Peipei He

As core infrastructure of power transmission networks, power towers require high-precision 3D models, which are critical for intelligent inspection and digital twin applications of power transmission lines. Traditional reconstruction methods, such as LiDAR scanning and oblique photogrammetry, suffer from issues including high operational risks, low modeling efficiency, and loss of fine details. To address these limitations, this paper proposes a 3D Gaussian Splatting (3DGS)-based method for power tower 3D reconstruction to enhance reconstruction efficiency and detail preservation capability. First, a multi-view data acquisition scheme combining “unmanned aerial vehicle + oblique photogrammetry” was designed to capture RGB images acquired by Unmanned Aerial Vehicle (UAV) platforms, which are used as the primary input for 3D reconstruction. Second, a sparse point cloud was generated via Structure from Motion. Finally, based on 3DGS, Gaussian model initialization, differentiable rendering, and adaptive density control were performed to produce high-precision 3D models of power towers. Taking two typical power tower types as experimental subjects, comparisons were made with the oblique photogrammetry + ContextCapture method. Experimental results demonstrate that 3DGS not only achieves high model completeness (with the reconstructed model nearly indistinguishable from the original images) but also excels in preserving fine details such as angle steels and cables. Additionally, the final modeling time is reduced by over 70% compared to traditional oblique photogrammetry. 3DGS enables efficient and high-precision reconstruction of power tower 3D models, providing a reliable technical foundation for digital twin applications in power transmission lines. By significantly improving reconstruction efficiency and reducing operational costs, the proposed method supports sustainable power infrastructure inspection, asset lifecycle management, and energy-efficient digital twin applications.

Accurate prediction of precipitable water vapor (PWV) is of great significance in meteorological applications. Global Navigation Satellite System (GNSS) is a widely used technique to obtain PWV data. However, many regions still suffer from sparse station coverage, with only a single station available in some cases. This study proposes a multichannel CNN–LSTM model designed for a single-station scenario by integrating key meteorological variables, including surface pressure, weighted mean temperature, and zenith wet delay, using a 5-day historical input sequence. Compared to the widely used Global Forecast System (GFS) and classical LSTM model, the CNN–LSTM model achieved superior performance, with an MAE of 0.694 mm, an RMS of 0.789 mm, and a correlation coefficient of 0.997. This indicates 69.8% reductions in MAE and 68.6% reductions in RMS relative to GFS, and a slight reduction in MAE along with a 20.8% reduction in RMS compared to LSTM. The subsequent seasonal and weather-specific analyses reveal the high accuracy in winter with 0.443-mm MAE and 0.580-mm RMS, and under clear skies with 0.708-mm MAE and 0.769-mm RMS. Performance declined during summer and rainfall periods due to heightened atmospheric instability and rapid PWV variations. Nevertheless, the developed CNN-LSTM model maintains robust prediction capability across all conditions, demonstrating the benefit of integrating meteorological features for PWV prediction in effectively data‑scarce or data-sparse regions.

Hyperspectral image classification (HSIC) represents a significant area of research within the domain of remote sensing. Given the intricate nature of hyperspectral images and the substantial volume of data they generate, it is essential to introduce innovative methodologies to effectively address the data pre-processing challenges encountered in HSIC. In this paper, we draw inspiration from the Segment Anything Model (SAM) within the realm of large language models to propose its application for HSIC, aiming to achieve significant advancements and breakthroughs in this field. Initially, we constructed the SAM and labeled a limited number of samples as segmentation prompts for the model. We conducted HSIC experiments utilizing three publicly available hyperspectral image datasets: Indian Pines (IP), Salinas (SA), and Pavia University (PU). Furthermore, a voting strategy was implemented during these experiments, with only five samples selected from each land type. The classification results obtained from the SAM-based hyperspectral images were compared with those derived from eight distinct machine learning, deep learning, and Transformer models. The findings indicate that the SAM requires only a limited number of samples to effectively perform hyperspectral image classification, achieving higher accuracy than the other models discussed in this paper. Building on this foundation, a voting strategy was implemented, leading to significant enhancements in the overall accuracy (OA) of HSIC across three datasets. The improvements were quantified at 66.76%, 74.66%, and 70.53%, respectively, culminating in final accuracies of 80.29%, 90.66%, and 86.51%. In this study, the SAM is utilized for unsupervised classification, thereby reducing the need for sample labeling while attaining effective classification outcomes.

Lakes play a crucial role in regional economic development and ecological construction. The variation in lake water depth has a direct impact on local economic activities, such as agriculture, livestock farming, and fisheries, as well as the stability of hydrological conditions and water ecology. In response to the lack of unified evaluation in the application of remote sensing water-depth estimation models for inland lakes, this study systematically compares the performance of numerical models and machine learning models for water-depth estimation in inland lakes. A machine learning-based water-depth estimation model construction methodology suitable for inland lakes is proposed. This study introduces an innovative approach by integrating machine learning techniques with multispectral remote sensing data, improving the accuracy and applicability of water-depth estimation models for inland lakes. The results show the following: (1) The machine learning models based on random forest (RF), BP neural networks (BP), and AdaBoost demonstrate better performance (R² = 0.88, 0.72, and 0.61; MAE = 0.12 m, 0.24 m, and 0.31 m; RMSE = 0.32 m, 0.48 m, and 0.57 m) compared to the multi-band logarithmic ratio (MLR) model (R² = 0.59; MAE = 0.32 m; RMSE = 0.58 m); (2) the machine learning water-depth estimation model constructed based on this methodology exhibits improved precision (R² = 0.92, 0.89, and 0.80; MAE = 0.11 m, 0.17 m, and 0.25 m; RMSE = 0.25 m, 0.30 m, and 0.41 m). This suggests that the methodology is more suitable for the estimation of water depth in medium- and small-sized lakes; (3) The machine learning model developed in this study, combined with multispectral remote sensing imagery, achieves the accuracy required for the evaluation of water depths for practical water resources. This model enables the rapid acquisition of high-precision underwater three-dimensional topographic maps, providing more accurate and timely hydrological data support for lake water resource management.

As global temperatures rise, the Greenland ice sheet (GrIS) is undergoing accelerating mass loss, with significant implications for sea level rise and climate systems. Using GRACE and GRACE Follow-On (GRACE-FO) RL06 data from April 2002 to May 2023, alongside MARv3.14 regional climate model outputs (ice melting, runoff, rainfall, snowfall, and land surface temperature (LST)), we investigated the drivers of GrIS mass changes. Continuous wavelet transform analysis revealed significant annual signals in all variables except snowfall, with wavelet decomposition showing the largest annual amplitudes for ice melting (58.8 Gt/month) and runoff (44.5 Gt/month), surpassing those of GRACE/GRACE-FO (31.1 Gt/month). Cross-correlation analysis identified ice melting, runoff, rainfall, snowfall, and LST as significantly correlated with GrIS mass changes, with ice melting, runoff, and LST emerging as primary drivers, while snowfall and runoff exerted secondary influences. Temporal lags of 3, 4, 4, 7, and 4 months were observed for ice melting, runoff, rainfall, snowfall, and LST, respectively. These findings highlight the complex interplay of climatic and hydrological processes driving GrIS mass loss.

Due to the high-density coverage of vegetation, the complexity of terrain, and occlusion issues, ground point extraction faces significant challenges. Airborne Light Detection and Ranging (LiDAR) technology plays a crucial role in complex mountainous areas. This article proposes a method for constructing fine terrain in high vegetation coverage areas based on implicit neural representation. This method consists of data preprocessing, multi-scale and multi-feature high-difference point cloud initial filtering, and an upsampling module based on implicit neural representation. Firstly, preprocess the regional point cloud data is preprocessed; then, K-dimensional trees (K-d trees) are used to construct spatial indexes, and spherical neighborhood methods are applied to capture the geometric and physical information of point clouds for multi-feature fusion, enhancing the distinction between terrain and non-terrain elements. Subsequently, a differential model is constructed based on DSM (Digital Surface Model) at different scales, and the elevation variation coefficient is calculated to determine the threshold for extracting the initial set of ground points. Finally, the upsampling module using implicit neural representation is used to finely process the initial ground point set, providing a complete and uniformly dense ground point set for the subsequent construction of fine terrain. To validate the performance of the proposed method, three sets of point cloud data from mountainous terrain with different features are selected as the experimental area. The experimental results indicate that, from a qualitative perspective, the proposed method significantly improves the classification of vegetation, buildings, and roads, with clear boundaries between different types of terrain. From a quantitative perspective, the Type I errors of the three selected regions are 4.3445%, 5.0623%, and 5.9436%, respectively. The Type II errors are 5.7827%, 6.8516%, and 7.3478%, respectively. The overall errors are 5.3361%, 6.4882%, and 6.7168%, respectively. The Kappa coefficients of the measurement areas all exceed 80%, indicating that the proposed method performs well in complex mountainous environments. Provide point cloud data support for the construction of wind and photovoltaic bases in China, reduce potential damage to the ecological environment caused by construction activities, and contribute to the sustainable development of ecology and energy.

Desertification poses a significant threat to dry and semi-arid regions worldwide, including Northeast Iran. This study investigates the impact of future climate and land-use changes on desertification in this region. Six remote sensing indices were selected to model desertification using four machine learning algorithms: Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting Machine (GBM), and Generalized Linear Models (GLM). To enhance the model’s reliability, an ensemble model was employed. Future climate and land-use scenarios were projected using the CNRM-CM6 model and Markov chain analysis, respectively. Results indicate that the RF and SVM models performed best in mapping current desertification patterns. The ensemble model highlights a 2% increase in decertified areas by 2040, primarily in the northwestern regions. The study underscores the importance of land-use change and climate change in driving desertification and emphasizes the need for sustainable land management practices and climate change adaptation strategies to mitigate future impacts.

Evapotranspiration (ET) is a critical component of the hydrological cycle, and it has a decisive impact on the ecosystem balance in arid and semi-arid regions. The Yinchuan Plain, located in the Gobi of Northwest China, has a strong surface ET, which has a significant impact on the regional water resource cycle. However, there is a current lack of high-resolution evapotranspiration datasets and a substantial amount of time is required for long-time series remote sensing evapotranspiration estimation. In order to assess the ET pattern in this region, we obtained the actual ET (ET_a) of the Yinchuan Plain between 1987 and 2020 using the Google Earth Engine (GEE) platform. Specifically, we used Landsat TM+/OLI remote sensing imagery and the GEE Surface Energy Balance Model (geeSEBAL) to analyze the spatial distribution pattern of ET over different seasons. We then reproduced the interannual variation in ET from 1987 to 2020, and statistically analyzed the distribution patterns and contributions of ET with regard to different land use types. The results show that (1) the daily ET_a of the Yinchuan Plain is the highest in the central lake wetland area in spring, with a maximum value of 4.32 mm day⁻¹; in summer, it is concentrated around the croplands and water bodies, with a maximum value of 6.90 mm day⁻¹; in autumn and winter, it is mainly concentrated around the water bodies and impervious areas, with maximum values of 3.93 and 1.56 mm day⁻¹, respectively. (2) From 1987 to 2020, the ET of the Yinchuan Plain showed an obvious upward and downward trend in some areas with significant land use changes, but the overall ET of the region remained relatively stable without dramatic fluctuations. (3) The ET_a values for different land use types in the Yinchuan Plain region are ranked as follows: water body > cultivated land > impervious > grassland > bare land. Our results showed that geeSEBAL is highly applicable in the Yinchuan Plain area. It allows for the accurate and detailed inversion of ET and has great potential for evaluating long-term ET in data-scarce areas due to its low meteorological sensitivity, which facilitates the study of the regional hydrological cycle and water governance.

Given the increasing frequency and severity of floods caused by climate change, there is a pressing requirement for creative ways to improve public comprehension and control of hydrological phenomena. Contemporary technology provides unparalleled possibilities to transform this domain. This project investigates the possibilities for merging gaming engines and digital twins to enhance flood education, data visualization, and interactive monitoring. This study proposes the utilization of immersive digital twins to enhance the comprehension of hydrological and hydraulic systems. The suggested method utilizes game engines to generate dynamic and interactive models that connect raw data to practical insights, enabling a more profound understanding of flood dynamics. This study underscores the wide-ranging usefulness of digital twins in various watersheds by focusing on the development of advanced monitoring systems, the benefits of improved data visualization, and educational outreach. The incorporation of real-time data via IoT technology considerably improves the significance and precision of these virtual models. This novel approach seeks to refashion flood management approaches by cultivating well-informed stakeholders and advocating for effective environmental education, ultimately leading to more resilient and prepared communities. An immersive digital twin of the real world can assist decision-makers technically, psychologically, and mentally by making complex phenomena easier to understand and visualize, thanks to real-time data and simulations that keep the information up-to-date, consequently leading to a more precise and intuitive decision-making process.

Spatiotemporally seamless precipitable water vapor (PWV) maps with high accuracy, spatiotemporal resolution, and continuity are of significance for climatical research. The current frameworks for the PWV maps have predominantly concentrated on fusing PWV derived from ERA5 reanalysis (ERA-PWV) and MODIS near-infrared data (MOD-NIR-PWV), falling short in accuracy. In this study, PWV derived from Global Navigation Satellite Systems (GNSS-PWV) is introduced to produce spatiotemporally PWV maps with improved accuracy. The fusion framework involves two main steps: 1) spatial fusion for producing an initial PWV map with spatiotemporal continuity through spherical cap harmonic analysis; 2) temporal fusion for producing a refined PWV map with high accuracy through residual correction. GNSS-PWV over 188 stations, 0.25°×0.25° ERA-PWV, and 0.05°×0.05° MOD-NIR-PWV over China from 2013 to 2018 are used to produce the daily 0.05°×0.05° PWV maps. The performance is evaluated using out-of-sample data, containing 18 GNSS-PWV and 90 ERA-PWV, and independent reference data, containing radiosonde-derived PWV over 72 stations. When compared to the out-of-sample GNSS-PWV and ERA-PWV, the PWV maps exhibit mean biases of -1.04 and -0.55 mm and RMS of 1.75 and 0.97 mm, respectively. These are equivalent to 8.7% and 32.1% reductions in bias and 25.5% and 49.5% reductions in RMSE relative to MOD-NIR-PWV. When radiosonde-derived PWV is used as the reference, the PWV maps have the mean bias and RMSE of -0.53 and 2.21 mm, respectively, which outperforms ERA-PWV (-0.75 and 2.69 mm). These results indicate the effectiveness of the novel fusion framework in producing seamless PWV maps.