Search Results (120)

This paper develops a novel modeling framework that integrates time-varying quantile-based spillover effects into a regime-switching realized volatility model. A dynamic spillover factor is constructed by identifying the most influential contributors to Bitcoin’s realized volatility across different quantile levels. This quantile-layered structure enables the model to capture heterogeneous spillover paths under varying market conditions at a macro level while also enhancing the sensitivity of volatility regime identification via its incorporation into a time-varying transition probability (TVTP) Markov-switching mechanism at a micro level. Empirical results based on the cryptocurrency market demonstrate the superior forecasting performance of the proposed TVTP-MS-HAR model relative to standard benchmark models. The model exhibits strong capability in identifying state-dependent spillovers and capturing nonlinear market dynamics. The findings further reveal an asymmetric dual-tail amplification and time-varying interconnectedness in the spillover effects, along with a pronounced asymmetry between market capitalization and systemic importance. Compared to decomposition-based approaches, the X-RV type of models—especially when combined with the proposed quantile-driven factor—offers improved robustness and predictive accuracy in the presence of extreme market behavior. This paper offers a coherent approach that bridges phenomenon identification, source localization, and predictive mechanism construction, contributing to both the academic understanding and practical risk assessment of cryptocurrency markets. Full article

In this paper, the authors introduce the transmuted geometric integer-valued autoregressive model with periodicity, designed specifically to analyze epidemiological and public health time series data. The model uses a transmuted geometric distribution as a marginal distribution of the process. It also captures varying tail behaviors seen in disease case counts and health data. Key statistical properties of the process, such as conditional mean, conditional variance, etc., are derived, along with estimation techniques like conditional least squares and conditional maximum likelihood. The ability to provide k-step-ahead forecasts makes this approach valuable for identifying disease trends and planning interventions. Monte Carlo simulation studies confirm the accuracy and reliability of the estimation methods. The effectiveness of the proposed model is analyzed using three real-world public health datasets: weekly reported cases of Legionnaires’ disease, syphilis, and dengue fever. Full article

Trajectory prediction under multimodal information is critical for autonomous driving, necessitating the integration of dynamic vehicle states and static high-definition (HD) maps to model complex agent–scene interactions effectively. However, existing methods often employ static scene encodings and unstructured latent spaces, limiting their ability to capture evolving spatial contexts and produce diverse yet contextually coherent predictions. To tackle these challenges, we propose MS-SLV, a novel generative framework that introduces (1) a time-aware scene encoder that aligns HD map features with vehicle motion to capture evolving scene semantics and (2) a structured latent model that explicitly disentangles agent-specific intent and scene-level constraints. Additionally, we introduce an auxiliary lane prediction task to provide targeted supervision for scene understanding and improve latent variable learning. Our approach jointly predicts future trajectories and lane sequences, enabling more interpretable and scene-consistent forecasts. Extensive evaluations on the nuScenes dataset demonstrate the effectiveness of MS-SLV, achieving a 12.37% reduction in average displacement error and a 7.67% reduction in final displacement error over state-of-the-art methods. Moreover, MS-SLV significantly improves multi-modal prediction, reducing the top-5 Miss Rate (${\mathrm{MR}}_5$) and top-10 Miss Rate (${\mathrm{MR}}_{10}$) by 26% and 33%, respectively, and lowering the Off-Road Rate (ORR) by 3%, as compared with the strongest baseline in our evaluation. Full article

Regional ecological environmental quality (EEQ) is a vital indicator for environmental management and supporting sustainable development. However, the absence of robust and accurate EEQ prediction models has hindered effective environmental strategies. This study proposes a novel approach to address this gap by integrating the ecological index (EI) model with several predictive models, including autoregressive integrated moving average (ARIMA), convolutional neural network (CNN), long short-term memory (LSTM), and cellular automata (CA), to forecast regional EEQ. Initially, the spatiotemporal evolution of the input data used to calculate the EI score was analyzed. Subsequently, tailored prediction models were developed for each dataset. These models were sequentially trained and validated, and their outputs were integrated into the EI model to enhance the accuracy and coherence of the final EEQ predictions. The novelty of this methodology lies not only in integrating existing predictive models but also in employing an innovative fusion technique that significantly improves prediction accuracy. Despite data quality issues in the case study dataset led to higher prediction errors in certain regions, the overall results exhibit a high degree of accuracy. A comparison of long-term EI predictions with EI assessment results reveals that the R² value for the EI score exceeds 0.96, and the kappa value surpasses 0.76 for the EI level, underscoring the robust performance of the integrated model in forecasting regional EEQ. This approach offers valuable insights into exploring regional EEQ trends and future challenges. Full article

Large-scale match data from esports games like League of Legends are stored in complex JSON files that often exceed the input token limitations of large language models (LLMs), restricting advanced analysis and applications such as automated commentary and strategic insight generation. This paper introduces the League of Legends Match Data Compactor (LoL-MDC), a tool designed to transform extensive match data into a concise and structured format optimized for LLM processing. By systematically summarizing structured match information—including match overviews, player and team statistics, timeline summaries, and algorithmically selected key events—the LoL-MDC significantly reduces the data size from approximately 80,000 tokens to under 2000 tokens while retaining analytical value. This method enables LLMs to generate coherent match summaries, analyze player performances, and identify key momentum shifts more effectively than processing raw JSON files. Additionally, the LoL-MDC integrates a winning probability metric to quantitatively enhance the selection of pivotal game events, ensuring relevance in esports analytics. Experimental evaluations demonstrate that the LoL-MDC improves data processing efficiency while maintaining critical insights. The proposed approach provides a structured and adaptable framework for applying LLMs to esports analytics and can be adapted to other competitive gaming environments, supporting AI-driven applications in match analysis, player performance evaluation, and strategic forecasting. Full article

Amidst the swift progression of urban expansion, transformations in land utilization have become increasingly pronounced, posing significant threats to ecosystem coherence and continuity. Establishing a well-designed ecological security pattern (ESP) framework proves essential for preserving environmental equilibrium and enhancing species diversity. This investigation centers on the Fuzhou urban agglomeration as its primary study zone, employing the patch-oriented land utilization simulation (PLUS) approach to forecast 2030 land cover modifications under environmentally conscious conditions. By integrating morphological spatial configuration assessment (MSPA) with habitat linkage evaluation, critical ecological hubs were pinpointed. Subsequent application of electrical circuit principles alongside the minimal cumulative resistance (MCR) methodology enabled the identification of vital ecological pathways and junctions, culminating in the development of a comprehensive territorial ESP framework. Key findings reveal the subsequent outcomes: (1) the main land use type in the Fuzhou metropolitan area is woodland, which accounts for over 80% of its area, and under the ecological priority scenario for 2030, woodland fragmentation was significantly improved; (2) ecological sources are mainly distributed in the northwest, northeast, and central regions, with their total area proportion increasing to 40.49% by 2030; (3) we constructed 35 ecological corridors and 42 ecological nodes, including 14 key ecological pinch points, 9 potential ecological pinch points, and 4 ecological barrier points; and (4) the final ESP formed the pattern of “three cores, three areas, multiple corridors, and multiple sources,” providing strong support for ecological protection and regional sustainable development in the Fuzhou metropolitan area. In this research, we explore the coupled methods of land use simulation and ecological network construction, offering insights for optimizing ESPs in other rapidly urbanizing areas. Full article

Marine atmospheric boundary-layer height (MABLH) is crucial for ocean heat, momentum, and substance transfer, affecting ocean circulation, climate, and ecosystems. Due to the unique geographical location of the South China Sea (SCS), coupled with its complex atmospheric environment and sparse ground-based observation stations, accurately determining the MABLH remains challenging. Coherent Doppler wind lidar (CDWL), as a laser-based active remote sensing technology, provides high-resolution wind profiling by transmitting pulsed laser beams and analyzing backscattered signals from atmospheric aerosols. In this study, we developed a stacking optimal ensemble model (SOEM) to estimate MABLH in the vicinity of the site by integrating CDWL measurements from a representative SCS site with ERA5 (fifth-generation reanalysis dataset from the European Centre for Medium-Range Weather Forecasts) data from December 2019 to May 2021. Based on the categorization of the total cloud cover data into weather conditions such as clear/slightly cloudy, cloudy/transitional, and overcast/rainy, the SOEM demonstrates enhanced performance with an average mean absolute percentage error of 3.7%, significantly lower than the planetary boundary-layer-height products of ERA5. The SOEM outperformed random forest, extreme gradient boosting, and histogram-based gradient boosting models, achieving a robustness coefficient ($R^2$) of 0.95 and the lowest mean absolute error of 32 m under the clear/slightly cloudy condition. The validation conducted in the coastal city of Qingdao further confirmed the superiority of the SOEM in resolving meteorological heterogeneity. The predictions of the SOEM aligned well with CDWL observations during Typhoon Sinlaku (2020), capturing dynamic disturbances in MABLH. Overall, the SOEM provides a precise approach for estimating convective boundary-layer height, supporting marine meteorology, onshore wind power, and coastal protection applications. Full article

Radar echo extrapolation, a critical spatiotemporal sequence forecasting task, requires precise modeling of motion trajectories and intensity evolution from sequential radar reflectivity inputs. Contemporary deep learning implementations face two operational limitations: progressive attenuation of predicted echo intensities during autoregressive inference and spectral leakage-induced diffusion at high-intensity echo boundaries. This study presents RaDiT, a hybrid architecture combining differential transformer with adversarial training for radar echo extrapolation. The framework employs a U-Net backbone augmented with vision transformer blocks, utilizing differential attention mechanisms to govern spatiotemporal interactions. Our differential attention mechanism enhances noise suppression under high-threshold conditions, effectively minimizing spurious feature generation while improving metric reliability. A conditional GAN discriminator is integrated to maintain microphysical consistency in generated sequences, simultaneously addressing spectral blurring and intensity dissipation. Comprehensive evaluations demonstrate RaDiT’s superior performance in preserving spatiotemporal coherence and intensity across 0–90 min forecasting horizons. The proposed architecture achieves CSI improvements of 10.23% and 2.88% at 4 × 4 and 16 × 16 spatial pooling scales, respectively, for ≥30 dBZ thresholds on the CMARC dataset compared to PreDiff. To our knowledge, this represents the first successful implementation of differential transformers for radar echo extrapolation. Full article

Understanding optical turbulence within the atmospheric boundary layer (ABL) is essential for refining atmospheric motion analyses, enhancing numerical weather prediction models, and improving light propagation assessments. This study develops an optical turbulence model for the boundary layer over the South China Sea (SCS) by integrating multiple observational and reanalysis datasets, including ERA5 data from the European Center for Medium-Range Weather Forecasts (ECMWF), radiosonde observations, coherent Doppler wind lidar (CDWL), and ultrasonic anemometer (CSAT3) measurements. Utilizing Monin–Obukhov Similarity Theory (MOST) as the theoretical foundation, the model’s performance is evaluated by comparing its outputs with the observed diurnal cycle of near-surface optical turbulence. Error analysis indicates a root mean square error (RMSE) of less than 1 and a correlation coefficient exceeding 0.6, validating the model’s predictive capability. Moreover, this study demonstrates the feasibility of employing ERA5-derived temperature and pressure profiles as alternative inputs for optical turbulence modeling while leveraging CDWL’s high-resolution observational capacity for all-weather turbulence characterization. A comprehensive statistical analysis of the atmospheric refractive index structure constant ($C_n^2$) from November 2019 to September 2020 highlights its critical implications for optoelectronic system optimization and astronomical observatory site selection in the SCS region. Full article

Accurate long-term electricity load forecasting is critical for energy planning, infrastructure development, and risk management, especially under increasing uncertainty from climate and economic shifts. This study proposes a multi-resolution probabilistic load forecasting framework that leverages temporal hierarchies to generate coherent forecasts at hourly, daily, monthly, and yearly levels. The model integrates climate and economic indicators and employs tailored forecasting techniques at each resolution, including XGBoost and ARIMAX. Initially incoherent forecasts across time scales are reconciled using advanced methods such as Ordinary Least Squares (OLS), Weighted Least Squares with Series Variance Scaling (WLS_V), and Structural Scaling (WLS_S) to ensure consistency. Using historical data from Alberta, Canada, the proposed approach improves the accuracy of deterministic forecasts and enhances the reliability of probabilistic forecasts, particularly when using the OLS reconciliation method. These results highlight the value of temporal hierarchy structures in producing high-resolution long-horizon load forecasts, providing actionable insights for utilities and policymakers involved in long-term energy planning and system optimization. Full article

Effectively managing carbon monoxide (CO) pollution in complex industrial cities like Jubail remains challenging due to the diversity of emission sources and local environmental dynamics. This study analyzes spatiotemporal CO patterns and builds accurate predictive models using five years (2018–2022) of data from ten monitoring stations, combined with meteorological variables. Exploratory analysis revealed distinct diurnal and moderate weekly CO cycles, with prevailing northwesterly winds shaping dispersion. Spatial correlation of CO was low (average 0.14), suggesting strong local sources, unlike temperature (0.92) and wind (0.5–0.6), which showed higher spatial coherence. Seasonal Trend decomposition (STL) confirmed stronger seasonality in meteorological factors than in CO levels. Low wind speeds were associated with elevated CO concentrations. Key predictive features, such as 3-h rolling mean and median values of CO, dominated feature importance. Spatiotemporal analysis highlighted persistent hotspots in industrial areas and unexpectedly high levels in some residential zones. A range of models was tested, with ensemble methods (Extreme Gradient Boosting (XGBoost) and Categorical Boosting (CatBoost)) achieving the best performance ($R^2>0.95$) and XGBoost producing the lowest Root Mean Squared Error (RMSE) of 0.0371 ppm. This work enhances understanding of CO dynamics in complex urban–industrial areas, providing accurate predictive models ($R^2>0.95$) and highlighting the importance of local sources and temporal patterns for improving air quality forecasts. Full article

Ocean forecasting is critical for various applications and is essential for understanding air–sea interactions, which contribute to mitigating the impacts of extreme events. While data-driven forecasting models have demonstrated considerable potential and speed, they often primarily focus on spatial variations while neglecting temporal dynamics. This paper presents the TSformer, a novel non-autoregressive spatio-temporal transformer designed for medium-range ocean eddy-resolving forecasting, enabling forecasts of up to 30 days in advance. We introduce an innovative hierarchical U-Net encoder–decoder architecture based on 3D Swin Transformer blocks, which extends the scope of local attention computation from spatial to spatio-temporal contexts to reduce accumulation errors. The TSformer is trained on 28 years of homogeneous, high-dimensional 3D ocean reanalysis datasets, supplemented by three 2D remote sensing datasets for surface forcing. Based on the near-real-time operational forecast results from 2023, comparative performance assessments against in situ profiles and satellite observation data indicate that the TSformer exhibits forecast performance comparable to leading numerical ocean forecasting models while being orders of magnitude faster. Unlike autoregressive models, the TSformer maintains 3D consistency in physical motion, ensuring long-term coherence and stability. Furthermore, the TSformer model, which incorporates surface auxiliary observational data, effectively simulates the vertical cooling and mixing effects induced by Super Typhoon Saola. Full article

This study introduces two distinct post-processing strategies to address systematic biases in sea surface temperature (SST) numerical forecasts, thereby enhancing SST predictive accuracy. The first strategy implements a spatiotemporal four-dimensional multi-grid analysis (4D-MGA) scheme within a three-dimensional variational (3D-Var) data assimilation framework. The second strategy establishes a hybrid deep learning architecture integrating empirical orthogonal function (EOF) analysis, empirical mode decomposition (EMD), and a backpropagation (BP) neural network (designated as EE–BP). The 4D-MGA strategy dynamically corrects systematic biases through a temporally coherent extrapolation of analysis increments, leveraging its inherent capability to characterize intrinsic temporal correlations in model error evolution. In contrast, the EE–BP strategy develops a bias correction model by learning the systematic biases of the SST numerical forecasts. Utilizing a satellite fusion SST dataset, this study conducted bias correction experiments that specifically addressed the daily SST numerical forecasts with 7-day lead times in the Kuroshio region south of Japan during 2017, systematically quantifying the respective error reduction potentials of both strategies. Quantitative verification reveals that EE–BP delivers enhanced predictive skill across all forecast horizons, achieving 18.1–22.7% root–mean–square error reduction compared to 1.2–9.1% attained by 4D-MGA. This demonstrates deep learning’s unique advantage in capturing nonlinear bias evolution patterns. Full article

The proliferation of low-emission zones (LEZs) across Europe is anticipated to accelerate in the coming years as a measure to enhance air quality in urban areas. Nevertheless, there is a lack of a standardized methodology to evaluate their effectiveness, and some of the proposed strategies may not adequately address air quality issues or overlook meteorological considerations. In this study, we employ three machine learning (ML) algorithms to forecast NO₂, PM₁₀ and PM_2.5 concentrations in the air in Madrid in 2022 (post-LEZ) based on data from the period 2015–2018 (pre-LEZ) under a business-as-usual scenario, accounting for seasonal and meteorological factors. According to the models, the reductions in NO₂ concentrations in 2022 varied from 29 to 35% in contrast to a scenario without the LEZ, which is coherent with the observed decrease in 2022 in traffic volume inside the area limited by the LEZ. However, no clear improvement was observed for PM₁₀ and PM_2.5 concentrations. Full article

Background: Anti-Vascular Endothelial Growth Factor (VEGF) therapy is an effective therapy for improving and stabilizing the vision of patients with neovascular age-related macular degeneration (nAMD). However, the treatment requirements, particularly the number of intraocular injections, can vary significantly among patients. This study aimed to analyze the vascular characteristics of macular neovascularizations (MNVs) to identify potential biomarkers that could predict the required injection frequency throughout the disease course. Methods: In all patients, the initial diagnosis of nAMD was confirmed using optic coherence tomography (OCT), fluorescein angiography, and OCT angiography (OCTA). MNVs detected using OCTA were subjected to quantitative vascular analysis of their area, total vascular length (sumL), fractal dimension (FD), and flow density. These results were then correlated with the number of intravitreal anti-VEGF treatments administered during the first 3 years of treatment. Additionally, the relationship between the parameters and visual acuity progression was analyzed. Results: A total of 68 treatment-naïve eyes were included in the study, comprising 31 eyes with type 1 MNV, 19 eyes with type 2 MNV, and 18 eyes with type 3 MNV. The average MNV area at baseline was 1.11 mm² ± 1.18 mm², the mean total vascular length was 12.95 mm ± 14.24 mm, the mean fractal dimension was 1.26 ± 0.14, and the mean flow density was 41.19 ± 5.87. On average, patients in our cohort received 19.8 ± 8.5 intravitreal injections (IVIs). A significant correlation was found between the number of administered IVIs in the first 3 treatment years and the MNV area (p < 0.005), sumL (p < 0.005), and FD (p < 0.05), while no correlation was found with flow density. Additionally, there was no significant association between MNV type and treatment requirements, nor between MNV vascular architecture and visual acuity progression. Conclusions: The results suggest that the specific vascular structure of untreated MNV may serve as a predictor of long-term treatment demand. With the emergence of new drug classes and advancements in imaging techniques, these parameters could offer valuable insights for forecasting treatment requirements. Full article