Search

Started in 2009, our journal will celebrate its 10th anniversary in 2019 [...]

The international symposium on remote sensing 2018 (ISRS 2018) was held in Pyeongchang, Korea, 9–11 May 2018 [...]

Convolutional neural network (CNN)-based deep learning (DL) has a wide variety of applications in the geospatial and remote sensing (RS) sciences, and consequently has been a focus of many recent studies. However, a review of accuracy assessment methods used in recently published RS DL studies, focusing on scene classification, object detection, semantic segmentation, and instance segmentation, indicates that RS DL papers appear to follow an accuracy assessment approach that diverges from that of traditional RS studies. Papers reporting on RS DL studies have largely abandoned traditional RS accuracy assessment terminology; they rarely reported a complete confusion matrix; and sampling designs and analysis protocols generally did not provide a population-based confusion matrix, in which the table entries are estimates of the probabilities of occurrence of the mapped landscape. These issues indicate the need for the RS community to develop guidance on best practices for accuracy assessment for CNN-based DL thematic mapping and object detection. As a first step in that process, we explore key issues, including the observation that accuracy assessments should not be biased by the CNN-based training and inference processes that rely on image chips. Furthermore, accuracy assessments should be consistent with prior recommendations and standards in the field, should support the estimation of a population confusion matrix, and should allow for assessment of model generalization. This paper draws from our review of the RS DL literature and the rich record of traditional remote sensing accuracy assessment research while considering the unique nature of CNN-based deep learning to propose accuracy assessment best practices that use appropriate sampling methods, training and validation data partitioning, assessment metrics, and reporting standards.

Taking Shanghai as an example, this paper uses remote sensing (RS) and geographical information systems (GIS) technology to conduct multisource data fusion and a spatial pattern analysis of urban carrying capacity at the micro scale. The main conclusions are as follows: (1) based on the “production, living and ecology” land functions framework and land use data, Shanghai is divided into seven types of urban spaces to reveal their heterogeneity and compatibility in terms of land use functions. (2) We propose an urban carrying capacity coupling model (UCCCM) based on multisource data. The model incorporates threshold and saturation effects, which improve its power to explain urban carrying capacity. (3) Using the exploratory spatial data analysis (ESDA) technique, this paper studies the spatial pattern of carrying capacity in different urban spaces of Shanghai. (4) We analyse the causes of the cold spots in each urban space and propose strategies to improve the urban carrying capacity according to local conditions.

Land surface temperature (LST) is an important environmental parameter in climate change, urban heat islands, drought, public health, and other fields. Thermal infrared (TIR) remote sensing is the main method used to obtain LST information over large spatial scales. However, cloud cover results in many data gaps in remotely sensed LST datasets, greatly limiting their practical applications. Many studies have sought to fill these data gaps and reconstruct cloud-free LST datasets over the last few decades. This paper reviews the progress of LST reconstruction research. A bibliometric analysis is conducted to provide a brief overview of the papers published in this field. The existing reconstruction algorithms can be grouped into five categories: spatial gap-filling methods, temporal gap-filling methods, spatiotemporal gap-filling methods, multi-source fusion-based gap-filling methods, and surface energy balance-based gap-filling methods. The principles, advantages, and limitations of these methods are described and discussed. The applications of these methods are also outlined. In addition, the validation of filled LST values’ cloudy pixels is an important concern in LST reconstruction. The different validation methods applied for reconstructed LST datasets are also reviewed herein. Finally, prospects for future developments in LST reconstruction are provided.

Poplar looper (Apocheima cinerarius Erschoff) is a destructive insect infesting Euphrates or desert poplars (Populus euphratica) in Xinjiang, China. Since the late 1950s, it has been plaguing desert poplars in the Tarim Basin in Xinjiang and caused widespread damages. This paper presents an approach to the detection of poplar looper infestations on desert poplars and the assessment of the severity of the infestations using time-series MODIS NDVI data via the wavelet transform and discriminant analysis, using the middle and lower reaches of the Yerqiang River as a case study. We first applied the wavelet transform to the NDVI time series data in the period of 2009–2014 for the study area, which decomposed the data into a representation that shows detailed NDVI changes and trends as a function of time. This representation captures both intra- and inter-annual changes in the data, some of which characterise transient events. The decomposed components were then used to filter out details of the changes to create a smoothed NDVI time series that represent the phenology of healthy desert poplars. Next the subset of the original NDVI time series spanning the time period when the pest was active was extracted and added to the smoothed time series to generate a blended time series. The wavelet transform was applied again to decompose the blended time series to enhance and identify the changes in the data that may represent the signals of the pest infestations. Based on the amplitude of the enhanced pest infestation signals, a predictive model was developed via discriminant analysis to detect the pest infestation and assess its severity. The predictive model achieved a severity classification accuracy of 91.7% and 94.37% accuracy in detecting the time of the outbreak. The methodology presented in this paper provides a fast, precise, and practical method for monitoring pest outbreak in dense desert poplar forests, which can be used to support the surveillance and control of poplar looper infestations on desert poplars. It is of great significance to the conservation of the desert ecological environment.

Convolutional neural network (CNN)-based deep learning (DL) is a powerful, recently developed image classification approach. With origins in the computer vision and image processing communities, the accuracy assessment methods developed for CNN-based DL use a wide range of metrics that may be unfamiliar to the remote sensing (RS) community. To explore the differences between traditional RS and DL RS methods, we surveyed a random selection of 100 papers from the RS DL literature. The results show that RS DL studies have largely abandoned traditional RS accuracy assessment terminology, though some of the accuracy measures typically used in DL papers, most notably precision and recall, have direct equivalents in traditional RS terminology. Some of the DL accuracy terms have multiple names, or are equivalent to another measure. In our sample, DL studies only rarely reported a complete confusion matrix, and when they did so, it was even more rare that the confusion matrix estimated population properties. On the other hand, some DL studies are increasingly paying attention to the role of class prevalence in designing accuracy assessment approaches. DL studies that evaluate the decision boundary threshold over a range of values tend to use the precision-recall (P-R) curve, the associated area under the curve (AUC) measures of average precision (AP) and mean average precision (mAP), rather than the traditional receiver operating characteristic (ROC) curve and its AUC. DL studies are also notable for testing the generalization of their models on entirely new datasets, including data from new areas, new acquisition times, or even new sensors.

In the context of earth observation and remote sensing, super-resolution aims to enhance the resolution of a captured image by upscaling and enhancing its details. In recent years, numerous methods for super-resolution of Sentinel-2 (S2) multispectral images have been suggested. Most of those methods depend on various tuning parameters that affect how effective they are. This paper’s aim is twofold. Firstly, we propose to use Bayesian optimization at a reduced scale to select tuning parameters. Secondly, we choose tuning parameters for eight S2 super-resolution methods and compare them using real and synthetic data. While all the methods give good quantitative results, Area-To-Point Regression Kriging (ATPRK), Sentinel-2 Sharpening (S2Sharp), and Sentinel-2 Symmetric Skip Connection convolutional neural network (S2 SSC) perform markedly better on several datasets than the other methods tested in this paper.

Land surface phenology (LSP) has been extensively explored from global archives of satellite observations to track and monitor the seasonality of rangeland ecosystems in response to climate change. Long term monitoring of LSP provides large potential for the evaluation of interactions and feedbacks between climate and vegetation. With a special focus on the rangeland ecosystems, the paper reviews the progress, challenges and emerging opportunities in LSP while identifying possible gaps that could be explored in future. Specifically, the paper traces the evolution of satellite sensors and interrogates their properties as well as the associated indices and algorithms in estimating and monitoring LSP in productive rangelands. Findings from the literature revealed that the spectral characteristics of the early satellite sensors such as Landsat, AVHRR and MODIS played a critical role in the development of spectral vegetation indices that have been widely used in LSP applications. The normalized difference vegetation index (NDVI) pioneered LSP investigations, and most other spectral vegetation indices were primarily developed to address the weaknesses and shortcomings of the NDVI. New indices continue to be developed based on recent sensors such as Sentinel-2 that are characterized by unique spectral signatures and fine spatial resolutions, and their successful usage is catalyzed with the development of cutting-edge algorithms for modeling the LSP profiles. In this regard, the paper has documented several LSP algorithms that are designed to provide data smoothing, gap filling and LSP metrics retrieval methods in a single environment. In the future, the development of machine learning algorithms that can effectively model and characterize the phenological cycles of vegetation would help to unlock the value of LSP information in the rangeland monitoring and management process. Precisely, deep learning presents an opportunity to further develop robust software packages such as the decomposition and analysis of time series (DATimeS) with the abundance of data processing tools and techniques that can be used to better characterize the phenological cycles of vegetation in rangeland ecosystems.

This paper deals with detecting small objects in remote sensing images from satellites or any aerial vehicle by utilizing the concept of image super-resolution for image resolution enhancement using a deep-learning-based detection method. This paper provides a rationale for image super-resolution for small objects by improving the current super-resolution (SR) framework by incorporating a cyclic generative adversarial network (GAN) and residual feature aggregation (RFA) to improve detection performance. The novelty of the method is threefold: first, a framework is proposed, independent of the final object detector used in research, i.e., YOLOv3 could be replaced with Faster R-CNN or any object detector to perform object detection; second, a residual feature aggregation network was used in the generator, which significantly improved the detection performance as the RFA network detected complex features; and third, the whole network was transformed into a cyclic GAN. The image super-resolution cyclic GAN with RFA and YOLO as the detection network is termed as SRCGAN-RFA-YOLO, which is compared with the detection accuracies of other methods. Rigorous experiments on both satellite images and aerial images (ISPRS Potsdam, VAID, and Draper Satellite Image Chronology datasets) were performed, and the results showed that the detection performance increased by using super-resolution methods for spatial resolution enhancement; for an IoU of 0.10, AP of 0.7867 was achieved for a scale factor of 16.

Coarse registration of 3D point clouds plays an indispensable role for parametric, semantically rich, and realistic digital twin buildings (DTBs) in the practice of GIScience, manufacturing, robotics, architecture, engineering, and construction. However, the existing methods have prominently been challenged by (i) the high cost of data collection for numerous existing buildings and (ii) the computational complexity from self-similar layout patterns. This paper studies the registration of two low-cost data sets, i.e., colorful 3D point clouds captured by smartphones and 2D CAD drawings, for resolving the first challenge. We propose a novel method named ‘Registration based on Architectural Reflection Detection’ (RegARD) for transforming the self-symmetries in the second challenge from a barrier of coarse registration to a facilitator. First, RegARD detects the innate architectural reflection symmetries to constrain the rotations and reduce degrees of freedom. Then, a nonlinear optimization formulation together with advanced optimization algorithms can overcome the second challenge. As a result, high-quality coarse registration and subsequent low-cost DTBs can be created with semantic components and realistic appearances. Experiments showed that the proposed method outperformed existing methods considerably in both effectiveness and efficiency, i.e., 49.88% less error and 73.13% less time, on average. The RegARD presented in this paper first contributes to coarse registration theories and exploitation of symmetries and textures in 3D point clouds and 2D CAD drawings. For practitioners in the industries, RegARD offers a new automatic solution to utilize ubiquitous smartphone sensors for massive low-cost DTBs.

Due to the difference of factors, such as lighting conditions, shooting environments, and time, there is compound brightness difference between adjacent images, which includes local brightness difference and radiometric difference. This paper proposed a method to eliminate the compound brightness difference of adjacent images after mosaicking, named local to global radiometric balance. It includes the brightness compensation model and brightness approach model. Firstly, the weighted average value of each row and column of image are calculated to express the brightness change; secondly, according to weighted average value, the brightness compensation model is built; thirdly, combined with the blocking method, the brightness compensation model is applied to image. Based on the value after above process, the brightness approach model is established to make the gray value of adjacent images approach to the mosaic line. In the paper, the standard deviation, MSE (mean square error) and mean value are used as the measure indices of the effect of brightness balance. The three groups of experimental results show that compared with the brightness stretch method, the histogram equalization method and the radiometric balance method, the local to global radiometric balance method not only realizes compound brightness balance, but also has better visual effects than others.

The synthetic aperture radar (SAR) is an important means of ship surveillance, but the motion of the ship leads to azimuth position offset, false targets, and azimuth defocusing for the spaceborne high-resolution and wide-swath (HRWS) SAR system, causing the degradation of imaging quality. The automatic identification system (AIS) can provide real-time information of the ships, which is an important auxiliary method for ship surveillance. Up to now, the traditional fusion of SAR and AIS mainly has focused on location matching and auxiliary recognition, and the next generation of GaoFen-3 (GF-3NG) satellite is equipped with both a SAR sensor and an AIS sensor to obtain the SAR images and simultaneous AIS information of ships. Consequently, this paper proposes a novel scheme to improve the imaging quality of moving ships for GF-3NG using AIS information. In this paper, through introducing the virtual stationary target, the slant range derivation (SRD) algorithm is proposed to estimate the radial velocity (RV) and the radial acceleration (RA) between the ship and the SAR platform relative to the stationary scene. According to the calculated RV, the azimuth position offset can be estimated and the ship can be repositioned on the image. After that, the traditional method is conducted to suppress the false targets. Finally, the method of using the RA to refocus ship slices is proposed. Additionally, the experiment results based on real data illustrate the effectiveness of the proposed methods.

Rivers play an essential role to humans and ecosystems, but they also burst their banks during floods, often causing extensive damage to crop, property, and loss of lives. This paper characterizes the 2014 flood of the Indus River in Pakistan using the US Army Corps of Engineers Hydrologic Engineering Centre River Analysis System (HEC-RAS) model, integrated into a geographic information system (GIS) and satellite images from Landsat-8. The model is used to estimate the spatial extent of the flood and assess the damage that it caused by examining changes to the different land-use/land-cover (LULC) types of the river basin. Extreme flows for different return periods were estimated using a flood frequency analysis using a log-Pearson III distribution, which the Kolmogorov–Smirnov (KS) test identified as the best distribution to characterize the flow regime of the Indus River at Taunsa Barrage. The output of the flood frequency analysis was then incorporated into the HEC-RAS model to determine the spatial extent of the 2014 flood, with the accuracy of this modelling approach assessed using images from the Moderate Resolution Imaging Spectroradiometer (MODIS). The results show that a supervised classification of the Landsat images was able to identify the LULC types of the study region with a high degree of accuracy, and that the most affected LULC was crop/agricultural land, of which 50% was affected by the 2014 flood. Finally, the hydraulic simulation of extent of the 2014 flood was found to visually compare very well with the MODIS image, and the surface area of floods of different return periods was calculated. This paper provides further evidence of the benefit of using a hydrological model and satellite images for flood mapping and for flood damage assessment to inform the development of risk mitigation strategies.

Earth Observation (EO) data is a critical information source for mapping and monitoring water resources over large inaccessible regions where hydrological in-situ networks are sparse. In this paper, we present a simple yet robust method for fusing optical and Synthetic Aperture Radar (SAR) data for mapping surface water dynamics over mainland China. This method uses a multivariate logistic regression model to estimate monthly surface water extent over a four-year period (2017 to 2020) from the combined usages of Sentinel-1, Sentinel-2 and Landsat-8 imagery. Multi-seasonal high-resolution images from the Chinese Gaofen satellites are used as a reference for an independent validation showing a high degree of agreement (overall accuracy 94%) across a diversity of climatic and physiographic regions demonstrating potential scalability beyond China. Through inter-comparison with similar global scale products, this paper further shows how this new mapping technique provides improved spatio-temporal characterization of inland water bodies, and for better capturing smaller water bodies (< 0.81 ha in size). The relevance of the results is discussed, and we find this new enhanced monitoring approach has the potential to advance the use of Earth observation for water resource management, planning and reporting.

Earth Observation (EO) imagery is difficult to find and access for the intermediate user, requiring advanced skills and tools to transform it into useful information. Currently, remote sensing data is increasingly freely and openly available from different satellite platforms. However, the variety of images in terms of different types of sensors, spatial and spectral resolutions generates limitations due to the heterogeneity and complexity of the data, making it difficult to exploit the full potential of satellite imagery. Addressing this issue requires new approaches to organize, manage, and analyse remote-sensing imagery. This paper focuses on the growing trend based on satellite EO and the analysis-ready data (ARD) to integrate two public optical satellite missions: Landsat 8 (L8) and Sentinel 2 (S2). This paper proposes a new way to combine S2 and L8 imagery based on a Local Nested Grid (LNG). The LNG designed plays a key role in the development of new products within the European EO downstream sector, which must incorporate assimilation techniques and interoperability best practices, automatization, systemization, and integrated web-based services that will potentially lead to pre-operational downstream services. The approach was tested in the Duero river basin (78,859 km2) and in the groundwater Mancha Oriental (7279 km2) in the Jucar river basin, Spain. In addition, a viewer based on Geoserver was prepared for visualizing the LNG of S2 and L8, and the Normalized Difference Vegetation Index (NDVI) values in points. Thanks to the LNG presented in this paper, the processing, storage, and publication tasks are optimal for the combined use of images from two different satellite sensors when the relationship between spatial resolutions is an integer (3 in the case of L8 and S2).

This paper estimates lake level variations over two small and adjacent lakes in the Tibetan plateau (TP), namely Gemang Co and Zhangnai Co, as well as the inland Dianchi Lake in China using CryoSat-2 SARIn-mode and LRM 20-Hz waveforms over the period of 2011–2018. Different retrackers and a dedicated data editing procedure have been used to process CryoSat-2 data for determining the lake level time series. The lake level estimations are indirectly validated against those from Jason-2 in TP and from in situ data in Dianchi Lake, both showing good agreement with strong correlation coefficients >0.74. The results of this paper suggest that the official ICE retracker for LRM data and APD-PPT retracker for SARIn-mode waveforms are the most appropriate retrackers over Dianchi Lake and TP lakes, respectively. The trend estimates of the time series derived by both retrackers are 61.0 ± 10.8 mm/yr for Gemang Co and Zhangnai Co in TP, and 30.9 ± 64.9 mm/yr for Dianchi Lake, indicating that the lake levels over three lakes were continuously rising over the study period. The results of this study show that CryoSat-2 SARIn-mode data can be used for monitoring many small lakes that have not been measured by other altimetry missions in TP.

In terms of land cover classification, optical images have been proven to have good classification performance. Synthetic Aperture Radar (SAR) has the characteristics of working all-time and all-weather. It has more significant advantages over optical images for the recognition of some scenes, such as water bodies. One of the current challenges is how to fuse the benefits of both to obtain more powerful classification capabilities. This study proposes a classification model based on random forest with the conditional random fields (CRF) for feature-level fusion classification using features extracted from polarized SAR and optical images. In this paper, feature importance is introduced as a weight in the pairwise potential function of the CRF to improve the correction rate of misclassified points. The results show that the dataset combining the two provides significant improvements in feature identification when compared to the dataset using optical or polarized SAR image features alone. Among the four classification models used, the random forest-importance_ conditional random fields (RF-Im_CRF) model developed in this paper obtained the best overall accuracy (OA) and Kappa coefficient, validating the effectiveness of the method.

The global positioning system (GPS) receiver has been one of the most important navigation systems for more than two decades. Although the GPS system was originally designed for near-Earth navigation, currently it is widely used in highly dynamic environments (such as low Earth orbit (LEO)). A space-capable GPS receiver (GPSR) is capable of providing timing and navigation information for spacecraft to determine the orbit and synchronize the onboard timing; therefore, it is one of the essential components of modern spacecraft. However, a space-grade GPSR is technology-sensitive and under export control. In order to overcome export control, the National Space Organization (NSPO) in Taiwan completed the development of a self-reliant space-grade GPSR in 2014. The NSPO GPSR, built in-house, has passed its qualification tests and is ready to fly onboard the Triton satellite. In addition to providing navigation, the GPS/global navigation satellite system (GNSS) is facilitated to many remote sensing missions, such as GNSS radio occultation (GNSS-RO) and GNSS reflectometry (GNSS-R). Based on the design of the NSPO GPSR, the NSPO is actively engaged in the development of the Triton program (a GNSS reflectometry mission). In a GNSS-R mission, the reflected signals are processed to form delay Doppler maps (DDMs) so that various properties (including ocean surface roughness, vegetation, soil moisture, and so on) can be retrieved. This paper describes not only the development of the NSPO GPSR but also the design, development, and special features of the Triton’s GNSS-R mission. Moreover, in order to verify the NSPO GNSS-R receiver, ground/flight tests are deemed essential. Then, data analyses of the airborne GNSS-R tests are presented in this paper.

In smartphone indoor positioning, owing to the strong complementarity between pedestrian dead reckoning (PDR) and WiFi, a hybrid fusion scheme of them is drawing more and more attention. However, the outlier of WiFi will easily degrade the performance of the scheme, to remove them, many researches have been proposed such as: improving the WiFi individually or enhancing the scheme. Nevertheless, due to the inherent received signal strength (RSS) variation, there still exist some unremoved outliers. To solve this problem, this paper proposes the first outlier detection and removal strategy with the aid of Machine Learning (ML), so called WiFi-AGNES (Agglomerative Nesting), based on the extracted positioning characteristics of WiFi when the pedestrian is static. Then, the paper proposes the second outlier detection and removal strategy, so called WiFi-Chain, based on the extracted positioning characteristics of WiFi, PDR, and their complementary characteristics when the pedestrian is walking. Finally, a hybrid fusion scheme is proposed, which integrates the two proposed strategies, WiFi, PDR with an inertial-navigation-system-based (INS-based) attitude heading reference system (AHRS) via Extended Kalman Filter (EKF), and an Unscented Kalman Filter (UKF). The experiment results show that the two proposed strategies are effective and robust. With WiFi-AGNES, the minimum percentage of the maximum error (MaxE) is reduced by 66.5%; with WiFi-Chain, the MaxE of WiFi is less than 4.3 m; further the proposed scheme achieves the best performance, where the root mean square error (RMSE) is 1.43 m. Moreover, since characteristics are universal, the proposed scheme integrated the two characteristic-based strategies also possesses strong robustness.

The incorporation of advanced technologies into Unmanned Aerial Vehicles (UAVs) platforms have enabled many practical applications in Precision Agriculture (PA) over the past decade. These PA tools offer capabilities that increase agricultural productivity and inputs’ efficiency and minimize operational costs simultaneously. However, these platforms also have some constraints that limit the application of UAVs in agricultural operations. The constraints include limitations in providing imagery of adequate spatial and temporal resolutions, dependency on weather conditions, and geometric and radiometric correction requirements. In this paper, a practical guide on technical characterizations of common types of UAVs used in PA is presented. This paper helps select the most suitable UAVs and on-board sensors for different agricultural operations by considering all the possible constraints. Over a hundred research studies were reviewed on UAVs applications in PA and practical challenges in monitoring and mapping field crops. We concluded by providing suggestions and future directions to overcome challenges in optimizing operational proficiency.

Recently, many convolutional networks have been built to fuse a low spatial resolution (LR) hyperspectral image (HSI) and a high spatial resolution (HR) multispectral image (MSI) to obtain HR HSIs. However, most deep learning-based methods are supervised methods, which require sufficient HR HSIs for supervised training. Collecting plenty of HR HSIs is laborious and time-consuming. In this paper, a self-supervised spectral-spatial residual network (SSRN) is proposed to alleviate dependence on a mass of HR HSIs. In SSRN, the fusion of HR MSIs and LR HSIs is considered a pixel-wise spectral mapping problem. Firstly, this paper assumes that the spectral mapping between HR MSIs and HR HSIs can be approximated by the spectral mapping between LR MSIs (derived from HR MSIs) and LR HSIs. Secondly, the spectral mapping between LR MSIs and LR HSIs is explored by SSRN. Finally, a self-supervised fine-tuning strategy is proposed to transfer the learned spectral mapping to generate HR HSIs. SSRN does not require HR HSIs as the supervised information in training. Simulated and real hyperspectral databases are utilized to verify the performance of SSRN.

Vehicle density and technological development increase the need for road and pedestrian safety systems. Identifying problems and addressing them through the development of systems to reduce the number of accidents and loss of life is imperative. This paper proposes the analysis and management of dangerous situations, with the help of systems and modules designed in this direction. The approach and classification of situations that can cause accidents is another feature analyzed in this paper, including detecting elements of a psychosomatic nature: analysis and detection of the conditions a driver goes through, pedestrian analysis, and maintaining a preventive approach, all of which are embedded in a modular architecture. The versatility and usefulness of such a system come through its ability to adapt to context and the ability to communicate with traffic safety systems such as V2V (vehicle-to-vehicle), V2I (vehicle-to-infrastructure), V2X (vehicle-to-everything), and VLC (visible light communication). All these elements are found in the operation of the system and its ability to become a portable device dedicated to road safety based on (radio frequency) RF-VLC (visible light communication).

Shridhar D. Jawak, Bo N. Andersen, Veijo Pohjola, Øystein Godøy, Kim Holmén, Agnar Sivertsen, Richard Hann, Hans Tømmervik, Andreas Kääb, Małgorzata Błaszczyk, Roberto Salzano, Bartłomiej Luks, Kjell Arild Høgda, Rune Storvold, Lennart Nilsen, Rosamaria Salvatori, Kottekkatu Padinchati Krishnan, Sourav Chatterjee, Dag A. Lorentzen, Rasmus Erlandsson, Tom Rune Lauknes, Eirik Malnes, Stein Rune Karlsen, Hiroyuki Enomoto, Ann Mari Fjæraa, Jie Zhang, Sabine Marty, Knut Ove Nygård, Heikki Lihavainen, Svalbard Integrated Arctic Earth Observing System (SIOS) is an international partnership of research institutions studying the environment and climate in and around Svalbard. SIOS is developing an efficient observing system, where researchers share technology, experience, and data, work together to close knowledge gaps, and decrease the environmental footprint of science. SIOS maintains and facilitates various scientific activities such as the State of the Environmental Science in Svalbard (SESS) report, international access to research infrastructure in Svalbard, Earth observation and remote sensing services, training courses for the Arctic science community, and open access to data. This perspective paper highlights the activities of SIOS Knowledge Centre, the central hub of SIOS, and the SIOS Remote Sensing Working Group (RSWG) in response to the unprecedented situation imposed by the global pandemic coronavirus (SARS-CoV-2) disease 2019 (COVID-19). The pandemic has affected Svalbard research in several ways. When Norway declared a nationwide lockdown to decrease the rate of spread of the COVID-19 in the community, even more strict measures were taken to protect the Svalbard community from the potential spread of the disease. Due to the lockdown, travel restrictions, and quarantine regulations declared by many nations, most physical meetings, training courses, conferences, and workshops worldwide were cancelled by the first week of March 2020. The resumption of physical scientific meetings is still uncertain in the foreseeable future. Additionally, field campaigns to polar regions, including Svalbard, were and remain severely affected. In response to this changing situation, SIOS initiated several operational activities suitable to mitigate the new challenges resulting from the pandemic. This article provides an extensive overview of SIOS’s Earth observation (EO), remote sensing (RS) and other operational activities strengthened and developed in response to COVID-19 to support the Svalbard scientific community in times of cancelled/postponed field campaigns in Svalbard. These include (1) an initiative to patch up field data (in situ) with RS observations, (2) a logistics sharing notice board for effective coordinating field activities in the pandemic times, (3) a monthly webinar series and panel discussion on EO talks, (4) an online conference on EO and RS, (5) the SIOS’s special issue in the Remote Sensing (MDPI) journal, (6) the conversion of a terrestrial remote sensing training course into an online edition, and (7) the announcement of opportunity (AO) in airborne remote sensing for filling the data gaps using aerial imagery and hyperspectral data. As SIOS is a consortium of 24 research institutions from 9 nations, this paper also presents an extensive overview of the activities from a few research institutes in pandemic times and highlights our upcoming activities for the next year 2021. Finally, we provide a critical perspective on our overall response, possible broader impacts, relevance to other observing systems, and future directions. We hope that our practical services, experiences, and activities implemented in these difficult times will motivate other similar monitoring programs and observing systems when responding to future challenging situations. With a broad scientific audience in mind, we present our perspective paper on activities in Svalbard as a case study.

To cope with the increasingly complex electromagnetic environment, multistatic radar systems, especially the passive multistatic radar, are becoming a trend of future radar development due to their advantages in anti-electronic jam, anti-destruction properties, and no electromagnetic pollution. However, one problem with this multi-source network is that it brings a huge amount of information and leads to considerable computational load. Aiming at the problem, this paper introduces the idea of selecting external illuminators in the multistatic passive radar system. Its essence is to optimize the configuration of multistatic T/R pairs. Based on this, this paper respectively proposes two multi-source optimization algorithms from the perspective of resolution unit and resolution capability, the Covariance Matrix Fusion Method and Convex Hull Optimization Method, and then uses a Global Navigation Satellite System (GNSS) as an external illuminator to verify the algorithms. The experimental results show that the two optimization methods significantly improve the accuracy of multistatic positioning, and obtain a more reasonable use of system resources. To evaluate the algorithm performance under large number of transmitting/receiving stations, further simulation was conducted, in which a combination of the two algorithms were applied and the combined algorithm has shown its effectiveness in minimize the computational load and retain the target localization precision at the same time.

Digital elevation model (DEM) interpolation is aimed at predicting the elevation values of unobserved locations, given a series of collected points. Over the years, the traditional interpolation methods have been widely used but can easily lead to accuracy degradation. In recent years, generative adversarial networks (GANs) have been proven to be more efficient than the traditional methods. However, the interpolation accuracy is not guaranteed. In this paper, we propose a GAN-based network named gated and symmetric-dilated U-net GAN (GSUGAN) for improved DEM interpolation, which performs visibly and quantitatively better than the traditional methods and the conditional encoder-decoder GAN (CEDGAN). We also discuss combinations of new techniques in the generator. This shows that the gated convolution and symmetric dilated convolution structure perform slightly better. Furthermore, based on the performance of the different methods, it was concluded that the Convolutional Neural Network (CNN)-based method has an advantage in the quantitative accuracy but the GAN-based method can obtain a better visual quality, especially in complex terrains. In summary, in this paper, we propose a GAN-based network for improved DEM interpolation and we further illustrate the GAN-based method’s performance compared to that of the CNN-based method.

Information about the growth, productivity, and distribution of vegetation, which are highly relied on and sensitive to natural and anthropogenic factors, is essential for agricultural production management and eco-environmental sustainability in the Amur River Basin (ARB). In this paper, the spatial–temporal trends of vegetation dynamics were analyzed at the pixel scale in the ARB for the period of 1982–2013 using remotely sensed data of long-term leaf area index (LAI), fractional vegetation cover (FVC), and terrestrial gross primary productivity (GPP). The spatial autocorrelation characteristics of the vegetation indexes were further explored with global and local Moran’s I techniques. The spatial–temporal relationships between vegetation and climatic factors, land use/cover types and hydrological variables in the ARB were determined using a geographical and temporal weighted regression (GTWR) model based on the observed meteorological data, remotely sensed vegetation information, while the simulated hydrological variables were determined with the soil and water assessment tool (SWAT) model. The results suggest that the variation in area-average annual FVC was significant with an increase rate of 0.0004/year, and LAI, FVC, and GPP all exhibited strong spatial heterogeneity trends in the ARB. For LAI and FVC, the most significant changes in local spatial autocorrelation were recognized over the Sanjiang Plain, and the low–low agglomeration in the Sanjiang Plain decreased continuously. The GTWR model results indicate that natural and anthropogenic factors jointly took effect and interacted with each other to affect the vegetated regime of the region. The decrease in the impact of precipitation to vegetation growth over the Songnen Plain was determined as having started around 1991, which was most likely attributed to dramatic changes in water use styles induced by local land use changes, and corresponded to the negative correlation between pasture areas and vegetation indexes during the same period. The analysis results presented in this paper can provide vital information to decision-makers for use in managing vegetation resources.

The high complexity of the reconstruction algorithm is the main bottleneck of the hyperspectral image (HSI) compression technology based on compressed sensing. Compressed sensing technology is an important tool for retrieving the maximum number of HSI scenes on the ground. However, the complexity of the compressed sensing algorithm is limited by the energy and hardware of spaceborne equipment. Aiming at the high complexity of compressed sensing reconstruction algorithm and low reconstruction accuracy, an equivalent model of the invertible transformation is theoretically derived by us in the paper, which can convert the complex invertible projection training model into the coupled dictionary training model. Besides, aiming at the invertible projection training model, the most competitive task-driven invertible projection matrix learning algorithm (TIPML) is proposed. In TIPML, we don’t need to directly train the complex invertible projection model, but indirectly train the invertible projection model through the training of the coupled dictionary. In order to improve the accuracy of reconstructed data, in the paper, the singular value transformation is proposed. It has been verified that the concentration of the dictionary is increased and that the expressive ability of the dictionary has not been reduced by the transformation. Besides, two-loop iterative training is established to improve the accuracy of data reconstruction. Experiments show that, compared with the traditional compressed sensing algorithm, the compressed sensing algorithm based on TIPML has higher reconstruction accuracy, and the reconstruction time is shortened by more than a hundred times. It is foreseeable that the TIPML algorithm will have a huge application prospect in the field of HSI compression.

Pine nematode is a highly contagious disease that causes great damage to the world’s pine forest resources. Timely and accurate identification of pine nematode disease can help to control it. At present, there are few research on pine nematode disease identification, and it is difficult to accurately identify and locate nematode disease in a single pine by existing methods. This paper proposes a new network, SCANet (spatial-context-attention network), to identify pine nematode disease based on unmanned aerial vehicle (UAV) multi-spectral remote sensing images. In this method, a spatial information retention module is designed to reduce the loss of spatial information; it preserves the shallow features of pine nematode disease and expands the receptive field to enhance the extraction of deep features through a context information module. SCANet reached an overall accuracy of 79% and a precision and recall of around 0.86, and 0.91, respectively. In addition, 55 disease points among 59 known disease points were identified, which is better than other methods (DeepLab V3+, DenseNet, and HRNet). This paper presents a fast, precise, and practical method for identifying nematode disease and provides reliable technical support for the surveillance and control of pine wood nematode disease.

Given the continuous increase in the global population, the food manufacturers are advocated to either intensify the use of cropland or expand the farmland, making land cover and land usage dynamics mapping vital in the area of remote sensing. In this regard, identifying and classifying a high-resolution satellite imagery scene is a prime challenge. Several approaches have been proposed either by using static rule-based thresholds (with limitation of diversity) or neural network (with data-dependent limitations). This paper adopts the inductive approach to learning from surface reflectances. A manually labeled Sentinel-2 dataset was used to build a Machine Learning (ML) model for scene classification, distinguishing six classes (Water, Shadow, Cirrus, Cloud, Snow, and Other). This models was accessed and further compared to the European Space Agency (ESA) Sen2Cor package. The proposed ML model presents a Micro-F1 value of 0.84, a considerable improvement when compared to the Sen2Cor corresponding performance of 0.59. Focusing on the problem of optical satellite image scene classification, the main research contributions of this paper are: (a) an extended manually labeled Sentinel-2 database adding surface reflectance values to an existing dataset; (b) an ensemble-based and a Neural-Network-based ML models; (c) an evaluation of model sensitivity, biasness, and diverse ability in classifying multiple classes over different geographic Sentinel-2 imagery, and finally, (d) the benchmarking of the ML approach against the Sen2Cor package.

Spectral unmixing (SU) aims at decomposing the mixed pixel into basic components, called endmembers with corresponding abundance fractions. Linear mixing model (LMM) and nonlinear mixing models (NLMMs) are two main classes to solve the SU. This paper proposes a new nonlinear unmixing method base on general bilinear model, which is one of the NLMMs. Since retrieving the endmembers’ abundances represents an ill-posed inverse problem, prior knowledge of abundances has been investigated by conceiving regularizations techniques (e.g., sparsity, total variation, group sparsity, and low rankness), so to enhance the ability to restrict the solution space and thus to achieve reliable estimates. All the regularizations mentioned above can be interpreted as denoising of abundance maps. In this paper, instead of investing effort in designing more powerful regularizations of abundances, we use plug-and-play prior technique, that is to use directly a state-of-the-art denoiser, which is conceived to exploit the spatial correlation of abundance maps and nonlinear interaction maps. The numerical results in simulated data and real hyperspectral dataset show that the proposed method can improve the estimation of abundances dramatically compared with state-of-the-art nonlinear unmixing methods.

Wetlands are ranked as very diverse ecosystems, covering about 4–6% of the global land surface. They occupy the transition zones between aquatic and terrestrial environments, and share characteristics of both zones. Wetlands play critical roles in the hydrological cycle, sustaining livelihoods and aquatic life, and biodiversity. Poor management of wetlands results in the loss of critical ecosystems goods and services. Globally, wetlands are degrading at a fast rate due to global environmental change and anthropogenic activities. This requires holistic monitoring, assessment, and management of wetlands to prevent further degradation and losses. Remote-sensing data offer an opportunity to assess changes in the status of wetlands including their spatial coverage. So far, a number of studies have been conducted using remotely sensed data to assess and monitor wetland status in semi-arid and arid regions. A literature search shows a significant increase in the number of papers published during the 2000–2020 period, with most of these studies being in semi-arid regions in Australia and China, and few in the sub-Saharan Africa. This paper reviews progress made in the use of remote sensing in detecting and monitoring of the semi-arid and arid wetlands, and focuses particularly on new insights in detection and monitoring of wetlands using freely available multispectral sensors. The paper firstly describes important characteristics of wetlands in semi-arid and arid regions that require monitoring in order to improve their management. Secondly, the use of freely available multispectral imagery for compiling wetland inventories is reviewed. Thirdly, the challenges of using freely available multispectral imagery in mapping and monitoring wetlands dynamics like inundation, vegetation cover and extent, are examined. Lastly, algorithms for image classification as well as challenges associated with their uses and possible future research are summarised. However, there are concerns regarding whether the spatial and temporal resolutions of some of the remote-sensing data enable accurate monitoring of wetlands of varying sizes. Furthermore, it was noted that there were challenges associated with the both spatial and spectral resolutions of data used when mapping and monitoring wetlands. However, advancements in remote-sensing and data analytics provides new opportunities for further research on wetland monitoring and assessment across various scales.

Marine raft aquaculture (MFA) plays an important role in the marine economy and ecosystem. With the characteristics of covering a large area and being sparsely distributed in sea area, MFA monitoring suffers from the low efficiency of field survey and poor data of optical satellite imagery. Synthetic aperture radar (SAR) satellite imagery is currently considered to be an effective data source, while the state-of-the-art methods require manual parameter tuning under the guidance of professional experience. To preclude the limitation, this paper proposes a segmentation network combined with nonsubsampled contourlet transform (NSCT) to extract MFA areas using Sentinel-1 images. The proposed method is highlighted by several improvements based on the feature analysis of MFA. First, the NSCT was applied to enhance the contour and orientation features. Second, multiscale and asymmetric convolutions were introduced to fit the multisize and strip-like features more effectively. Third, both channel and spatial attention modules were adopted in the network architecture to overcome the problems of boundary fuzziness and area incompleteness. Experiments showed that the method can effectively extract marine raft culture areas. Although further research is needed to overcome the problem of interference caused by excessive waves, this paper provides a promising approach for periodical monitoring MFA in a large area with high efficiency and acceptable accuracy.

More and more scholars are committed to light detection and ranging (LiDAR) as a roadside sensor to obtain traffic flow data. Filtering and clustering are common methods to extract pedestrians and vehicles from point clouds. This kind of method ignores the impact of environmental information on traffic. The segmentation process is a crucial part of detailed scene understanding, which could be especially helpful for locating, recognizing, and classifying objects in certain scenarios. However, there are few studies on the segmentation of low-channel (16 channels in this paper) roadside 3D LiDAR. This paper presents a novel segmentation (slice-based) method for point clouds of roadside LiDAR. The proposed method can be divided into two parts: the instance segmentation part and semantic segmentation part. The part of the instance segmentation of point cloud is based on the regional growth method, and we proposed a seed point generation method for low-channel LiDAR data. Furthermore, we optimized the instance segmentation effect under occlusion. The part of semantic segmentation of a point cloud is realized by classifying and labeling the objects obtained by instance segmentation. For labeling static objects, we represented and classified a certain object through the related features derived from its slices. For labeling moving objects, we proposed a recurrent neural network (RNN)-based model, of which the accuracy could be up to 98.7%. The result implies that the slice-based method can obtain a good segmentation effect and the slice has good potential for point cloud segmentation.

Over the last decade, particular interest in using state-of-the-art emerging technologies for inspection, assessment, and management of civil infrastructures has remarkably increased. Advanced technologies, such as laser scanners, have become a suitable alternative for labor intensive, expensive, and unsafe traditional inspection and maintenance methods, which encourage the increasing use of this technology in construction industry, especially in bridges. This paper aims to provide a thorough mixed scientometric and state-of-the-art review on the application of terrestrial laser scanners (TLS) in bridge engineering and explore investigations and recommendations of researchers in this area. Following the review, more than 1500 research publications were collected, investigated and analyzed through a two-fold literature search published within the last decade from 2010 to 2020. Research trends, consisting of dominated sub-fields, co-occurrence of keywords, network of researchers and their institutions, along with the interaction of research networks, were quantitatively analyzed. Moreover, based on the collected papers, application of TLS in bridge engineering and asset management was reviewed according to four categories including (1) generation of 3D model, (2) quality inspection, (3) structural assessment, and (4) bridge information modeling (BrIM). Finally, the paper identifies the current research gaps, future directions obtained from the quantitative analysis, and in-depth discussions of the collected papers in this area.

Canada’s successful space-based earth-observation (EO) radar program has earned widespread and expanding user acceptance following the launch of RADARSAT-1 in 1995. RADARSAT-2, launched in 2007, while providing data continuity for its predecessor’s imaging capabilities, added new polarimetric modes. Canada’s follow-up program, the RADARSAT Constellation Mission (RCM), launched in 2019, while providing continuity for its two predecessors, includes an innovative suite of polarimetric modes. In an effort to make polarimetry accessible to a wide range of operational users, RCM uses a new method called hybrid compact polarization (HCP). There are two essential elements to this approach: (1) transmit only one polarization, circular; and (2) receive two orthogonal polarizations, for which RCM uses H and V. This configuration overcomes the conventional dual and full polarimetric system limitations, which are lacking enough polarimetric information and having a small swath width, respectively. Thus, HCP data can be considered as dual-pol data, while the resulting polarimetric classifications of features in an observed scene are of comparable accuracy as those derived from the traditional fully polarimetric (FP) approach. At the same time, RCM’s HCP methodology is applicable to all imaging modes, including wide swath and ScanSAR, thus overcoming critical limitations of traditional imaging radar polarimetry for operational use. The primary image data products from an HCP radar are different from those of a traditional polarimetric radar. Because the HCP modes transmit circularly polarized signals, the data processing to extract polarimetric information requires different approaches than those used for conventional linearly polarized polarimetric data. Operational users, as well as researchers and students, are most likely to achieve disappointing results if they work with traditional polarimetric processing tools. New tools are required. Existing tutorials, older seminar notes, and reference papers are not sufficient, and if left unrevised, could succeed in discouraging further use of RCM polarimetric data. This paper is designed to provide an initial response to that need. A systematic review of studies that used HCP SAR data for environmental monitoring is also provided. Based on this review, HCP SAR data have been employed in oil spill monitoring, target detection, sea ice monitoring, agriculture, wetland classification, and other land cover applications.

The estimation of ambiguity in the global navigation satellite system/inertial navigation system (GNSS/INS) tightly coupled system is a key issue for GNSS/INS precise navigation positioning. Only when the ambiguity is solved correctly can the integrated navigation system obtain high-precision positioning results. Aiming at the problem of ambiguity parameter estimation in GNSS/INS tightly coupled system, a new strategy for ambiguity parameter estimation and elimination is proposed in this paper. Here, the ambiguity parameter is first added to the state equations of GNSS/INS in the estimation process. Then, the strategy of eliminating the parameter is used to improve efficiency. A residual test is carried out based on introducing the ambiguity parameter, thereby reducing or avoiding its influence on the filtering estimation process. Two groups of experiments were carried out and compared with GNSS positioning results. The results showed that, in the open sky observation environment, the positioning accuracy of the GNSS/INS tightly coupled method proposed in this paper was within 5 cm, and the ambiguity fixed rate was more than 97%, which is basically consistent. In a GNSS-denied environment, the positioning accuracy of the GNSS/INS tightly coupled method proposed in this paper was obviously better than that of GNSS, and the positioning accuracy in X, Y, and Z directions was improved by 82.46%, 78.87%, and 79.67%, respectively. The fixed rate of ambiguity increased from 73% to 78.57%. Therefore, in a GNSS-challenged environment, the novel strategy of the GNSS/INS tightly coupled system has higher ambiguity fixed rate and significantly improves positioning accuracy and continuity.

Earth observation data is becoming more accessible and affordable thanks to the Copernicus programme and its Sentinel missions. Every location worldwide can be freely monitored approximately every 5 days using the multi-spectral images provided by Sentinel-2. The spatial resolution of these images for RGBN (RGB + Near-infrared) bands is 10 m, which is more than enough for many tasks but falls short for many others. For this reason, if their spatial resolution could be enhanced without additional costs, any posterior analyses based on these images would be benefited. Previous works have mainly focused on increasing the resolution of lower resolution bands of Sentinel-2 (20 m and 60 m) to 10 m resolution. In these cases, super-resolution is supported by bands captured at finer resolutions (RGBN at 10 m). On the contrary, this paper focuses on the problem of increasing the spatial resolution of 10 m bands to either 5 m or 2.5 m resolutions, without having additional information available. This problem is known as single-image super-resolution. For standard images, deep learning techniques have become the de facto standard to learn the mapping from lower to higher resolution images due to their learning capacity. However, super-resolution models learned for standard images do not work well with satellite images and hence, a specific model for this problem needs to be learned. The main challenge that this paper aims to solve is how to train a super-resolution model for Sentinel-2 images when no ground truth exists (Sentinel-2 images at 5 m or 2.5 m). Our proposal consists of using a reference satellite with a high similarity in terms of spectral bands with respect to Sentinel-2, but with higher spatial resolution, to create image pairs at both the source and target resolutions. This way, we can train a state-of-the-art Convolutional Neural Network to recover details not present in the original RGBN bands. An exhaustive experimental study is carried out to validate our proposal, including a comparison with the most extended strategy for super-resolving Sentinel-2, which consists in learning a model to super-resolve from an under-sampled version at either 40 m or 20 m to the original 10 m resolution and then, applying this model to super-resolve from 10 m to 5 m or 2.5 m. Finally, we will also show that the spectral radiometry of the native bands is maintained when super-resolving images, in such a way that they can be used for any subsequent processing as if they were images acquired by Sentinel-2. M.G. was partially supported by Tracasa Instrumental S.L. under projects OTRI 2018-901-073, OTRI 2019-901-091 and OTRI 2020-901-050. C.A. (Christian Ayala) was partially supported by the Goverment of Navarra under the industrial PhD program 2020 reference 0011-1408-2020-000008. M.G. was partially supported by Tracasa Instrumental S.L. under projects OTRI 2018-901-073, OTRI 2019-901-091 and OTRI 2020-901-050. C.A. (Christian Ayala) was partially supported by the Goverment of Navarra under the industrial PhD program 2020 reference 0011-1408-2020-000008.

Mobile platform visual image sequence inevitably has large areas with various types of weak textures, which affect the acquisition of accurate pose in the subsequent platform moving process. The visual–inertial odometry (VIO) with point features and line features as visual information shows a good performance in weak texture environments, which can solve these problems to a certain extent. However, the extraction and matching of line features are time consuming, and reasonable weights between the point and line features are hard to estimate, which makes it difficult to accurately track the pose of the platform in real time. In order to overcome the deficiency, an improved effective point–line visual–inertial odometry system is proposed in this paper, which makes use of geometric information of line features and combines with pixel correlation coefficient to match the line features. Furthermore, this system uses the Helmert variance component estimation method to adjust weights between point features and line features. Comprehensive experimental results on the two datasets of EuRoc MAV and PennCOSYVIO demonstrate that the point–line visual–inertial odometry system developed in this paper achieved significant improvements in both localization accuracy and efficiency compared with several state-of-the-art VIO systems.

Building extraction from high-resolution remote sensing images plays a vital part in urban planning, safety supervision, geographic databases updates, and some other applications. Several researches are devoted to using convolutional neural network (CNN) to extract buildings from high-resolution satellite/aerial images. There are two major methods, one is the CNN-based semantic segmentation methods, which can not distinguish different objects of the same category and may lead to edge connection. The other one is CNN-based instance segmentation methods, which rely heavily on pre-defined anchors, and result in the highly sensitive, high computation/storage cost and imbalance between positive and negative samples. Therefore, in this paper, we propose an improved anchor-free instance segmentation method based on CenterMask with spatial and channel attention-guided mechanisms and improved effective backbone network for accurate extraction of buildings in high-resolution remote sensing images. Then we analyze the influence of different parameters and network structure on the performance of the model, and compare the performance for building extraction of Mask R-CNN, Mask Scoring R-CNN, CenterMask, and the improved CenterMask in this paper. Experimental results show that our improved CenterMask method can successfully well-balanced performance in terms of speed and accuracy, which achieves state-of-the-art performance at real-time speed.

Remote sensing of plant phenology as an indicator of climate change and for mapping land cover has received significant scientific interest in the past two decades. The advancing of spring events, the lengthening of the growing season, the shifting of tree lines, the decreasing sensitivity to warming and the uniformity of spring across elevations are a few of the important indicators of trends in phenology. The Sentinel-2 satellite sensors launched in June 2015 (A) and March 2017 (B), with their high temporal frequency and spatial resolution for improved land mapping missions, have contributed significantly to knowledge on vegetation over the last three years. However, despite the additional red-edge and short wave infra-red (SWIR) bands available on the Sentinel-2 multispectral instruments, with improved vegetation species detection capabilities, there has been very little research on their efficacy to track vegetation cover and its phenology. For example, out of approximately every four papers that analyse normalised difference vegetation index (NDVI) or enhanced vegetation index (EVI) derived from Sentinel-2 imagery, only one mentions either SWIR or the red-edge bands. Despite the short duration that the Sentinel-2 platforms have been operational, they have proved their potential in a wide range of phenological studies of crops, forests, natural grasslands, and other vegetated areas, and in particular through fusion of the data with those from other sensors, e.g., Sentinel-1, Landsat and MODIS. This review paper discusses the current state of vegetation phenology studies based on the first five years of Sentinel-2, their advantages, limitations, and the scope for future developments.

Optical and Synthetic Aperture Radar (SAR) fusion is addressed in this paper. Intensity–Hue–Saturation (IHS) is an easily implemented fusion method and can separate Red–Green–Blue (RGB) images into three independent components; however, using this method directly for optical and SAR images fusion will cause spectral distortion. The Gradient Transfer Fusion (GTF) algorithm is proposed firstly for infrared and gray visible images fusion, which formulates image fusion as an optimization problem and keeps the radiation information and spatial details simultaneously. However, the algorithm assumes that the spatial details only come from one of the source images, which is inconsistent with the actual situation of optical and SAR images fusion. In this paper, a fusion algorithm named IHS-GTF for optical and SAR images is proposed, which combines the advantages of IHS and GTF and considers the spatial details from the both images based on pixel saliency. The proposed method was assessed by visual analysis and ten indices and was further tested by extracting impervious surface (IS) from the fused image with random forest classifier. The results show the good preservation of spatial details and spectral information by our proposed method, and the overall accuracy of IS extraction is 2% higher than that of using optical image alone. The results demonstrate the ability of the proposed method for fusing optical and SAR data effectively to generate useful data.

Remote sensing data and methods are increasingly being embedded into assessments of volcanic processes and risk. This happens thanks to their capability to provide a spectrum of observation and measurement opportunities to accurately sense the dynamics, magnitude, frequency, and impacts of volcanic activity in the ultraviolet (UV), visible (VIS), infrared (IR), and microwave domains. Launched in mid-2018, the Special Issue “Remote Sensing of Volcanic Processes and Risk” of Remote Sensing gathers 19 research papers on the use of satellite, aerial, and ground-based remote sensing to detect thermal features and anomalies, investigate lava and pyroclastic flows, predict the flow path of lahars, measure gas emissions and plumes, and estimate ground deformation. The strong multi-disciplinary character of the approaches employed for volcano monitoring and the combination of a variety of sensor types, platforms, and methods that come out from the papers testify the current scientific and technology trends toward multi-data and multi-sensor monitoring solutions. The research advances presented in the published papers are achieved thanks to a wealth of data including but not limited to the following: thermal IR from satellite missions (e.g., MODIS, VIIRS, AVHRR, Landsat-8, Sentinel-2, ASTER, TET-1) and ground-based stations (e.g., FLIR cameras); digital elevation/surface models from airborne sensors (e.g., Light Detection And Ranging (LiDAR), or 3D laser scans) and satellite imagery (e.g., tri-stereo Pléiades, SPOT-6/7, PlanetScope); airborne hyperspectral surveys; geophysics (e.g., ground-penetrating radar, electromagnetic induction, magnetic survey); ground-based acoustic infrasound; ground-based scanning UV spectrometers; and ground-based and satellite Synthetic Aperture Radar (SAR) imaging (e.g., TerraSAR-X, Sentinel-1, Radarsat-2). Data processing approaches and methods include change detection, offset tracking, Interferometric SAR (InSAR), photogrammetry, hotspots and anomalies detection, neural networks, numerical modeling, inversion modeling, wavelet transforms, and image segmentation. Some authors also share codes for automated data analysis and demonstrate methods for post-processing standard products that are made available for end users, and which are expected to stimulate the research community to exploit them in other volcanological application contexts. The geographic breath is global, with case studies in Chile, Peru, Ecuador, Guatemala, Mexico, Hawai’i, Alaska, Kamchatka, Japan, Indonesia, Vanuatu, Réunion Island, Ethiopia, Canary Islands, Greece, Italy, and Iceland. The added value of the published research lies on the demonstration of the benefits that these remote sensing technologies have brought to knowledge of volcanoes that pose risk to local communities; back-analysis and critical revision of recent volcanic eruptions and unrest periods; and improvement of modeling and prediction methods. Therefore, this Special Issue provides not only a collection of forefront research in remote sensing applied to volcanology, but also a selection of case studies proving the societal impact that this scientific discipline can potentially generate on volcanic hazard and risk management.

In recent years, with the improvement of synthetic aperture radar (SAR) imaging resolution, it is urgent to develop methods with higher accuracy and faster speed for ship detection in high-resolution SAR images. Among all kinds of methods, deep-learning-based algorithms bring promising performance due to end-to-end detection and automated feature extraction. However, several challenges still exist: (1) standard deep learning detectors based on anchors have certain unsolved problems, such as tuning of anchor-related parameters, scale-variation and high computational costs. (2) SAR data is huge but the labeled data is relatively small, which may lead to overfitting in training. (3) To improve detection speed, deep learning detectors generally detect targets based on low-resolution features, which may cause missed detections for small targets. In order to address the above problems, an anchor-free convolutional network with dense attention feature aggregation is proposed in this paper. Firstly, we use a lightweight feature extractor to extract multiscale ship features. The inverted residual blocks with depth-wise separable convolution reduce the network parameters and improve the detection speed. Secondly, a novel feature aggregation scheme called dense attention feature aggregation (DAFA) is proposed to obtain a high-resolution feature map with multiscale information. By combining the multiscale features through dense connections and iterative fusions, DAFA improves the generalization performance of the network. In addition, an attention block, namely spatial and channel squeeze and excitation (SCSE) block is embedded in the upsampling process of DAFA to enhance the salient features of the target and suppress the background clutters. Third, an anchor-free detector, which is a center-point-based ship predictor (CSP), is adopted in this paper. CSP regresses the ship centers and ship sizes simultaneously on the high-resolution feature map to implement anchor-free and nonmaximum suppression (NMS)-free ship detection. The experiments on the AirSARShip-1.0 dataset demonstrate the effectiveness of our method. The results show that the proposed method outperforms several mainstream detection algorithms in both accuracy and speed.

High-resolution precipitation field has been widely used in hydrological and meteorological modeling. This paper establishes the spatial and temporal distribution model of precipitation in Hubei Province from 2006 through 2014, based on the data of 75 meteorological stations. This paper applies a geographically and temporally weighted regression kriging (GTWRK) model to precipitation and assesses the effects of timescales and a time-weighted function on precipitation interpolation. This work’s results indicate that: (1) the optimal timescale of the geographically and temporally weighted regression (GTWR) precipitation model is daily. The fitting accuracy is improved when the timescale is converted from months and years to days. The average mean absolute error (MAE), mean relative error (MRE), and the root mean square error (RMSE) decrease with scaling from monthly to daily time steps by 36%, 56%, and 35%, respectively, and the same statistical indexes decrease by 13%, 15%, and 14%, respectively, when scaling from annual to daily steps; (2) the time weight function based on an exponential function improves the predictive skill of the GTWR model by 3% when compared to geographically weighted regression (GWR) using a monthly time step; and (3) the GTWRK has the highest accuracy, and improves the MAE, MRE and RMSE by 3%, 10% and 1% with respect to monthly precipitation predictions, respectively, and by 3%, 10% and 5% concerning annual precipitation predictions, respectively, compared with the GWR results.

Urban functional area (UFA) recognition is one of the most important strategies for achieving sustainable city development. As remote-sensing and social-sensing data sources have increasingly become available, UFA recognition has received a significant amount of attention. Research on UFA recognition that uses a single dataset suffers from a low update frequency or low spatial resolution, while data fusion-based methods are limited in efficiency and accuracy. This paper proposes an integrated model to identify UFA using satellite images and taxi global positioning system (GPS) trajectories in four steps. First, blocks were generated as spatial units in the study area, and the spatiotemporal information entropy of the taxi GPS trajectory (STET) for each block was calculated. Second, a 24-hour time-frequency series was formed based on the pick-up and drop-off points extracted from taxi trajectories and used as the interpretation indicator of the blocks. The K-Means++ and k-Nearest Neighbor (kNN) algorithm were used to identify their social functions. Third, a multilabel classification method based on the residual neural network (MLC-ResNets) and “You Only Look Once” (YOLO) target detection algorithms were used to identify the features of the typical and atypical spatial textures, respectively, of the satellite images in the blocks. The confidence scores of the features of the blocks were categorized by the decision tree algorithm. Fourth, to find the best way to integrate the two sub-models for UFA identification, the 10-fold cross-validation method based on stratified random sampling was applied to determine the most optimal STET thresholds. The results showed that the average accuracy reached 82.0%, with an average kappa of 73.5%—significant improvements over most existing studies. This paper provides new insights into how the advantages of satellite images and taxi trajectories in UFA identification can be fully exploited to support sustainable city management.

Synthetic aperture radar (SAR) imaging systems derive microwave data, from space or airborne (piloted and remote piloted), that provide opportunities for the interpretation of many characteristics of the terrain surface. The increasing number of satellites equipped with SAR data acquisition systems that are being launched with a range of wavelengths, polarizations, and operating characteristics are enabling a better understanding of the earth’s environment, for such activities as vegetation analysis, forest inventories, land subsidence, and urban analysis. In addition, airborne systems for remote piloted systems and ground-based systems are available. This Special Issue presents six quality scientific papers on typical applications of SAR technologies. They include methods for the determination of above ground biomass (AGB), crop mapping using data from an advanced X-band system developed in Japan, analysis of natural and human-induced slow-rate ground deformations in the region of Campania, in Italy, the location of landslides caused by natural phenomena based on SAR images derived from the Japanese high-resolution Advanced Land Observing Satellite-2 (ALOS-2), and monitoring the size of refugee camps and their environmental impacts caused by the displacement of people from Myanmar to the Cox’s Bazar District, around Kutupalong, in Bangladesh. The paper concludes with some comments on the future directions of developments in SAR systems.

This paper presents the analysis and a methodology for monitoring asparagus crops from remote sensing observations in a tropical region, where the local climatological conditions allow farmers to grow two production cycles per year. We used the freely available dual-polarisation GRD data provided by the Sentinel-1 satellite, temperature from a ground station and ground truth from January to August of 2019 to perform the analysis. We showed how particularly the VH polarisation can be used for monitoring the canopy formation, density and the growth rate, revealing connections with temperature. We also present a multi-output machine learning regression algorithm trained on a rich spatio-temporal dataset in which each output estimates the number of asparagus stems that are present in each of the pre-defined crop phenological stages. We tested several scenarios that evaluated the importance of each input data source and feature, with results that showed that the methodology was able to retrieve the number of asparagus stems in each crop stage when using information about starting date and temperature as predictors with coefficients of determination ( R 2 ) between 0.84 and 0.86 and root mean squared error (RMSE) between 2.9 and 2.7. For the multitemporal SAR scenario, results showed a maximum R 2 of 0.87 when using up to 5 images as input and an RMSE that maintains approximately the same values as the number of images increased. This suggests that for the conditions evaluated in this paper, the use of multitemporal SAR data only improved mildly the retrieval when the season start date and accumulated temperature are used to complement the backscatter.

The natural environment is essential for human survival and development since it provides water resources, land resources, biological resources and climate resources etc. As a developing country, China has witnessed a significant change in the natural environment in recent decades; and therefore, monitoring and mastering the status of the environment is of great significance. Due to the characteristics of large-scale and dynamic observation, remote sensing technology has been an indispensable approach for environmental monitoring. This paper reviews the satellite resources, institutions and policies for environmental monitoring in China, and the advances in research and application of remote sensing from five aspects: ecological index retrieval, environmental monitoring in protected areas, rural areas, urban areas and mining areas. The remote sensing models and methods for various types of environmental monitoring, and the specific applications in China are comprehensively summarized. This paper also points out major challenges existing at the current stage: satellite sensor problems, integrated use challenges of datasets, uncertainty in the retrieval process of ecological variables, scaling effect problems, a low degree of automation, the weak ability of forecasting and comprehensive analysis, and a lack of computational power for massive datasets. Finally, the development trend and future directions are put forward to direct the research and application of environmental monitoring and protection in the new era.

The urban functional zone, as a special fundamental unit of the city, helps to understand the complex interaction between human space activities and environmental changes. Based on the recognition of physical and social semantics of buildings, combining remote sensing data and social sensing data is an effective way to quickly and accurately comprehend urban functional zone patterns. From the object level, this paper proposes a novel object-wise recognition strategy based on very high spatial resolution images (VHSRI) and social sensing data. First, buildings are extracted according to the physical semantics of objects; second, remote sensing and point of interest (POI) data are combined to comprehend the spatial distribution and functional semantics in the social function context; finally, urban functional zones are recognized and determined by building with physical and social functional semantics. When it comes to building geometrical information extraction, this paper, given the importance of building boundary information, introduces the deeper edge feature map (DEFM) into the segmentation and classification, and improves the result of building boundary recognition. Given the difficulty in understanding deeper semantics and spatial information and the limitation of traditional convolutional neural network (CNN) models in feature extraction, we propose the Deeper-Feature Convolutional Neural Network (DFCNN), which is able to extract more and deeper features for building semantic recognition. Experimental results conducted on a Google Earth image of Shenzhen City show that the proposed method and model are able to effectively, quickly, and accurately recognize urban functional zones by combining building physical semantics and social functional semantics, and are able to ensure the accuracy of urban functional zone recognition.