Search Results (495)

Autoregressive models with exogenous variables (ARX) constitute a fundamental class of dynamic regression models used extensively for time series analysis across a wide range of applications. A pervasive limitation of the existing Bayesian analyses of ARX models is their near-exclusive reliance on the Gaussian error assumption, which is routinely violated in empirical applications exhibiting heavy-tailed innovations, distributional outliers, or excess kurtosis. To address this deficiency, we develop a rigorous Bayesian estimation framework for these models whose errors are drawn from the scale-mixtures of normal (SMN) family, which is a rich, symmetric, heavy-tailed class of distributions. Exploiting the hierarchical stochastic representation of the SMN family through observation-specific latent scale-mixing variables, the ARX model is embedded in an augmented data structure that restores Gaussian conditional structure. Under three distinct prior formulations—namely, normal-gamma, Zellner’s g-prior, and Jeffreys’ prior—we derive closed-form full conditional posterior distributions for the ARX coefficient vector and the error scale parameter, which follow multivariate normal and inverse-gamma distributions, respectively. In addition, for the SMN-specific shape parameters, we derive the full conditional posteriors for each distribution in the family, and some of them are non-standard distributions handled by embedding Metropolis-Hastings steps within the Gibbs sampler. The resulting hybrid MCMC algorithm is validated through a comprehensive simulation study spanning three ARX model configurations and all three SMN special cases. A real macroeconomic application to US consumer price inflation demonstrates the practical utility of the framework, confirming heavy-tailed residuals and yielding precise, well-calibrated posterior estimates. Full article

This study investigates the relationship between energy consumption and ecological sustainability in South Africa over the period 1990–2023, with a particular focus on the roles of renewable energy consumption, non-renewable energy consumption, and economic growth. Ecological sustainability is proxied by the Load Capacity Factor (LCF), a comprehensive measure that captures the balance between biocapacity and environmental pressure. The study employs the Nonlinear Autoregressive Distributed Lag (NARDL) model to capture both short-run and long-run asymmetric effects, decomposing renewable energy consumption into positive and negative shocks to identify nonlinear dynamics. Descriptive statistics reveal moderate stability in the LCF, increasing adoption of renewable energy, sustained economic growth, and persistent dependence on fossil fuels. Unit root tests confirm mixed integration orders, justifying the use of the NARDL framework. Empirical results indicate that positive shocks in renewable energy consumption significantly enhance ecological sustainability, while negative shocks reduce the LCF, highlighting the asymmetric impact of renewable energy. Non-renewable energy consumption exhibits a statistically significant long-run association with ecological sustainability, reflecting South Africa’s continued structural dependence on fossil-fuel-based energy systems during the study period. Granger causality tests show that renewable energy and non-renewable energy consumption are key drivers of ecological sustainability, whereas economic growth and environmental conditions exhibit bidirectional feedback. The findings provide evidence for the strategic importance of promoting renewable energy adoption, reducing fossil fuel reliance, and integrating sustainability considerations into economic planning. Policy recommendations emphasize investment in renewable energy infrastructure, incentives for green energy adoption, and the integration of environmental objectives into economic development strategies to enhance South Africa’s ecological resilience. Full article

This study examines the determinants of carbon dioxide (CO₂) emissions across 25 European Union countries over the period 2000–2021, with particular emphasis on the roles of environmental taxation and green innovation in shaping environmental sustainability. The analysis is grounded in ecological modernization theory, endogenous growth theory, and the Environmental Kuznets Curve hypothesis, which collectively explain the long-run and dynamic interactions between environmental policy, economic activity, structural transformation, and environmental outcomes. To ensure robust empirical inference, this study applies a comprehensive econometric framework that accounts for cross-sectional dependence, heterogeneity, non-stationarity, cointegration, and endogeneity. The empirical strategy begins with Pesaran cross-sectional dependence tests and slope heterogeneity diagnostics, followed by second-generation panel unit root tests (Pesaran CADF/CIPS) and Westerlund cointegration tests to establish the existence of long-run equilibrium relationships among the variables. Long-run coefficients are estimated using Fully Modified Ordinary Least Squares (FMOLS), Dynamic Ordinary Least Squares (DOLS), Canonical Cointegrating Regression (CCR), and Common Correlated Effects Mean Group (CCEMG) estimators. In addition, the Panel Autoregressive Distributed Lag (ARDL) model is employed to capture both short-run dynamics and long-run adjustment processes, while the System Generalized Method of Moments (System GMM) estimator addresses potential endogeneity, reverse causality, omitted variable bias, and dynamic persistence in CO₂ emissions. The empirical results indicate that environmental taxation has a positive and statistically significant association with CO₂ emissions, suggesting that current fiscal environmental policies in EU-25 countries may not yet be sufficiently effective in discouraging pollution-intensive activities. In contrast, green innovation is found to significantly reduce CO₂ emissions, underscoring the critical role of innovation-driven environmental investment and technological progress in improving environmental quality. Economic growth, exports, and urbanization are associated with higher emissions, while imports contribute to emission reductions, reflecting differences between domestic production-based effects and trade-related structural adjustments. The System GMM results further confirm the persistence of CO₂ emissions over time and validate the robustness of the long-run relationships identified by alternative estimators. Likewise, the CCEMG and Panel ARDL results support the stability and consistency of the findings under conditions of cross-sectional dependence and heterogeneous country dynamics. Taken together, the results highlight the importance of integrating environmental taxation with green innovation policies, innovation-driven investment, and sustainable trade policies to achieve long-term emission reductions in the European Union. This study contributes to the environmental economics literature by providing robust empirical evidence using second-generation panel econometric techniques that explicitly address cross-sectional dependence, heterogeneity, and endogeneity in the analysis of environmental sustainability. Full article

Qinghai Lake, the largest endorheic saline lake in China, has undergone a pronounced hydrological regime shift from a multi-decadal decline to a rapid post-2004 recovery, reflecting strong hydroclimatic non-stationarity in the northeastern Tibetan Plateau (TP). This paper supplements the current water level and lake area status of Qinghai Lake to provide basic background for future prediction. Reliable forecasting of such climate sensitive lake systems remains difficult because conventional statistical models often fail to capture non-linear fluctuations, whereas standalone deep learning models may overlook long-term deterministic evolution. To address this challenge, we developed a serial decomposition GeoAI framework that integrates autoregressive integrated moving average (ARIMA), one-dimensional convolutional neural networks (1D-CNNs), and long short-term memory (LSTM) networks for non-stationary water level forecasting. Using annual water level observations from 1960 to 2025, the ARIMA component was first used to extract the low-frequency deterministic trend, after which the CNN-LSTM module reconstructed the nonlinear residual variability. The model was trained on the 1960–2012 period and validated over 2013–2025, which represents the most dynamic expansion stage of Qinghai Lake. The hybrid framework outperformed the benchmark models, achieving a Root Mean Square Error (RMSE) of 0.2033 m, Mean Absolute Error (MAE) of 0.1727 m, and Mean Squared Error (MSE) of 0.0413 m² during validation. The decomposition strategy effectively reduced phase lag and amplitude attenuation, improving both predictive accuracy and process interpretability. Multi-step forecasting for 2026–2056 suggests that Qinghai Lake will continue to rise, reaching approximately 3204.08 m by 2056, although the growth rate is projected to slow as negative hydrological feedback strengthen. By explicitly separating deterministic climate scale signals from nonlinear short-term variability, the proposed framework provides a robust and transferable geoinformation based tool for forecasting water level dynamics and supporting adaptive management in climate sensitive, data scarce lake basins. Full article

Background: Dengue fever has emerged as a major public health concern in Bangladesh, with increasing incidence and geographic spread of outbreaks in recent years. This study aimed to investigate the lagged and non-linear associations between climatic factors and dengue incidence across all eight administrative divisions of Bangladesh from 2014 to 2025. Materials and Methods: An ecological time-series design was employed using monthly dengue case data (n = 741,338) and meteorological variables. A generalized additive model (GAM) with a negative binomial distribution was applied to account for overdispersion and capture complex relationships. Descriptive analysis was conducted to assess spatial heterogeneity, and choropleth maps were constructed to visualize the spatial distribution and regional variation in dengue burden across the country. Cross-correlation analysis was performed to identify significant lagged associations between climatic variables and dengue incidence. Results: Descriptive analysis showed substantial spatial heterogeneity, with the highest incidence observed in Dhaka (6.53 per 100,000) and the lowest in Sylhet (0.21 per 100,000). Choropleth maps illustrated distinct spatial distribution and regional variation in dengue burden across the country. Cross-correlation analysis identified significant lagged associations for temperature and rainfall (lag 1–3 months), humidity (lag 1–2 months), and wind speed (lag 2–3 months). The final GAM explained 88.6% of the deviance in dengue incidence (AIC = 7404.15; dispersion = 0.767). The approximate significance of smooth terms revealed that temperature at a lag of 1 month (p < 0.001, edf = 12.28), rainfall at a lag of 3 months (p < 0.001, edf = 2.85), and wind speed at a lag of 2 months (p < 0.001, edf = 2.25) were highly significant non-linear predictors of dengue transmission. Relative humidity was not significantly associated with dengue incidence. Non-linear effects revealed peak dengue risk at temperatures between 25 and 30 °C and moderate rainfall (~10 mm), particularly during monsoon months (June–October). A strong autoregressive effect indicated that prior dengue incidence significantly influenced current transmission. Conclusions: Overall, dengue transmission in Bangladesh is driven by complex, lagged, and non-linear interactions between climatic variables, seasonality, and regional factors. These findings provide critical evidence for climate-based early warning systems, enhance outbreak prediction, and inform evidence-based vector control strategies. Full article

This study examines the dynamic relationships among oil prices, monetary conditions, and nominal GDP growth in Saudi Arabia, with particular attention to short-run adjustment and long-run equilibrium patterns in an oil-dependent economy operating under a fixed exchange-rate regime. Rather than identifying structural monetary policy shocks, the study focuses on reduced-form dynamic associations between market-based monetary indicators, oil-price movements, and nominal economic activity. Using a high-frequency monthly dataset covering key macroeconomic variables, the analysis employs the Autoregressive Distributed Lag (ARDL) framework to estimate both short-run dynamics and long-run equilibrium relationships. An Error Correction Model (ECM) is used to capture the speed of adjustment toward equilibrium, while Granger causality tests assess short-term predictive linkages. The empirical results reveal that monetary indicators, particularly interest rates and money supply, exhibit lagged and non-monotonic associations with nominal GDP growth, reflecting delayed transmission under exchange-rate constraints. Oil-price movements emerge as a dominant driver, showing strong contemporaneous and lagged associations with growth, whereas inflation and exchange-rate movements display limited short-run predictive relevance. The ECM results indicate relatively rapid convergence toward long-run equilibrium, suggesting efficient adjustment dynamics. Granger causality findings further confirm the short-term predictive content of key macroeconomic variables. By integrating high-frequency data with ARDL–ECM estimation, VAR-based robustness checks, and sensitivity analysis, the study provides evidence on how oil-price movements, liquidity conditions, and interest-rate dynamics jointly shape growth fluctuations in Saudi Arabia. Full article

The intermittent nature of renewable energy sources such as solar and wind power poses significant challenges for grid stability and energy management. Accurate forecasting is crucial for mitigating these challenges, as traditional models such as Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA) often fail to capture the non-linear relationships between weather patterns and energy generation. To address this limitation, this research proposes a machine learning framework leveraging Convolutional Neural Networks (CNNs) for spatial pattern recognition and Recurrent Neural Networks (RNNs) for time-series forecasting. By integrating system design parameters with meteorological data, the framework aims to enhance prediction accuracy. The potential outcomes of this framework are not just improved grid stability, optimized energy storage utilization, and reduced operational costs, but also a significant step towards the efficient integration of renewable energy into the power system, fostering a sense of optimism for the future of renewable energy forecasting. Full article

Extracting reliable damage-sensitive features from sparse sensor networks under Environmental and Operational Variations (EOV) remains a critical challenge in Structural Health Monitoring (SHM). The purpose of this study is to overcome this limitation by proposing a novel, data-driven framework utilizing a cost-effective network of high-sensitivity triaxial roving accelerometers. The methodology integrates an AutoRegressive with eXogenous inputs (ARX) model and Wavelet Packet Decomposition (WPD) to extract robust, damage-sensitive features from complex vibration data. To handle the high-dimensionality of the extracted signals and achieve optimal multi-sensor data fusion, Block-wise Principal Component Analysis (PCA) is employed as a signal sanitation and feature reduction tool. This algorithmic pipeline is applied to a full-scale bridge pier subjected to RC jacketing. The structural enhancements and dynamic behavior shifts post-retrofitting were statistically quantified using the Mahala Nobis distance. The analysis revealed a 41.2% attenuation in median vibration intensity and successfully verified the structural improvements at a 99% confidence interval, clearly distinguishing the retrofitting effects from ambient noise. The proposed framework successfully isolates true structural changes from EOV, providing a reliable non-destructive evaluation tool for continuous monitoring in practical civil engineering applications. Full article

The hydrological prediction in transboundary river basins is difficult because of their heterogeneous data distribution, restrictions of data sovereignty, and the irregular nature of the discharge pattern. In this paper, Federated Learning (FL) with an LSTM neural network is proposed for next-day predictions of discharge in the Chu–Talas transboundary basin. The basin area belongs to both Kazakhstan and Kyrgyzstan. In an FL scenario, two hydrological stations from the basin were selected as client nodes, representing two different discharge regimes. Station 15125—the Chu main channel is characterized by the highest discharge regime among stations located in the basin, while Station 15233—Merke tributary represents a small catchment with an irregular regime. The federated LSTM model is compared against a centralized LSTM and a local-only LSTM baseline model. The training process is based on nearly three decades of daily discharge measurements. The preprocessing step includes synchronization, lag calculation, and windowing operation. The models are trained using three metrics: root mean square error, mean absolute error, and Nash–Sutcliffe Efficiency, as well as using Monte Carlo Dropout for estimation of the probabilistic uncertainty. The results demonstrate that the federated model demonstrates comparable performance with the centralized one for the Chu main channel. It also improves prediction accuracy for the smaller Merke tributary compared with both centralized and local-only models. These findings show that FL can work effectively with non-IID and heterogeneous hydrological data. The study makes three main contributions: (i) it implements the FedAvg algorithm on transboundary, heterogeneous hydrological data, proving that decentralized optimization can effectively capture autoregressive temporal hydrology without data centralization; (ii) it systematically compares federated, centralized, and local-only models, demonstrating that the federated approach eliminates the scale bias that traditionally neglects smaller, high-variance catchments; and (iii) it utilizes Monte Carlo Dropout to translate deterministic AI outputs into risk-aware probabilistic bounds. Ultimately, the results of this study demonstrate the practical and scientific usefulness of FL in operational water management, as the method presents a privacy-saving means of increasing predictive capacity and enabling risk-based decision-making in transboundary river basins. Full article

The municipal solid waste incineration (MSWI) process plays a vital role in promoting ecological civilization and sustainable development. Accurate multi-step CO₂ prediction in MSWI is particularly difficult due to complex combustion dynamics and highly non-stationary emission patterns, with current models often failing to capture both linear and nonlinear relationships effectively. To address these limitations, this study proposes a novel hybrid approach combining autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) models, optimized through Bayesian optimization (BO), chosen for its sample efficiency and ability to handle noisy objective functions in high-dimensional parameter spaces. This method first defines the search space and acquisition function and then integrates the predicted values of the ARIMA linear model and the LSTM nonlinear model to construct the objective function and finally obtains the optimal combination of hyperparameters. Based on the measured data of a MSWI power plant in Beijing, the verification shows that the RMSE of the model is reduced to 0.1856 and the MAE is reduced to 0.1453, which are reduced by 10.3% and 11.9%, respectively, compared with the baseline model LSTM. This hybrid approach to BO proved to be particularly effective for MSWI plants with variable waste composition and frequent operational changes, and for modeling data containing both linear and nonlinear mappings. The framework’s generalizability suggests promising applications for other environmental prediction tasks requiring combined linear-nonlinear modeling, while future work could explore its extension to multi-pollutant forecasting systems and intelligent emission reduction control. Full article

This paper estimates an extended Cobb–Douglas production function for five major economies (China, the EU, India, the Russian Federation, and the USA) over the period of 1990–2023, incorporating electricity production from renewable, non-renewable, and nuclear sources as discrete production inputs. To capture complex properties in time series, a comprehensive econometric strategy is adopted, which combines linearity tests, multiple detection of structural changes, linear and nonlinear unit root tests, autoregressive distributed lag (ARDL) bounds testing for cointegration, error correction modelling, and error correction model (ECM)-based Granger causality. The results confirm the presence of mixed orders of integration, nonlinear dynamics, and structural instability across countries, justifying the use of the ARDL framework. The bounds test reveals a long-run cointegrating relationship between output, capital, labour, and energy inputs in all five economies. Long-run elasticities differ significantly across countries, highlighting strong structural heterogeneity. The short-term dynamics show that energy shocks have asymmetric and country-specific effects on output, while the error correction terms confirm convergence towards the long-run equilibrium, with the fastest adjustment observed in the EU and the slowest in the US. The causality results support the hypothesis of growth-led energy in China, India and the Russian Federation, while two-way feedback is observed in the EU and the US. These findings suggest that energy policy cannot be uniform across countries and must be aligned with domestic production structures, technological intensity, and energy transition stages. Full article

Origin–destination (OD) matrix forecasting is essential for urban railway operations because it enables simultaneous understanding of the direction and magnitude of passenger flows. However, OD matrices in large-scale subway networks are difficult to predict owing to their high dimensionality and sparsity, and existing approaches often rely on station-level predictions or complex structural designs. This study addresses the offline full-matrix OD forecasting problem, where complete historical OD sequences are available at prediction time, and proposes Metro-GATF, a spatiotemporal forecasting framework that jointly models railway topology and dynamic OD interactions. The model employs a GATv2-based spatial encoder to learn static inter-station relationships and encodes time-varying interactions using sparse OD graphs. A non-autoregressive transformer decoder generates future multi-step node representations in parallel, whereas origin–destination factorization and sparsity-aware gating are used to reconstruct the full OD matrix. Experiments on minute-level AFC-based OD data from a 637-station metropolitan subway network demonstrated that Metro-GATF achieved the lowest sMAPE among the compared full-matrix models. These results indicate that the proposed framework effectively captures complex spatiotemporal OD patterns and offers a practical end-to-end framework for forecasting urban railway demand. Full article

Forecasting scrap steel prices is crucial for the economic sustainability of recycling operations, yet it remains challenging due to inherent volatility and non-stationary behavior. In this study, we develop and evaluate a delta-targeted Hybrid forecasting pipeline for short horizons of 1, 3, and 7 days. We benchmark classical baselines (Naive, Seasonal Autoregressive Integrated Moving Average (SARIMA), and Exponential Smoothing (ETS)) against recurrent deep learning models (Simple Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM)) and recent neural forecasting baselines, including Decomposition-Linear (DLinear), Convolutional Kolmogorov–Arnold Network (C-KAN), and Neural Basis Expansion Analysis for Time Series (N-BEATS), using real-world daily scrap steel price data. The results indicate that delta-targeting generally yields more stable predictive performance than direct raw-price forecasting as the prediction horizon increases. For example, at the 7-day horizon, the predictive fit improves from approximately $R^2\approx 0.87$ for raw-price LSTM to around $R^2\approx 0.90$ for delta-trained recurrent models. At the same horizon, a delta-based RNN achieves the lowest Mean Absolute Percentage Error (MAPE) among the evaluated models (approximately $1.39\%$), while the proposed Hybrid model remains competitive across all tested horizons and maintains a goodness-of-fit of approximately $R^2\approx 0.90$ without uniformly minimizing point error relative to the best-performing recurrent baseline. Attention profiling and permutation-based feature importance analyses indicate that the model places relatively higher weight on calendar-related inputs, consistent with the presence of weekly patterns in the data; these results should be interpreted as sensitivity diagnostics rather than causal evidence. Overall, the findings suggest that delta-transformed targets provide a more suitable prediction space than raw-price targets for short-horizon scrap steel forecasting, while the Hybrid design offers a balanced combination of predictive performance and diagnostic interpretability for operational decision support. Full article

Accurate prediction of the behavior of alloys and metal matrix composites during high-temperature deformation requires strict consideration of the loading history. To address this problem, a hybrid rheological model for flow stress prediction has been developed, combining a phenomenological description of the yield stress with a recurrent neural network based on the NARX (Nonlinear AutoRegressive with eXogenous inputs) architecture. The memory effect is formed by expanding the input parameters with the response values from the previous step. The identification of the weight coefficients of the NARX neural network is implemented by training an equivalent multilayer perceptron. To improve the generalization ability of the model and eliminate its dependence on a fixed discretization step, the training dataset includes data obtained under non-monotonic changes in the strain rate over time and a variable time interval. The article justifies the structure of the model input parameters, excluding the accumulated strain from the input set due to its lack of informativeness during active softening processes. Verification of the hybrid model on the 7075/2.5% TiC composite in the temperature range of 300–500 °C demonstrated an average relative error of 1.5% when predicting modes that were not involved in the training. The predicted flow stress values fall within the experimental scatter interval of ±5% and accurately reproduce the local features of the flow stress curves. The proposed model and its identification technique provide correct consideration of the deformation history under the complex interaction of hardening and softening processes. Full article

The objective of this study was to explore the impact of exchange rate volatility on corporate financial stability in European corporations, with particular emphasis on the Eurozone and non-Eurozone. The data set of this study consisted of 80 publicly listed non-financial corporations in eight European countries over the period of 2010–2024. The model was able to capture the impact of various macroeconomic changes that affected European corporations in the past few years. The macroeconomic changes that were captured in this study were the European sovereign debt crisis, the COVID-19 pandemic in the world, and the conflict in Ukraine. The financial stability was measured by the Altman Z-score, the leverage ratio, and the current ratio. In this study, the financial impact of the exchange rate was measured by the rolling standard deviations and the conditional volatility with the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) models. The fixed effects model estimation with the System Generalized Method of Moments (GMM) was used in this study. The results of this study showed that the exchange rate volatility was negatively correlated with financial stability in terms of the leverage ratio. However, the Eurozone provides protection against the financial impact of the exchange rate volatility in terms of the leverage ratio. The diagnostic tests in this study were carried out with the Hansen Test and the Arellano-Bond Test. The diagnostic tests confirmed that the results were valid. The significance of this study was that it provided longitudinal data on the impact of the exchange rate on the financial stability of European corporations with particular emphasis on the Eurozone and non-Eurozone. The study also provided new insights on the exchange rate in corporate finance. The Eurozone provides protection against the financial impact of the exchange rate. Full article