ABSTRACT This study proposes a heuristic approach for constructing time-scaled topology maps of indoor WiFi networks using only WiFi log data, without relying on access point (AP) coordinates or signal strength measurements. The method extracts time differences (TD) between consecutive AP transitions from remote authentication dial in user service (RADIUS) server logs. It uses the interquartile range (IQR) method to remove outliers caused by delayed handoffs or inconsistent logging intervals. Descriptive statistics – including the mean and the 25th, 50th, 75th, and 95th percentiles – are then applied to summarize travel behavior and construct time-based distance matrices. A modified Dijkstra algorithm limited to two-hop paths is employed to address missing TD values using both shortest-path and average-path estimation strategies. These completed matrices are projected into two-dimensional space using multidimensional scaling (MDS) to generate topology maps that reflect temporal proximities among APs. The proposed approach is validated through experiments conducted on two floors of a university library, with ground truth walking-time data collected through controlled experiments. Evaluation using Procrustes analysis and normalized Frobenius norm reveal that the 95th percentile provides the most accurate and robust representation of spatial structure, effectively capturing delays and transitional lags commonly observed in indoor mobility. Moreover, average-path Dijkstra estimation outperforms the shortest-path approach in maintaining spatial continuity when direct TD data are missing. This framework enables scalable, low-cost indoor mobility analysis. It offers practical applications in indoor navigation, smart facility management, and spatio-temporal behavior modeling in environments where physical layout information is unavailable or impractical.

ABSTRACT Understanding the relationships between urban crime and street environment is essential for effective crime prevention. However, due to difficulty in crime location extraction and data representation, traditional statistical and machine learning approaches are hard to model complex, nonlinear interactions between street features and crime distribution. For these issues, we present a novel method, which combine advantages of large language model and machine learning to assess crime risk on urban street. Specifically, the proposed method uses a knowledge-enhanced large language model to accurately extract criminal locations from legal documents. After that, it employs high-dimensional features from street view images, replacing traditional manual features. Various experiments conducted on public datasets demonstrate that our method outperforms other state-of-the-art methods. Building on these findings, we applied our method in Wuhan, China and results show its well capability for assessing urban crime risk, further validating its superiority over existing approaches.

ABSTRACT Changes in forest cover significantly influence carbon-climate dynamics, yet integrated assessment frameworks that connect water-heat-carbon interactions are still limited for subtropical hilly regions. This study presents a spatiotemporal framework for evaluating the impact of forest changes on water-heat-carbon and biophysical processes. Based on effective moving-window samples (Hangzhou: 168; Zhaoqing: 175), we employed partial least squares structural equation modeling (GOF: 0.81/0.71), variance partitioning analysis, and hierarchical partitioning (R 2 : 0.79/0.73) to investigate their interactive relationships and evaluate their accuracy. Results indicate that forest changes exert consistent effects on water-heat-carbon dynamics and biophysical processes in Hangzhou and Zhaoqing, with afforestation and deforestation yielding opposite impacts. The net changes in land surface temperature caused by forest changes from 2000–2010 and 2010–2020 were −0.23 ± 0.40°C/–0.11 ± 0.29°C for Hangzhou and 0.4 ± 0.25°C/–0.49 ± 0.38°C for Zhaoqing, respectively. These changes were significantly larger than the variations in air temperature. Precipitation changes were 13.02 ± 4.66 mm/2.68 ± 5.09 mm and 2.88 ± 1.24 mm/0.62 ± 1.45 mm, with afforestation yielding a greater precipitation increase effect. Carbon stock changes were −8.17 ± 1.79 t/ha/–1.59 ± 1.95 t/ha and −2.76 ± 0.99 t/ha/–2.92 ± 1.28 t/ha. Deforestation resulted in greater carbon losses. We found that the combined effects of biophysical mechanisms exert a greater influence than their individual contributions, and evapotranspiration primarily controls water-heat-carbon interactions. Our study demonstrates that careful management of hilly forests and urban areas is crucial for enhancing carbon sequestration and stabilizing the regional climate. Urban planning should focus on identifying priority afforestation areas. While fully considering the water-heat-carbon benefits of forests, it is also necessary to strengthen forest supervision and establish a monitoring network to achieve sustainable development.

ABSTRACT The safe operation and maintenance of urban water supply and drainage systems are crucial for sustainable socio-economic development. Traditional pipeline health inspection methods suffer from complicated operation, high cost, and low efficiency. To tackle these issues, the sewer floating capsule robot (SFCR) is proposed as a new and convenient automated inspection solution. However, sewer pipelines are often narrow, and water flow is rapid, which significantly degrades the quality of SFCR data, leading to issues such as uneven lighting, water vapor fogging, and motion blurring. To address these problems, a computer-based enhanced defect recognition framework (EDR-Fra) is proposed to improve image qualities and defect recognition performance of SFCRs. The framework consists of three core networks: FogClearNet (FoCNet), CheckerboardClearGAN (CCGAN), and YOLOv5. FoCNet employs a dual-branch feature fusion module, integrating channel-level and global-level high-order features to effectively eliminate water vapor fogging influence on images. CCGAN is built on the architecture of generative adversarial networks (GANs), where the generator produces deblurred images that are then fed to the discriminator for quality evaluation. YOLOv5 is employed to identify and localize various types of sewer defects (i.e. crack, break, and deformation). Experimental results on the SFCRs dataset show that FoCNet improves the image peak signal-to-noise ratio (PSNR) by 24.04 and structural similarity (SSIM) by 0.271. CCGAN improves PSNR by 6.33 and SSIM by 0.066. After image enhancement, the defect recognition performance of YOLOv5 increases nearly 12% in mean average precision (mAP) at the speed of 113.12 fps. These results demonstrate that the proposed framework EDR-Fra is a promising tool for efficient and low-cost defect detection in urban underground sewer pipelines.

ABSTRACT The evolution of open-pit coal mining over several decades has encompassed two distinct stages: resource exploitation and ecological restoration. Each phase has led to significant changes in surface coverage and elevation, accompanied by distinct patterns of surface deformation. Reconstructing deformation characteristics across both mining and restoration periods, analyzing the underlying mechanisms, and validating results are crucial for understanding the surface evolution. This study examines post-restoration deformation characteristics using archived Synthetic Aperture Radar (SAR) data and Intermittent Small Baseline Subset-Interferometric Synthetic Aperture Radar (ISBAS-InSAR) techniques. Non-negative Matrix Factorization (NMF) is then applied to decompose deformation signals and analyze the two-stage deformation mechanisms. Lastly, validation is performed through comparisons with differential Digital Elevation Models (DEM) and optical imagery acquired before and during the open-pit mining phase. The Emma mining area in Spain was selected as the study site. Sentinel-1 SAR imagery from 2017 to 2024 reveals vertical deformation rates of up to 21.6 cm/year. The two components derived from NMF correspond to long-term subsidence due to historical mining and short-term deformation resulting from slope restoration. The first NMF component is validated using differential DEM (2009–2020), revealing a positive correlation between deformation magnitude and backfill thickness. The second component is supported by optical imagery from 2015 to 2016, indicating that large-scale slope modification during ecological restoration contributed to short-term deformation. This study presents a quantitative framework for analyzing mining-induced deformation and assessing the effects of ecological restoration on terrain stability.

ABSTRACT 3D line segments not only enable lightweight representation of large-scale building point clouds but also contribute to enhanced contour accuracy in models. Moreover, they play an essential role in structural feature extraction, multimodal data registration, and scene semantic understanding. However, current 3D line segment extraction techniques still face challenges such as low accuracy, significant omissions, and difficulty in parameter selection. To address these issues, we propose a 3D line segment extraction workflow for architectural facades based on a neighbor weighted local centroid (NWLC) and a slicing strategy. Specifically, an adaptive centroid displacement amplification module based on NWLC is designed to achieve automated, robust, and complete contour point extraction. Subsequently, point cloud slicing combined with label connected component (LCC) analysis is employed to cluster contour points into line segment units. Finally, an inlier-outlier projection strategy is introduced to generate and optimize 3D line segments under architectural geometric regularization constraints. Extensive qualitative and quantitative evaluations are conducted on both public datasets–collected via TLS, MLS, ALS, and BIM–and self-acquired datasets. The results demonstrate that both the proposed contour point extraction and 3D line segment extraction algorithm outperform competing methods in terms of precision, robustness, and efficiency.

ABSTRACT Long time series impervious surface mapping (ISM) is important for understanding urban expansion, environmental impacts, and urban planning. There are some historical global ISM products, such as GAIA and NUACI datasets, whereas they may not meet the user’s diverse application needs in the aspects of mapping timeliness, temporal resolution, and spatial resolution. Therefore, this study proposes an automatic, rapid, and continuous impervious surface mapping and updating framework based on historical land cover datasets without using other labeled data, to improve the updating speed and spatio-temporal resolution of impervious surface maps. The main process is divided into three steps: (1) Multi-temporal samples for classification were obtained by using GAIA dataset, FROM-GLC dataset and the unsupervised continuous change detection (CCD) algorithm; (2) Quarterly long time series ISM results (ISMs) were obtained by using multi-temporal samples and quarterly features; (3) The final results were obtained by using the post-processing operations in the obtained quarterly long time series ISMs to improve the mapping accuracy. The proposed framework is applied to eight cities around the world, and the total overall accuracy (OA) and Kappa of long time series ISMs with post-processing in the eight cities are 92.64% and 0.8525, respectively, improving the OA and Kappa of those without post-processing by 1.41% and 0.0281, respectively, and those of GAIA dataset by 4.57% and 0.0914, respectively, which proved the effectiveness of the proposed method. This study also analyzed the spatial patterns of impervious surface expansion in eight cities and identified different spatial patterns of expansion that existed among the cities, while capturing the abrupt change in the spatial patterns of expansion in Rosario and Novosibirsk after the second quarter of 2021. The proposed framework achieved rapid mapping and updating of impervious surface without any labeled samples, and has the potential to map the global impervious surface continuously.

ABSTRACT Seafloor observation based on multi-beam echo sounder (MBES) backscatter strength (BS) image has become increasingly important in guiding the management of marine ecosystems. However, the application has been limited by radiometric distortion. Currently, existing methods that rely on a single characteristic cannot reveal the intrinsic illumination and albedo components of BS images, resulting in poor radiometric correction performance. To this end, this paper proposes a correction method based on the variational Retinex framework that integrates multi-prior information to decompose an observed BS image into the separated seafloor albedo component and the acoustic illumination component. The albedo component corresponds to the radiometric distortion-free data. Firstly, we review the MBES BS observation model and analyze the multi-sector observation mode. Then, by modeling the angular response (AR) effect and incorporating weighted geomorphological smoothness and low-rank priors as beam pattern constraints, we model the acoustic illumination constraints; by introducing the weighted anisotropic total variation (WATV) as a geomorphology constraint and incorporating it with the sediment information term, we model the seafloor albedo constraints. By jointly considering these constraints, we build a decomposition model with well-structured priors in this paper. Both real and simulated experiments have verified the effectiveness of the proposed method.

ABSTRACT As building structures grow increasingly complex and demands for indoor navigation rise rapidly, representing dynamic indoor environments has become an urgent necessity for indoor path planning. Nevertheless, the majority of existing indoor data models still lack the capacity to depict the changing elements of indoor objects. In this paper, a hybrid data model (NRDM) that combines a node-relation graph (NRG) model and raster map is proposed to represent the temporal information of indoor objects. The spatial, attribute, and semantic information are extracted from a building information model (BIM) to define the subspaces and construct the NRDM. Meanwhile, a door-to-door (D2D) D* Lite algorithm is also proposed to plan the optimal path in a 2D/2.5D dynamic indoor environment for the humanoid robot with the semantic information derived from the BIM. The NRDM and D2D D* Lite algorithm were tested using two datasets (data from a single-story residential building (Dataset 1) and a multi-story office building (Dataset 2)) under two scenarios (door state changes (S1) and indoor fire propagation (S2)). The experimental results show that the NRDM can effectively represent dynamic information in an indoor space. The path lengths obtained by the D2D D*Lite algorithm using Dataset 1 under S1 and S2 are 49.87 m and 27.62 m respectively, and those obtained using Dataset 2 are 93.96 m and 38.73 m respectively. Although the lengths of the paths are longer than those of the two comparative algorithms D* Lite and LPA* in most cases, the paths obtained by D2D D*Lite algorithm can effectively avoid and stay away from obstacles, making the paths safer.

ABSTRACT Satellite aerosol products provide valuable large-scale atmospheric information for environment and climate research. Nevertheless, limitations due to cloud contamination and retrieval assumptions often result in significant gaps in Aerosol Optical Depth (AOD) observations, diminishing their representativeness and utility. Therefore, we propose an adaptive spatiotemporal reconstruction method (Spatio-Temporal Reconstruction with Ecw and Auds Method, STREAM) based solely on a single data source, which integrates Empirical Correlation Weighting (ECW) for interpolation with Adaptive Up/Down Scaling (AUDS) for seamless reconstruction. This method was applied to Moderate Resolution Imaging Spectroradiometer (MODIS) Deep Blue (DB) AOD over the North China Plain (NCP) from 2002 to 2023 at a 0.05° resolution. Case comparisons demonstrate that STREAM efficiently fills data gaps, and the STREAM AOD presents strong concordance with both the DB AOD and reference datasets. Cross-validation indicates that as the missing rate rises, the correlation (R) between the STREAM AOD and the DB AOD decreases, while Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) increase. Validation against AERONET data shows that STREAM AOD achieves an R value of 0.88, RMSE of 0.29, and MAE of 0.18 for STREAM AOD, with 52.39% of the data falling within the expected error range. Compared to Long-term Gap-free High-resolution Air Pollutants (LGHAP) AOD, our approach reveals minor discrepancies in values and spatial distribution despite relying on a single data source. The robust performance of STREAM AOD in the NCP highlights potential applicability to utilize in broader regions as well as other atmospheric remote sensing products.