Assessing the suitability of data from Sentinel-1A and 2A for crop classification

Sentinel-1A C-SAR and Sentinel-2A MultiSpectral Instrument (MSI) provide data applicable to the remote identification of crop type. In this study, six crop types (beans, beetroot, grass, maize, potato, and winter wheat) were identified using five C-SAR images and one MSI image acquired during the 2016 growing season. To assess the potential for accurate crop classification with existing supervised learning models, the four different approaches namely kernel-based extreme learning machine (KELM), multilayer feedforward neural networks, random forests, and support vector machine were compared. Algorithm hyperparameters were tuned using Bayesian optimization. Overall, KELM yielded the highest performance, achieving an overall classification accuracy of 96.8%. Evaluation of the sensitivity of classification models and relative importance of data types using data-based sensitivity analysis showed that the set of VV polarization data acquired on 24 July (Sentinel-1A) and band 4 data (Sentinel-2A) had the greatest potential for use in crop classification.     

Estimation of winter wheat crop growth parameters using time series Sentinel-1A SAR data

In the present study, Sentinel-1A Synthetic Aperture Radar analysis of time series data at C-band was carried out to estimate the winter wheat crop growth parameters. Five different date images were acquired during January 2015–April 2015 at different growth stages from tillering to ripening in Varanasi district, India. The winter wheat crop parameters, i.e. leaf area index, vegetation water content (VWC), fresh biomass (FB), dry biomass (DB) and plant height (PH) were estimated using random forest regression (RFR), support vector regression (SVR), artificial neural network regression (ANNR) and linear regression (LR) algorithms. The Ground Range Detected products of Interferometric Wide (IW) Swath were used at VV polarization. The three different subplots of 1 m² area were taken for the measurement of crop parameters at every growth stage. In total, 73 samples were taken as the training data-sets and 39 samples were taken as testing data-sets. The highest sensitivity (adj. R^2?=?0.95579) of backscattering with VWC was found using RFR algorithm, whereas the lowest sensitivity (adj. R^2?=?0.66201) was found for the PH using LR algorithm. Overall results indicate more accurate estimation of winter wheat parameters by the RFR algorithm followed by SVR, ANNR and LR algorithms.     

Detecting Sirex noctilio grey-attacked and lightning-struck pine trees using airborne hyperspectral data,random forest and support vector machines classifiers

The visual progression of sirex (Sirex noctilio) infestation symptoms has been categorized into three distinct infestation phases, namely the green, red and grey stages. The grey stage is the final stage which leads to almost complete defoliation resulting in dead standing trees or snags. Dead standing pine trees however, could also be due to the lightning damage. Hence, the objective of the present study was to distinguish amongst healthy, sirex grey-attacked and lightning-damaged pine trees using AISA Eagle hyperspectral data, random forest (RF) and support vector machines (SVM) classifiers. Our study also presents an opportunity to look at the possibility of separating amongst the previously mentioned pine trees damage classes and other landscape classes on the study area. The results of the present study revealed the robustness of the two machine learning classifiers with an overall accuracy of 74.50% (total disagreement = 26%) for RF and 73.50% (total disagreement = 27%) for SVM using all the remaining AISA Eagle spectral bands after removing the noisy ones. When the most useful spectral bands as measured by RF were exploited, the overall accuracy was considerably improved; 78% (total disagreement = 22%) for RF and 76.50% (total disagreement = 24%) for SVM. There was no significant difference between the performances of the two classifiers as demonstrated by the results of McNemar’s test (chi-squared; χ² = 0.14, and 0.03 when all the remaining ASIA Eagle wavebands, after removing the noisy ones and the most important wavebands were used, respectively). This study concludes that AISA Eagle data classified using RF and SVM algorithms provide relatively accurate information that is important to the forest industry for making informed decision regarding pine plantations health protocols.     

A kernel functions analysis for support vector machines for land cover classification

Information about the Earth's surface is required in many wide-scale applications. Land cover/use classification using remotely sensed images is one of the most common applications in remote sensing, and many algorithms have been developed and applied for this purpose in the literature. Support vector machines (SVMs) are a group of supervised classification algorithms that have been recently used in the remote sensing field. The classification accuracy produced by SVMs may show variation depending on the choice of the kernel function and its parameters. In this study, SVMs were used for land cover classification of Gebze district of Turkey using Landsat ETM+ and Terra ASTER images. Polynomial and radial basis kernel functions with their estimated optimum parameters were applied for the classification of the data sets and the results were analyzed thoroughly. Results showed that SVMs, especially with the use of radial basis function kernel, outperform the maximum likelihood classifier in terms of overall and individual class accuracies. Some important findings were also obtained concerning the changes in land use/cover in the study area. This study verifies the effectiveness and robustness of SVMs in the classification of remotely sensed images.     

Discriminating transplanted and direct seeded rice using Sentinel-1 intensity data

Improved rice crop and water management practices that make the sustainable use of resources more efficient are important interventions towards a more food secure future. A remote sensing-based detection of different rice crop management practices, such as crop establishment method (transplanting or direct seeding), can provide timely and cost-effective information on which practices are used as well as their spread and change over time as different management practices are adopted. Establishment method cannot be easily observed since it is a rapid event, but it can be inferred from resulting observable differences in land surface characteristics (i.e. field condition) and crop development (i.e. delayed or prolonged stages) that take place over a longer time. To examine this, we used temporal information from Synthetic Aperture Radar (SAR) backscatter to detect differences in field condition and rice growth, then related those to crop establishment practices in Nueva Ecija (Philippines). Specifically, multi-temporal, dual-polarised, C-band backscatter data at 20m spatial resolution was acquired from Sentinel-1A every 12 days over the study area during the dry season, from November 2016 to May 2017. Farmer surveys and field observations were conducted in four selected municipalities across the study area in 2017, providing information on field boundaries and crop management practices for 61 fields. Mean backscatter values were generated per rice field per SAR acquisition date. We matched the SAR acquisition dates with the reported dates for land management activities and with the estimated dates for when the crop growth stages occurred. The Mann-Whitney U test was used to identify significant differences in backscatter between the two practices during the land management activities and crop growth stages. Significant differences in cross-polarised, co-polarised and band ratio backscatter values were observed in the early growing season, specifically during land preparation, crop establishment, rice tillering and stem elongation. These findings indicate the possibility to discriminate crop establishment methods by SAR at those stages, suggesting that there is more opportunity for discrimination than has been presented in previous studies. Further testing in a wider range of environments, seasons, and management practices should be done to determine how reliably rice establishment methods can be detected. The increased use of dry and wet direct seeding has implications for many remote sensing-based rice detection methods that rely on a strong water signal (typical of transplanting) during the early season.     

A support vector machine to identify irrigated crop types using time-series Landsat NDVI data

Site-specific information of crop types is required for many agro-environmental assessments. The study investigated the potential of support vector machines (SVMs) in discriminating various crop types in a complex cropping system in the Phoenix Active Management Area. We applied SVMs to Landsat time-series Normalized Difference Vegetation Index (NDVI) data using training datasets selected by two different approaches: stratified random approach and intelligent selection approach using local knowledge. The SVM models effectively classified nine major crop types with overall accuracies of >86% for both training datasets. Our results showed that the intelligent selection approach was able to reduce the training set size and achieved higher overall classification accuracy than the stratified random approach. The intelligent selection approach is particularly useful when the availability of reference data is limited and unbalanced among different classes. The study demonstrated the potential of utilizing multi-temporal Landsat imagery to systematically monitor crop types and cropping patterns over time in arid and semi-arid regions.     

利用Sentinel-1A数据监测地表形变案例分析

雷达卫星结合InSAR技术已广泛应用于高精度地表形变监测领域。本文选取2017年九寨沟地震为研究案例,利用Sentinel-1A地震前后的单视复数影像,基于D-InSAR技术获取该次地震的同震形变场。结果显示:震中西北侧表现出相对均匀的下沉现象,沉降漏斗区雷达视线向最大沉降量达25.1 cm;东南侧呈现不均匀抬升状态,地表破碎较为明显,最大抬升量为11.6 cm。研究表明基于Sentinel-1A数据的D-InSAR技术可以为地震形变场的定量分析提供一种快速有效的手段,为阐释地震发震机理及评估受灾情况提供必要的数据支撑,具有广阔的应用前景。     

An experimental approach for selection/elimination in stream network generalization using support vector machines

Multi-representation databases (MRDB) are used in several Geographical Information System applications for different purposes. MRDB are mainly obtained through model and cartographic generalizations. The model generalization is essentially achieved with the selection/elimination process in which a decision must be made to include or exclude the object at the target level. In this study, support vector machines (SVM) was, for the first time, used for the selection/elimination process in stream network generalization. Within this context, the attributes to be used as input data in the SVM method were determined and weighted according to the associations determined in a chi-squared independence test. 1:100,000-scale (medium resolution) stream networks were derived from two 1:24,000-scale (high resolution) stream networks with different patterns in the United States Geological Survey National Hydrography Data-sets. The derived stream networks were quite similar to the 1:100,000-scale original stream networks in both qualitative and visual aspects.     

利用Sentinel-1 SAR数据及SBAS技术的大区域地表形变监测

雷达干涉测量技术为地面沉降高精度快速准确监测提供了新的手段。对于数万平方千米的大范围地面沉降,要求测量手段不仅具备高精度,还要具备大范围同步测量的能力。为解决这一问题,本文提出了利用Sentinel-1数据结合SBAS技术的监测方法,首先对黄河三角洲区域进行形变监测,然后利用CORS数据进行验证,最后对地面沉降的时空分布情况进行分析。该研究证明了采用该方法对大区域形变监测的适用性,为该区域沉降预防和治理提供了重要依据。     

基于Sentinel-1A数据的多种机器学习算法识别冰山的比较

冰山识别对于海洋环境监测和船只安全运行等具有重要的意义,是北极航道开通和北极开发过程中的重要内容。采用合成孔径雷达(SAR)影像进行冰山识别具有独特的优势,多种机器学习算法均可用于SAR影像的冰山识别中。为了最大限度地发挥机器学习算法的性能,有必要对不同机器学习算法及其搭配使用的特征与特征标准化方法进行评估,从而进行最优冰山识别方法的选择。因此,本文基于Sentinel-1A SAR影像,采用多种机器学习方法、多种特征组合及多种特征标准化方法进行冰山识别,并比较各流程方法的识别性能差异。采用的机器学习算法包括贝叶斯分类器(Bayes)、反向神经网络(BPNN)、线性判别分析(LDA)、随机森林(RF)以及支持向量机(SVM);特征标准化方法包括Min-max标准化、Z-score标准化及log函数标准化;数据集是含有12个SAR影像特征的969个冰山与非冰山样本,样本主要位于格陵兰岛东海岸。分类效果采用接收者操作特性(ROC)曲线下的面积(AUC)进行衡量。结果显示,最佳搭配下的RF的AUC值最高,达到了0.945,比最差的Bayes高出0.09。从识别率上来看,RF在冰山查全率为80%的情况下非冰山查全率达到92.6%,效果最好,比第2位的BPNN高出1.4%,比最差的Bayes高出2.6%;BPNN在冰山查全率为90%的情况下非冰山查全率达到87.4%,比第2位的RF高出0.8%,比最差的Bayes高出2.7%。上述结果表明,对冰山识别而言,选择最优的机器学习算法和最佳的特征与特征标准化方法都是十分重要的。     

融合Landsat 8与Sentinel-2数据的红树林物候信息提取与分类

科学准确地监测红树林是保护海陆过渡性生态系统的基础和前提,但红树林分布于潮间带,难以进行大规模人工监测。遥感技术能够对红树林进行长时间、大面积监测,但已有研究尚存不足。一方面,红树林分布于热带、亚热带区域,受到天气条件限制难以获得长时间覆盖的有效光学遥感数据;另一方面,红树林极易与其他陆生植被混淆,仅利用多波段数据的光谱信息难以精确识别。本文以恒河三角洲孙德尔本斯地区为例,基于谷歌地球引擎GEE（Google Earth Engine）获取2016年全年的Landsat 8 OLI和Sentinel-2 MSI数据,利用物候信息进行红树林提取研究。首先,基于最小二乘回归构建两个传感器在相同指数之间的关系,重建时间序列数据,之后根据可分性判据选取增强型植被指数EVI（Enhanced Vegetation Index）和陆地表面水分指数LSWI（Land Surface Water Index）。其次,对两个指数的时间序列数据进行Savitzky-Golay滤波处理,并分别提取生长期始期等13种物候信息。最后,将两个指数的物候信息进行特征级联,采用随机森林RF（Random Forest）方法进行分类,提取研究区红树林范围。实验结果表明：Landsat 8 OLI和Sentinel-2 MSI数据融合可有效提升时间序列质量,与基于单一传感器数据的分类结果相比,总体精度提高1.58%;物候信息可以显著增强红树林与其他植被的可分性,与直接使用时间序列数据的分类结果相比,总体精度提高1.92%;同时考虑EVI和LSWI指数可极大地提升分类效果,与采用单一指数相比,总体精度分别提高14.11%和9.69%。因此,本文通过数据融合、物候信息提取和指数特征级联可以更好地提取红树林,总体精度达到91.02%,Kappa系数为0.892。研究验证了物候信息在红树林遥感监测中的应用潜力,提出的方法对科学准确地监测全球或区域红树林具有一定参考价值。     

Sentinel-1A数据的四川宜宾Ms6.0同震形变分析

为了获取2019年6月17日发生的四川宜宾Ms6.0地震引起的地表形变情况,该文利用欧空局宽幅模式的高分辨率新型Sentinel-1A卫星获取了此次地震的第一对同震干涉像对数据,使用D-InSAR技术获取宜宾市长宁县地区的同震形变场。结果显示,本次地震在震中西北方向分别形成了1个明显的沉降区和抬升区,在雷达视线方向上的最大沉降量为7.9 cm,最大抬升量为8.1 cm。通过与同一时间内的GPS高程测量形变量相比,D-InSAR解算的地表形变量与GPS监测点形变量基本一致,均不超过3 mm,表明了本文的D-InSAR形变解算结果的可靠性,体现了新型Sentinel-1A雷达卫星在地震形变监测领域有着很高的应用价值和潜力。     

Mapping wetland characteristics using temporally dense Sentinel-1 and Sentinel-2 data: A case study in the St. Lucia wetlands,South Africa

Wetlands have been determined as one of the most valuable ecosystems on Earth and are currently being lost at alarming rates. Large-scale monitoring of wetlands is of high importance, but also challenging. The Sentinel-1 and -2 satellite missions for the first time provide radar and optical data at high spatial and temporal detail, and with this a unique opportunity for more accurate wetland mapping from space arises. Recent studies already used Sentinel-1 and -2 data to map specific wetland types or characteristics, but for comprehensive wetland characterisations the potential of the data has not been researched yet. The aim of our research was to study the use of the high-resolution and temporally dense Sentinel-1 and -2 data for wetland mapping in multiple levels of characterisation. The use of the data was assessed by applying Random Forests for multiple classification levels including general wetland delineation, wetland vegetation types and surface water dynamics. The results for the St. Lucia wetlands in South Africa showed that combining Sentinel-1 and -2 led to significantly higher classification accuracies than for using the systems separately. Accuracies were relatively poor for classifications in high-vegetated wetlands, as subcanopy flooding could not be detected with Sentinel-1’s C-band sensors operating in VV/VH mode. When excluding high-vegetated areas, overall accuracies were reached of 88.5% for general wetland delineation, 90.7% for mapping wetland vegetation types and 87.1% for mapping surface water dynamics. Sentinel-2 was particularly of value for general wetland delineation, while Sentinel-1 showed more value for mapping wetland vegetation types. Overlaid maps of all classification levels obtained overall accuracies of 69.1% and 76.4% for classifying ten and seven wetland classes respectively.     

一种利用哨兵1号数据提取南极接地线方法

针对因IW工作模式数据在南极地区覆盖不全面导致对南极接地线的全面提取造成影响的问题,提出利用双差干涉测量提取接地线的基本原理,分别利用工作模式为IW和EW的Sentinel-1雷达卫星数据,对东南极毛德皇后地沿岸冰川接地线进行提取,将提取结果分别与MEa-SUREs接地线产品进行对比,同时再将这两种模式下的提取结果进行对比分析。结果表明,双差干涉测量可以去除冰流相位的影响,使用EW工作模式的Sentinel-1数据进行南极接地线提取可以忽略其地面分辨率较低这一缺陷,同时,这一模式的Sentinel-1数据在幅宽、南极覆盖范围等方面更具优势。因此,综合利用IW和EW工作模式的Sentinel-1数据,对南极接地线的全面、高效、长期动态监测具有重要意义。     

Support vector machines for tree species identification using LiDAR-derived structure and intensity variables

Tree species identification and forest type classification are critical for sustainable forest management and native forest conservation. Recent success in forest classification and tree species identification using LiDAR (light detection and ranging)-derived variables has been reported in many studies. However, there is still considerable scope for further improvement in classification accuracy. It has driven research into more efficient classifiers such as support vector machines (SVMs) to take maximum advantage of the information extracted from LiDAR data for potential increases in the accuracy of tree species classification. This study demonstrated the success of the SVMs for the identification of the Myrtle Beech (the dominant species of the Australian cool temperate rainforest in the study area) and adjacent tree species – notably, the Silver Wattle at individual tree level using LiDAR-derived structure and intensity variables. An overall accuracy of 92.8% was achieved from the SVM approach, showing significant advantages of the SVMs over the traditional classification methods such as linear discriminant analysis in terms of classification accuracy.     

Supervised change detection in VHR images using contextual information and support vector machines

In this paper we study an effective solution to deal with supervised change detection in very high geometrical resolution (VHR) images. High within-class variance as well as low between-class variance that characterize this kind of imagery make the detection and classification of ground cover transitions a difficult task. In order to achieve high detection accuracy, we propose the inclusion of spatial and contextual information issued from local textural statistics and mathematical morphology. To perform change detection, two architectures, initially developed for medium resolution images, are adapted for VHR: Direct Multi-date Classification and Difference Image Analysis. To cope with the high intra-class variability, we adopted a nonlinear classifier: the Support Vector Machines (SVM). The proposed approaches are successfully evaluated on two series of pansharpened QuickBird images.     

最小二乘支持向量机回归的卫星钟差非线性组合预报

针对应用单一方法预报卫星钟差的局限性,文章提出了基于最小二乘支持向量机回归的卫星钟差非线性组合预报方法:首先根据历史钟差数据建立二次多项式模型和灰色模型,然后利用这些模型进行钟差预报,最后采用最小二乘支持向量机回归算法对两种模型的预报结果进行非线性组合,以获得最终预报值;对比了RBF核函数、线性核函数和多项式核函数对组合预报性能的影响,并将本文组合预报方法与经典权组合方法进行比较。结果表明,本文方法优于经典权法,且线性核函数更适合组合预报。     

条件随机场框架下基于随机森林的城市土地利用/覆盖遥感分类

针对"基于像素的条件随机场(conditional random fields,CRFs)模型能否在m级分辨率的多光谱遥感图像分类中表现良好"的问题,提出了集成图像的光谱、方向梯度直方图和多尺度多方向Texton纹理等多种线索的CRFs模型定义方法。利用上述特征,选择随机森林(random forests,RF)定义CRFs关联势函数;利用特征对比度加权的Potts函数定义CRFs交互势函数,并且建立了多标签的RF-CRFs模型;对该模型进行分项参数训练以及基于图割的α-膨胀算法推理;利用典型城区的Quick Bird多光谱图像进行模型的验证与精度评价。结果表明RF-CRFs模型的分类精度可达82.52%以上,比RF分类器的分类精度提高了3.35%。     

面向对象规则和支持向量机的天宫一号高光谱影像分类

传统的高光谱分类方法通常基于单一像元的光谱或纹理特征,很少考虑地物空间结构信息与空间相关特征.本文将面向对象规则与基于像元的分类进行融合,利用对象的空间结构特征和光谱特征进行混合分类,旨在克服像元层次分类的不足.本文尝试性的提出了两种混合分类方法:(1)基于分形网络演化的多尺度分割支持向量机分类(2)基于多层分水岭分割的SVM分类,并将这两种方法应用到天宫一号高光谱数据上.结果表明:基于面向对象规则的混合分类方法有效地提高了分类精度,不仅能够改善同谱异物现象,而且解决分类结果中地物破碎的问题.     

Evaluation of polarimetric capabilities of dual polarized Sentinel-1 and TerraSAR-X data to improve the PSInSAR algorithm using amplitude dispersion index optimization

Polarimetric data is an additional source of information in PSI technique to improve its performance in land subsidence estimation. The combination of polarimetric data and radar interferometry can lead to an increase in coherence and the number of PS pixels. In this paper, we evaluated and compared the dual polarized Sentinel-1A (S1A) and TerraSAR-X (TSX) data to improve the PSInSAR algorithm. The improvement of this research is based on minimizing Amplitude Dispersion Index (ADI) by finding the optimum scattering mechanism to increase the number of PSC and PS pixels. The proposed method was tested using a dataset of 40 dual-pol SAR data (VV/VH) acquired by S1A and 20 dual-pol SAR data (HH/VV) acquired by TSX. The results revealed that using the TSX data, the number of PS pixels increased about 3 times in ESPO method than using the conventional channels, e.g., HH, and VV. This increase in S1A data was about 1.7 times in ESPO method. In addition, we investigated the efficiency of the three polarimetric optimization methods i.e. ESPO, BGSM, and Best for the dual polarized S1A and TSX data. Results showed that the PS density increased about 1.9 times in BGSM and about 1.5 times in Best method in TSX data. However, in S1A data, PS density increased about 1.1 times in BGSM. The Best method was not successful in increasing the PS density using the S1A data. Also, the effectiveness of the method was evaluated in urban and non-urban regions. The experimental results showed that the method was successful in significantly increasing the number of final PS pixels in both regions.