Remote sensing heritage in a petabyte-scale: satellite data and heritage Earth Engine© applications

ABSTRACT

This paper aims to demonstrate results and considerations regarding the use of remote sensing big data for archaeological and Cultural Heritage management large scale applications. For this purpose, the Earth Engine© developed by Google© was exploited. Earth Engine© provides a robust and expandable cloud platform where several freely distributed remote sensing big data, such as Landsat, can be accessed, analysed and visualized. Two different applications are presented here as follows: the first one is based on the evaluation of multi-temporal Landsat series datasets for the detection of buried Neolithic tells (‘magoules’) in the area of Thessaly, in Greece using linear orthogonal equations. The second case exploits European scale multi-temporal DMSP-OLS Night-time Lights Time Series to visualize the impact of urban sprawl in the vicinity of UNESCO World Heritage sites and monuments. Both applications highlight the considerable opportunities that big data can offer to the fields of archaeology and Cultural Heritage, while the studies also demonstrate the great challenges that still are needed to be overcome in order to make the exploitation of big data process manageable and fruitful for future applications.     

Multi-frequency satellite radar imaging of cultural heritage: the case studies of the Yumen Frontier Pass and Niya ruins in the Western Regions of the Silk Road Corridor

Synthetic Aperture Radar (SAR) remote sensing is increasingly favoured in archaeological applications. However, the effectiveness of this technology for archaeological prospection has so far not been fully assessed. In this study, an integrated single-date and multi-temporal SAR data-processing chain was proposed to sharpen archaeological signs and hence their detection and monitoring. In total, 14 scenes of X-band Cosmo-SkyMed, C-band Sentinel-1 and L-band PALSAR data covering the Western Regions of the Silk Road Corridor in China were employed for two important archaeological sites including the Yumen Frontier Pass with emerging archaeological traces and Niya ruins with subsurface remains. The results pointed out that single-date satellite radar data were useful for the identification of subsurface traces buried under desert in the landscape-scale, whereas for the identification of emerging monuments, Sentinel-1 was limited by its lower spatial resolution compared to TerraSAR and PALSAR data. Multi-date products, such as interferometric coherence, the averaged radar signatures and RGB multi-temporal composites, were effective to sharpen archaeological traces as well as for change detection in Yumen Frontier Pass. This study presents a pilot assessment of satellite SAR data for the analysis and monitoring of archaeological features in the predominantly arid-sandy environmental characteristic of investigated sites.     

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.     

断裂活动及孕震过程遥感热异常分析的研究进展

断裂活动及孕震过程遥感热异常分析是对地观测及遥感应用的重要主题。本文从遥感数据应用、异常分析方法、异常认知理解3个方面系统回顾了近30年来该主题的研究概况与主要进展。具体包括:(1)关于遥感数据应用的红外亮温、微波亮温与长波辐射、对地观测同化数据及多源数据综合的4个方面;(2)关于地震遥感异常分析的目视解译定性分析、图像处理定量分析以及多参数时空关联分析的3个发展阶段;(3)关于地震遥感异常认知理解的地球放气、应力致热、地壳岩石电池转换、氡衰变潜热释放与多圈层耦合效应等理论学说。展望未来,提出了面向典型断裂活动区的遥感监测分析与异常识别、基于地球系统地震响应的遥感异常理解分析、空天地立体观测数据的时空关联分析等3个方面的攻关重点。     

长时间序列多源遥感数据的森林干扰监测算法研究进展

时空意义明确的森林干扰和恢复信息是评价森林生态系统碳动态的关键因素之一。然而由于诸多的现实困难,多尺度的森林干扰定量化时空信息相对缺乏。Landsat数据具备光谱、时间和空间分辨率上的优势,以及可以免费获取的特点,使其成为主要的长时间序列动态监测的遥感数据源之一,为长时间周期内提供具有合适的空间细节和时间频率的森林干扰信息成为可能。特别是基于Landsat时间序列堆栈(LTSS)的森林干扰自动分析算法的出现,更为森林生态系统的近实时监测提供强有力的工具。本文全面评述了长时间序列遥感数据准备和预处理技术以及国内外基于遥感数据源的多时相森林干扰监测方法,重点分析了基于Landsat的多种指数监测和自动化方法的优缺点,并总结了其与多源数据结合的扩展应用,最后就现有方法与国内外新的数据、技术手段的关联进行了展望,以期为推广中国本土卫星影像应用于森林干扰监测提供理论借鉴。     

全球高分辨率数字高程模型研究进展与展望

简要介绍了数字高程模型（digital elevation model,DEM）的起源与定义,根据4种不同的观测平台分类介绍了DEM数据获取方法,给出目前国际上发布的高分辨率全球DEM的主要性质和特点。重点介绍了9大类全球DEM,分析了DEM质量评估相关的评定方法和精度指标。论述了DEM在地质灾害监测、海岸带脆弱性分析方面的应用,以美国地质勘探局和德国航空太空中心正在开展的DEM项目为例,讨论了高精度、高分辨率全球同质DEM和地形测深高程模型的最新需求,最后总结展望全球高分辨率DEM的发展趋势。     

多时相遥感影像变化检测的现状与展望

多时相遥感影像变化检测技术能够监测生态环境变化、跟踪城市发展,对于研究人类与自然环境之间的交互关系有着重要的意义。随着新型遥感影像的不断普及,变化检测也在高光谱影像变化检测和高分辨率影像变化检测两个方向上有了深入的探索。本文围绕变化检测的基本流程,从预处理、变化检测方法、阈值分割与精度评价4个角度介绍了变化检测研究的最新进展,并总结了变化检测技术的主要应用领域。最后,对变化检测技术未来的发展进行了展望。     

融合空间和时序遥感信息的深度学习水稻提取

为了得到更加精细的水稻提取结果,提出一种结合高分辨率和多时序遥感影像的深度学习水稻提取方法.构建全卷积网络(FCN)对BJ-2高分辨率遥感影像进行分类,并利用长短期记忆网络(LSTM)和随机森林(RF)分类器对Sentinel-2多时序遥感影像进行分类,再通过面向对象的分割和投票对3种方法的分类结果进行融合,得到最终提...     

基于多源数字遥感影像的“两违”监测服务体系

"两违"综合治理工作因涉及范围广、频率高,亟须采取相应的数字化手段为工作开展提供技术支持。高分辨率遥感技术具有高空间分辨率技术特点,可为"两违"执法工作提供实时详尽的高分辨工作底图,加以遥感处理分析,可以达到对监控区域"两违"变化多时相监测的目的。本文设计了一套以遥感监测为主要手段,集成卫星遥感、航空遥感、无人机航测技术,从多源影像获取、多源数字正射影像工作底图制作、"两违"疑似图斑提取与建库到基于移动互联网技术的"两违"遥感地理信息系统开发的辅助城市规划监测服务体系。     

Research on SAR data integrated processing methodology oriented on earth environment factor inversions

ABSTRACT

As an important advanced technique in the field of Earth observations, Synthetic Aperture Radar (SAR) plays a key role in the study of global environmental change, resources exploration, disaster mitigation, urban environments, and even lunar exploration. However, studies on imaging, image processing, and Earth factor inversions have often been conducted independently for a long time, which significantly limits the application effectiveness of SAR remote sensing due to the lack of an overall integrated design scheme and integrated information processing. Focusing on this SAR application issue, this paper proposes and describes a new SAR data processing methodology – SAR data integrated processing (DIP) oriented on Earth environment factor inversions. The simple definition, typical integrated modes and overall implementation ideas are introduced. Finally, focusing on building information extraction (man-made targets) and sea ice classification (natural targets) applications, three SAR DIP methods and experiments are conducted. Improved results are obtained under the guidance of the SAR DIP framework. Therefore, the SAR DIP theoretical framework and methodology represent a new SAR science application mode that has the capability to improve the SAR remote sensing quantitative application level and promote the development of new theories and methodologies.     

不同时相MODIS L1B数据间定量关系研究

由不同时相和不同传感器所导致的遥感数据非一致性是定量监测地表长期变化所必须面对的一个重要问题。用于消减遥感数据非一致性的归一化辐射校正和传感器交叉定标,多采用统计方法,难以满足定量遥感发展的需求。本文针对MODISL1B光学波段产品数据,推导了不同时相非变像元灰度值(SI)之间的数学表达式,并利用MODIS的可见光-短波红外波段L1B数据对该定量关系进行了验证。研究表明,在可见光-短波红外波段,L1B非变像元在不同时相间的定量关系分为乘性和加性两部分,主要与太阳光照条件、大气状态以及传感器自身等变化因素有关。虽然基于MODIS非变像元时相关系的检验结果与理想状态下的结果存在偏差,但总体趋势仍然较好。     

雷达遥感六十年：四个阶段的发展

雷达遥感问世60年来已经历了4个阶段的发展,其在对地观测中的作用正日益凸显,已经广泛应用于不同领域。4个阶段分别是单波段单极化阶段,多波段多极化阶段,极化和干涉阶段,以及以双/多站或星座、高时序高分宽幅、3维成像为代表的新阶段。本文结合作者长期在雷达遥感领域的研究经历,总结和回顾了雷达遥感的阶段发展和具有里程碑式的代表性技术;从观测技术、数据处理和应用角度阐述了新阶段雷达遥感的发展趋势,以及雷达遥感与人工智能和大数据结合的思考;最后着眼未来,介绍了月基雷达对地观测平台的前瞻性研究。     

A workflow for Sustainable Development Goals indicators assessment based on high-resolution satellite data

ABSTRACT

For evaluating the progresses towards achieving the Sustainable Development Goals (SDGs), a global indicator framework was developed by the UN Inter-Agency and Expert Group on Sustainable Development Goals Indicators. In this paper, we propose an improved methodology and a set of workflows for calculating SDGs indicators. The main improvements consist of using moderate and high spatial resolution satellite data and state-of-the-art deep learning methodology for land cover classification and for assessing land productivity. Within the European Network for Observing our Changing Planet (ERA-PLANET), three SDGs indicators are calculated. In this research, harmonized Landsat and Sentinel-2 data are analyzed and used for land productivity analysis and yield assessment, as well as Landsat 8, Sentinel-2 and Sentinel-1 time series are utilized for crop mapping. We calculate for the whole territory of Ukraine SDG indicators: 15.1.1 – ‘Forest area as proportion of total land area’; 15.3.1 – ‘Proportion of land that is degraded over total land area’; and 2.4.1 – ‘Proportion of agricultural area under productive and sustainable agriculture’. Workflows for calculating these indicators were implemented in a Virtual Laboratory Platform. We conclude that newly available high-resolution remote sensing products can significantly improve our capacity to assess several SDGs indicators through dedicated workflows.     

遥感影像时—空融合的“点”—“线”—“面”质量评价

遥感影像时—空融合可集成多源数据高空间分辨率和高时间分辨率互补优势,生成时间连续的高空间分辨率影像,在遥感影像的动态监测与时序分析等方面具有重要应用价值。然而,现有多数研究往往基于单一数据产品对时—空融合算法进行评价,而在实际生产应用中,需要验证算法在多种遥感产品数据的融合表现;此外,目前研究大多基于"单点时刻"进行评价,忽略了时—空融合在"时间线"上的有效验证。本文提出遥感影像时—空融合的"点"—"线"—"面"多角度综合质量评价策略,基于Landsat TM和MODIS影像,建立了时—空融合系列数据集,包括地表反射率、植被指数和地表温度,并在此基础上从单时相("点")、时间序列("线")、多种数据产品("面")多个角度对4种典型融合算法进行定性和定量的综合评价。结果表明,基于不同产品类型的数据集更能充分验证算法性能,且结合单点时刻和时间序列的评价更加客观。     

结合变化向量分析和直觉模糊聚类的遥感影像变化检测方法

针对多时相遥感影像变化检测存在数据不确定性、检测精度不高等问题，提出了一种结合变化向量分析（CVA）和直觉模糊C均值聚类算法（IFCM）的多时相遥感影像变化检测方法. 首先通过CVA构建两个时相遥感影像的差异影像；然后采用直觉模糊C均值聚类算法对差异影像进行聚类得出变化区域和未变化区域；最后对变化检测结果进行二值化处理并进行精度评价. 选取两个时相的高分一号遥感影像和Szada数据集影像作为实验数据. 实验结果表明，采用提出的方法可有效解决传统方法存在的数据不确定性问题，变化检测精度达到了95.92%和92.70%，是一种可行的遥感影像变化检测方法. 研究结果可用于森林动态变化监测、土地复垦利用规划变化分析以及灾损评估.      

一种基于线特征的道路网变化检测算法

提出一种基于线特征的道路网变化检测算法。首先根据边缘的梯度信息从多时相遥感图像中提取变化的线特征;然后根据变化线特征的局部特性,检测出与道路模型相符合的变化道路段;最后通过道路网的全局约束条件,进行变化道路段的连接,实现变化道路的检测。提出的道路网变化检测算法将边缘的相位和幅度信息作为变化检测的判定依据,从而避免了道路的匹配与比较工作,降低了变化检测算法的复杂度,具有很强的实用性。将本文提出的方法用于多时相遥感图像的道路网变化检测,从实验结果可以看出该方法的有效性。     

多时相遥感影像变化检测综述

近几十年来,多时相影像处理和变化检测是遥感领域一个较为活跃的研究方向。虽然在环境变化监测和检测方面成功的应用有很多,但是从多时相影像及时提取地球环境和人类活动的动态信息仍匝临很多挑战。近年来,随着新型遥感平台和传感器的发展,在克服技术障碍方面取得了很大进步。历史影像档案提供范围的扩大也使得长期变化检测和建模成为可能。这些发展推动了更先进的影像处理方法的开发和处理时间维度影像数据新方法的研究工作。本文回顾了多时相数据处理和变化检测的发展现状。作者首先对地球表面环境变化的性质进行了分析,从四个方面总结了遥感变化检测技术的发展,包括变化检测影像预处理、变化检测方法和途径分类、遥感变化检测方法和多时相影像处理的准确度评估。文章试图在先验知识的基础上从多源数据、集成处理和智能方法角度提出综合解决方案。为促进遥感影像变化检测技术的深入研究,本文还指出了变化检测所面临的挑战和可能的对策。     

山地遥感主要研究进展、发展机遇与挑战

山地遥感是研究在山地这一特定环境中的遥感基本原理、方法及其应用的科学技术。从山地遥感研究的基本内涵出发,总结面临的若干前沿科学问题,指出当前主要研究内容:(1)电磁波与山地地表相互作用机理及建模理论;(2)山地遥感数据时—空—谱归一化处理方法;(3)山地地表信息遥感建模、反演与同化方法;(4)山地遥感尺度效应与算法/产品验证;(5)山地遥感信息综合应用等。从山地遥感研究的基础理论方法以及山地遥感应用两个层面回顾了近年来山地遥感研究取得的进展,并就新时代背景下山地遥感研究面临的机遇与挑战进行了分析,最后对山地遥感研究前景进行了展望。     

Combining European Earth Observation products with Dynamic Global Vegetation Models for estimating Essential Biodiversity Variables

ABSTRACT

Global, fast and accessible monitoring of biodiversity is one of the main pillars of the efforts undertaken in order to revert it loss. The Group on Earth Observations Biodiversity Observation Network (GEO-BON) provided an expert-based definition of the biological properties that should be monitored, the Essential Biodiversity Variables (EBVs). Initiatives to provide indicators for EBVs rely on global, freely available remote sensing (RS) products in combination with empirical models and field data, and are invaluable for decision making. In this study, we provide alternatives for the expansion and improvement of the EBV indicators, by suggesting current and future data from the European Space Agencýs COPERNICUS and explore the potential of RS-integrated Dynamic Global Vegetation Models (DGVMs) for the estimation of EBVs. Our review found that mainly due to the inclusion of the Sentinel constellation, Copernicus products have similar or superior potential for EBV indicator estimation in relation to their NASA counterparts. DGVMs simulate the ecosystem level EBVs (ecosystem function and structure), and when integrated with remote sensing data have great potential to not only offer improved estimation of current states but to provide projection of ecosystem impacts. We suggest that focus on producing EBV relevant outputs should be a priority within the research community, to support biodiversity preservation efforts.     

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.