Interferometric synthetic aperture radar (InSAR) has developed rapidly over the past years and is considered as an important method for surface deformation monitoring, benefiting from growing data quantities and improving data quality. However, the handing of SAR big data poses significant challenges for related algorithms and pipeline, particularly in large-scale SAR data processing. In addition, InSAR algorithms are highly complex, and their task dependencies are intricate. There is a lack of efficient optimization models and task scheduling for InSAR pipeline. In this paper, we design parallel time-series InSAR processing models based on multi-thread technology for high efficiency in processing InSAR big data. These models concentrate on parallelizing critical algorithms that have high complexity, with a focus on deconstructing two computationally intensive algorithms through loop unrolling. Our parallel models have shown a significant improvement of 10–20 times in performance. We have also developed a parallel optimization tool, Simultaneous Task Automatic Runtime (STAR), which utilizes a data flow optimization strategy with thread pool technology to address the problem of low CPU utilization resulting from multiple modules and task dependencies in the InSAR processing pipeline. STAR provides a data-driven pipeline and enables concurrent execution of multiple tasks, with greater flexibility to keep the CPU busy and further improve CPU utilization through predetermined task flow. Additionally, a supercomputing-based system has been constructed for processing massive InSAR scientific big data and providing technical support for nationwide surface deformation measurement, in accordance with the framework of time series InSAR data processing. Using this system, we processed InSAR data with the volumes of 500 TB and 700 TB in 5 and 7 days, respectively. Finally we generated two maps of land surface deformation all over China. Full article

Space-Air-GroundIntegrated Network (SAGIN) has been becoming a promising future network construction to enable the integration of terrestrial communications, aerial networks and satellite systems, for achieving high data rate wireless access and seamless coverage. Focusing on the space-to-air propagation, which is requiring transmitted signal of large Doppler shift resilience in dynamic circumstances, the proposed signal as employing I/Q modulation to accommodate frequency-hopping binary offset carrier (FH-BOC) signal and orthogonal frequency division multiplexing (OFDM) signal, and to exploit respective benefits. Finally, numeric results are provided to demonstrate performance superiority on Bit Error Rate (BER) and signal tracking stability. In conclusion, our designed signal requires about 8 dB less energy per bit at the desired BER level than normally compensated OFDM signal. Full article

Mapping is a fundamental application of remote sensing images, and the accurate evaluation of remote sensing image information extraction using artificial intelligence is critical. However, the existing evaluation method, based on Intersection over Union (IoU), is limited in evaluating the extracted information’s boundary accuracy. It is insufficient for determining mapping accuracy. Furthermore, traditional remote sensing mapping methods struggle to match the inflection points encountered in artificial intelligence contour extraction. In order to address these issues, we propose the mean inflection point distance (MPD) as a new segmentation evaluation method. MPD can accurately calculate error values and solve the problem of multiple inflection points, which traditional remote sensing mapping cannot match. We tested three algorithms on the Vaihingen dataset: Mask R-CNN, Swin Transformer, and PointRend. The results show that MPD is highly sensitive to mapping accuracy, can calculate error values accurately, and is applicable for different scales of mapping accuracy while maintaining high visual consistency. This study helps to assess the accuracy of automatic mapping using remote sensing artificial intelligence. Full article

The accurate mapping of soil organic carbon (SOC) distribution is important for carbon sequestration and land management strategies, contributing to mitigating climate change and ensuring agricultural productivity. The Heihe River Basin in China is an important region that has immense potential for SOC storage. Phenological variables are effective indicators of vegetation growth, and hence are closely related to SOC. However, few studies have incorporated phenological variables in SOC prediction, especially in alpine areas such as the Heihe River Basin. This study used random forest (RF) and extreme gradient boosting (XGBoost) to study the effects of phenological variables (e.g., Greenup, Dormancy, etc.) obtained from MODIS (i.e., Moderate Resolution Imaging Spectroradiometer) product (MCD12Q2) on SOC content prediction in the middle and upper reaches of Heihe River Basin. The current study also identified the dominating variables in SOC prediction and compared model performance using a cross validation procedure. The results indicate that: (1) when phenological variables were considered, the ${\mathrm{R}}^2$ (coefficient of determination) of RF and XGBoost were 0.68 and 0.56, respectively, and RF consistently outperforms XGBoost in various cross validation experiments; (2) the environmental variables MAT, MAP, DEM and NDVI play the most important roles in SOC prediction; (3) the phenological variables can account for 32–39% of the spatial variability of SOC in both the RF and XGBoost models, and hence were the most important factor among the five categories of predictive variables. This study proved that the introduction of phenological variables can significantly improve the performance of SOC prediction. They should be used as indispensable variables for accurately modeling SOC in related studies. Full article

Electron density measured at high latitudes by the Swarm satellites was compared with measurements by the incoherent scatter radars at Resolute Bay and Poker Flat. Overall, the ratio of Swarm-based electron density to that measured by the radars was about 0.5–0.6. Smaller ratios were observed at larger electron densities, usually during the daytime. At low electron densities less than 3 × 10¹⁰ m⁻³, the ratios were typically above 1, indicating an overestimation effect. The overestimation effect was stronger at night and for Swarm B. It was more evident at lower solar activity when the electron densities in the topside ionosphere were lower. Full article

The surface-to-borehole transient electromagnetic (SBTEM) method can provide images at higher resolution for deep earth because its receivers are close to targets. However, as usually the boreholes distribute sparsely, the limited EM data can result in an “equivalent trap” in SBTEM inversions, i.e., the data are well-fitted, but the model is not properly recovered. To overcome this non-unique problem, we propose a dual-mesh three-dimensional (3D) SBTEM inversion scheme. We first use a coarse mesh to obtain a rough resistivity distribution near the borehole, and then we map the coarse mesh attribute into a fine one and capture details from the fine mesh inversion. We test our method on both synthetic data and survey data acquired in Daye, Hubei Province, China. Numerical experiments show that our dual-mesh inversion strategy can better recover the location and resistivity of targets. Full article

Inthis study, remote sensing measurements were utilized to examine the characteristics of storm surges and sea surface cooling in Chinese coastal waters caused by typhoons. Altimetric data from satellite altimeters were used to determine the magnitude, cross-shelf decaying scale, and propagating speed of storm surges from typhoons. The results were in agreement with estimates obtained from a theoretical model and tide gauge data, showing that the two storm surges propagated as continental shelf waves along the southeastern coast of China. The sea surface cooling, driven by Typhoons 1319Usagi and 1323Fitow, was analyzed using the remote sensing sea surface temperature product, named the global 1 km sea surface temperature (G1SST) dataset, revealing a considerable decrease in the temperature, with the largest decrease reaching 4.5 °C after the passage of 1319Usagi, in line with buoy estimates of 4.6 °C. It was found that 1323Fitow and 1324Danas jointly impacted the southeastern coast of China, resulting in a significant temperature drop of 4.0 °C. Our study shows that incorporating remotely sensed measurements into the study of oceanic responses to typhoons has significant benefits and complements the traditional tide gauge network and buoy data. Full article

The continuous acquisition of spatial distribution information for offshore hydrocarbon exploitation (OHE) targets is crucial for the research of marine carbon emission activities. The methodological framework based on time-series night light remote sensing images with a feature increment strategy coupled with machine learning models has become one of the most novel techniques for OHE target extraction in recent years. Its performance is mainly influenced by machine learning models, target features, and regional differences. However, there is still a lack of internal comparative studies on the different influencing factors in this framework. Therefore, based on this framework, we selected four different typical experimental regions within the hydrocarbon basins in the South China Sea to validate the extraction performance of six machine learning models (the classification and regression tree (CART), random forest (RF), artificial neural networks (ANN), support vector machine (SVM), Mahalanobis distance (MaD), and maximum likelihood classification (MLC)) using time-series VIIRS night light remote sensing images. On this basis, the influence of the regional differences and the importance of the multi-features were evaluated and analyzed. The results showed that (1) the RF model performed the best, with an average accuracy of 90.74%, which was much higher than the ANN, CART, SVM, MLC, and MaD. (2) The OHE targets with a lower light radiant intensity as well as a closer spatial location were the main subjects of the omission extraction, while the incorrect extractions were mostly caused by the intensive ship activities. (3) The coefficient of variation was the most important feature that affected the accuracy of the OHE target extraction, with a contribution rate of 26%. This was different from the commonly believed frequency feature in the existing research. In the context of global warming, this study can provide a valuable information reference for studies on OHE target extraction, carbon emission activity monitoring, and carbon emission dynamic assessment. Full article

In non-terrestrial networks, where low Earth orbit satellites and user equipment move relative to each other, line-of-sight tracking and adapting to channel state variations due to endpoint movements are a major challenge. Therefore, continuous line-of-sight estimation and channel impairment compensation are crucial for user equipment to access a satellite and maintain connectivity. In this paper, we propose a framework based on actor-critic reinforcement learning for traffic scheduling in non-terrestrial networks scenario where the channel state is non-stationary due to the variability of the line of sight, which depends on the current satellite elevation. We deploy the framework as an agent in a multipath routing scheme where the user equipment can access more than one satellite simultaneously to improve link reliability and throughput. We investigate how the agent schedules traffic in multiple satellite links by adopting policies that are evaluated by an actor-critic reinforcement learning approach. The agent continuously trains its model based on variations in satellite elevation angles, handovers, and relative line-of-sight probabilities. We compare the agent’s retraining time with the satellite visibility intervals to investigate the effectiveness of the agent’s learning rate. We carry out performance analysis while considering the dense urban area of Paris, where high-rise buildings significantly affect the line of sight. The simulation results show how the learning agent selects the scheduling policy when it is connected to a pair of satellites. The results also show that the retraining time of the learning agent is up to $0.1times$ the satellite visibility time at given elevations, which guarantees efficient use of satellite visibility. Full article

Heatwaves are now considered one of the main stressors of global warming. As a result of anthropogenic warming, atmospheric and oceanic heatwaves have increased in frequency, intensity and duration in recent decades. These extreme events have recently become a major concern in climate research due to their economic and environmental impacts on ecosystems. In this study, we investigated the co-occurrence and relationship between atmospheric and marine heatwaves (AHW/MHW) in the Eastern Mediterranean (EMED) over the last four decades (1982–2021). Furthermore, the spatio-temporal variability and trends of sea surface temperature (SST), near-surface air temperature (SAT), AHW and MHW characteristics (frequency and duration) were examined. For these objectives, we used daily gridded high-resolution satellite SST data (0.05° × 0.05°) and the fifth generation European Centre for Medium-Range Weather Forecasts (ECMWF-ERA5) atmospheric reanalysis SAT and wind components (0.25° × 0.25°). The results showed an average warming trend of about 0.38 ± 0.08 °C/decade and 0.43 ± 0.05 °C/decade for SAT and SST, respectively. A high statistically significant (p < 0.05) correlation (R = 0.90) was found between AHW and MHW frequency. Our results showed that more than half of the MHWs in the EMED co-occurred with AHWs throughout the study period. The most intense summer MHW in 2021, which co-occurred with AHW, was associated with higher positive anomalies of SAT and SST, and a decrease in the wind speed anomaly. Full article

Updating vector road maps from current remote-sensing images provides fundamental data for applications, such as smart transportation and autonomous driving. Updating historical road vector maps involves verifying unchanged roads, extracting newly built roads, and removing disappeared roads. Prior work extracted roads from a current remote-sensing image to build a new road vector map, yielding inaccurate results and redundant processing procedures. In this paper, we argue that changes in roads are closely related to changes in road intersections. Hence, a novel changed road-intersection-guided vector road map updating framework (VecRoadUpd) is proposed to update road vector maps with high efficiency and accuracy. Road-intersection changes include the detection of newly built or disappeared road junctions and the discovery of road branch changes at each road junction. A CNN-based intersection-detection network (CINet) is adopted to extract road intersections from a current image and an old road vector map to discover newly built or disappeared road junctions. A road branch detection network (RoadBranchNet) is used to detect the direction of road branches for each road junction to find road branch changes. Based on the discovery of direction-changed road branches, the VecRoadUpd framework extracts newly built roads and removes disappeared roads through directed road tracing, thus, updating the whole road vector map. Extensive experiments conducted on the public MUNO21 dataset demonstrate that the proposed VecRoadUpd framework exceeds the comparative methods by 11.01% in pixel-level Qual-improvement and 13.85% in graph-level F1-score. Full article

Accurate and reliable perception systems are essential for autonomous driving and robotics. To achieve this, 3D object detection with multi-sensors is necessary. Existing 3D detectors have significantly improved accuracy by adopting a two-stage paradigm that relies solely on LiDAR point clouds for 3D proposal refinement. However, the sparsity of point clouds, particularly for faraway points, makes it difficult for the LiDAR-only refinement module to recognize and locate objects accurately. To address this issue, we propose a novel multi-modality two-stage approach called FusionRCNN. This approach effectively and efficiently fuses point clouds and camera images in the Regions of Interest (RoI). The FusionRCNN adaptively integrates both sparse geometry information from LiDAR and dense texture information from the camera in a unified attention mechanism. Specifically, FusionRCNN first utilizes RoIPooling to obtain an image set with a unified size and gets the point set by sampling raw points within proposals in the RoI extraction step. Then, it leverages an intra-modality self-attention to enhance the domain-specific features, followed by a well-designed cross-attention to fuse the information from two modalities. FusionRCNN is fundamentally plug-and-play and supports different one-stage methods with almost no architectural changes. Extensive experiments on KITTI and Waymo benchmarks demonstrate that our method significantly boosts the performances of popular detectors. Remarkably, FusionRCNN improves the strong SECOND baseline by 6.14% mAP on Waymo and outperforms competing two-stage approaches. Full article

The construction of transport facilities plays a pivotal role in enhancing people’s living standards, stimulating economic growth, maintaining social stability and bolstering national security. During the construction of transport facilities, it is essential to identify the distinctive features of a construction area to anticipate the construction process and evaluate the potential risks associated with the project. This paper presents a multi-objective semantic segmentation algorithm based on an improved U-Net network, which can improve the recognition efficiency of various types of features in the construction zone of transportation facilities. The main contributions of this paper are as follows: A multi-class target sample dataset based on UAV remote sensing and construction areas is established. A new virtual data augmentation method based on semantic segmentation of transport facility construction areas is proposed. A semantic segmentation model for the construction regions based on data augmentation and transfer learning is developed and future research directions are given. The results of the study show that the validity of the virtual data augmentation approach has been verified; the semantic segmentation of the transport facility model can semantically segment a wide range of target features. The highest semantic segmentation accuracy of the feature type was 97.56%. Full article

A typical ultrasonic sensor has a major lobe that extends beyond 45 degrees. Because the wide beam of the ultrasonic sensor’s main lobe, which is used for straightforward distance measurement, has a low angular resolution, conventional methods such as incidence angle and linear angle measurements cannot accurately determine the azimuthal angle. Determining whether one or more objects are present in a single beam is also challenging. In this study, the azimuthal angles of two or more objects placed beneath a single beam are determined by the Doppler frequency shift. An ultrasonic sensor is mounted on an automobile to transmit and receive an ultrasound when the car moves towards stationary objects. The sensor picks up the object’s reflected Doppler shift signal. The azimuth angle of the objects is determined by estimating the received Doppler shift signal using a standard signal processing method. Near-field motion detection systems and autonomous driving heavily rely on the ability to evaluate the azimuthal angle of objects in a vehicle’s surroundings using the Doppler Effect. These are examples of low-cost technology and active safety, which the experimental results support. Based on the results and error estimation, there is an average error of less than 3% between measured and computed values. Full article

Semantic segmentation has played an essential role in remote sensing image interpretation for decades. Although there has been tremendous success in such segmentation with the development of deep learning in the field, several limitations still exist in the current encoder–decoder models. First, the potential interdependencies of the context contained in each layer of the encoder–decoder architecture are not well utilized. Second, multi-scale features are insufficiently used, because the upper-layer and lower-layer features are not directly connected in the decoder part. In order to solve those limitations, a global attention gate (GAG) module is proposed to fully utilize the interdependencies of the context and multi-scale features, and then a global multi-attention UResNeXt (GMAUResNeXt) module is presented for the semantic segmentation of remote sensing images. GMAUResNeXt uses GAG in each layer of the decoder part to generate the global attention gate (for utilizing the context features) and connects each global attention gate with the uppermost layer in the decoder part by using the Hadamard product (for utilizing the multi-scale features). Both qualitative and quantitative experimental results demonstrate that use of GAG in each layer lets the model focus on a certain pattern, which can help improve the effectiveness of semantic segmentation of remote sensing images. Compared with state-of-the-art methods, GMAUResNeXt not only outperforms MDCNN by 0.68% on the Potsdam dataset with respect to the overall accuracy but is also the MANet by 3.19% on the GaoFen image dataset. GMAUResNeXt achieves better performance and more accurate segmentation results than the state-of-the-art models. Full article