基于时间序列Sentinel-1A数据的水稻识别

基于时间序列的Sentinel-1A数据,利用光谱相似性方法(SSM)对广东省台山县汶村镇和海宴镇进行了水稻识别。首先将SSM应用于时间序列SAR图像中,计算光谱相似度;再通过设置阈值获得初始水稻种植面积图;最后消除斑点噪声,获得水稻种植面积图。结果表明,基于VH极化图像,利用SSM和阈值法获得的水稻种植面积图的总体精度最高为97.34%,Kappa系数为0.94。因此,时间序列Sentinel-1A数据对于识别水稻或其他作物具有很大的潜力。     

基于Sentinel-1A与Sentinel-2A融合的土地利用/覆盖分类研究——以昆明市呈贡区为例

为提高土地利用/覆盖分类精度,本文以昆明市呈贡区为例,融合Sentinel-1A(S1A)与Sentinel-2A(S2A)遥感数据,采用支持向量机(SVM)的监督分类方法对土地利用/覆盖进行分类。对比分析了Sentinel-1A与Sentinel-2A数据在不同组合情况下所有分类结果的总体精度,结果表明:将Sentinel-1A的强度数据、纹理数据与添加植被指数的Sentinel-2A数据融合时分类精度相对较高,总体精度可达93.60%。采用雷达数据与光学数据融合的方法可以在一定程度上提升土地利用/覆盖分类精度。     

时序Sentinel-1A数据支持的长江中下游汛情动态监测

合成孔径雷达（SAR）因其对地观测全天候、全天时优势,成为多云多雨天气限制下洪水动态监测中不可或缺的数据来源之一。由于GEE（Google Earth Engine）云计算平台的兴起和短重访Sentinel-1数据的可获取性,洪水监测与灾害评估目前正面向动态化、广域化快速发展。顾及洪水淹没区土地覆盖变化的复杂性和发生时间的不确定性,基于时序Sentinel-1A卫星数据提出了针对大尺度范围、连续长期的汛情自动检测及动态监测方法。该方法首先,利用图像二值化分割时序SAR数据实现水体时空分布粗制图,逐像素计算时间序列中被识别为水体候选点的频率。然后,利用Sentinel-2光学影像对精度较粗的初期SAR水体提取结果进行校正,得到精细的水体分布图。最后,针对不同频率区间的淹没特点,采用差异化的时序异常检测策略识别淹没范围：对低频覆水区利用欧氏距离检测时序断点,以提取扰动强度大、淹没时间短的洪涝灾害区;对高频覆水区利用标准分数（Z-Score）检测时序断点,以提取季节性水体覆盖区。在GEE平台上利用该方法,实现了2020-05—10长江中下游地区全域洪水淹没范围时空信息的自动、快速、有效监测,揭示了不同区域汛情发展模式的差异性。本文提出的洪水快速监测方法对大尺度下的汛情动态监测、灾害定量评估和快速预警响应具有重要的现实意义。     

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。     

Sentinel-2A数据支持下的雷州半岛植被类型识别

本文以雷州半岛为研究区,利用Sentinel-2A影像数据和真实植被样本数据,综合探讨了机器学习中随机森林与支持向量机的分类效果,并与传统的最大似然法进行比较。提取Sentinel-2A影像9个波段、7个植被指数、72个纹理特征,通过递归特征消除法挑选了10个特征组合,并将其应用于3种分类方法中,对其分类效果进行比较。结果表明:①有效使用多种特征变量是提高植被类型识别精度的关键,就不同特征对植被类型识别的重要性而言,光谱特征与纹理特征相当且大于植被指数,三者重要性相差不大;②随机森林分类效果最佳,不但能对特征进行有效选择,而且能保证植被类型提取精度,提高运行效率;③基于随机森林特征选择的递归特征消除法得到的特征组合不能对其他分类器性能进行优化,对随机森林模型本身的优化效果也有限。     

基于Sentinel-1A数据的地表形变监测

提取滑坡形变数据、分析形变趋势对地质灾害防治工作具有指导意义.合成孔径雷达干涉测量技术(InSAR)具有全天候、全天时精确获取地表形变数据的能力,是当前形变监测的重要手段.分别利用DInSAR和SBAS-InSAR技术处理了22景哨兵一号(Sentinel-1)C波段数据,得到了四川省安州区高川乡大光包滑坡2018年3月-2020年2月的形变数据特征.结果表明,大光包滑坡点共有3个相对明显的形变区域;近两年的平均形变速率最高不超过100 mm/a,其形变时间序列随降雨量变化具有周期性;总体地表形变趋于稳定,周边地区中小型地震的发生没有造成地质灾害隐患.     

基于Sentinel-1B SAR数据的洪水提取和监测

洪涝灾害是我国最严重的气象灾害之一,及时准确的洪灾监测是防灾减灾的重要前期工作和基础。本文利用sentinel-1B雷达数据,以黑瞎子岛为研究区,联合使用OSTU阈值分割法和随机森林面向对象分类法针对像素统计单波形、双波形、多波形SAR影像提取洪水要素,实现对洪灾淹没面积的时序监测,为灾情监测提供数据和技术支撑。     

基于Sentinel-1A雷达影像地表覆盖信息提取研究

为提取不同类别地表覆盖信息,本文利用Sentinel-1A双极化星载合成孔径雷达影像,使用Cloude极化分解方法获得雷达卫星探测到的地表目标散射机制信息,并以由散射熵H和α角所构成的特征空间中不同地表覆盖区域所对应的不同散射机制区域为基础,划分监督样本并结合Wishart迭代监督分类方法以及SVM分类方法进行地表覆盖信息提取,结果显示,根据H-α特征空间进行的监督分类方法中H/α-Wishart分类方法精度评价Kappa系数为0.804,H/α-SVM方法Kappa系数为0.827,两种不同方法的地表覆盖分类结果都能够达到较高的分类准确性,说明根据H-α特征空间进行地表覆盖信息提取是有效、可行的分类方法.     

Sentinel-1卫星数据产品应用探讨

以Sentinel-1卫星的特点、传感器的特点、数据产品以及潜在应用为逻辑主线,介绍了Sentinel-1卫星的基本参数、C波段传感器的参数特性以及Sentinel-1的数据产品,为Sentinel-1的进一步应用提供参考。     

基于SBAS-InSAR技术和Sentinel-1A的城市地表沉降监测

基于SBAS-InSAR技术对覆盖研究区2017—2018年20景Sentinel-1A影像数据进行处理,得到研究区年沉降速率及时序形变信息,并与PS-InSAR结果进行对比验证,最后进一步分析了研究区沉降的成因.结果表明沉降主要发生在燕郊镇中部与西部区域,平均沉降速率超过20 mm/a,集中沉降区域平均沉降速率超过3...     

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.     

Land cover and land use classification performance of machine learning algorithms in a boreal landscape using Sentinel-2 data

ABSTRACT

In recent years, the data science and remote sensing communities have started to align due to user-friendly programming tools, access to high-end consumer computing power, and the availability of free satellite data. In particular, publicly available data from the European Space Agency’s Sentinel missions have been used in various remote sensing applications. However, there is a lack of studies that utilize these data to assess the performance of machine learning algorithms in complex boreal landscapes. In this article, I compare the classification performance of four non-parametric algorithms: support vector machines (SVM), random forests (RF), extreme gradient boosting (Xgboost), and deep learning (DL). The study area chosen is a complex mixed-use landscape in south-central Sweden with eight land-cover and land-use (LCLU) classes. The satellite imagery used for the classification were multi-temporal scenes from Sentinel-2 covering spring, summer, autumn and winter conditions. Using stratified random sampling, each LCLU class was allocated 1477 samples, which were divided into training (70%) and evaluation (30%) subsets. Accuracy was assessed through metrics derived from an error matrix, but primarily overall accuracy was used in allocating algorithm hierarchy. A two-proportion Z-test was used to compare the proportions of correctly classified pixels of the algorithms and a McNemar’s chi-square test was used to compare class-wise predictions. The results show that the highest overall accuracy was produced by support vector machines (0.758 ± 0.017), closely followed by extreme gradient boosting (0.751 ± 0.017), random forests (0.739 ± 0.018), and finally deep learning (0.733 ± 0.0023). The Z-test comparison of classifiers showed that a third of algorithm pairings were statistically different. On a class-wise basis, McNemar’s test results showed that 62% of class-wise predictions were significant from one another at the 5% level or less. Variable importance metrics show that nearly half of the top twenty Sentinel-2 bands belonged to the red edge (25%) and shortwave infrared (23%) portions of the electromagnetic spectrum, and were dominated by scenes from spring (38%) and summer (40%). The results are discussed within the scope of recent studies involving machine learning and Sentinel-2 data and key knowledge gaps identified. The article concludes with recommendations for future research.     

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。     

哨兵1号和高分三号SAR数据海浪谱反演精度评估

Ocean wave is one of the important marine dynamic phenomenon that affect human activities. At present, the main observation means include buoy observation, marine numerical prediction model, and microwave remote sensing observation. However, we cannot conduct large-scale observation by buoy, and the marine numerical prediction model’s result is not measured data. Spectrometers and altimeters in microwave remote sensing instruments can also measure spectral parameters. However, SAR, which has a higher resolution, can provide 2D sea surface information. The Sentinel-1 satellite of ESA and GF-3 satellite independently developed by China are now in orbit, and numerous teams are working to retrieve wave parameters from SAR data of these two satellites. In this work, we compared the wave parameter inversion accuracy of Sentinel-1 SAR Interferometric Wide Swath model and GF-3 SAR strip model based on wave spectrum, which provides a reference for the wide application of GF-3 SAR data. The sea states according to the ERA-5 data of ECMWF are divided into three categories: low, moderate, and high sea states. The sea areas of Hormuz and Malacca Straits of the maritime Silk Road in the Indian Ocean and the coastal waters of the Pacific and Atlantic Ocean are selected as the study areas. Meanwhile, the SAR data of Sentinel-1 and GF-3 satellites under different sea states are selected as the data source. The MPI method is used to retrieve the wave spectrum and wave parameters using the E spectrum as the initial guess. Subsequently, the SAR data inversion results of the two satellites under different sea states are compared with the ERA-5 and buoy wave data. The inversion accuracy of the wave parameters can be verified by calculating the values of the Root Mean Square Error (RMSE) and Scatter Index (SI), and the inversion accuracy of the wave parameters of the two satellites under different sea conditions can be compared. The RMSEs of significant wave height (Hs) retrieved by GF-3 SAR under low, moderate, and high sea conditions are 0.30, 0.34, and 0.48 m, and those of mean wave period (Tm) are 1.02, 0.99, and 0.95 s, respectively, compared with the ERA-5 data. In addition, the RMSE of Hs retrieved by Sentinel-1 SAR under low, moderate, and high sea conditions are 0.30, 0.29, and 0.33 m, respectively, and the RMSEs of Tm are 0.94, 0.51, and 0.64 s, respectively. The RMSEs of Hs and Tm under different sea conditions retrieved by GF-3 SAR are 0.38 m and 0.99 s, and those of Hs and Tm retrieved by Sentinel-1 SAR are 0.31 m and 0.70 s, respectively, compared with the ERA-5 data. The RMSEs of the retrieved Hs and Tm of GF-3 satellite are 0.42 m and 0.94 s, and those of the retrieved Hs and Tm of Sentinel-1 are 0.40 m and 0.91 s, respectively, compared with the buoy data. The SAR wave parameter inversion of Sentinel-1 and GF-3 SAR based on the wave spectrum shows that the inversion results of the two satellites meet the index requirements in this field, and the accuracy of the inversion results of wave spectrum is the same. The strip mode SAR data of GF-3 satellite, China’s first self-developed SAR satellite, has broad prospects in marine research fields. © 2023 National Remote Sensing Bulletin. All rights reserved.     

High-resolution mapping of forest canopy height using machine learning by coupling ICESat-2 LiDAR with Sentinel-1, Sentinel-2 and Landsat-8 data

Forest canopy height is an important indicator of forest carbon storage, productivity, and biodiversity. The present study showed the first attempt to develop a machine-learning workflow to map the spatial pattern of the forest canopy height in a mountainous region in the northeast China by coupling the recently available canopy height (H_canopy) footprint product from ICESat-2 with the Sentinel-1 and Sentinel-2 satellite data. The ICESat-2 H_canopy was initially validated by the high-resolution canopy height from airborne LiDAR data at different spatial scales. Performance comparisons were conducted between two machine-learning models – deep learning (DL) model and random forest (RF) model, and between the Sentinel and Landsat-8 satellites. Results showed that the ICESat-2 H_canopy showed the highest correlation with the airborne LiDAR canopy height at a spatial scale of 250 m with a Pearson’s correlation coefficient (R) of 0.82 and a mean bias of -1.46 m, providing important evidence on the reliability of the ICESat-2 vegetation height product from the case in China’s forest. Both DL and RF models obtained satisfactory accuracy on the upscaling of ICESat-2 H_canopy assisted by Sentinel satellite co-variables with an R-value between the observed and predicted H_canopy equalling 0.78 and 0.68, respectively. Compared to Sentinel satellites, Landsat-8 showed relatively weaker performance in H_canopy prediction, suggesting that the addition of the backscattering coefficients from Sentinel-1 and the red-edge related variables from Sentinel-2 could positively contribute to the prediction of forest canopy height. To our knowledge, few studies have demonstrated large-scale vegetation height mapping in a resolution ≤ 250 m based on the newly available satellites (ICESat-2, Sentinel-1 and Sentinel-2) and DL regression model, particularly in the forest areas in China. Thus, the present work provided a timely and important supplementary to the applications of these new earth observation tools.     

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.     

Automatic sub-pixel co-registration of Landsat-8 Operational Land Imager and Sentinel-2A Multi-Spectral Instrument images using phase correlation and machine learning based mapping

ABSTRACT

This study investigates misregistration issues between Landsat-8/ Operational Land Imager and Sentinel-2A/ Multi-Spectral Instrument at 30?m resolution, and between multi-temporal Sentinel-2A images at 10?m resolution using a phase-correlation approach and multiple transformation functions. Co-registration of 45 Landsat-8 to Sentinel-2A pairs and 37 Sentinel-2A to Sentinel-2A pairs were analyzed. Phase correlation proved to be a robust approach that allowed us to identify hundreds and thousands of control points on images acquired more than 100 days apart. Overall, misregistration of up to 1.6 pixels at 30?m resolution between Landsat-8 and Sentinel-2A images, and 1.2 pixels and 2.8 pixels at 10?m resolution between multi-temporal Sentinel-2A images from the same and different orbits, respectively, were observed. The non-linear random forest regression used for constructing the mapping function showed best results in terms of root mean square error (RMSE), yielding an average RMSE error of 0.07?±?0.02 pixels at 30?m resolution, and 0.09?±?0.05 and 0.15?±?0.06 pixels at 10?m resolution for the same and adjacent Sentinel-2A orbits, respectively, for multiple tiles and multiple conditions. A simpler 1st order polynomial function (affine transformation) yielded RMSE of 0.08?±?0.02 pixels at 30?m resolution and 0.12?±?0.06 (same Sentinel-2A orbits) and 0.20?±?0.09 (adjacent orbits) pixels at 10?m resolution.     

Coseismic surface deformation of the 2014 Napa earthquake mapped by Sentinel-1A SAR and accuracy assessment with COSMO-SkyMed and GPS data as cross validation

ABSTRACT

The new land observation satellite Sentinel-1A was launched on 25 April 2014 with a C-band synthetic aperture radar (SAR) sensor, which has the significant enhancements in terms of revisit period and high resolution. The Mw 6.1 Napa, California earthquake occurring on 24 August 2014, almost 4 months after the launch, is the first moderate earthquake imaged by the Sentinel-1A. This provides an opportunity to map the coseismic deformation of the event and evaluate the potential of Sentinel-1A SAR for earthquake study. Two techniques including the interferometric SAR (InSAR) and pixel offset-tracking (PO) are, respectively, employed to map the surface deformation along the radar line of sight (LOS), azimuth and slant-range directions. The cross comparison between Sentinel-1A InSAR LOS deformation and GPS observations indicates good agreement with an accuracy of ～2.6?mm. We further estimate the earthquake source model with the external COSMO-SkyMed InSAR and GPS data as constraints, and forward calculate the surface deformation as cross validation with the Sentinel-1A observations. The comparison between the observed and modeled deformation shows that the Sentinel-1A measurement accuracy can achieve 1.6?cm for InSAR technique along LOS direction, and 6.3 and 6.7?cm for PO along azimuth and range directions, respectively.