overall classification accuracy to reach 99.9%. In this study, fully polarimetric C-band RADARSAT-2 data collected over Franklin Bay, Canadian Arctic, is used.     

机载X波段极化干涉SAR数据非监督分类方法研究

针对经典极化分类算法在处理机载X波段SAR数据时将过多地物分为体散射类型,并且容易受噪声影响,分类结果存在大量误分现象的问题,通过对机载X波段SAR数据非监督分类方法的研究,提出将极化干涉信息用于机载X波段极化干涉SAR数据的分类。通过运用极化干涉数据进行目标分解得到参数A1和A2对数据进行初始分类,然后结合改进的Wishart最大似然分类算法来进行地物的自适应分类。实验结果表明,该方法能有效避免平地效应的影响,抗噪性好,能正确区分三种典型散射类型,分类效果明显优于极化分类效果。     

ScanSAR模式海冰图像的分割

合成孔径雷达SAR(Synthetic Aperture Radar)图像的非平稳性是SAR海冰图像自动解释的主要障碍,入射角效应是导致海冰图像特征不稳定的主要因素之一。基于Radarsat-1 ScanSAR模式数据,本文提出了一种集成入射角效应校正步骤的分割算法。该方法综合考虑了入射角效应、斑点噪声等不确定因素,经由像素到区域再到大尺度区域这一途径,把区域聚类、类尺度上的入射角效应校正以及区域合并等操作组合起来,以有效提高分割算法对非平稳性的适应能力。针对巴芬湾和和波斯尼亚湾ScanSAR模式图像的实验表明,本文提出的方法可有效提高分割准确性。     

Analyzing fine-scale wetland composition using high resolution imagery and texture features

In order to monitor natural and anthropogenic disturbance effects to wetland ecosystems, it is necessary to employ both accurate and rapid mapping of wet graminoid/sedge communities. Thus, it is desirable to utilize automated classification algorithms so that the monitoring can be done regularly and in an efficient manner. This study developed a classification and accuracy assessment method for wetland mapping of at-risk plant communities in marl prairie and marsh areas of the Everglades National Park. Maximum likelihood (ML) and Support Vector Machine (SVM) classifiers were tested using 30.5 cm aerial imagery, the normalized difference vegetation index (NDVI), first and second order texture features and ancillary data. Additionally, appropriate window sizes for different texture features were estimated using semivariogram analysis. Findings show that the addition of NDVI and texture features increased classification accuracy from 66.2% using the ML classifier (spectral bands only) to 83.71% using the SVM classifier (spectral bands, NDVI and first order texture features).     

Development of fuzzy rule-based parameters for urban object-oriented classification using very high resolution imagery

Urban areas consist of spectrally and spatially heterogeneous features. Advanced information extraction techniques are needed to handle high resolution imageries in providing detailed information for urban planning applications. This study was conducted to identify a technique that accurately maps impervious and pervious surfaces from WorldView-2 (WV-2) imagery. Supervised per-pixel classification algorithms including Maximum Likelihood and Support Vector Machine (SVM) were utilized to evaluate the capability of spectral-based classifiers to classify urban features. Object-oriented classification was performed using supervised SVM and fuzzy rule-based approach to add spatial and texture attributes to spectral information. Supervised object-oriented SVM achieved 82.80% overall accuracy which was the better accuracy compared to supervised per-pixel classifiers. Classification based on the proposed fuzzy rule-based system revealed satisfactory output compared to other classification techniques with an overall accuracy of 87.10% for pervious surfaces and an overall accuracy of 85.19% for impervious surfaces.     

典型遥感数据分类方法的适用性分析——以遥感图像场景分类为例

目前普遍采用的分类器通常都是针对单一或小量任务而设计的,在小数据量的处理中能取得比较满意的结果。但对于海量遥感数据的处理,其在处理时效和分类精度方面还有待研究。本文以遥感图像场景分类任务为例,着重对遥感数据分类问题中几种典型分类方法的适用性进行比较研究,包括K近邻(KNN)、随机森林(RF),支持向量机(SVM)和稀疏表达分类器(SRC)等。分别从参数敏感性,训练样本数据量,待分类样本数据量和样本特征维数对分类器性能的影响等几个方面进行比较分析。实验结果表明:(1)KNN,RF和L0-SRC方法相比RBF-SVM,Linear-SVM和L1-SRC,受参数影响的程度更弱;(2)待分类样本固定的情况下,随着训练样本数目的增加,SRC类型分类方法的分类性能最佳,SVM类型方法次之,然后是RF和KNN,在总体分类时间上呈现出L0-SRCL1-SRCRFRBF-SVM/Linear-SVMKNN/L0-SRC-Batch的趋势;(3)训练样本固定的情况下,所有分类方法的分类精度几乎都不受待分类样本数目变化的影响,RBF-SVM方法性能最佳,其次是L1-SRC,然后是Linear-SVM,最后是RF和L0-SRC/L0-SRC-Batch,在总体分类时间上,L1-SRC和L0-SRC相比其他分类方法最为耗时;(4)样本特征维数的变化不仅影响分类器的运行效率,同时也影响其分类精度,其中SRC和KNN分类器器无需较高的特征维数即可获得较好的分类结果,SVM对高维特征具有较强的包容性和学习能力,RF分类器对特征维数增加则表现得并不敏感,特征维数的增加并不能对其分类精度的提升带来更多的贡献。总的来说,在大数据量的遥感数据分类任务中,现有分类方法具有良好的适用性,但是对于分类器的选择应当基于各自的特点和优势,结合实际应用的特点进行权衡和选择,选择参数敏感性较小,分类总体时间消耗低但分类精度相对较高的分类方法。     

Evaluation of different machine learning methods for land cover mapping of a Mediterranean area using multi-seasonal Landsat images and Digital Terrain Models

Land cover monitoring using digital Earth data requires robust classification methods that allow the accurate mapping of complex land cover categories. This paper discusses the crucial issues related to the application of different up-to-date machine learning classifiers: classification trees (CT), artificial neural networks (ANN), support vector machines (SVM) and random forest (RF). The analysis of the statistical significance of the differences between the performance of these algorithms, as well as sensitivity to data set size reduction and noise were also analysed. Landsat-5 Thematic Mapper data captured in European spring and summer were used with auxiliary variables derived from a digital terrain model to classify 14 different land cover categories in south Spain. Overall, statistically similar accuracies of over 91% were obtained for ANN, SVM and RF. However, the findings of this study show differences in the accuracy of the classifiers, being RF the most accurate classifier with a very simple parameterization. SVM, followed by RF, was the most robust classifier to noise and data reduction. Significant differences in their performances were only reached for thresholds of noise and data reduction greater than 20% (noise, SVM) and 25% (noise, RF), and 80% (reduction, SVM) and 50% (reduction, RF), respectively.     

Discrimination of species composition types of a grazed pasture landscape using Sentinel-1 and Sentinel-2 data

Species composition is one of the important measurable indices of alpha diversity and hence aligns with the measurable Essential Biodiversity Variables meant to fulfil the Aichi Biodiversity Targets by 2020. Graziers also seek for pasture fields with varied species composition for their livestock, but visual determination of the species composition is not practicable for graziers with large fields. Consequently, this study demonstrated the capability of Sentinel-1 Synthetic Aperture Radar (S1) and Sentinel-2 Multispectral Instrument (S2) to discriminate pasture fields with single-species composition, two-species composition and multi-species composition for a pastoral landscape in Australia. The study used K-Nearest Neighbours (KNN), Random Forest (RF) and Support Vector Machine (SVM) classifiers to evaluate the strengths of S1-alone and S2-alone features and the combination of these S1 and S2 features to discriminate the composition types. For the S1 experiment, KNN which was the reference classifier achieved an overall accuracy of 0.85 while RF and SVM produced 0.74 and 0.89, respectively. The S2 experiment produced accuracies higher than the S1 in that the overall performance of the KNN classifier was 0.87 while RF and SVM were 0.93 and 0.89, respectively. The combination of the S1 and S2 features elicited the highest accuracy estimates of the classifiers in that the KNN classifier recorded 0.89 while RF and SVM produced 0.96 and 0.93, respectively. In conclusion, the inclusion of S1 features improve the classifiers created with S2 features only.     

利用目标分解特征的全极化SAR海冰分类

特征提取及其选择是SAR海冰分类的重要步骤之一。在众多特征中选取有效特征,进而构建表达地物类型的特征空间是提高分类精度的关键。为此,本文提出一种基于目标分解特征的全极化SAR海冰分类算法。首先,对全极化SAR数据进行多视化处理及滤波操作,生成相干矩阵;其次,对相干矩阵进行目标分解,并针对分解结果提取散射特征参数,进而构建特征空间;再次,通过对所提取的特征进行统计相关性分析,并对高相关特征采用PCA降维,以优化特征组合;最后,设计BP神经网络分类器,并将所得的优化特征矢量作为输入,海冰类别为输出,实现海冰分类。本文以格陵兰中部海域作为研究试验区域,采用L波段ALOS PALSAR全极化数据。通过对本文算法与对比算法的分类结果进行定性定量分析,可以得出本文所选取的特征对海冰识别较好。此外,通过对利用各个不同特征海冰分类结果的性能分析,可以得出基于散射模型的目标分解比基于特征值的H/α/A分解更有助于海冰分类。     

Water-Body types identification in urban areas from radarsat-2 fully polarimetric SAR data

This paper presents a novel method for supervised water-body extraction and water-body types identification from Radarsat-2 fully polarimetric (FP) synthetic aperture radar (SAR) data in complex urban areas. First, supervised water-body extraction using the Wishart classifier is performed, and the false alarms that are formed in built-up areas are removed using morphological processing methods and spatial contextual information. Then, the support vector machine (SVM), the classification and regression tree (CART), TreeBagger (TB), and random forest (RF) classifiers are introduced for water-body types (rivers, lakes, ponds) identification. In SAR images, certain other objects that are misclassified as water are also considered in water-body types identification. Several shape and polarimetric features of each candidate water-body are used for identification. Radarsat-2 PolSAR data that were acquired over Suzhou city and Dongguan city in China are used to validate the effectiveness of the proposed method, and the experimental results are evaluated at both the object and pixel levels. We compared the water-body types classification results using only shape features and the combination of shape and polarimetric features, the experimental results show that the polarimetric features can eliminate the misclassifications from certain other objects like roads to water areas, and the increasement of classification accuracy embodies at both the object and pixel levels. The experimental results show that the proposed methods can achieve satisfactory accuracies at the object level [89.4% (Suzhou), 95.53% (Dongguan)] and the pixel level [96.22% (Suzhou), 97.95% (Dongguan)] for water-body types classification, respectively.     

利用SVM的全极化、双极化与单极化SAR图像分类性能的比较

支持向量机(SVM)以其在小训练样本时良好的分类性能,目前已广泛应用于多个领域.本文在极化SAR图像特征提取基础上,将SVM应用于极化SAR图像分类,定性和定量地比较了全极化、双极化和单极化SAR图像的分类性能,分析了不同的极化组合对分类结果的影响,并根据地物极化散射特性分析了分类精度差异的成因.实测极化SAR数据的实验结果表明,全极化数据能获得最好的分类性能,双极化次之,单极化最低,且在某些情况下,双极化与全极化分类性能接近.     

Assessing integration of intensity,polarimetric scattering,interferometric coherence and spatial texture metrics in PALSAR-derived land cover classification

Synthetic aperture radar (SAR) is an important alternative to optical remote sensing due to its ability to acquire data regardless of weather conditions and day/night cycle. The Phased Array type L-band SAR (PALSAR) onboard the Advanced Land Observing Satellite (ALOS) provided new opportunities for vegetation and land cover mapping. Most previous studies employing PALSAR investigated the use of one or two feature types (e.g. intensity, coherence); however, little effort has been devoted to assessing the simultaneous integration of multiple types of features. In this study, we bridged this gap by evaluating the potential of using numerous metrics expressing four feature types: intensity, polarimetric scattering, interferometric coherence and spatial texture. Our case study was conducted in Central New York State, USA using multitemporal PALSAR imagery from 2010. The land cover classification implemented an ensemble learning algorithm, namely random forest. Accuracies of each classified map produced from different combinations of features were assessed on a pixel-by-pixel basis using validation data obtained from a stratified random sample. Among the different combinations of feature types evaluated, intensity was the most indispensable because intensity was included in all of the highest accuracy scenarios. However, relative to using only intensity metrics, combining all four feature types increased overall accuracy by 7%. Producer’s and user’s accuracies of the four vegetation classes improved considerably for the best performing combination of features when compared to classifications using only a single feature type.     

An effective ensemble classification framework using random forests and a correlation based feature selection technique

Accurate classification of heterogeneous land surfaces with homogeneous land cover classes is a challenging task as satellite images are characterized by a large number of features in the spectral and spatial domains. The identifying relevance of a feature or feature set is an important task for designing an effective classification scheme. Here, an ensemble of random forests (RF) classifiers is realized on the basis of relevance of features. Correlation‐based Feature Selection (CFS) was utilized to assess the relevance of a subset of features by studying the individual predictive ability of each feature along with the degree of redundancy between them. Predictability of RF was greatly improved by random selection of the relevant features in each of the splits. An investigation was carried out on different types of images from the Landsat Enhanced Thematic Mapper Plus (Landsat ETM+) and QuickBird sensors. It has been observed that the performance of the RF classifier was significantly improved while using the optimal set of relevant features compared with a few of the most advanced supervised classifiers such as maximum likelihood classifier (MLC), Navie Bayes, multi‐layer perception (MLP), support vector machine (SVM) and bagging.