Search Results (121)

We present the results of a Ground-Penetrating Radar (GPR) survey conducted at the archaeological site of Bisya and Salūt (Sultanate of Oman), aimed at assessing archaeological risk associated with the planned infrastructural development of the site. The survey employed a dual-frequency GPR system with a survey rugged cart to adapt to the varying conditions of the area. The survey was designed around a scale-adaptive grid strategy, across three sectors, combining medium- and low-definition acquisitions over broader areas to identify zones with low archaeological potential, with a high-density grid near previously excavated structures. Data interpretation was integrated with Geographic Information System (GIS)-based spatial mapping, allowing the definition of a parametric risk indicator for subsurface archaeological potential derived from radar facies characterisation and point-by-point anomaly analysis along GPR profiles. Within the area of higher density, the method successfully mapped buried alignments suggestive of anthropogenic features. The results confirmed the effectiveness of GPR as a predictive tool for archaeological prospection, particularly when combined with spatial analysis. Overall, this study highlights the feasibility of incorporating non-invasive methods into heritage protection strategies, contributing to the sustainable development and planning of archaeological landscapes. Full article

Maritime safety, environmental protection, and efficient traffic management increasingly rely on data-driven technologies. However, leveraging Automatic Identification System (AIS) data for predictive modelling faces two major challenges: the massive volume of data generated in real-time and growing privacy concerns associated with proprietary vessel information. This paper proposes a novel, privacy-preserving framework for vessel traffic density (VTD) prediction that addresses both challenges. The approach combines the European Maritime Observation and Data Network’s (EMODNet) grid-based VTD calculation method with Convolutional Neural Networks (CNN) to model spatiotemporal traffic patterns and employs Federated Learning to collaboratively build a global predictive model without the need for explicit sharing of proprietary AIS data. Three geographically diverse AIS datasets were harmonized, processed, and used to train local CNN models on hourly VTD matrices. These models were then aggregated via a Federated Learning framework under a lifelong learning scenario. Evaluation using Sparse Mean Squared Error shows that the federated global model achieves promising accuracy in sparse data scenarios and maintains performance parity when compared with local CNN-based models, all while preserving data privacy and minimizing hardware performance needs and data communication overheads. The results highlight the approach’s effectiveness and scalability for real-world maritime applications in traffic forecasting, safety, and operational planning. Full article

With the significant increase in solar power generation’s proportion in power systems, the uncertainty of its power output poses increasingly severe challenges to grid operation. In recent years, solar forecasting models have achieved remarkable progress, with various developed models each exhibiting distinct advantages and characteristics. To address complex and variable geographical and meteorological conditions, it is necessary to adopt a multi-model fusion approach to leverage the strengths and adaptability of individual models. This paper proposes a photovoltaic power prediction framework based on multi-stage ensemble learning, which enhances prediction robustness by integrating the complementary advantages of heterogeneous models. The framework employs a three-level optimization architecture: first, a recursive feature elimination (RFE) algorithm based on LightGBM–XGBoost–MLP weighted scoring is used to screen high-discriminative features; second, mutual information and hierarchical clustering are utilized to construct a heterogeneous model pool, enabling competitive intra-group and complementary inter-group model selection; finally, the traditional static weighting strategy is improved by concatenating multi-model prediction results with real-time meteorological data to establish a time-period-based dynamic weight optimization module. The performance of the proposed framework was validated across multiple dimensions—including feature selection, model screening, dynamic integration, and comprehensive performance—using measured data from a 75 MW photovoltaic power plant in Inner Mongolia and the open-source dataset PVOD. Full article

Surrogate models are widely recognized as effective, data-driven predictive tools for storm surge risk assessment. For such applications, surrogate models (referenced also as emulators or metamodels) are typically developed using existing databases of synthetic storm simulations, and once calibrated can provide fast-to-compute approximations of the storm surge for a variety of downstream analyses. The storm surge predictions need to be established for different geographic locations of interest, typically corresponding to the computational nodes of the original numerical model. A number of inland nodes will remain dry for some of the database storm scenarios, requiring an imputation for them to estimate the so-called pseudo-surge in support of the surrogate model development. Past work has examined the adoption of kNN (k-nearest neighbor) spatial interpolation for this imputation. The enhancement of kNN with hydraulic connectivity information, using the grid or mesh of the original numerical model, was also previously considered. In this enhancement, neighboring nodes are considered connected only if they are connected within the grid. This work revisits the imputation of peak storm surge within a surrogate modeling context and examines three distinct advancements. First, a response-based correlation concept is considered for the hydraulic connectivity, replacing the previous notion of connectivity using the numerical model grid. Second, a Gaussian Process interpolation (GPI) is examined as alternative spatial imputation strategy, integrating a recently established adaptive covariance tapering scheme for accommodating an efficient implementation for large datasets (large number of nodes). Third, a data completion approach is examined for imputation, treating dry instances as missing data and establishing imputation using probabilistic principal component analysis (PPCA). The combination of spatial imputation with PPCA is also examined. In this instance, spatial imputation is first deployed, followed by PPCA for the nodes that were misclassified in the first stage. Misclassification corresponds to the instances for which imputation provides surge estimates higher than ground elevation, creating the illusion that the node is inundated even though the original predictions correspond to the node being dry. In the illustrative case study, different imputation variants established based on the aforementioned advancements are compared, with comparison metrics corresponding to the predictive accuracy of the surrogate models developed using the imputed databases. Results show that incorporating hydraulic connectivity based on response similarity into kNN enhances the predictive performance, that GPI provides a competitive (to kNN) spatial interpolation approach, and that the combination of data completion and spatial interpolation emerges as the recommended approach. Full article

With the accelerating global energy transition, wind power has become a core pillar of renewable energy systems. However, its inherent intermittency and volatility pose significant challenges to the safe, stable, and economical operation of power grids—making ultra-short-term wind power prediction a critical technical link in optimizing grid scheduling and promoting large-scale wind power integration. Current forecasting techniques are plagued by problems like the inadequate representation of features, the poor separation of features, and the challenging clarity of deep learning models. This study introduces a method for the prediction of wind energy using spatiotemporal contrastive learning, employing seasonal trend decomposition to encapsulate the diverse characteristics of time series. A contrastive learning framework and a feature disentanglement loss function are employed to effectively decouple spatiotemporal features. Data on geographical positions are integrated to simulate spatial correlations, and a convolutional network of spatiotemporal graphs, integrated with a multi-head attention system, is crafted to improve the clarity. The proposed method is validated using operational data from two actual wind farms in Northwestern China. The research indicates that, compared with typical baselines (e.g., STGCN), this method reduces the RMSE by up to 38.47% and the MAE by up to 44.71% for ultra-short-term wind power prediction, markedly enhancing the prediction precision and offering a more efficient way to forecast wind power. Full article

Recent approaches to geo-referencing X posts have focused on the use of language modelling techniques that learn geographic region-specific language and use this to infer geographic coordinates from text. These approaches rely on large amounts of labelled data to build accurate predictive models. However, obtaining significant volumes of geo-referenced data from Twitter, recently renamed X, can be difficult. Further, existing language modelling approaches can require the division of a given area into a grid or set of clusters, which can be dataset-specific and challenging for location prediction at a fine-grained level. Regression-based approaches in combination with deep learning address some of these challenges as they can assign coordinates directly without the need for clustering or grid-based methods. However, such approaches have received only limited attention for the geo-referencing task. In this paper, we adapt state-of-the-art neural network models for the regression task, focusing on geo-referencing wildlife Tweets where there is a limited amount of data. We experiment with different transfer learning techniques for improving the performance of the regression models, and we also compare our approach to recently developed Large Language Models and prompting techniques. We show that using a location names extraction method in combination with regression-based disambiguation, and purely regression when names are absent, leads to significant improvements in locational accuracy over using only regression. Full article

Aiming at the problem of accuracy degradation caused by the mixing of spatiotemporal disturbance patterns in sound speed profile (SSP) inversion using the traditional geographic grid division method, this study proposes an acoustic stability pre-clustering framework that integrates principal component analysis and machine learning clustering. Disturbance mode principal component analysis is first used to extract characteristic parameters, and then a machine learning clustering algorithm is adopted to pre-classify SSP samples according to acoustic stability. The SSP inversion experimental results show that: (1) the SSP samples of the South China Sea can be divided into three clusters of disturbance modes with statistically significant differences. (2) The regression inversion method based on cluster attribution reduces the average error of SSP inversion for data from 2018 to 1.24 m/s, which is more than 50% lower than what can be achieved with the traditional method without pre-clustering. (3) Transmission loss prediction verification shows that the proposed method can produce highly accurate sound field calculations in environmental assessment tasks. The acoustic stability pre-clustering technology proposed in this study provides an innovative solution for the statistical modeling of marine environment parameters by effectively decoupling the mixed effect of SSP spatiotemporal disturbance patterns. Its error control level (<1.5 m/s) is 37% higher than that of the single empirical orthogonal function regression method, showing important potential in underwater acoustic applications in complex marine dynamic environments. Full article

Communication delay, as a key factor restricting the rapid and accurate transmission of data in the smart grid, will affect the collaborative operation of power electronic devices represented by the Distributed Power Flow Controller (DPFC), and further affect the construction and safe and stable operation of the new power system. Aiming at the problem of DPFC communication delay prediction, this paper proposes a new SAR-ARIMA-LSTM hybrid prediction model. This model introduces the spatial autoregressive model (SAR) on the basis of the traditional ARIMA-LSTM model to extract the spatial correlation between devices caused by geographical location and communication load, and then combines ARIMA-LSTM prediction. The experimental structure shows that compared with the traditional ARIMA-LSTM model, the model proposed in this paper predicts that RMSE decreases from 1.59 to 1.2791 and MAE decreases from 1.27 to 1.0811, with a reduction of more than 14%. The method proposed in this paper can effectively reduce the communication delay prediction data of DPFC at different spatial positions, has a stronger ability to handle high-delay fluctuations, and provides a new technical approach for improving the reliability of the power grid communication network. Full article

With a potentially increasing share of the electricity grid relying on wind to provide generating capacity and energy, there is an expanding global need for historically accurate, spatiotemporally continuous, high-resolution wind data. Conventional downscaling methods for generating these data based on numerical weather prediction have a high computational burden and require extensive tuning for historical accuracy. In this work, we present a novel deep learning-based spatiotemporal downscaling method using generative adversarial networks (GANs) for generating historically accurate high-resolution wind resource data from the European Centre for Medium-Range Weather Forecasting Reanalysis version 5 data (ERA5). In contrast to previous approaches, which used coarsened high-resolution data as low-resolution training data, we use true low-resolution simulation outputs. We show that by training a GAN model with ERA5 as the low-resolution input and Wind Integration National Dataset Toolkit (WTK) data as the high-resolution target, we achieved results comparable in historical accuracy and spatiotemporal variability to conventional dynamical downscaling. This GAN-based downscaling method additionally reduces computational costs over dynamical downscaling by two orders of magnitude. We applied this approach to downscale 30 km, hourly ERA5 data to 2 km, 5 min wind data for January 2000 through December 2023 at multiple hub heights over Ukraine, Moldova, and part of Romania. With WTK coverage limited to North America from 2007–2013, this is a significant spatiotemporal generalization. The geographic extent centered on Ukraine was motivated by stakeholders and energy-planning needs to rebuild the Ukrainian power grid in a decentralized manner. This 24-year data record is the first member of the super-resolution for renewable energy resource data with wind from the reanalysis data dataset (Sup3rWind). Full article

The widespread adoption of electric vehicles introduces significant challenges to power grid stability due to uncoordinated large-scale charging and discharging behaviors. By addressing these challenges, mobile energy storage systems emerge as a flexible resource. To maximize the synergistic potential of jointly scheduling electric vehicles and mobile energy storage systems, this study develops a collaborative scheduling model incorporating the prediction of geographically and chronologically varying distributions of electric vehicles. Non-dominated sorting genetic algorithm-III is then applied to solve this model. Validation through case studies, conducted on the IEEE-69 bus system and an actual urban road network in southern China, demonstrates the model’s efficacy. Case studies reveal that compared to the initial disordered state, the optimized strategy yields a 122.6% increase in profits of the electric vehicle charging station operator, a 44.7% reduction in costs to the electric vehicle user, and a 62.5% decrease in voltage deviation. Furthermore, non-dominated sorting genetic algorithm-III exhibits superior comprehensive performance in multi-objective optimization when benchmarked against two alternative algorithms. Full article

Accurate real-time icing grid fields are critical for preventing ice-related disasters during winter and protecting property. These fields are essential for both mapping ice distribution and predicting icing using physical models combined with numerical weather prediction systems. However, developing precise real-time icing grids is challenging due to the uneven distribution of monitoring stations, data confidentiality restrictions, and the limitations of existing interpolation methods. In this study, we propose a new approach for constructing real-time icing grid fields using 1339 online terminal monitoring datasets provided by the China Southern Power Grid Research Institute Co., Ltd. (CSPGRI) during the winter of 2023. Our method integrates static geographic information, dynamic meteorological factors, and ice_kriging values derived from parameter-optimized Empirical Bayesian Kriging Interpolation (EBKI) to create a spatiotemporally matched, multi-source fused icing thickness grid dataset. We applied five machine learning algorithms—Random Forest, XGBoost, LightGBM, Stacking, and Convolutional Neural Network Transformers (CNNT)—and evaluated their performance using six metrics: R, RMSE, CSI, MAR, FAR, and fbias, on both validation and testing sets. The stacking model performed best, achieving an R-value of 0.634 (0.893), RMSE of 3.424 mm (2.834 mm), CSI of 0.514 (0.774), MAR of 0.309 (0.091), FAR of 0.332 (0.161), and fbias of 1.034 (1.084), respectively, when comparing predicted icing values with actual measurements on pylons. Additionally, we employed the SHAP model to provide a physical interpretation of the stacking model, confirming the independence of selected features. Meteorological factors such as relative humidity (RH), 10 m wind speed (WS₁₀), 2 m temperature (T₂), and precipitation (PRE) demonstrated a range of positive and negative contributions consistent with the observed growth of icing. Thus, our multi-source remote-sensing data-fusion approach, combined with the stacking model, offers a highly accurate and interpretable solution for generating real-time icing grid fields. Full article

Climate change causes extreme weather events to occur frequently, such as drought, which may exacerbate forest fire regimes; as such, forest fire regimes may be closely related to drought characteristics. The spatial non-stationarity of factors affecting forest fires has not been fully clarified and needs further exploration. This study intends to address how drought characteristics affect forest fire regimes in China and whether spatial non-stationarity can improve the model prediction based on methods such as the run theory and GWR. Our results show that geographically weighted regression models perform better (AICc, AUC, R², RMSE, and MAE) than global regression models in modeling forest fire regimes. Although GWR improves accuracy, small sample sizes (vegetation zones, climatic zones) may affect its accuracy. Drought characteristics significantly affect (p < 0.05) the forest fire regimes, and the correlation is spatially non-static. At the grid scale, a positive correlation between the forest fire occurrence probability and drought characteristics is mostly distributed in the southwest and northwest regions. Our study is conducive to an in-depth understanding of the relationship between forest fire regimes and drought, aiming to provide a scientific basis for the development of forest fire management measures to mitigate drought stress according to local conditions. Full article

Range expansions driven by global warming are increasingly documented, particularly in birds and insects. The House Bunting, a species native to North Africa, has recently established the first confirmed breeding population in mainland Europe in Algeciras, southern Spain. This study presents the results of the first systematic survey of this population, conducted in December 2024. Using a standardized survey method across a grid of hexagonal sampling units, we recorded a minimum of 18 individuals, including juveniles, indicating both successful reproduction and possible new arrivals. Observations were concentrated in low-rise urban areas, mirroring the species’ preferred habitats in Morocco. The presence of individuals with juvenile plumage in December suggests an extended breeding season, which may facilitate population growth. Given the geographical proximity to North Africa and predicted increases in aridity due to climate change, further expansion into Iberia appears likely. Although no immediate ecological impacts have been detected, the potential for interactions with resident species justifies continued monitoring. This study provides a baseline for assessing the establishment and growth of this population, contributing to a broader understanding of how climate change influences species distributions and the colonization dynamics of expanding bird populations. Full article

Accurate renewable energy forecasting is crucial for grid stability and efficient energy management. This study introduces a hybrid model that combines signal decomposition and artificial intelligence to enhance the prediction of solar radiation and wind speed. The framework uses a one-stage decomposition strategy, applying variational mode decomposition and an improved empirical mode decomposition method with adaptive noise. This process effectively extracts meaningful components while reducing background noise, improving data quality, and minimizing uncertainty. The complexity of these components is assessed using entropy-based selection to retain only the most relevant features. The refined data are then fed into advanced predictive models, including a bidirectional neural network for capturing long-term dependencies, an extreme learning machine, and a support vector regression model. These models address nonlinear patterns in the historical data. To optimize forecasting accuracy, outputs from all models are combined using a least-squares regression technique that assigns optimal weights to each prediction. The hybrid model was tested on datasets from three geographically diverse locations, encompassing varying weather conditions. Results show a notable improvement in accuracy, achieving a root mean square error as low as 2.18 and a coefficient of determination near 0.999. Compared to traditional methods, forecasting errors were reduced by up to 30%, demonstrating the model’s effectiveness in supporting sustainable and reliable energy systems. Full article

Air conditioning loads in power systems exhibit spatiotemporal heterogeneity across geographical regions, complicating accurate load forecasting. This study proposes a framework that integrates Deep Reinforcement Learning-guided DBSCAN (DRL-DBSCAN) clustering with a Graph Attention Network (GAT)-based Graph Neural Network to model spatial dependencies and temporal dynamics. Using meteorological features like temperature and humidity, the framework clusters geographical grids and applies GAT to capture spatial patterns. On a Pecan Street dataset of 25 households in Austin, the GAT with DRL-DBSCAN achieves a Test MSE of 0.0216 and MAE of 0.0884, outperforming K-Means (MSE: 0.0523, MAE: 0.1456), Hierarchical clustering (MSE: 0.0478, MAE: 0.1321), no-clustering (MSE: 0.0631, MAE: 0.1678), LSTM (MSE: 0.3259, MAE: 0.3442), Transformer (MSE: 0.6415, MAE: 0.4835), and MLP (MSE: 0.7269, MAE: 0.5240) baselines. This approach enhances forecasting accuracy for real-time grid management and energy efficiency in smart grids, though further refinement is needed for standardizing predicted load ranges. Full article