Advances in unmanned aerial vehicle (UAV)technology are fostering new forms of productivity in the low-altitude economy and creating an urgent demand for the development and utilization of low-altitude airspace.As a core enabler in this context,geospatial surveying and mapping provides the safety assurance and information backbone needed for high-density,highly dynamic,and high-precision low-altitude flight.However,the low-altitude economy is still in its infancy,and how geospatial information can effectively support its development has become a key scientific question.This paper systematically analyzes the sources of risk in low-altitude flight and clarifies the critical technical roles of geospatial information in risk quantification,route planning,navigation,and applications.Firstly,we review domestic and international frameworks and methods for risk quantification,summarizing approaches driven by both static and dynamic data such as terrain features,3D buildings,and human mobility.Secondly,at the level of low-altitude route planning,we outline an evolutionary pathway from single-UAV trajectory planning,to multi-UAV network optimization,and ultimately to the construction of low-altitude route maps,and we discuss key techniques for local path planning,route-network design,and route-map generation.Thirdly,in the domain of high-precision navigation,we introduce the emerging “BeiDou+low-altitude” navigation system,which provides positioning and routing services for low-altitude operations.Finally,we examine the industrial applications of geospatial information in low-altitude surveying,low-altitude transportation,and low-altitude emergency response.Overall,geospatial surveying and mapping constitute essential public digital infrastructure for the large-scale and intelligent development of the low-altitude economy.

The low-altitude economy constitutes a pivotal intersection between China's strategic emerging industrial clusters and the advancement of national security capabilities in novel domains.Its high-quality development critically depends on precise,dynamic spatio-temporal intelligence underpinned by surveying,mapping,and geospatial information technologies.This paper focuses on a four-element collaborative architecture—encompassing airspace,aerial route networks,takeoff and landing facilities,and unmanned systems—and systematically examines the technological evolution of geospatial information in constructing human-environment systems for low-altitude operations,advancing digital twin methodologies,and enabling multimodal intelligent sensing frameworks.It delineates the developmental trajectory of spatio-temporal intelligence and its empowering mechanisms in key operational functions such as airspace planning and real-time traffic management.Through case studies in representative applications—including low-altitude logistics and emergency response—the study evaluates the enabling efficacy of these technologies alongside persistent challenges such as data latency and interoperability gaps.Building on this analysis,the paper proposes forward-looking pathways:an integrated “communication-sensing-computing-intelligence” closed-loop system,standardized frameworks for dynamic digital foundations,and a mapping-as-a-service (MaaS)ecosystem.These strategies aim to transition geospatial information from static data provisioning toward intelligent,decision-ready services,thereby providing core impetus for the new-quality development of geospatial information and building a high-quality intelligent support system for the low-altitude economy.

The methods of Traditional highway bridge inspection face some challenges such as low efficiency,high costs,and delayed response.It is particularly urgent to carry out intelligent inspection for bridge structures that are large in scale but increasingly severe in safety situation.This study takes the Maguohe Extra Large Bridge,a key control project of S101 provincial highway in Yunnan province,as the research object.It automatically acquires high-precision low-altitude remote sensing data by deploying an unmanned automated airport on-site,optimizes the close-range photogrammetry algorithm based on high-precision geographical entities for refined inspection route planning of the bridge,improves the AI algorithm for bridge defect detection based on YOLOv5,conducts slope analysis using the improved M3C2 algorithm,and thereby constructs an intelligent inspection technical route for the bridge.Compared with traditional bridge inspection routes,the proposed method in this study offers more convenient data acquisition,more intelligent route planning,and significantly improved bridge defect detection performance,while enabling effective identification of slope changes.proposed in this paper can provide a new technical approach for the intelligent inspection of bridges in plateau mountainous areas.

With the low-altitude economy emerging as a national strategic industry,this paper explores how a low-altitude remote sensing system,driven by surveying,mapping and geographic information,can support the entire lifecycle of high-standard farmland,including construction,management,and utilization.An integrated “air-sky-ground-network” monitoring architecture was established by integrating multi-source geospatial data from BeiDou navigation,5G communication,high-resolution satellites,UAV remote sensing,and ground-based sensors.By incorporating AI-based image interpretation and spatio-temporal analysis models,a geomatics-driven digital management framework for high-standard farmland was developed.In a pilot application conducted in Huanxian county,Gansu province,the proposed framework achieved over 92% accuracy in automatic identification of farmland engineering facilities and 88.4% accuracy in crop growth status classification.In addition,during an emergency response to an irrigation system failure,anomalies in multi-source geospatial data enabled fault localization and early warning to be completed within three hours.The results demonstrate that the integration of low-altitude remote sensing with geomatics provides an effective solution for the digital and intelligent management of high-standard farmland.The proposed framework offers a replicable and scalable paradigm for the large-scale application of the low-altitude economy in agriculture.

Low-altitude path planning is a core link to ensure the safe and efficient development of the low-altitude economy.Traditional A^*algorithms face problems such as low search efficiency and insufficient path safety in three-dimensional low-altitude environments.To address these challenges,this paper proposes an improved A^*algorithm integrated with GeoSOT-3D grid modeling for low-altitude path planning.Based on the GeoSOT-3D grid,the algorithm constructs a three-dimensional low-altitude environmental model,introduces a 7-neighborhood extended search strategy,incorporates a safety obstacle avoidance mechanism,and adopts Catmull-Rom spline curves to smooth and optimize the result paths.Comparative results of three groups of simulation experiments show that,in the 19th,20th and 21st level GeoSOT-3D grid environments,the improved A^*algorithm reduces the average number of searched and expanded nodes by more than 83%.Moreover,the average time consumption of the improved A^* algorithm is reduced by approximately 17%～26% compared with the traditional A^*algorithm,and by approximately 1%～12% compared with the Theta^*algorithm.While maintaining both path safety and smoothness,the improved algorithm enhances the efficiency of path planning.

The rapid development of the low-altitude economy creates an urgent demand for high-precision and computable urban 3D spatial data.As the core digital foundation for route planning and airspace management of low-altitude aircraft,the rapid and precise construction of LOD1.3 building models is crucial.However,existing methods suffer from issues such as low accuracy and high computational redundancy in roof facet segmentation.This paper proposes an efficient airborne LiDAR point cloud modeling method that integrates dynamic normal vector optimization with an adaptive RANSAC iteration strategy.By dynamically adjusting the neighborhood radius through curvature feedback and combining it with a point cloud density-adaptive RANSAC iteration,the method enhances the robustness of plane segmentation.It further integrates PCA fitting to optimize the geometric accuracy of roof facets.Experimental results show that the root mean square error of plane fitting reaches 0.11 m,representing a 47.6%reduction compared to traditional methods.The modeling efficiency achieves 1 km²/d,marking a 300% improvement.The segmentation accuracy reaches 86%,while the error rate for complex roofs decreases to 12.3%.This method provides a high-precision and low-cost LOD1.3 modeling solution for 3D real-scene construction,effectively supporting the digital and intelligent development of low-altitude economy applications.

To address the challenges of information silos,low efficiency,and poor coordination inherent in traditional medical emergency response models within complex urban environments,this study designs and implements a WebGIS-based three-dimensional low-altitude medical emergency dispatch cloud platform.The platform adopts a three-tier B/S architecture and a front-end/back-end decoupled development framework.By integrating mainstream technologies such as Vue.js,Cesium,and Django,it constructs a comprehensive management system encompassing emergency work-order management,medical supplies dispatching,urban 3D visualization,UAV route planning,and real-time status monitoring.A representative medical emergency scenario is simulated to quantitatively compare the response performance of UAV transport and traditional ground-vehicle transport under varying traffic conditions.Experimental results show that the platform can reduce the overall emergency response time by more than 64%.In addition,it enables end-to-end digital management and visual command of emergency tasks,significantly enhancing dispatching efficiency and the level of intelligent decision-making.The simulation experiments validate the platform's potential to improve urban medical emergency response efficiency and provide a feasible and effective technical solution—and platform-level support—for advancing low-altitude economy applications in intelligent urban emergency management.

To address the difficulties in 3D fusion of multi-source heterogeneous data and bottlenecks in high-concurrency access within complex low-altitude environments,a Low-Altitude Spatio-Temporal Cube aggregation model (LAST-Cube)based on GeoSOT-3D is proposed.First,a high-precision 3D subdivision framework for near-ground dense obstacle environments was constructed.Algorithms for conservative voxelization of static obstacles and spatio-temporal tube mapping for dynamic flow data were developed to establish a logical normalization mechanism for heterogeneous data.Second,a dual-table storage architecture with dynamic-static separation and a spatio-temporal linearized RowKey considering load balancing were designed,creating a storage-computation integrated retrieval mechanism based on HBase.Experiments demonstrate that the write throughput of the proposed method is approximately 13 times higher than that of PostGIS under a scale of hundreds of millions of trajectories,and it achieves millisecond-level response times for complex 3D collision detection.The proposed model effectively resolves the challenges of efficient organization and computation of low-altitude data,providing robust support for the refined management and control of low-altitude airspace.

In response to the characteristics of large data volume and high reliability requirements for low-altitude geospatial information products,this study investigates the risks of zero-defect sampling inspection in quality control of these products.Using the sampling plan from the GB/T 24356—2023 standard as the research subject,this paper analyzes the correlation between the number of nonconforming items,the limiting quality level,and the consumer's risk.The study found that the sampling plan specified in the standard entails a high consumer risk in scenarios involving large batch sizes and low quality.For instance,when the defective rate is 10%,the consumer's risk exceeds 11% for lot sizes of 282 or fewer.Moreover,zero-defect sampling exhibits an unbalanced risk allocation mechanism,and batch-by-batch inspection strategies significantly increase the consumer's risk.Therefore,for low-altitude geographic information products,zero-defect sampling should be optimized according to specific application scenarios.When necessary,sample sizes should be enlarged,and prior knowledge should be leveraged to enhance the targeting of sampling,thereby achieving the goal of improving the reliability of quality control.

Point cloud semantic segmentation has become a key technology for achieving multi-semantic visualization in underground alleyway health monitoring.To address the low segmentation accuracy of target edges in alleyway scenarios,this paper constructs a large-scale point cloud semantic segmentation dataset for alleyway scenarios ALSD,and proposes a segmentation method adapted to this scenario.Based on backbone feature extraction,it introduces a local multi-scale neighborhood considering 3D curvature and a global spatial feature enhancement module,combined with an attention mechanism to improve the representation ability of small components and complex boundaries.An evaluation index system for alleyway scenarios is also established.On the ALSD dataset of real alleyway scenarios,we systematically analyzed the impact of training set size,input dimension,and hyperparameter settings on model performance.Experiments show that the proposed method achieves IoUs of 0.858,0.883,0.933,and 0.822 for pipes,supports,ground,and columns,respectively,with an mIoU of 0.865 and an overall accuracy (OA)of 98.7%.Compared with typical deep learning baseline methods such as PointNet++ and RandLA-Net,the proposed model achieves higher semantic segmentation accuracy on the ALSD dataset,which can provide high-precision 3D semantic support for the structural health monitoring of underground alleyways.

In underwater target recognition,acoustic data is greatly affected by noise and susceptible to interference,while the difficulty of obtaining optical data increases significantly with depth.This paper proposes a method of fusing acoustic and optical images to improve the accuracy of underwater target recognition.To address the scarcity of corresponding acoustic and optical image datasets for underwater targets,a Cycle-GAN network is employed for dataset sample augmentation,followed by image enhancement processing on the generated dataset.In the field of target recognition algorithms,the Transformer cross-modal attention module and the channel prior convolutional attention mechanism are integrated into the YOLOv8 algorithm to improve target recognition accuracy and precision.This study utilizes a sonar-scanned shipwreck target dataset.Experimental results indicate that to the cross-modal acoustic-optical fusion target in target recognition algorithms,the average and average accuracy rates have respectively improved 0.175 and 0.165. Constructed optimized backbone network enables cross-modal integration of acoustic and optical features,enhancing the efficiency of feature extraction and addressing the challenge of distinguishing the edges of submerged shipwrecks from their surrounding environments.

To address the challenges of insufficient automatic recognition accuracy of InSAR technology and difficulty in adapting complex terrain landslide features in current landslide detection,as well as the lack of existing deep learning models for InSAR landslide recognition methods,and the limited ability of recognizing fine deformation and small-scale landslides,this paper proposes a method of automatic detection of active landslides by fusing SBAS-InSAR with the improvement of YOLOv8,in order to achieve the accurate identification of active landslides in large areas.The method first generates a surface deformation rate map by processing multi-temporal SAR images with SBAS-InSAR,and then constructs the improved VRO_YOLO model: We propose variable kernel convolution to adapt to the irregular morphology of landslides,and integrate RepVGG,ShuffleNet,and One-Shot Aggregation to construct the channel one-shot shuffle (RVS-OSA)module to enhance the multi-scale identification of active landslides.Taking the Pinglu Canal area in Guangxi as the study area,49-view Sentinel-1 SAR images are used to generate the rate map and construct the dataset to carry out the experiments.Finally,the multi-dimensional validation by combining high-resolution remote sensing,UAV tilt photography and field exploration further supports the accuracy of the method.The results show that the detection precision of VRO_YOLO reaches 51.2%,the recall rate reaches 55.2%,and the mean accuracy reaches 46.8%,and the further comparisons,ablations,and generalization experiments validate the applicability and accuracy of the model accuracy.In conclusion,the method provides a strong potential for landslide detection,contributing to disaster prevention and risk reduction.

Nighttime remote sensing data has unique advantages for estimating metropolitan area populations.Its strong correlation with human activity makes it a popular tool in sociology and human dynamics research.This paper presents a nighttime population estimation model based on multi-tree fusion to predict the population in the Chengdu area with high precision using nighttime remote sensing data.The study uses nighttime remote sensing and population data from various regions in Chengdu from 2000 to 2020 to construct long-term nighttime remote sensing data.XGBoost,random forest,and decision tree models are used as base models for preliminary predictions.These predictions are then integrated and fused using a linear regression meta-model to form a multi-tree fusion nighttime population estimation model.This model is then used to predict the population of various Chengdu regions in 2021 and 2023.The results are compared with the actual values to validate the model.Overall,the model's prediction accuracy is excellent.The average prediction accuracy for 2021 is 99.54%,with an average absolute error of 3437 people.The average accuracy for 2022 is 98.87%,with an average error of 9156 people,and the average accuracy for 2023 is 98.86%,with an average error of 9832 people.Districts such as Xinjin district (99.85% in 2021)and Jinniu district (99.93% in 2023)achieved an accuracy level exceeding 99.5%.However,only a few districts,such as Longquanyi district (96.55% in 2023)and Wuhou district (97.58% in 2022),experienced slight accuracy fluctuations due to rapid urban functional changes.The study confirms that the multi-tree fusion model effectively captures the correlation between nighttime remote sensing data and population changes.This provides reliable data support for Chengdu's urban planning and resource allocation.

The rapid expansion of the urban underground transportation network and the frequent crossing of subway construction through complex geological areas can easily lead to potential safety hazards such as ground subsidence and structural damage to buildings.As a typical plateau fault basin city,Kunming faces unique geological challenges with its subway system.This study aims to analyze the spatio-temporal differentiation patterns and evolution trends of deformation along the subway line,quantitatively assess the driving mechanisms,and provide a basis for subway planning and disaster prevention.InSAR technology has become an important tool for monitoring deformation in urban infrastructure due to its large-scale and high-precision monitoring capabilities.This study selects the area along the Kunming metro as the subject,integrates multi-source SAR data,and proposes a cross-track multi-source InSAR point cloud fusion method.Using GIS spatial analysis techniques and incorporating a four-dimensional system of driving factors such as land cover,and is conducted.It reveals the spatio-temporal evolution patterns of deformation along the Kunming subway and identifies the main driving factors.This provides a scientific basis for subway planning and disaster prevention.

Post-earthquake landslides are secondary geological hazards in areas adjacent to fault zones,posing a serious threat to human life and infrastructure.To address the limitation of traditional landslide susceptibility assessments,which generally fail to consider the spatiotemporal dynamics of post-earthquake landslides,this study employs SBAS-InSAR technology combined with a ConvLSTM neural network model to evaluate landslide susceptibility following the Ms6.4 Yangbi earthquake in the northern segment of the Honghe fault zone.Firstly,time-series surface deformation information is obtained from 204 Sentinel-1A ascending and descending orbit images acquired from January 2021 to January 2025.This is combined with high-resolution optical imagery for landslide identification.Secondly,environmental factors are analyzed using the geographical detector method and Pearson correlation analysis.Finally,the ConvLSTM neural network model is used to classify landslide susceptibility levels,and the results are compared with those of three other neural network models: BP,LSTM,and CNN.The results show that the root mean square error and mean absolute error of the ConvLSTM model are both lower than those of the other three models,and the model achieves an AUC value of 0.912,indicating higher accuracy and better performance.High-risk and above-risk areas are concentrated to the west of the northern segment of the Honghe fault zone,distributed within 10 km on both sides of the Weixi—Weishan fault.This method further improves the accuracy of landslide susceptibility assessment and can provide data support and technical reference for post-earthquake landslide disaster prevention and control in areas near fault zones.

Hancheng city,a city born out of coal,is rich in mineral resources and has diverse geological structures and ecological environments.It is also prone to frequent geological disasters.Monitoring and analyzing the surface stability of the entire region over the past few years is of great significance.Currently,research on Hancheng primarily focuses on short-term studies of local mining areas,with insufficient attention paid to monitoring and predicting surface stability across the entire region.In this study,we utilize advanced time-series InSAR technology and deep learning algorithms to process the SAR dataset from the Sentinel-1 satellite that covers the entire Hancheng from 2019 to 2023,to obtain the surface deformation of the whole Hancheng and predict its future development trend.It will also conduct a focused analysis on the surface instability caused by typical mining activities in the area.The results indicate that deformation areas are highly correlated with geological conditions and human activities in terms of spatiotemporal distribution.The local deformation rate exceeds -50 mm/a,and the maximum cumulative settlement reaches approximately 250 mm.The established deep learning model performs well in deformation fitting and prediction for the study area.The mean absolute error,root mean squared error,and mean absolute percentage error are 0.30,1.08,and 11.76 cm,respectively.The research results can provide methodological references and data support for the census and prevention of surface instability and geological disasters in Hancheng city.

Landslides pose a serious threat to the safety of ultra-high-voltage (UHV)transmission corridors.In mountainous areas with large relief and complex geology,displacement signals are strongly nonlinear,multi-stage,and prone to abrupt mutations; reliable short-term prediction is therefore essential for risk mitigation.We propose a multi-stage landslide displacement forecasting framework that fuses variational mode decomposition (VMD)and a bidirectional long short-term memory (BiLSTM)with time-series InSAR observations.In a high-hazard segment of the Lingzhou-Shaoxing UHV line (Shaanxi,China),SBAS-InSAR is used to retrieve surface deformation; VMD decomposes and denoises the displacement series,and the BiLSTM captures bidirectional temporal dependencies for prediction.The InSAR results reveal up to 110 mm of cumulative subsidence and >50 mm displacement during single accelerated episodes.The proposed model accurately forecasts large-amplitude,multi-stage motions within -120 to 60 mm,achieving a maximum absolute error ≤2.6 mm and a root-mean-square error of 1.0~1.5 mm across typical points,with pronounced advantages during rapid acceleration and impending instability.The method faithfully characterizes multi-phase evolution and extreme deformation of landslides and provides robust technical support for proactive monitoring and intelligent early warning along UHV transmission corridors.

Flatness detection of large rockfill dams is critical to structural safety.Conventional flatness detection methods suffer from low efficiency and insufficient accuracy.To address these limitations,a multi-layer random sample consensus-based detection method is proposed for the multi-level Nuozhadu large rockfill dam.The proposed method consists of three key steps: ①point cloud registration and approximate voxel filtering for data downsampling; ②a PCA-based adaptive clustering denoising approach that reduces the point cloud to two dimensions to remove noise,combined with height stratification and angular clustering to segment the main dam surface point cloud; ③optimized ML-RANSAC plane fitting with normal vector constraints and distance thresholds to achieve accurate segmentation and flatness analysis of multi-layer dam surfaces.Experimental results show that,compared with the traditional RANSAC algorithm,the proposed method reduces the plane-fitting mean square error by 43.4%and improves detection efficiency by 55.2%.It also effectively identifies local surface deviations and generates visualized deviation heat maps.By integrating stratified sampling and local model fusion,the method significantly enhances large-scale point cloud processing efficiency and detection accuracy for complex geometries,providing a high-precision,low-risk automated solution for rockfill dam quality assessment.

This study addresses the issues of boundary detail loss and insufficient use of dual-temporal change information in SAR images for flood inundation extraction.A Squeeze-and-Excitation weighted ResNet (SE-wResNet)model is proposed,to improve accuracy and robustness in flood detection.The SE-wResNet model is based on ResNet.It uses a dual-temporal,dual-channel input structure to capture changes between pre-and post-flood SAR images.The model incorporates squeeze-and-excitation(SE) and convolutional block attention module(CBAM) mechanisms to enhance flood-sensitive feature extraction in both channel and spatial dimensions.A multi-scale feature fusion decoder is also introduced to improve boundary preservation and semantic discrimination.The model is tested using RadarSat-2 imagery from Dongdian flood detention area in Tianjin.Experiments show that SE-wResNet outperforms models like U-Net and DeepLabV3+ in precision,recall,and overall accuracy.It achieves precision of 0.984 6,recall of 0.988 8,and overall accuracy of 0.997 8.The results show a significant reduction in false positives and missed detections,especially in complex flood scenarios.This demonstrates superior boundary restoration and robustness.The SE-wResNet model provides a reliable solution for automatic flood inundation extraction from SAR images.Its use of dual-temporal information,attention mechanisms,and multi-scale feature fusion enhances detection accuracy.This model is a robust tool for emergency flood monitoring and assessment.

To address the potential threats to power grid safety posed by construction changes in surrounding structures (e.g.,factories,residences,temporary buildings),this study proposes an efficient and reliable change detection method.A multi-level attention-driven Mamba building change detection network is designed.Adopting an encoder-decoder architecture,the encoder extracts multi-level features based on the Visual Mamba framework.The decoder enhances feature expression in regions of interest and multi-scale information fusion through a feature enhancement module (FEM)and a hierarchical feature fusion module (HFFM),enabling automatic identification of building changes in dual-phase remote sensing images.Comparative and ablation experiments on synthetic datasets demonstrate superior performance across multiple metrics compared to existing mainstream methods.The approach significantly improves detection accuracy for small targets and buildings in complex backgrounds,exhibiting enhanced change recognition capability and robustness.In real-world power line scenarios,the proposed method accurately identifies newly constructed and demolished buildings with clear change boundaries and high localization precision.Integrating the Mamba architecture with attention mechanisms effectively enhances remote sensing change detection performance,providing an efficient and reliable technical approach for monitoring construction changes in buildings surrounding power grid lines.

With the continuous expansion of nuclear energy capacity in China,the production of spent fuel from nuclear power plants has been steadily increasing.The storage and management of these highly radioactive materials are of critical importance.Once storage facilities are put into operation,it becomes difficult to conduct regular internal inspections and maintenance.Taking a nuclear power plant as an example,this study utilizes the Leica RTC360 3D laser scanner to obtain point cloud data of equipment rooms.The data are processed using Cyclone software,and by integrating the advantages of Cyclone for modeling regular objects and 3ds Max for irregular objects,a 3D model is successfully constructed.The modeling results provide an intuitive representation of the spatial layout and positioning of various equipment in the nuclear power plant,facilitating later maintenance and inspection tasks,thereby further enhancing the management and operational efficiency of the plant.Additionally,it has been confirmed that the 3D model constructed through the collaboration of Cyclone and 3ds Max offers advantages such as high efficiency,high precision,and broad applicability.

Regarding the safety issues caused by subsidence due to mining,this study takes the Heidaigou coal mine in Ordos city,Inner Mongolia as an example.Using SBAS-InSAR technology,it obtained monitoring results of deformation in the internal dumping site in the study area from August 2021 to April 2023,and employed both the LSTM neural network model and an improved LSTM-ARIMA model to conduct time series predictions of slope feature points in the mine's internal dumping site.The research results indicate that: ①The annual average deformation rate of the internal dumping site at Heidaigou coal mine from August 2021 to April 2023 ranged from -458.76 to 4.44 mm/a.Cross-validation using PS-InSAR technology showed a coherence coefficient of 0.86 for homologous points between the two methods.②Analysis of the deformation results revealed that the displacement on the eastern slope was greater than that on the western slope.Further analysis of the causes of subsidence found that heavy rainfall accelerates deformation.③The LSTM-ARIMA model optimized with the ARIMA model demonstrated better stability in time series prediction compared to LSTM alone and showed higher prediction accuracy,with R² values all above 0.85.The study provides strong technical support and theoretical reference for precise monitoring,risk warning,and scientific control of mine dumping sites.

Addressing the automation challenges in boulder point cloud measurement using UAV-borne LiDAR,particularly in boulder region extraction and volume estimation,this paper proposes an automated processing method based on cloth simulation filtering and distance clustering.Furthermore,a volume calculation strategy is presented based on the difference between loaded and unloaded deck point cloud models.First,ship hull points are extracted to identify the carrier structure,and then the cloth simulation algorithm is employed to accurately extract the bottom points (i.e.,the deck points within the cargo area),leveraging the spatial distribution characteristics of the loaded stone point clouds.Subsequently,a local coordinate system is constructed to analyze the geometric features of the bottom points,determining the horizontal boundaries of the boulder distribution and obtaining an initial boulder point cloud set.A distance clustering algorithm is then introduced to process these initial points,enabling precise separation of boulder points from residual hull points.Finally,by constructing 3D models of both the boulder point clouds and the corresponding empty-ship deck point clouds,volume estimation is achieved through model differencing.Accuracy assessments indicate that the proposed method achieves high precision in boulder point cloud extraction,with volume results consistent with manual estimations,effectively meeting the practical requirements of navigation channel improvement projects.

To address the challenges of high cost and difficult deployment of traditional structural displacement sensors in complex environments,and to validate the applicability of vision-based measurement methods in practical engineering,a real-time displacement monitoring system based on monocular vision sensing and deep learning technology was developed.The system uses a low-cost CMOS camera to perceive a specially designed target.An intelligent recognition module based on the YOLOv11 algorithm enables real-time target detection.Ellipse fitting technology is employed to extract subpixel coordinates of the target center,and actual displacement is calculated through scale conversion.To mitigate measurement anomalies caused by on-site wind disturbances,the median absolute deviation (MAD)algorithm is introduced for error compensation.Compared with single-BDS displacement monitoring results,the system achieved a root mean square error (RMSE)of less than 1 mm in both horizontal and vertical directions,significantly outperforming the single-BDS method (RMSE of 1.88 and 1.57 mm in the plane direction,and 3.28 mm in the elevation direction).At monitoring distances of 20,50,and 75 m,the MAD compensation algorithm improved measurement accuracy by 26.6%,24.2%,and 35.6%,respectively.Experimental results demonstrate the excellent performance of the proposed vision-based sensing system in complex environments.It provides a low-cost,high-precision,non-contact technical solution for structural health monitoring of slopes,buildings,and other engineering structures,showing high potential for engineering application and promotion.

To evaluate the feasibility and potential biases of the PLUS model when applied at the central urban area scale.Taking the central urban area of Zoucheng city as the study site,this paper coupled the GMOP and PLUS models to simulate blue-green space patterns under four scenarios—planning constraints,economic priority,ecological conservation,and comprehensive development—by 2035.These results were systematically compared with the national territorial spatial master plan.Findings indicate: ①Spatial evolution in Zoucheng's central urban area exhibits eastward expansion and integration of blue-green-gray clusters.②The ecological conservation scenario represents the baseline pathway for implementing the planning blueprint,while the planning constraints scenario serves as the ideal path for achieving high-quality,sustainable development and enhancing long-term comprehensive value.③The PLUS model exhibits limitations in simulating policy-driven and engineering-based land uses such as undeveloped land,roadside green spaces,and planned artificial water systems.This study enhances the PLUS model's predictive precision through the GMOP model.However,integrating policy rules with multi-source data remains the developmental trend for simulating blue-green space at the urban scale.

Incorporating a temporal dimension into habitat network construction holds significant importance for biodiversity conservation.This paper constructs habitat networks for current and future climate scenarios using MaxEnt and LCM model,proposes a method for constructing spatio-temporal habitat networks,and optimizes it through path selection strategy to enhance the protection efficiency of habitat networks under climate change.Taking Falco tinnunculus in Urad Front Banner as an example,the results indicate: Compared to the present,0.07%～43% of habitats will be lost in the future,while 190.28%～629.50% of habitats will be increased.The spatio-temporal habitat network achieves a 100% protection rate for the integrity of both current and future habitat networks,with the connectivity protection rate of networks of the same level reaching 100% and 92.53%,respectively; The path selection strategy shows a significant optimization effect,achieving 100% integrity of current and future habitat networks with only 11.45% of the basic paths,while connectivity reaches 99.88% and 97.39%,respectively.The Falco tinnunculus spatio-temporal habitat network exhibits a “one axis and two cores” pattern.Wuliangsu Lake and the plain region at the southern foot of the Wula Mountain should be regarded as the key protection area of Falco tinnunculus habitats.This paper establishes a methodological framework for analyzing the dynamics of species habitat networks under climate change,providing a scientific basis for formulating effective biodiversity conservation strategies and responding to global climate change.