Remote Sensing

Considering the great time and labor consumption involved in conventional hazard assessment methods in compiling landslide inventory, the construction of a transferable landslide susceptibility prediction model is crucial. This study employs UAV images as data sources to interpret the typical alpine valley area of Beichuan County. Eight environmental factors including a digital elevation model (DEM) are extracted to establish a pixel-wise dataset, along with interpreted landslide data. Two landslide susceptibility models were built, each with a deep neural network (DNN) and a support vector machine (SVM) as the learner, and the DNN model was determined to have the best pre-training performance (accuracy = 88.6%, precision = 91.3%, recall = 94.8%, specificity = 87.8%, F1-score = 93.0%, and area under curve = 0.943), with higher parameters in comparison to the SVM model (accuracy = 77.1%, precision = 80.9%, recall = 87.8%, specificity = 73.9%, F1-score = 84.2%, and area under curve = 0.878). The susceptibility model of Beichuan County is then transferred to Mao County (which has no available dataset) to realize cross-regional landslide susceptibility prediction. The results suggest that the model predictions accomplish susceptibility zoning principles and that the DNN model can more precisely distinguish between high and very-high susceptibility areas in relation to the SVM model. Full article

Accurate delineation of individual agricultural plots, the foundational units for agriculture-based activities, is crucial for effective government oversight of agricultural productivity and land utilization. To improve the accuracy of plot segmentation in high-resolution remote sensing images, the paper collects GF-2 satellite remote sensing images, uses ArcGIS10.3.1 software to establish datasets, and builds UNet, SegNet, DeeplabV3+, and TransUNet neural network frameworks, respectively, for experimental analysis. Then, the TransUNet network with the best segmentation effects is optimized in both the residual module and the skip connection to further improve its performance for plot segmentation in high-resolution remote sensing images. This article introduces Deformable ConvNets in the residual module to improve the original ResNet50 feature extraction network and combines the convolutional block attention module (CBAM) at the skip connection to calculate and improve the skip connection steps. Experimental results indicate that the optimized remote sensing plot segmentation algorithm based on the TransUNet network achieves an Accuracy of 86.02%, a Recall of 83.32%, an F1-score of 84.67%, and an Intersection over Union (IOU) of 86.90%. Compared to the original TransUNet network for remote sensing land parcel segmentation, whose F1-S is 81.94% and whose IoU is 69.41%, the optimized TransUNet network has significantly improved the performance of remote sensing land parcel segmentation, which verifies the effectiveness and reliability of the plot segmentation algorithm. Full article

Landslide geological disasters, occurring globally, often result in significant loss of life and extensive economic damage. In recent years, the severity of these disasters has increased, likely due to the frequent occurrence of extreme rainstorms associated with global warming. This escalating trend emphasizes the urgent need for a simple and efficient method to identify hidden dangers related to landslide geological disasters. Areas experiencing seasonal heavy rainfall are particularly susceptible to such disasters, posing a serious threat to the lives and property of local residents. In response to the challenging characteristics of landslide geological hazards, such as their strong concealment and the high vegetation coverage in the Liupan Mountain area of the Loess Plateau, this study focuses on the integrated remote sensing identification and research of hidden landslide dangers in Longde County. The methodology combines differential interferometric synthetic aperture radar technology (D-InSAR) and high-resolution optical remote sensing. Surface deformation information of Longde County was obtained by analyzing 85 Sentinel-1A data from 2019 to mid-2020 using Stacking-InSAR, in conjunction with high-resolution optical remote sensing image data from GF-2 in 2019. Furthermore, the study conducted integrated remote sensing identification and field verification of landslide hazards throughout the entire county. This involved interpreting the shape and deformation marks of landslide hazards, identifying the disaster-bearing bodies, and expertly interpreting the environmental factors contributing to the hazards. As a result, 47 suspected landslide hazards and 21 field investigation points were identified, with 16 hazards verified with an accuracy of 76.19%. This outcome directly confirms the applicability and accuracy of the integrated remote sensing identification technology in the study area. The research results presented in this paper provide an effective scientific and theoretical basis for the monitoring and treatment of landslide geological disasters in the future stages. They also play a pivotal role in the prevention of such disasters. Full article

Impact craters are extensively researched geological features that contribute to various aspects of lunar science, such as evaluating the model age, regolith thickness, etc. The method for identifying impact craters has gradually transitioned from manual counting to automated identification. Automatic crater detection based on the digital elevation model (DEM) is commonly used to detect larger craters. However, using only DEM has limitations in discerning smaller craters (diameter < ~1 km). This study utilizes an improved Faster R-CNN algorithm and the Kaguya Terrain Camera (TC) morning map to detect small impact craters in the Chang’e-5 (CE-5) landing site. It uses model fusion to improve the precision of small crater identification. The results show a recall rate of 96.33% and a precision value of 90.19% for craters with diameters exceeding 200 m. The model found a total of 187,101 impact craters in the CE-5 region. The spatial distribution density of impact craters with diameters ranging from 100 m to 200 m is approximately 2.5706/km². For craters with diameters ranging from 200 m to 1 km, the average spatial distribution density is about 0.9016/km². By the unbiased impact crater density of chronological analysis, the model age of the Im2 and Em4 geological units in the CE-5 region is 3.78 Ga and 2.07 Ga, respectively. Full article

Space infrared (IR) target recognition has always been a key issue in the field of space technology. The imaging distance is long, the target is weak, and the feature discrimination is low, making it difficult to distinguish between high-threat targets and decoys. However, most existing methods ignore the fuzziness of multi-dimensional features, and their performance mainly depends on the accuracy of feature extraction, with certain limitations in handling uncertainty and noise. This article proposes a space IR dim target fusion recognition method, which is based on fuzzy comprehensive of spatio-temporal correlation. First, we obtained multi-dimensional IR features of the target through multi-time and multi-spectral detectors, then we established and calculated the adaptive fuzzy-membership function of the features. Next, we applied the entropy weight method to ascertain the objective fusion weights of each feature and computed the spatially fuzzified fusion judgments for the targets. Finally, the fuzzy comprehensive function was used to perform temporal recursive judgment, and the ultimate fusion recognition result was obtained by integrating the results of each temporal recursive judgment. The simulation and comparative experimental results indicate that the proposed method improved the accuracy and robustness of IR dim target recognition in complex environments. Under ideal conditions, it can achieve an accuracy of 88.0% and a recall of 97.5% for the real target. In addition, this article also analyzes the impact of fusion feature combinations, fusion frame counts, different feature extraction errors, and feature database size on recognition performance. The research in this article can enable space-based IR detection systems to make more accurate and stable decisions, promoting defense capabilities and ensuring space security. Full article

Crop residue burning (CRB) is a major source of air pollution in many parts of the world, especially Asia. Policymakers, practitioners, and researchers have invested in measuring the extent and impacts of burning and developing interventions to reduce its occurrence. However, any attempt to measure burning, in terms of its extent, impact, or the effectiveness of interventions to reduce it, requires data on where burning occurs. These data are challenging to collect in the field, both in terms of cost and feasibility, because crop-residue fires are short-lived, each covers only a small area, and evidence of burning disappears once fields are tilled. Remote sensing offers a way to observe fields without the complications of on-the-ground monitoring. However, the same features that make CRB hard to observe on the ground also make remote-sensing-based measurements prone to inaccuracies. The extent of crop burning is generally underestimated due to missing observations, while individual plots are often falsely identified as burned due to the local dominance of the practice, a lack of training data on tilled vs. burned plots, and a weak signal-to-noise ratio that makes it difficult to distinguish between the two states. Here, we summarize the current literature on the measurement of CRB and flag five common pitfalls that hinder analyses of CRB with remotely sensed data: inadequate spatial resolution, inadequate temporal resolution, ill-fitted signals, improper comparison groups, and inadequate accuracy assessment. We take advantage of data from ground-based monitoring of CRB in Punjab, India, to calibrate and validate analyses with PlanetScope and Sentinel-2 imagery and illuminate each of these pitfalls. We provide tools to assist others in planning and conducting remote sensing analyses of CRB and stress the need for rigorous validation. Full article

Maize gross primary productivity (GPP) contributes the most to the global cropland GPP, making it crucial to accurately estimate maize GPP for the global carbon cycle. Previous research validated machine learning (ML) methods using remote sensing and meteorological data to estimate plant GPP, yet they disregard vegetation physiological dynamics driven by phenology. Leaf nitrogen content per unit leaf area (i.e., specific leaf nitrogen (SLN)) greatly affects photosynthesis. Its maximum allowable value correlates with a phenological factor conceptualized as normalized maize phenology (NMP). This study aims to validate SLN and NMP for maize GPP estimation using four ML methods (random forest (RF), support vector machine (SVM), convolutional neutral network (CNN), and extreme learning machine (ELM)). Inputs consist of vegetation index (NDVI), air temperature, solar radiation (SSR), NMP, and SLN. Data from four American maize flux sites (NE1, NE2, and NE3 sites in Nebraska and RO1 site in Minnesota) were gathered. Using data from three NE sites to validate the effect of SLN and MMP shows that the accuracy of four ML methods notably increased after adding SLN and MMP. Among these methods, RF and SVM achieved the best performance of Nash–Sutcliffe efficiency coefficient (NSE) = 0.9703 and 0.9706, root mean square error (RMSE) = 1.5596 and 1.5509 gC·m⁻²·d⁻¹, and coefficient of variance (CV) = 0.1508 and 0.1470, respectively. When evaluating the best ML models from three NE sites at the RO1 site, only RF and CNN could effectively incorporate the impact of SLN and NMP. But, in terms of unbiased estimation results, the four ML models were comprehensively enhanced by adding SLN and NMP. Due to their fixed relationship, introducing SLN or NMP alone might be more effective than introducing both simultaneously, considering the data redundancy for methods like CNN and ELM. This study supports the integration of phenology and leaf-level photosynthetic factors in plant GPP estimation via ML methods and provides a reference for similar research. Full article

In this research, E2YOLOX-VFL is proposed as a novel approach to address the challenges of optical image multi-scale ship detection and recognition in complex maritime and land backgrounds. Firstly, the typical anchor-free network YOLOX is utilized as the baseline network for ship detection. Secondly, the Efficient Channel Attention module is incorporated into the YOLOX Backbone network to enhance the model’s capability to extract information from objects of different scales, such as large, medium, and small, thus improving ship detection performance in complex backgrounds. Thirdly, we propose the Efficient Force-IoU (EFIoU) Loss function as a replacement for the Intersection over Union (IoU) Loss, addressing the issue whereby IoU Loss only considers the intersection and union between the ground truth boxes and the predicted boxes, without taking into account the size and position of targets. This also considers the disadvantageous effects of low-quality samples, resulting in inaccuracies in measuring target similarity, and improves the regression performance of the algorithm. Fourthly, the confidence loss function is improved. Specifically, Varifocal Loss is employed instead of CE Loss, effectively handling the positive and negative sample imbalance, challenging samples, and class imbalance, enhancing the overall detection performance of the model. Then, we propose Balanced Gaussian NMS (BG-NMS) to solve the problem of missed detection caused by the occlusion of dense targets. Finally, the E2YOLOX-VFL algorithm is tested on the HRSC2016 dataset, achieving a 9.28% improvement in mAP compared to the baseline YOLOX algorithm. Moreover, the detection performance using BG-NMS is also analyzed, and the experimental results validate the effectiveness of the E2YOLOX-VFL algorithm. Full article

Utilizing in situ measurement data to assess satellite-derived long-term ocean color products under different observational conditions is crucial for ensuring data quality and integrity. In this study, we conducted an extensive evaluation and analysis of Visible Infrared Imaging Radiometer Suite (VIIRS) remote sensing reflectance (Rrs) products using long-term OC-CCI in situ data from 2012 to 2021. Our research findings indicate that, well beyond its designed operational lifespan, the root mean square difference accuracy of VIIRS Rrs products across most spectral bands remains superior to 0.002 (sr⁻¹). However, VIIRS Rrs products in shorter wavelength bands (e.g., at 412 nm) have exhibited significantly lower accuracy and a long-term bias in recent years. The annual precision of VIIRS Rrs products demonstrated a declining trend, particularly in coastal or eutrophic waters. This degradation in accuracy highlights the imperative for continuous monitoring of VIIRS performance and further advancements in the atmospheric correction algorithm, especially to address satellite records at high solar zenith angles (SZAs) and observation zenith angles (OZAs). Our analysis indicates that, in observation environments with high SZAs (greater than 70°), the accuracy of VIIRS Rrs products has declined by nearly 50% compared to typical solar zenith angle observation conditions. To address the challenge of declining accuracy under large observation geometries, we introduced the neural network atmospheric correction model (NN-V). Developed based on meticulously curated VIIRS products, the NN-V model exhibits outstanding performance in handling VIIRS data in conditions of extensive observation geometries. During the winter season in high-latitude marine regions, the NN-V model demonstrates a remarkable enhancement in ocean color product coverage, achieving an increase of nearly 20 times compared to traditional methods. Full article

This study demonstrates a framework for using high-resolution satellite imagery to automatically map and monitor outbreaks of red needle cast (Phytophthora pluvialis) in planted pine forests. This methodology was tested on five WorldView satellite scenes collected over two sites in the Gisborne Region of New Zealand’s North Island. All scenes were acquired in September: four scenes were acquired yearly (2018–2020 and 2022) for Wharerata, while one more was obtained in 2019 for Tauwhareparae. Training areas were selected for each scene using manual delineation combined with pixel-level thresholding rules based on band reflectance values and vegetation indices (selected empirically) to produce ‘pure’ training pixels for the different classes. A leave-one-scene-out, pixel-based random forest classification approach was then used to classify all images into (i) healthy pine forest, (ii) unhealthy pine forest or (iii) background. The overall accuracy of the models on the internal validation dataset ranged between 92.1% and 93.6%. Overall accuracies calculated for the left-out scenes ranged between 76.3% and 91.1% (mean overall accuracy of 83.8%), while user’s and producer’s accuracies across the three classes were 60.2–99.0% (71.4–91.8% for unhealthy pine forest) and 54.4–100% (71.9–97.2% for unhealthy pine forest), respectively. This work demonstrates the possibility of using a random forest classifier trained on a set of satellite scenes for the classification of healthy and unhealthy pine forest in new and completely independent scenes. This paves the way for a scalable and largely autonomous forest health monitoring system based on annual acquisitions of high-resolution satellite imagery at the time of peak disease expression, while greatly reducing the need for manual interpretation and delineation. Full article

In a SAR image acquired by the ERS-2 satellite, crossed “X-shape” internal solitary waves (ISWs) south to Dongsha Island are found to be a wave–wave interaction composed of five solitons: two head waves, two tail waves, and the overlapped part. To explain this remote sensing phenomenon, based on a high-resolution three-dimensional MIT general circulation model (MITgcm) using realistic topography and tidal forcing, the “X-shape” internal waves are reproduced at the same location. The development processes of the waves indicate that the “X-shape” ISWs are two waves diffracted from one internal wave southeast to Dongsha Island. During the propagation, the amplitude of their overlapped part of the “X-shape” ISWs becomes significantly larger than the sum of the amplitudes of both head waves, which proves that nonlinear wave–wave interaction has occurred. Based on wave–wave interaction theory, the theoretical maximum value of the amplitude of the overlapped part at the initial moment is calculated as 14.12 m, which is in good agreement with the model results of 14 m. Meanwhile, the variation of the theoretical amplitude of the overlapped part is basically consistent with that of the modeled one, confirming the occurrence of the wave–wave interaction. Besides, when the waves propagate over varying water depths, the type of the wave–wave interaction can change rather than being fixed from the start. Full article

Flooding is a natural disaster that coexists with human beings and causes severe loss of life and property worldwide. Although numerous studies for flood susceptibility modelling have been introduced, a notable gap has been the overlooked or reduced consideration of the uncertainty in the accuracy of the produced maps. Challenges such as limited data, uncertainty due to confidence bounds, and the overfitting problem are critical areas for improving accurate models. We focus on the uncertainty in susceptibility mapping, mainly when there is a significant variation in the predictive relevance of the predictor factors. It is also noted that the receiver operating characteristic (ROC) curve may not accurately depict the sensitivity of the resulting susceptibility map to overfitting. Therefore, reducing the overfitting problem was targeted to increase accuracy and improve processing time in flood prediction. This study created a spatial repository to test the models, containing data from historical flooding and twelve topographic and geo-environmental flood conditioning variables. Then, we applied random forest (RF) and extreme gradient boosting (XGB) algorithms to map flood susceptibility, incorporating a variable drop-off in the empirical loop function. The results showed that the drop-off loop function was a crucial method to resolve the model uncertainty associated with the conditioning factors of the susceptibility modelling and methods. The results showed that approximately 8.42% to 9.89% of Marib City and 9.93% to 15.69% of Shibam City areas were highly vulnerable to floods. Furthermore, this study significantly contributes to worldwide endeavors focused on reducing the hazards linked to natural disasters. The approaches used in this study can offer valuable insights and strategies for reducing natural disaster risks, particularly in Yemen. Full article

Achieving the accurate and efficient monitoring of forests at the tree level can provide detailed information for precise and scientific forest management. However, the detection of individual trees under planted forests characterized by dense distribution, serious overlap, and complicated background information is still a challenge. A new deep learning network, YOLO-DCAM, has been developed to effectively promote individual tree detection amidst complex scenes. The YOLO-DCAM is constructed by leveraging the YOLOv5 network as the basis and further enhancing the network’s capability of extracting features by reasonably incorporating deformable convolutional layers into the backbone. Additionally, an efficient multi-scale attention module is integrated into the neck to enable the network to prioritize the tree crown features and reduce the interference of background information. The combination of these two modules can greatly enhance detection performance. The YOLO-DCAM achieved an impressive performance for the detection of Chinese fir instances within a comprehensive dataset comprising 978 images across four typical planted forest scenes, with model evaluation metrics of precision (96.1%), recall (93.0%), F1-score (94.5%), and [email protected] (97.3%), respectively. The comparative test showed that YOLO-DCAM has a good balance between model accuracy and efficiency compared with YOLOv5 and advanced detection models. Specifically, the precision increased by 2.6%, recall increased by 1.6%, F1-score increased by 2.1%, and [email protected] increased by 1.4% compared to YOLOv5. Across three supplementary plots, YOLO-DCAM consistently demonstrates strong robustness. These results illustrate the effectiveness of YOLO-DCAM for detecting individual trees in complex plantation environments. This study can serve as a reference for utilizing UAV-based RGB imagery to precisely detect individual trees, offering valuable implications for forest practical applications. Full article

In this work, we develop a software suite for studies of atmosphere–underlying SNOW-spaceborne optical receiver light TRANsmission calculations (SNOWTRAN) with applications for the solution of forward and inverse radiative transfer problems in polar regions. Assuming that the aerosol load is extremely low, the proposed theory does not require the numerical procedures for the solution of the radiative transfer equation and is based on analytical equations for the spectral nadir reflectance and simple approximations for the local optical properties of atmosphere and snow. The developed model is validated using EnMAP and PRISMA spaceborne imaging spectroscopy data close to the Concordia research station in Antarctica. A new, fast technique for the determination of the snow grain size and assessment of the snowpack vertical inhomogeneity is then proposed and further demonstrated on EnMAP imagery over the Aviator Glacier and in the vicinity of the Concordia research station in Antarctica. The results revealed a large increase in precipitable water vapor at the Concordia research station in February 2023 that was linked to a warming event and a four times larger grain size at Aviator Glacier compared with Dome C. Full article

Earth rotation parameters (ERPs) are fundamental to geodetic and astronomical studies. With its high measurement accuracy and stability, the Very Long Baseline Interferometry (VLBI) plays an irreplaceable role in estimating the ERPs and maintaining the earth reference frame. However, the imperfect global station distribution, observation discontinuity, and vast cost of the VLBI make the GNSS a more attractive technique. In 2020, the third generation of the BeiDou Navigation System (BDS), namely BDS-3, was constructed completely. In this study, we conducted a series of experiments to estimate Earth’s rotation parameters based on the continuous BDS-3 observation data, the discontinuous VLBI observation data, and the combined BDS-3 and discontinuous VLBI observation data. We used two methods, namely the weighted averaging method and the normal equation combination method, to obtain ERP combination solutions. The results are compared with the International Earth Rotation and Reference Systems Service (IERS) EOP 20C04 at 00:00:00 UTC. Final results show that (a) the estimation accuracy becomes stable when the number of BDS-3 tracking stations is more than 40. At the same time, both the number of stations and the volume of polyhedrons formed by the observing stations affect the accuracy of the ERPs estimated by the BDS-3 or VLBI. (b) Results have also shown that the inclusion of the BDS-3 IGSO and GEO satellites contributes little to the ERP estimation. (c) For the BDS-3-only MEO satellites solution, the root mean square (RMS) was 113.2 µas, 102.8 µas, and 13.1 µs/day for X-pole coordinate, Y-pole coordinate, and length of day (LOD), respectively. For the VLBI solution, the RMSs of the X-pole, Y-pole, and LOD were 100.4 µas for the X-pole, 94.2 µas for the Y-pole, and 14.1 µs/day. The RMS was 82.6 µas, 70.3 µas, and 10.5 µs/day for the combined X-pole, Y-pole, and LOD using the weighted averaging method. It was 78.2 µas, 62.6 µas, and 8.6 µs/day when the normal equation combination method was applied. This demonstrates that by taking advantage of the BDS-3 and VLBI technique combinations, accuracy in estimating the ERPs can be improved over that using either of them, in addition to enhanced stability and reliability. Full article

This paper proposes a method for the intelligent detection of high-frequency surface wave radar (HFSWR) targets. This method cascades the adaptive constant false alarm (CFAR) detector variability index (VI) with the convolutional neural network (CNN) to form a cascade detector (VI)CFAR-CNN. First, the (VI)CFAR algorithm is used for the first-level detection of the range–Doppler (RD) spectrum; based on this result, the two-dimensional window slice data are extracted using the window with the position of the target on the RD spectrum as the center, and input into the CNN model to carry out further target and clutter identification. When the detection rate of the detector reaches a certain level and cannot be further improved due to the convergence of the CNN model, this paper uses a dual-detection maps fusion method to compensate for the loss of detection performance. First, the optimized parameters are used to perform the weighted fusion of the dual-detection maps, and then, the connected components in the fused detection map are further processed to achieve an independent (VI)CFAR to compensate for the (VI)CFAR-CNN detection results. Due to the difficulty in obtaining HFSWR data that include comprehensive and accurate target truth values, this paper adopts a method of embedding targets into the measured background to construct the RD spectrum dataset for HFSWR. At the same time, the proposed method is compared with various other methods to demonstrate its superiority. Additionally, a small amount of automatic identification system (AIS) and radar correlation data are used to verify the effectiveness and feasibility of this method on completely measured HFSWR data. Full article

Traditional methods for assessing the stability of rubble mound breakwaters (RMBs) often rely on 2.5D data, which may fall short in capturing intricate changes in the armor units, such as tilting and lateral shifts. Achieving a detailed analysis of RMB geometry typically requires fully 3D methods, but these often hinge on expensive acquisition technologies like terrestrial laser scanning (TLS) or airborne light detection and ranging (LiDAR). This article introduces an innovative approach to evaluate the structural stability of RMBs by integrating UAV-based photogrammetry and the random sample consensus (RANSAC) algorithm. The RANSAC algorithm proves to be an efficient and scalable tool for extracting primitives from point clouds (PCs), effectively addressing challenges presented by outliers and data noise in photogrammetric PCs. Photogrammetric PCs of the RMB, generated using Structure-from-Motion and MultiView Stereo (SfM-MVS) from both pre- and post-storm flights, were subjected to the RANSAC algorithm for plane extraction and segmentation. Subsequently, a spatial proximity criterion was employed to match cuboids between the two time periods. The methodology was validated on the detached breakwater of Cabedelo do Douro in Porto, Portugal, with a specific focus on potential rotations or tilting of Antifer cubes within the protective layer. The results, assessing the effects of the Leslie storm in 2018, demonstrate the potential of our approach in identifying and quantifying structural changes in RMBs. Full article

The time-domain electromagnetic (TDEM) method is acknowledged for its simplicity in setup and non-intrusive detection capabilities, particularly within shallow subsurface detection methodologies. However, extant TDEM systems encounter constraints when detecting intricate topographies and hazardous zones. The rapid evolution in unmanned aerial vehicle (UAV) technology has engendered the inception of UAV-based time-domain electromagnetic systems, thereby augmenting detection efficiency while mitigating potential risks associated with human casualties. This study introduces the UAV-TDEM system designed explicitly for discerning shallow subsurface targets. The system comprises a UAV platform, a host system, and sensors that capture the electromagnetic response of the area while concurrently recording real-time positional data. This study also proposes a processing technique rooted in robust local mean decomposition (RLMD) and approximate entropy (ApEn) methodology to address noise within the original data. Initially, the RLMD decomposes the original data to extract residuals alongside multiple product functions (PFs). Subsequently, the residual is combined with various PFs to yield several cumulative sums, wherein the approximate entropy of these cumulative sums is computed, and the resulting output signals are filtered using a predetermined threshold. Ultimately, the YOLOv8 (You Only Look Once version 8) network is employed to extract anomalous regions. The proposed denoising method can process data within one second, and the trained YOLOv8 network achieves an accuracy rate of 99.0% in the test set. Empirical validation through multiple flight tests substantiates the efficiency of UAV-TDEM in detecting targets situated up to 1 m below the surface. Both simulated and measured data corroborate the proposed workflow’s effectiveness in mitigating noise and identifying targets. Full article

Three-dimensional semantic segmentation is the foundation for automatically creating enriched Digital Twin Cities (DTCs) and their updates. For this task, prior-level fusion approaches show more promising results than other fusion levels. This article proposes a new approach by developing and benchmarking three prior-level fusion scenarios to enhance the outcomes of point cloud-enriched semantic segmentation. The latter were compared with a baseline approach that used the point cloud only. In each scenario, specific prior knowledge (geometric features, classified images, or classified geometric information) and aerial images were fused into the neural network’s learning pipeline with the point cloud data. The goal was to identify the one that most profoundly enhanced the neural network’s knowledge. Two deep learning techniques, “RandLaNet” and “KPConv”, were adopted, and their parameters were modified for different scenarios. Efficient feature engineering and selection for the fusion step facilitated the learning process and improved the semantic segmentation results. Our contribution provides a good solution for addressing some challenges, particularly for more accurate extraction of semantically rich objects from the urban environment. The experimental results have demonstrated that Scenario 1 has higher precision (88%) on the SensatUrban dataset compared to the baseline approach (71%), the Scenario 2 approach (85%), and the Scenario 3 approach (84%). Furthermore, the qualitative results obtained by the first scenario are close to the ground truth. Therefore, it was identified as the efficient fusion approach for point cloud-enriched semantic segmentation, which we have named the efficient prior-level fusion (Efficient-PLF) approach. Full article