Search Results (668)

Accurate prediction of airport delays under convective weather conditions is essential for effective traffic coordination and improving overall airport efficiency. Traditional methods mainly rely on numerical weather and traffic indicators, but they often fail to capture the spatial distribution of traffic flows within the terminal area. To address this limitation, we propose a novel image-based representation named Multi-Channel Traffic and Weather Scene Image (MTWSI), which maps both meteorological and traffic information onto a two-dimensional airspace grid, thereby preserving spatial relationships. Based on the MTWSI, we develop a delay prediction model named ADLCNN. This model first uses a convolutional neural network to extract deep spatial features from the scene images and then classifies each sample into a delay level. Using real operational data from Guangzhou Baiyun Airport, this paper shows that ADLCNN achieves significantly higher prediction accuracy compared to traditional machine learning methods. The results confirm that MTWSI provides a more accurate representation of real traffic conditions under convective weather. Full article

Synthetic aperture radar (SAR), as an active microwave imaging system, has the capability of all-weather and all-time observation. In response to the challenges of aircraft detection in SAR images due to the complex background interference caused by the continuous scattering of airport buildings and the demand for real-time processing, this paper proposes a YOLOv7-MTI recognition model that combines the attention mechanism and involution. By integrating the MTCN module and involution, performance is enhanced. The Multi-TASP-Conv network (MTCN) module aims to effectively extract low-level semantic and spatial information using a shared lightweight attention gate structure to achieve cross-dimensional interaction between “channels and space” with very few parameters, capturing the dependencies among multiple dimensions and improving feature representation ability. Involution helps the model adaptively adjust the weights of spatial positions through dynamic parameterized convolution kernels, strengthening the discrete strong scattering points specific to aircraft and suppressing the continuous scattering of the background, thereby alleviating the interference of complex backgrounds. Experiments on the SAR-AIRcraft-1.0 dataset, which includes seven categories such as A220, A320/321, A330, ARJ21, Boeing737, Boeing787, and others, show that the mAP and mRecall of YOLOv7-MTI reach 93.51% and 96.45%, respectively, outperforming Faster R-CNN, SSD, YOLOv5, YOLOv7, and YOLOv8. Compared with the basic YOLOv7, mAP is improved by 1.47%, mRecall by 1.64%, and FPS by 8.27%, achieving an effective balance between accuracy and speed, providing research ideas for SAR aircraft recognition. Full article

High-resolution range profile (HRRP) recognition serves as a foundational task in radar automatic target recognition (RATR), enabling robust classification under all-day and all-weather conditions. However, existing approaches often struggle to simultaneously capture the multi-scale spatial dependencies and global spectral relationships inherent in HRRP signals, limiting their effectiveness in complex scenarios. To address these limitations, we propose a novel multi-scale domain perception network tailored for HRRP-based target recognition, called MSDP-Net. MSDP-Net introduces a hybrid spatial–spectral representation learning strategy through a multiple-domain perception HRRP (DP-HRRP) encoder, which integrates multi-head convolutions to extract spatial features across diverse receptive fields, and frequency-aware filtering to enhance critical spectral components. To further enhance feature fusion, we design a hierarchical scale fusion (HSF) branch that employs stacked semantically enhanced scale fusion (SESF) blocks to progressively aggregate information from fine to coarse scales in a bottom-up manner. This architecture enables MSDP-Net to effectively model complex scattering patterns and aspect-dependent variations. Extensive experiments on both simulated and measured datasets demonstrate the superiority of MSDP-Net, achieving 80.75% accuracy on the simulated dataset and 94.42% on the measured dataset, highlighting its robustness and practical applicability. Full article

The sustainable integration of Distributed Energy Resources (DER) with the next-generation distribution networks requires robust, adaptive, and accurate hosting capacity (HC) forecasting. Dynamic Operating Envelopes (DOE) provide real-time constraints for power import/export to the grid, ensuring dynamic DER integration and efficient network operation. However, conventional HC analysis and forecasting approaches struggle to capture temporal dependencies, the impact of DOE constraints on network operation, and uncertainty in DER output. This study introduces a dynamic optimization framework that leverages the benefits of the sensitivity gate of the Sensitivity-Enhanced Recurrent Neural Network (SERNN) forecasting model, Particle Swarm Optimization (PSO), and Bayesian Optimization (BO) for HC forecasting. The PSO determines the optimal weights and biases, and BO fine-tunes hyperparameters of the SERNN forecasting model to minimize the prediction error. This approach dynamically adjusts the import/export of the DER output to the grid by integrating the DOE constraints into the SG-PSO-BO architecture. Performance evaluation on the IEEE-123 test network and a real Australian distribution network demonstrates superior HC forecasting accuracy, with an $R^2$ score of 0.97 and 0.98, Mean Absolute Error (MAE) of 0.21 and 0.16, and Root Mean Square Error (RMSE) of 0.38 and 0.31, respectively. The study shows that the model effectively captures the non-linear and time-sensitive interactions between network parameters, DER variables, and weather information. This study offers valuable insights into advancing dynamic HC forecasting under real-time DOE constraints in sustainable DER integration, contributing to the global transition towards net-zero emissions. Full article

Meteorological satellites play a critical role in weather forecasting, climate monitoring, water resource management, and more. These satellites feature an array of radiative imaging bands, capturing dozens of spectral images that span from visible to infrared. However, the spatial resolution of these bands varies, with images at longer wavelengths typically exhibiting lower spatial resolutions, which limits the accuracy and reliability of subsequent applications. To alleviate this issue, we propose a channel–spatial attention-based network, named CSAN, designed to super-resolve all low-resolution (LR) bands to the available maximal high-resolution (HR) scale. The CSAN consists of an information fusion unit, a feature extraction module, and an image restoration unit. The information fusion unit adaptively fuses LR and HR images, effectively capturing inter-band spectral relationships and spatial details to enhance the input representation. The feature extraction module integrates channel and spatial attention into the residual network, enabling the extraction of informative spectral and spatial features from the fused inputs. Using these deep features, the image restoration unit reconstructs the missing spatial details in LR images. Extensive experiments demonstrate that the proposed network outperforms other state-of-the-art approaches quantitatively and visually. Full article

The agricultural sector faces significant sustainability, productivity, and environmental impact challenges. In this context, geographic information systems (GISs) have become a key tool to optimize resource management and make informed decisions based on spatial data. These data support planning the best cotton planting and harvest dates based on agroclimatic conditions, such as temperature, precipitation, and soil type, as well as identifying areas with a lower risk of water or thermal stress. As a result, cotton productivity is optimized, and costs associated with supplementary irrigation or losses due to adverse conditions are reduced. However, data from automatic weather stations in Mexico are scarce and incomplete. Instead, grid meteorological databases (DMM, in Spanish) were used with daily temperature and precipitation data from 1983 to 2020 to determine the heat units (HUs) for each cotton crop development stage; daily and accumulated HU; minimum, mean, and maximum temperatures; and mean annual precipitation. This information was used to determine areas that comply with environmental, geographic, and regulatory conditions (NOM-059-SEMARNAT-2010, NOM-026-SAG/FITO-2014) to delimit areas with agricultural potential for planting genetically modified (GM) cotton. The methodology made it possible to produce thirty-four maps at a 1:250,000 scale and a digital GIS with 95% accuracy. These maps indicate whether a given agricultural parcel is optimal for cultivating GM cotton. Full article

Precisely predicting photovoltaic (PV) output is crucial for reliable grid integration; so far, most models rely on site-specific sensor data or treat large meteorological datasets as black boxes. This study proposes an explainable machine-learning framework that simultaneously ranks the most informative weather parameters and reveals their physical relevance to PV generation. Starting from 27 local and plant-level variables recorded at 15 min resolution for a 1 MW array in Çanakkale region, Türkiye (1 August 2022–3 August 2024), we apply a three-stage feature-selection pipeline: (i) variance filtering, (ii) hierarchical correlation clustering with Ward linkage, and (iii) a meta-heuristic optimizer that maximizes a neural-network R² while penalizing poor or redundant inputs. The resulting subset, dominated by apparent temperature and diffuse, direct, global-tilted, and terrestrial irradiance, reduces dimensionality without significantly degrading accuracy. Feature importance is then quantified through two complementary aspects: (a) tree-based permutation scores extracted from a set of ensemble models and (b) information gain computed over random feature combinations. Both views converge on shortwave, direct, and global-tilted irradiance as the primary drivers of active power. Using only the selected features, the best model attains an average R² ≅ 0.91 on unseen data. By utilizing transparent feature-reduction techniques and explainable importance metrics, the proposed approach delivers compact, more generalized, and reliable PV forecasts that generalize to sites lacking embedded sensor networks, and it provides actionable insights for plant siting, sensor prioritization, and grid-operation strategies. Full article

Understanding and mapping forest fire vulnerability is essential for informed landscape management and disaster risk reduction, especially in the context of increasing anthropogenic and climatic pressures. This study aims to model and spatially predict forest fire vulnerability across Romania using two machine learning algorithms: MaxEnt and XGBoost. We integrated forest fire occurrence data from 2006 to 2024 with a suite of climatic, topographic, ecological, and anthropogenic predictors at a 250 m spatial resolution. MaxEnt, based on presence-only data, achieved moderate predictive performance (AUC = 0.758), while XGBoost, trained on presence–absence data, delivered higher classification accuracy (AUC = 0.988). Both models revealed that the impact of environmental variables on forest fire occurrence is complex and heterogeneous, with the most influential predictors being the Fire Weather Index, forest fuel type, elevation, and distance to human proximity features. The resulting vulnerability and uncertainty maps revealed hotspots in Sub-Carpathian and lowland regions, especially in Mehedinți, Gorj, Dolj, and Olt counties. These patterns reflect historical fire data and highlight the role of transitional agro-forested landscapes. This study delivers a replicable, data-driven approach to wildfire risk modelling, supporting proactive management and emphasising the importance of integrating vulnerability assessments into planning and climate adaptation strategies. Full article

Landslides are among the most destructive natural hazards in the Western Ghats region of Kerala, driven by complex interactions between geological, hydrological, and anthropogenic factors. This study aims to generate a high-resolution Landslide Susceptibility Level Map (LSLM) using a machine learning (ML)-based Random Forest (RF) model integrated with Geographic Information Systems (GIS). A total of 231 historical landslide locations obtained from the Bhukosh portal were used as reference data. Eight predictive factors—Stream Order, Drainage Density, Slope, Aspect, Geology, Land Use/Land Cover (LULC), Normalized Difference Vegetation Index (NDVI), and Moisture Stress Index (MSI)—were derived from remote sensing and ancillary datasets, preprocessed, and reclassified for model input. The RF model was trained and validated using a 50:50 split of landslide and non-landslide points, with variable importance values derived to weight each predictive factor of the raster layer in ArcGIS. The resulting Landslide Susceptibility Index (LSI) was reclassified into five susceptibility zones: Very Low, Low, Moderate, High, and Very High. Results indicate that approximately 17.82% of the study area falls under high to very high susceptibility, predominantly in the steep, weathered, and high rainfall zones of the Western Ghats. Validation using Area Under the Curve–Receiver Operating Characteristic (AUC-ROC) analysis yielded an accuracy of 0.890, demonstrating excellent model performance. The output LSM provides valuable spatial insights for planners, disaster managers, and policymakers, enabling targeted mitigation strategies and sustainable land-use planning in landslide-prone regions. Full article

Thermal simulations of buildings play a critical role in optimizing energy efficiency, thermal comfort, and heating, ventilation and air conditioning (HVAC) systems design. Accurate weather data is essential for reliable simulations, as local weather and climate have a significant impact on energy requirements for space heating and cooling and thermal comfort. This study conducted a literature review regarding the sources, types, and uncertainties of weather data used for thermal simulations of buildings, including typical meteorological years (TMYs) and extreme weather files under current and future climates. Additionally, this paper evaluates methods for weather data processing, including interpolation, downscaling, and synthetic generation, to improve simulation accuracy. Finally, approaches are proposed for constructing weather files for the future and extreme conditions under a changing climate. This review aims to provide a guide for researchers and practitioners to enhance the reliability of thermal modeling through informed construction, selection, and application of weather data. Full article

While space weather indices (e.g., F10.7, Dst index) are commonly employed to characterize ionospheric activity levels, the Global Mean Electron Content (GMEC) provides a more direct and comprehensive indicator of the global ionospheric state. This metric demonstrates greater potential than space weather indices for calibrating empirical ionospheric models such as IRI-2020. The COSMIC-2 constellation enables continuous, all-weather global ionospheric monitoring via radio occultation, unimpeded by land–sea distribution constraints, with over 8000 daily occultation events suitable for GMEC modeling. This study developed two lightweight GMEC models using COSMIC-2 data: (1) a POD GMEC model based on slant TEC (STEC) extracted from Level 1b podTc2 products and (2) a PROF GMEC model derived from vertical TEC (VTEC) calculated from electron density profiles (EDPs) in Level 2 ionPrf products. Both backpropagation neural network (BPNN)-based models generate hourly GMEC outputs as global spatial averages. Critically, GMEC serves as an essential intermediate step that addresses the challenges of utilizing spatially irregular occultation data by compressing COSMIC-2’s ionospheric information into an integrated metric. Building on this compressed representation, we implemented a convolutional neural network (CNN) that incorporates GMEC as an auxiliary feature to calibrate IRI-2020’s global ionospheric maps. This approach enables computationally efficient correction of systemic IRI TEC errors. Experimental results demonstrate (i) 48.5% higher accuracy in POD/PROF GMEC relative to IRI-2020 GMEC estimates, and (ii) the calibrated global IRI TEC model (designated GCIRI TEC) reduces errors by 50.15% during geomagnetically quiet periods and 28.5% during geomagnetic storms compared to the original IRI model. Full article

In recent years, the world has seen a significant increase in extreme weather events, such as floods, hurricanes, and storms, which have caused extensive damage to infrastructure and communities. These events result from natural phenomena and human-induced factors, including climate change and natural climate variations. For instance, the floods in Europe in 2024 and the hurricanes in the United States have highlighted the vulnerability of urban and rural areas. These extreme events are often unpredictable and pose considerable challenges for spatial planning and risk management. This study explores an innovative approach that employs machine learning and Markov chains to enhance spatial planning and predict flood risk areas. By utilizing data such as weather records, land use and land cover (LULC) information, topographic LIDAR data, and advanced predictive models, the study aims to identify the most vulnerable areas and provide recommendations for risk mitigation. The results indicate that integrating these technologies can improve forecasting accuracy, thereby supporting more informed decisions in land management. Given the effects of climate change and the increasing frequency of extreme events, adopting advanced forecasting and planning tools is crucial for protecting communities and reducing economic and social damage. This method was applied to the Calopinace area, also known as the Calopinace River or Fiumara della Cartiera, which crosses Reggio Calabria and is notorious for its historical floods. It can serve as part of an early warning system, enabling alerts to be issued throughout the monitored area. Furthermore, it can be integrated into existing emergency protocols, thereby enhancing the effectiveness of disaster response. Future research could investigate incorporating additional data and AI techniques to improve accuracy. Full article

To address the challenge of insufficient spatial resolution in remote sensing precipitation data, this paper proposes a novel Multi-Scale Residual Generative Adversarial Network (MSRGAN) for reconstructing high-resolution precipitation images. The model integrates multi-source meteorological information and topographic priors, and it employs a Deep Multi-Scale Perception Module (DeepInception), a Multi-Scale Feature Modulation Module (MSFM), and a Spatial-Channel Attention Network (SCAN) to achieve high-fidelity restoration of complex precipitation structures. Experiments conducted using Weather Research and Forecasting (WRF) simulation data over the continental United States demonstrate that MSRGAN outperforms traditional interpolation methods and state-of-the-art deep learning models across various metrics, including Critical Success Index (CSI), Heidke Skill Score (HSS), False Alarm Rate (FAR), and Jensen–Shannon divergence. Notably, it exhibits significant advantages in detecting heavy precipitation events. Ablation studies further validate the effectiveness of each module. The results indicate that MSRGAN not only improves the accuracy of precipitation downscaling but also preserves spatial structural consistency and physical plausibility, offering a novel technological approach for urban flood warning, weather forecasting, and regional hydrological modeling. Full article

In addition to the use of reference instruments, low-cost sensors (LCSs) are becoming increasingly popular for air quality monitoring both indoors and outdoors. These sensors provide real-time measurements of pollutants and facilitate better spatial and temporal coverage. However, these simpler devices are typically characterised by lower accuracy and precision and can be more sensitive to the environmental conditions than the reference instruments. It is therefore crucial to characterise the applicability and limitations of these instruments, for which a possible solution is their comparison with reference measurements in real-world conditions. To this end, a measurement campaign has been carried out to evaluate the PM_2.5 readings of several low- and medium-cost air quality instruments of different types and categories (IQAir AirVisual Pro, TSI DustTrak™ II Aerosol Monitor 8532, Xiaomi Mijia Air Detector, and Xiaomi Smartmi PM_2.5 Air Detector). A GRIMM EDM180 instrument was used as the reference. This campaign took place in Budapest, Hungary, from 12 November to 15 December 2020, during typically humid and foggy weather conditions, when the air pollution level was high due to the increased anthropogenic emissions, including wood burning for heating purposes. The results indicate that the individual sensors tracked the dynamics of PM_2.5 concentration changes well (in a linear fashion), but the readings deviated from the reference measurements to varying degrees. Even though the AirVisual sensors performed generally well (0.85 < R² < 0.93), the accuracy of the units showed inconsistency (13–93%) with typical overestimation, and their readings were significantly affected by elevated relative humidity levels and by temperature. Despite the overall overestimation of PM_2.5 by the Xiaomi sensors, they also exhibited strong correlation coefficients with the reference, with R² values of 0.88 and 0.94. TSI sensors exhibited slight underestimations with high explained variance (R² = 0.93–0.94) and good accuracy. The results indicated that despite the inherent bias, the low-cost sensors are capable of capturing the temporal variability of PM_2.5, thus providing relevant information. After simple and multiple linear regression-based correction, the low-cost sensors provided acceptable results. The results indicate that sensor data correction is a necessary prerequisite for the usability of the instruments. The ensemble method is a reasonable alternative for more accurate estimations of PM_2.5. Full article

Time series forecasting is critical for decision-making in numerous domains, yet achieving high accuracy across both short-term and long-term horizons remains challenging. In this paper, we propose a general hybrid forecasting framework that integrates a traditional statistical model (ARIMA) with modern deep learning models (such as LSTM and Transformer). The core of our approach is a novel multi-scale prediction mechanism that combines the strengths of both model types to better capture short-range patterns and long-range dependencies. We design a dual-stage forecasting process, where a classical time series component first models transparent linear trends and seasonal patterns, and a deep neural network then learns complex nonlinear residuals and long-term contexts. The two outputs are fused through an adaptive mechanism to produce the final prediction. We evaluate the proposed framework on eight public datasets (electricity, exchange rate, weather, traffic, illness, ETTh1/2, and ETTm1/2) covering diverse domains and scales. The experimental results show that our hybrid method consistently outperforms stand-alone models (ARIMA, LSTM, and Transformer) and recent, specialized forecasters (Informer and Autoformer) in both short-horizon and long-horizon forecasts. An ablation study further demonstrates the contribution of each module in the framework. The proposed approach not only achieves state-of-the-art accuracy across varied time series but also offers improved interpretability and robustness, suggesting a promising direction for combining statistical and deep learning techniques in time series forecasting. Full article