Remote Sens., Volume 15, Issue 18 (September-2 2023) – 282 articles

Convolutional neural networks (CNNs) have shown outstanding feature extraction capability and become a hot topic in the field of hyperspectral image (HSI) classification. However, most of the prior works usually focus on designing deeper or wider network architectures to extract spatial and spectral features, which give rise to difficulty for optimization and more parameters along with higher computation. Moreover, how to learn spatial and spectral information more effectively is still being researched. To tackle the aforementioned problems, a decompressed spectral-spatial multiscale semantic feature network (DSMSFNet) for HSI classification is proposed. This model is composed of a decompressed spectral-spatial feature extraction module (DSFEM) and a multiscale semantic feature extraction module (MSFEM). The former is devised to extract more discriminative and representative global decompressed spectral-spatial features in a lightweight extraction manner, while the latter is constructed to expand the range of available receptive fields and generate clean multiscale semantic features at a granular level to further enhance the classification performance. Compared with progressive classification approaches, abundant experimental results on three benchmark datasets prove the superiority of our developed DSMSFNet model. Full article

The National Key Ecological Function Zones (NKEFZ) serve as crucial ecological security barriers in China, playing a vital role in enhancing ecosystem services. This study employed the theoretical framework of ecological benefits assessment in major ecological engineering projects. The primary focus was on the ecosystem macrostructure, ecosystem quality, and key ecosystem services, enabling quantitative analysis of the spatiotemporal changes in the ecosystem status of the NKEFZ from 2000 to 2019. To achieve this, remote sensing data, meteorological data, and model simulations were employed to investigate five indicators, including land use types, vegetation coverage, net primary productivity of vegetation, soil conservation services, water conservation services, and windbreak and sand fixation services. The analysis incorporated the Theil–Sen Median method to construct an evaluation system for assessing the restoration status of ecosystems, effectively integrating ecosystem quality and ecosystem services indicators. The research findings indicated that land use changes in NKEFZ were primarily characterized by the expansion of unused land and the in of grassland. The overall ecosystem quality of these zones improved, showing a stable and increasing trend. However, there were disparities in the changes related to ecosystem services. Water conservation services exhibited a decreasing trend, while soil conservation and windbreak and sand fixation services showed a steady improvement. The ecosystem of the NKEFZ, in general, displayed a stable and recovering trend. However, significant spatial heterogeneity existed, particularly in the southern region of the Qinghai–Tibet Plateau and at the border areas between western Sichuan and northern Yunnan, where some areas still experienced deteriorating ecosystem conditions. Compared to other functional zones, the trend in the ecosystem of the NKEFZ might not have been the most favorable. Nonetheless, this could be attributed to the fact that most of these areas were situated in environmentally fragile regions, and conservation measures may not have been as effective as in other functional zones. These findings highlighted the considerable challenges ahead in the construction and preservation of the NKEFZ. In future development, the NKEFZ should leverage their unique natural resources to explore distinctive ecological advantages and promote the development of eco-friendly economic industries, such as ecological industry, ecological agriculture, and eco-tourism, transitioning from being reliant on external support to self-sustainability. Full article

Strawberry anthracnose, caused by Colletotrichum spp., is a major disease that causes tremendous damage to cultivated strawberry plants (Fragaria × ananassa Duch.). Examining and distinguishing plants potentially carrying the pathogen is one of the most effective ways to prevent and control strawberry anthracnose disease. Herein, we used this method on Colletotrichum gloeosporioides at the crown site on indoor strawberry plants and established a classification and distinguishing model based on measurement of the spectral and textural characteristics of the disease-free zone near the disease center. The results, based on the successive projection algorithm (SPA), competitive adaptive reweighted sampling (CARS), and interval random frog (IRF), extracted 5, 14, and 11 characteristic wavelengths, respectively. The SPA extracted fewer effective characteristic wavelengths, while IRF covered more information. A total of 12 dimensional texture features (TFs) were extracted from the first three minimum noise fraction (MNF) images using a grayscale co-occurrence matrix (GLCM). The combined dataset modeling of spectral and TFs performed better than single-feature modeling. The accuracy rates of the IRF + TF + BP model test set for healthy, asymptomatic, and symptomatic samples were 99.1%, 93.5%, and 94.5%, the recall rates were 100%, 94%, and 93%, and the F1 scores were 0.9955, 0.9375, and 0.9374, respectively. The total modeling time was 10.9 s, meaning that this model demonstrated the best comprehensive performance of all the constructed models. The model lays a technical foundation for the early, non-destructive detection of strawberry anthracnose. Full article

The OpenStreetMap (OSM) project is an open-source, community-based, user-generated street map/data service. It is the most popular project within the state of the art for crowdsourcing. Although geometrical features and tags of annotations in OSM are usually precise (particularly in metropolitan areas), there are instances where volunteer mapping is inaccurate. Despite the appeal of using OSM semantic information with remote sensing images, to train deep learning models, the crowdsourced data quality is inconsistent. High-resolution remote sensing image segmentation is a mature application in many fields, such as urban planning, updated mapping, city sensing, and others. Typically, supervised methods trained with annotated data may learn to anticipate the object location, but misclassification may occur due to noise in training data. This article combines Very High Resolution (VHR) remote sensing data with computer vision methods to deal with noisy OSM. This work deals with OSM misalignment ambiguity (positional inaccuracy) concerning satellite imagery and uses a Convolutional Neural Network (CNN) approach to detect missing buildings in OSM. We propose a translating method to align the OSM vector data with the satellite data. This strategy increases the correlation between the imagery and the building vector data to reduce the noise in OSM data. A series of experiments demonstrate that our approach plays a significant role in (1) resolving the misalignment issue, (2) instance-semantic segmentation of buildings with missing building information in OSM (never labeled or constructed in between image acquisitions), and (3) change detection mapping. The good results of precision (0.96) and recall (0.96) demonstrate the viability of high-resolution satellite imagery and OSM for building detection/change detection using a deep learning approach. Full article

Desert oases are vital for maintaining the ecological balance in arid regions’ inland river basins. However, fine-grained assessments of water stress in desert oasis ecosystems are limited. In our study, we aimed to evaluate the water stress in desert oasis ecosystems in the middle reaches of the Keriya River Basin, with a specific focus on their ecological functions and optimizing water resource management. We hypothesized that evapotranspiration has significant effects on ecological water consumption. First, we estimated the actual evapotranspiration (ET) and potential evapotranspiration (PET) based on the SEBS (surface energy balance system) model and remote sensing downscaling model. Then, the ecological water requirement (EWR) and ecological water stress (EWS) index were constructed to evaluate the ecological water resource utilization. Finally, we explored the influencing factors and proposed coping strategies. It was found that regions with higher ET values were mainly concentrated along the Keriya River and its adjacent farmland areas, while the lower values were observed in bare land or grassland areas. The total EWR exhibited the sequence of grassland > cropland > forest, while the EWR per unit area followed the opposite order. The grassland’s EWS showed a distinct seasonal response, with severe, moderate, and mild water shortages and water plenitude corresponding to spring, summer, autumn, and winter, respectively. In contrast, the land use types with the lowest EWS were water areas that remained in a state of water plentitude grade (0.08–0.20) throughout the year. Temperature and vegetation index were identified as the primary influencing factors. Overall, this study provides a reliable method for evaluating the EWR and EWS values of basin scale vegetation, which can serve as a scientific basis for formulating water resource management and regulation policies in the region. Full article

In recent years, there has been a growing interest in remote sensing image–text cross-modal retrieval due to the rapid development of space information technology and the significant increase in the volume of remote sensing image data. Remote sensing images have unique characteristics that make the cross-modal retrieval task challenging. Firstly, the semantics of remote sensing images are fine-grained, meaning they can be divided into multiple basic units of semantic expression. Different combinations of basic units of semantic expression can generate diverse text descriptions. Additionally, these images exhibit variations in resolution, color, and perspective. To address these challenges, this paper proposes a multi-task guided fusion encoder (MTGFE) based on the multimodal fusion encoding method, the progressiveness of which has been proved in the cross-modal retrieval of natural images. By jointly training the model with three tasks: image–text matching (ITM), masked language modeling (MLM), and the newly introduced multi-view joint representations contrast (MVJRC), we enhance its capability to capture fine-grained correlations between remote sensing images and texts. Specifically, the MVJRC task is designed to improve the model’s consistency in joint representation expression and fine-grained correlation, particularly for remote sensing images with significant differences in resolution, color, and angle. Furthermore, to address the computational complexity associated with large-scale fusion models and improve retrieval efficiency, this paper proposes a retrieval filtering method, which achieves higher retrieval efficiency while minimizing accuracy loss. Extensive experiments were conducted on four public datasets to evaluate the proposed method, and the results validate its effectiveness. Full article

Forests are essential for sustaining ecosystems, regulating the climate, and providing economic benefits to human society. However, activities such as commercial practices, fuelwood collection, and land use changes have resulted in severe forest degradation and deforestation. Timor-Leste, a small island nation, faces environmental sustainability challenges due to land use changes, limited infrastructure, and agricultural practices. This study proposes a simplified and highly accessible approach to assess deforestation (SHAD) nationally using limited human and non-human resources such as experts, software, and hardware facilities. To assess deforestation in developing countries, we utilize open-source software (Dryad), employ the U-Net deep learning algorithm, and utilize open-source data generated from the Google Earth Engine platform to construct a time-series land cover classification model for Timor-Leste. In addition, we utilize the open-source land cover map as label data and satellite imagery as model training inputs, and our model demonstrates satisfactory performance in classifying time-series land cover. Next, we classify the land cover in Timor-Leste for 2016 and 2021, and verified that the forest classification achieved high accuracy ranging from 0.79 to 0.89. Thereafter, we produced a deforestation map by comparing the two land cover maps. The estimated deforestation rate was 1.9% annually with a primary concentration in the northwestern municipalities of Timor-Leste with dense population and human activities. This study demonstrates the potential of the SHAD approach to assess deforestation nationwide, particularly in countries with limited scientific experts and infrastructure. We anticipate that our study will support the development of management strategies for ecosystem sustainability, climate adaptation, and the conservation of economic benefits in various fields. Full article

This paper presents a novel version control system for point clouds, which allows the complete editing history of a dataset to be stored. For each intermediate version, this system stores only the information that changes with respect to the previous one, which is compressed using a new strategy based on several algorithms. It allows undo/redo functionality in memory, which serves to optimize the operation of the version control system. It can also manage changes produced from third-party applications, which makes it ideal to be integrated into typical Computer-Aided Design workflows. In addition to automated management of incremental versions of point cloud datasets, the proposed system has a much lower storage footprint than the manual backup approach for most common point cloud workflows, which is essential when working with LiDAR (Light Detection and Ranging) data in the context of spatial big data. Full article

While recent advances in the field of neural rendering have shown impressive 3D reconstruction performance, it is still a challenge to accurately capture the appearance and geometry of a scene by using neural rendering, especially for remote sensing scenes. This is because both rendering methods, i.e., surface rendering and volume rendering, have their own limitations. Furthermore, when neural rendering is applied to remote sensing scenes, the view sparsity and content complexity that characterize these scenes will severely hinder its performance. In this work, we aim to address these challenges and to make neural rendering techniques available for 3D reconstruction in remote sensing environments. To achieve this, we propose a novel 3D surface reconstruction method called UniRender. UniRender offers three improvements in locating an accurate 3D surface by using neural rendering: (1) unifying surface and volume rendering by employing their strengths while discarding their weaknesses, which enables accurate 3D surface position localization in a coarse-to-fine manner; (2) incorporating photometric consistency constraints during rendering, and utilizing the points reconstructed by structure from motion (SFM) or multi-view stereo (MVS), to constrain reconstructed surfaces, which significantly improves the accuracy of 3D reconstruction; (3) improving the sampling strategy by locating sampling points in the foreground regions where the surface needs to be reconstructed, thus obtaining better detail in the reconstruction results. Extensive experiments demonstrate that UniRender can reconstruct high-quality 3D surfaces in various remote sensing scenes. Full article

With growing global concern for food and water insecurity, an efficient method to monitor irrigation projects is essential, especially in the developing world where irrigation performance is often suboptimal. In Nepal, the irrigated area has not been objectively recorded, although their assessment has substantial implications for national policy, project’s annual budgets, and donor funding. Here, we present the application of Landsat images to measure irrigated areas in Nepal for the past 17 years to contribute to the assessment of the irrigation performance. Landsat 5 TM (2006–2011) and Landsat 8 OLI (2013–2022) images were used to develop a machine learning model, which classifies irrigated and non-irrigated areas in the study areas. The random forest classification achieved an overall accuracy of 82.2% and kappa statistics of 0.72. For the class of irrigation areas, the producer’s accuracy and consumer’s accuracy were 79% and 96%, respectively. Our regionally trained machine learning model outperforms the existing global cropland map, highlighting the need for such models for local irrigation project evaluations. We assess irrigation project performance and its drivers by combining long-term changes in satellite-derived irrigated areas with local data related to irrigation performance, such as annual budget, irrigation service fee, crop yield, precipitation, and main canal discharge. Full article

It is crucial to evaluate the expansion of urban entities to implement sustainable urban planning strategies in China. Thus, this study attempted to extract and evaluate the growth of urban entities 270 prefecture cities in mainland China (2000–2020) using a novel approach based on consistent night light images. After the urban entities were extracted, a rationality assessment was carried out to compare the derived urban entities with the LandScan population product, Landsat, and road network results. Additionally, the results were compared with other physical extent products, such as the Moderate Resolution Imaging Spectrometer (MODIS) and urban built-up area products (HE) products. According to the findings, the urban entities were basically consistent with the LandScan, road network, and HE and MODIS products. However, the urban entities more accurately reflected the concentration of human activities than did the impervious extents of the MODIS and HE products. At the prefecture levels, the area of urban entities increased from 8082 km² to 74,417 km² between 2000 and 2020, showing an average growth rate of 10.8% over those twenty years. As a reliable supplementary resource and guide for urban mapping, this research will inform new research on the K-means algorithm and on variations in NTL data brightness threshold dynamics at regional and global scales. Full article

Realizing the high-precision monitoring of wheat stripe rust over a large area is of great significance in ensuring the safety of wheat production. Existing studies have mostly focused on the fusion of multi-source data and the construction of key monitoring features to improve the accuracy of disease monitoring, with less consideration for the regional distribution characteristics of the disease. In this study, based on the occurrence and spatial distribution patterns of wheat stripe rust in the experimental area, we constructed a multi-source monitoring feature set, then utilized geographical detectors for feature selection that integrates the spatial-distribution differences of the disease. The research results show that the optimal monitoring feature set selected by the geographical detectors has a higher monitoring accuracy. Based on the Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Support Vector (SVM) models, the disease monitoring results demonstrate that the monitoring feature set constructed in this study has an overall accuracy in its disease monitoring that is 3.2%, 2.7%, and 4.3% higher, respectively, than that of the ReliefF method, with Kappa coefficient higher by 0.064, 0.044, and 0.087, respectively. Furthermore, the optimal monitoring feature set obtained by the geographical detectors method exhibits a higher stability, and the spatial distribution of wheat stripe rust in the monitoring results generated by the different models demonstrates good consistency. In contrast, the features selected by the ReliefF method exhibit significant spatial-distribution differences in the wheat stripe rust among the different monitoring results, indicating poor stability and consistency. Overall, incorporating information on disease spatial-distribution differences in stripe-rust monitoring can improve the accuracy and stability of disease monitoring, and it can provide data and methodological support for regional stripe-rust detection and accurate preventions. Full article

The ocean surface current influences the roughness of the sea surface, subsequently affecting the scatterometer’s measurement of wind speed. In this study, the effect of surface currents on ASCAT-retrieved winds is investigated based on in-situ observations of both surface winds and currents from 40 open ocean moored buoys in the tropical and mid-latitude oceans. A total of 28,803 data triplets, consisting of buoy-observed wind vectors, current vectors, and ASCAT Level 2 wind vectors, were collected from the dataset spanning over 10 years. It is found that the bias between scatterometer-retrieved wind speed and buoy-observed wind speed is negatively correlated with the ocean surface current speed. The wind speed bias is approximately 0.96 times the magnitude of the downwind surface current. The root-mean-square error between the ASCAT wind speeds and buoy observations is reduced by about 15% if rectification with ocean surface currents is involved. Therefore, it is essential to incorporate surface current information into wind speed calibration, particularly in regions with strong surface currents. Full article

TBD (Track-Before-Detect) algorithms allow the detection and tracking of objects of which the signal is lost in the background noise. The use of convolutional neural networks (ConvNN) allows to obtain more effective algorithms than the previous, because it is possible to take into account the background as well as the spatial and temporal characteristics of the tracked object signal. The article presents solutions for taking into account the motion with variable trajectory and speed through segmental interpolation and rectification of the trajectory, which allows the effective convolutional implementation of the TBD algorithm. The boundary of object detection was determined depending on the number of pixels of the object in relation to the number of pixels of the image stack and signal strength for the simplest neural network, so it is possible to analyse and compare more complex solutions with the proposed reference. Full article

3D reconstruction of urban scenes is an important research topic in remote sensing. Neural Radiance Fields (NeRFs) offer an efficient solution for both structure recovery and novel view synthesis. The realistic 3D urban models generated by NeRFs have potential future applications in simulation for autonomous driving, as well as in Augmented and Virtual Reality (AR/VR) experiences. Previous NeRF methods struggle with large-scale, urban environments. Due to the limited model capability of NeRF, directly applying them to urban environments may result in noticeable artifacts in synthesized images and inferior visual fidelity. To address this challenge, we propose a sparse voxel-based NeRF. First, our approach leverages LiDAR odometry to refine frame-by-frame LiDAR point cloud alignment and derive accurate initial camera pose through joint LiDAR-camera calibration. Second, we partition the space into sparse voxels and perform voxel interpolation based on 3D LiDAR point clouds, and then construct a voxel octree structure to disregard empty voxels during subsequent ray sampling in the NeRF, which can increase the rendering speed. Finally, the depth information provided by the 3D point cloud on each viewpoint image supervises our NeRF model, which is further optimized using a depth consistency loss function and a plane constraint loss function. In the real-world urban scenes, our method significantly reduces the training time to around an hour and enhances reconstruction quality with a PSNR improvement of 1–2 dB, outperforming other state-of-the-art NeRF models. Full article

This work reports an information-based landmarks assisted simultaneous localization and mapping (InfoLa-SLAM) in large-scale scenes using single-line lidar. The solution employed two novel designs. The first design was a keyframe selection method based on Fisher information, which reduced the computational cost of the nonlinear optimization for the back-end of SLAM by selecting a relatively small number of keyframes while ensuring the accuracy of mapping. The Fisher information was acquired from the point cloud registration between the current frame and the previous keyframe. The second design was an efficient global descriptor for place recognition, which was achieved by designing a unique graphical feature ID to effectively match the local map with the global one. The results showed that compared with traditional keyframe selection strategies (e.g., based on time, angle, or distance), the proposed method allowed for a 35.16% reduction in the number of keyframes in a warehouse with an area of about 10,000 m². The relocalization module demonstrated a high probability (96%) of correction even under high levels of measurement noise (0.05 m), while the time consumption for relocalization was below 28 ms. The proposed InfoLa-SLAM was also compared with Cartographer under the same dataset. The results showed that InfoLa-SLAM achieved very similar mapping accuracy to Cartographer but excelled in lightweight performance, achieving a 9.11% reduction in the CPU load and a significant 56.67% decrease in the memory consumption. Full article

The influence of solar activity on the ionosphere, a critical area of investigation due to its relevance to the Sun–Earth relationship, has been extensively examined through various methodologies. The ability of solar events to induce disturbances in both the ionosphere and the geomagnetic field is widely acknowledged. This specific study focused on sporadic incidents resulting from X-class solar flares that occurred between 2021 and 2022. Utilizing a methodology that involved analyzing data at 5Hz intervals using wavelet algorithms, the data from the GNSS stations of the National Autonomous University of Mexico (UNAM) were investigated. The primary emphasis was on deducing the Total Electron Content (TEC) within the ionosphere. Subsequently, this parameter for each satellite during instances of solar flares was analyzed. The approach uncovered disruptions in the ionosphere triggered by solar flares, even in cases where events transpired at the periphery of the solar disk and were of magnitudes smaller than X2. Full article

Object detection in remote sensing images (RSIs) has become crucial in recent years. However, researchers often prioritize detecting small objects, neglecting medium- to large-sized ones. Moreover, detecting objects hidden in shadows is challenging. Additionally, most detectors have extensive parameters, leading to higher hardware costs. To address these issues, this paper proposes a multi-scale and high-precision lightweight object detector named MHLDet. Firstly, we integrated the SimAM attention mechanism into the backbone and constructed a new feature-extraction module called validity-neat feature extract (VNFE). This module captures more feature information while simultaneously reducing the number of parameters. Secondly, we propose an improved spatial pyramid pooling model, named SPPE, to integrate multi-scale feature information better, enhancing the model to detect multi-scale objects. Finally, this paper introduces the convolution aggregation crosslayer (CACL) into the network. This module can reduce the size of the feature map and enhance the ability to fuse context information, thereby obtaining a feature map with more semantic information. We performed evaluation experiments on both the SIMD dataset and the UCAS-AOD dataset. Compared to other methods, our approach achieved the highest detection accuracy. Furthermore, it reduced the number of parameters by 12.7% compared to YOLOv7-Tiny. The experimental results illustrated that our proposed method is more lightweight and exhibits superior detection accuracy compared to other lightweight models. Full article

Hyperspectral sensors mounted on unmanned aerial vehicles (UAV) offer the prospect of high-resolution multi-temporal spectral analysis for a range of remote-sensing applications. However, although accurate onboard navigation sensors track the moment-to-moment pose of the UAV in flight, geometric distortions are introduced into the scanned data sets. Consequently, considerable time-consuming (user/manual) post-processing rectification effort is generally required to retrieve geometrically accurate mosaics of the hyperspectral data cubes. Moreover, due to the line-scan nature of many hyperspectral sensors and their intrinsic inability to exploit structure from motion (SfM), only 2D mosaics are generally created. To address this, we propose a fast, automated and computationally robust georectification and mosaicking technique that generates 3D hyperspectral point clouds. The technique first morphologically and geometrically examines (and, if possible, repairs) poorly constructed individual hyperspectral cubes before aligning these cubes into swaths. The luminance of each individual cube is estimated and normalised, prior to being integrated into a swath of images. The hyperspectral swaths are co-registered to a targeted element of a luminance-normalised orthomosaic obtained using a standard red–green–blue (RGB) camera and SfM. To avoid computationally intensive image processing operations such as 2D convolutions, key elements of the orthomosaic are identified using pixel masks, pixel index manipulation and nearest neighbour searches. Maximally stable extremal regions (MSER) and speeded-up robust feature (SURF) extraction are then combined with maximum likelihood sample consensus (MLESAC) feature matching to generate the best geometric transformation model for each swath. This geometrically transforms and merges individual pushbroom scanlines into a single spatially continuous hyperspectral mosaic; and this georectified 2D hyperspectral mosaic is then converted into a 3D hyperspectral point cloud by aligning the hyperspectral mosaic with the RGB point cloud used to create the orthomosaic obtained using SfM. A high spatial accuracy is demonstrated. Hyperspectral mosaics with a 5 cm spatial resolution were mosaicked with root mean square positional accuracies of 0.42 m. The technique was tested on five scenes comprising two types of landscape. The entire process, which is coded in MATLAB, takes around twenty minutes to process data sets covering around 30 Ha at a 5 cm resolution on a laptop with 32 GB RAM and an Intel^® Core i7-8850H CPU running at 2.60 GHz. Full article

Recently, considerable efforts have been devoted to the estimation of soil properties using optical payloads mounted on drones or satellites. Nevertheless, many studies focus on diverse pretreatments and modeling techniques, while there continues to be a conspicuous absence of research examining the impact of parameters related to optical remote sensing payloads on predictive performance. The main aim of this study is to evaluate how the spectral resolution and signal-to-noise ratio (SNR) of spectrometers affect the precision of predictions for soil organic matter (SOM) content. For this purpose, the initial soil spectral library was partitioned into to two simulated soil spectral libraries, each of which were individually adjusted with respect to the spectral resolutions and SNR levels. To verify the consistency and generality of our results, we employed four multiple regression models to develop multivariate calibration models. Subsequently, in order to determine the minimum spectral resolution and SNR level without significantly affecting the prediction accuracy, we conducted ANOVA tests on the RMSE and ${\mathrm{R}}^2$ obtained from the independent validation dataset. Our results revealed that (i) the factors significantly affecting SOM prediction performance, in descending order of magnitude, were the SNR levels > spectral resolutions > estimation models, (ii) no substantial difference existed in predictive performance when the spectral resolution fell within 100 nm, and (iii) when the SNR levels exceeded 15%, altering them did not notably affect the SOM predictive performance. This study is expected to provide valuable insights for the design of future optical remote sensing payloads aimed at monitoring large-scale SOM dynamics. Full article

For high-precision Global Navigation Satellite Systems (GNSS) positioning based on carrier-phase measurements, knowledge of the GNSS receiver antenna electrical signal reception characteristics, i.e., phase center, is crucial. Numerous studies have led to the understanding of the influence of GNSS receiver antenna phase center corrections (PCCs) on GNSS positioning accuracy and other estimated parameters (e.g., receiver clock estimates, ambiguities, etc.). With the goal of determining the PCC model of GNSS receiver antennas, only a few antenna calibration systems/facilities are in operation or under development worldwide. The International GNSS Service (IGS) publishes type-mean PCC models for almost all geodetic-grade GNSS antennas. However, the type-mean models are not perfect and do not fully reflect the signal reception properties of individual GNSS receiver antennas. Relevant published scientific research has shown that the application of individual PCC models significantly improves the accuracy of GNSS positioning and other estimated parameters. In this article, the new automated GNSS antenna calibration system, recently developed at the Laboratory for Measurements and Measuring Technique (LMMT) of the Faculty of Geodesy of the University of Zagreb in Croatia, is presented. The developed system is an absolute field calibration system based on the utilization of a Mitsubishi MELFA 6-axis industrial robot. During calibration, the robot tilts and rotates the GNSS antenna under test (AUT) around a fixed point within the antenna. The antenna PCC modelling is based on time-differenced double-difference carrier-phase observations. Our preliminary results for the Global Positioning System (GPS) L1 (G01) frequency show a submillimeter repeatability of the estimated PCC model and a submillimeter agreement with the Geo++ GmbH calibration results. Full article

Global greening and its relationship with climate change remain the hot topics in recent years, and are of critical importance for understanding the interactions between the terrestrial ecosystem carbon cycle and the climate system. China, especially north China, has contributed a lot to global greening during the past few decades. As a water-limited ecosystem, human activities, not precipitation amount, were thought as the main contributor to the greening of north China. Considering the importance of precipitation event characteristics (PEC) in the altered precipitation regimes, we integrated long-term normalized difference vegetation index (NDVI) and meteorological datasets to reveal the role of precipitation regimes, especially PECs, on vegetation growth across temperate grasslands in north China. Accompanied with a significantly decreased growing season precipitation (GSP), NDVI increased significantly in the largest area of the temperate grasslands during 1982–2015, i.e., greening. We found that 28.44% of the area was explained by PECs, including more heavy or extreme precipitation events, alleviated extreme drought, and fewer light events, while only 0.92% of the area was associated with GSP. NDVI did not always increase over the 30 years and there was a decrease during 1996–2005. Taking afforestation projects in desertified lands into account, we found that precipitation, mainly PECs, explained more the increase and decline of NDVI during 1982–1995 and 1996–2005, respectively, while an equivalent explanatory power of precipitation and afforestation projects to the increase in NDVI after 2005. Our study indicates a possible higher productivity under future precipitation regime scenario (e.g., fewer but larger precipitation events) or intensive afforestation activity, implying more carbon sequestration or livestock production of temperate steppe in the future. Full article

The inspection and monitoring of structural conditions are crucial for the maintenance of semi-rigid base pavement. To achieve the inverse calculation of material parameters and obtain the mechanical response of asphalt pavement, a method of modulus correction by reducing the error between tested and simulated strains was first developed. The relationship between the temperature at various depths within the pavement structure and atmospheric temperature was effectively demonstrated using a dual sinusoidal regression model. Subsequently, pavement monitoring data illustrated that as loading weight and temperature increased and loading speed decreased, the three-way strain of the asphalt layer increased. Thus, the relationship model between loading conditions and three-way strain was established with a good fitting degree (R² > 0.95). The corrected modulus was obtained by approximating the error between simulated and measured strains. Then, the finite element analysis was performed to calculate key mechanical index values under various working conditions and predict the fatigue life of asphalt and base layers. Finally, ground-penetrating radar (GPR) detection was performed, and the internal pavement condition index was defined for quantitative assessment of structure conditions. The results show that there is a good correlation between the internal pavement condition index (IPCI) and remaining life of pavement structure. Therefore, our works solve the problems of the parameter reliability of pavement structures and quantitative assessment for structural conditions, which could support the performance prediction and maintenance analysis on asphalt pavement with a semi-rigid base. Full article

In response to the challenges of long crossing distances and difficult site selection for linear engineering projects in mountainous areas, this article proposes a multi-scale engineering geological zoning (EGZ) method. This method is based on the linear engineering construction stage and transitions from regional EGZ to EGZ of key sections (areas with poor or worst engineering geological conditions). This method not only ensures the effect of EGZ but also reduces the workload. When carrying out the EGZ of key sections, the assessment ideas of geological disaster hazards were taken into consideration. An improved method for calculating the time probability and magnitude probability of disaster occurrence is proposed. Taking the National Highway 318 Chengdu-Shigatse section as an example, EGZ was carried out. Its results revealed that the Nyingchi section was the key section with poor and worst engineering geological conditions. EGZ of the key section showed that the areas with poor and worst engineering geological conditions were mainly distributed in the curved sections on the northern side of the linear project. The proposed method in this article provides guidance for EGZ for linear engineering projects in mountainous areas. Full article

Poverty is a social issue of global concern. Although socioeconomic indicators can easily reflect poverty status, the coarse statistical scales and poor timeliness have limited their applications. While spatial big data with reasonable timeliness, easy access, and wide coverage can overcome such limitations, the integration of high-resolution nighttime light and spatial big data for assessing relative poverty is still limited. More importantly, few studies have provided poverty assessment results at a grid scale. Therefore, this study takes the Pearl River Delta, where there is a large disparity between the rich and the poor, as an example. We integrated Luojia 1-01, points of interest, and housing prices to construct a big data poverty index (BDPI). To evaluate the performance of the BDPI, we compared this new index with the traditional multidimensional poverty index (MPI), which builds upon socioeconomic indicators. The results show that the impoverished counties identified by the BDPI are highly similar to those identified by the MPI. In addition, both the BDPI and MPI gradually decrease from the center to the fringe of the study area. These two methods indicate that impoverished counties were mainly distributed in ZhaoQing, JiangMen and HuiZhou Cities, while there were also several impoverished parts in rapidly developing cities, such as CongHua and HuaDu Counties in GuangZhou City. The difference between the two poverty assessment results suggests that the MPI can effectively reveal the poverty status in old urban areas with convenient but obsolete infrastructures, whereas the BDPI is suitable for emerging-development areas that are rapidly developing but still lagging behind. Although BDPI and MPI share similar calculation procedures, there are substantial differences in the meaning and suitability of the methodology. Therefore, in areas lacking accurate socioeconomic statistics, the BDPI can effectively replace the MPI to achieve timely and fine-scale poverty assessment. Our proposed method could provide a reliable reference for formulating targeted poverty-alleviation policies. Full article

Adverse weather conditions such as haze and snowfall can degrade the quality of captured images and affect performance of drone detection. Therefore, it is challenging to locate and identify targets in adverse weather scenarios. In this paper, a novel model called Object Detection in a Foggy Condition with YOLO (ODFC-YOLO) is proposed, which performs image dehazing and object detection jointly by multi-task learning approach. Our model consists of a detection subnet and a dehazing subnet, which can be trained end-to-end to optimize both tasks. Specifically, we propose a Cross-Stage Partial Fusion Decoder (CSP-Decoder) in the dehazing subnet to recover clean features of encoder from complex weather conditions, thereby reducing the feature discrepancy between hazy and clean images, thus enhancing the feature consistency between different tasks. Additionally, to increase the feature modeling and representation capabilities of our network, we also propose an efficient Global Context Enhanced Extraction (GCEE) module to extract beneficial information from blurred images by constructing global feature context long-range dependencies. Furthermore, we propose a Correlation-Aware Aggregated Loss (CAALoss) to average noise patterns and tune gradient magnitudes across different tasks, accordingly implicitly enhancing data diversity and alleviating representation bias. Finally, we verify the advantages of our proposed model on both synthetic and real-world foggy datasets, and our ODFC-YOLO achieves the highest mAP on all datasets while achieving 36 FPS real-time detection speed. Full article

Tracked robots equipped with flippers and LiDAR sensors have been widely used in urban search and rescue. Achieving autonomous flipper control is important in enhancing the intelligent operation of tracked robots within complex urban rescuing environments. While existing methods mainly rely on the heavy work of manual modeling, this paper proposes a novel Deep Reinforcement Learning (DRL) approach named ICM-D3QN for autonomous flipper control in complex urban rescuing terrains. Specifically, ICM-D3QN comprises three modules: a feature extraction and fusion module for extracting and integrating robot and environment state features, a curiosity module for enhancing the efficiency of flipper action exploration, and a deep Q-Learning control module for learning robot-control policy. In addition, a specific reward function is designed, considering both safety and passing smoothness. Furthermore, simulation environments are constructed using the Pymunk and Gazebo physics engine for training and testing. The learned policy is then directly transferred to our self-designed tracked robot in a real-world environment for quantitative analysis. The consistently high performance of the proposed approach validates its superiority over hand-crafted control models and state-of-the-art DRL strategies for crossing complex terrains. Full article

Climate change has significantly influenced water resource patterns in arid regions. Applying effective water-saving measures to improve irrigation efficiency and evaluate their future water-saving capabilities is crucial for ensuring the sustainable development of irrigation agriculture. Based on the daily meteorological data from 15 global climate models (GCMs) in the sixth phase of the Coupled Model Intercomparison Project (CMIP6), this study used the AquaCrop model to perform high-resolution (0.1° × 0.1°) grid simulations of cotton yields and irrigation requirements. The study also investigated the ability of film-mulched drip irrigation (FMDI) to improve future irrigation efficiency under two shared socio-economic pathways (SSP245 and SSP585) in the Tarim River Basin (TRB), Central Asia, from 2025 to 2100. The results showed that the cotton yield and irrigation water productivity (WP_I) in the TRB exhibited an upward trend of 13.82 kg/ha/decade (80.68 kg/ha/decade) and 0.015 kg/m³/decade (0.068 kg/m³/decade), respectively, during the study period. The cotton yield and WP_I were higher in the northern, northwestern plains, and northeastern intermountain basin areas, where they reach over 4000 kg/ha and 0.8 kg/m³/decade. However, the cotton yield and WP_I were lower in the southwestern part of the study area. Therefore, large-scale cotton production was not recommended there. Furthermore, compared to flood irrigation, the use of FMDI can, on average, improve the WP_I by approx. 25% and reduce irrigation water requirements by more than 550 m³/ha. Therefore, using FMDI can save a substantial amount of irrigation water in cotton production, which is beneficial for improving irrigation efficiency and ensuring the future stable production of cotton in the TRB. The research results provide a scientific reference for the efficient utilization and management of water resources for cotton production in the TRB and in similar arid regions elsewhere in the world. Full article

Deep learning has achieved significant success in various synthetic aperture radar (SAR) imagery interpretation tasks. However, automatic aircraft detection is still challenging due to the high labeling cost and limited data quantity. To address this issue, we propose a multi-stage domain adaptation training framework to efficiently transfer the knowledge from optical imagery and boost SAR aircraft detection performance. To overcome the significant domain discrepancy between optical and SAR images, the training process can be divided into three stages: image translation, domain adaptive pretraining, and domain adaptive finetuning. First, CycleGAN is used to translate optical images into SAR-style images and reduce global-level image divergence. Next, we propose multilayer feature alignment to further reduce the local-level feature distribution distance. By applying domain adversarial learning in both the pretrain and finetune stages, the detector can learn to extract domain-invariant features that are beneficial to the learning of generic aircraft characteristics. To evaluate the proposed method, extensive experiments were conducted on a self-built SAR aircraft detection dataset. The results indicate that by using the proposed training framework, the average precision of Faster RCNN gained an increase of 2.4, and that of YOLOv3 was improved by 2.6, which outperformed other domain adaptation methods. By reducing the domain discrepancy between optical and SAR in three progressive stages, the proposed method can effectively mitigate the domain shift, thereby enhancing the efficiency of knowledge transfer. It greatly improves the detection performance of aircraft and offers an effective approach to address the limited training data problem of SAR aircraft detection. Full article

Investigating the spatiotemporal variation characteristics of aerosol optical depth (AOD) and its driving factors is essential for assessing atmospheric environmental quality and alleviating air pollution. Based on a 22-year high-resolution AOD dataset, the spatiotemporal variations of AOD in mainland China and ten national urban agglomerations were explored based on the Mann–Kendall trend test and Theil–Sen median method. Random forest (RF) and multiscale geographically weighted regression (MGWR) were combined to identify the main driving factors of AOD in urban agglomerations and to reveal the spatial heterogeneity of influencing factors. The results showed that areas with high annual average AOD concentrations were mainly concentrated in the Chengdu–Chongqing, Central Plains, Shandong Peninsula, and Middle Yangtze River urban agglomerations. Southern Beijing–Tianjin–Hebei and its surrounding areas revealed the highest AOD pollution during summer, whereas the worst pollution during the remaining three seasons occurred in the Chengdu–Chongqing urban agglomeration. Temporally, except for the Ha-Chang and Mid-Southern Liaoning urban agglomerations, where the average annual AOD increased, the other urban agglomerations showed a decreasing trend. Among them, the Central Plains, Middle Yangtze River, Guanzhong Plain, and Yangtze River Delta urban agglomerations all exhibited a decline greater than 20%. According to the spatial trends, most urban agglomerations encompassed much larger areas of decreasing AOD values than areas of increasing AOD values, indicating that the air quality in most areas has recently improved. RF analysis revealed that PM_2.5 was the dominant factor in most urban clusters, followed by meteorological factors. MGWR results show that the influencing factors have different spatial scale effects on AOD in urban agglomerations. The socioeconomic factors and PM_2.5 showed strong spatial non-stationarity with regard to the spatial distribution of AOD. This study can provide a comprehensive understanding of AOD differences among urban agglomerations, and it has important theoretical and practical implications for improving the ecological environment and promoting sustainable development. Full article