Search Results (1,203)

This paper proposes a generalized seasonal beta prime autoregressive moving average model with dynamic precision, denoted by BPSARMA, for modeling and forecasting positive-valued seasonal time series. The proposed framework extends the generalized BPARMA model by incorporating stochastic seasonal dynamics in the conditional mean through seasonal autoregressive and moving average components while allowing a flexible autoregressive structure for the conditional precision parameter, thereby accommodating time-varying uncertainty. The model also allows the inclusion of covariates and deterministic seasonal regressors. Parameter estimation is carried out by conditional maximum likelihood, and the main inferential and diagnostic tools are discussed. Monte Carlo simulations are conducted to examine the finite-sample behavior of the estimators and associated inference procedures. The practical usefulness of the proposed approach is illustrated through hydro-environmental time series applications, where its forecasting performance is evaluated using both in-sample and out-of-sample predictive measures. The empirical results indicate that the BPSARMA specification often provides competitive or superior forecasting accuracy relative to competing models, highlighting its usefulness for modeling and prediction in positive seasonal time series. Full article

Raw sentiment extracted from Chinese financial news is noisy and difficult to use directly for market prediction. This study proposes a mathematical filtering framework that converts noisy Chinese financial news sentiment into reliable quantitative signals for financial market prediction. Three daily sentiment measures were constructed from Chinese financial news: sentiment mean, sentiment dispersion, and polarity imbalance. Seven filtering methods were applied to each measure, including exponential smoothing, autoregressive filtering, ARIMA filtering, moving average smoothing, discrete wavelet transform, Savitzky–Golay filtering, and Kalman filtering. The seven filtered outputs were averaged to produce an ensemble-smoothed sentiment signal. Support vector machines and neural networks were then used to compare the predictive performance of raw and filtered signals for stock index log returns and realized volatility. Filtering reduced the standard deviation of sentiment mean by 48%, sentiment dispersion by 55%, and polarity imbalance by 50%, while mean levels remained stable. Filtered sentiment consistently outperformed raw sentiment across all model configurations. The improvement was larger for realized volatility than for returns: the best support vector machine reduced volatility prediction error by 16.9% and return prediction error by 5.8%. A moderate neural network with 20 hidden neurons achieved optimal performance for both outcomes. Mathematical filtering extracts stable and informative sentiment signals from Chinese financial news. Filtered sentiment is more useful than raw sentiment for predicting market volatility, and the improvement holds across multiple machine learning models. Full article

This paper examines how artificial intelligence can support sustainability assessment in cultural industries, using national film industries as a test case. The Film Industry Sustainability Index (FISI) is introduced as a composite indicator covering cultural diversity, economic resilience, and Sustainable Development Goal (SDG) alignment for 42 national economies from 2005 to 2023. Knowledge-Enhanced Mamba (KE-Mamba), a selective state-space forecasting model, is then proposed to combine annual panel indicators with country-level film-industry knowledge graph (KG) embeddings and large language model (LLM)-derived screenplay-oriented narrative proxies from film synopses. To reduce factual errors in title-level narrative scoring, the LLM is anchored to verified United Nations Educational, Scientific and Cultural Organization (UNESCO) records and the European Audiovisual Observatory’s LUMIERE film-admissions database using rank-one model editing (ROME). On the 2020–2023 held-out test period, KE-Mamba achieves a composite FISI mean absolute error (MAE) of 0.0389, a mean absolute percentage error (MAPE) of 5.61%, and an $R^2$ of 0.934, outperforming autoregressive integrated moving average (ARIMA), tree-based, long short-term memory (LSTM), and base Mamba baselines. Additional robustness checks using a pre-pandemic split, two-way fixed-effects panel regression, alternative FISI weighting schemes, KG embedding ablations, and human validation of LLM narrative scores support the reliability of the proposed framework. Policy simulations are interpreted as model-based projected associations rather than causal estimates. The results show that knowledge-enhanced sequence models can provide transparent forecasting support for sustainable cultural-industry policy. 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

Water Resource Carrying Capacity (WRCC) is a crucial measure for assessing the balance between regional water availability, socioeconomic development, and ecological needs, especially in arid and semi-arid regions. This study evaluates the spatiotemporal evolution of WRCC across 14 prefecture-level units in Gansu Province, China, from 2000 to 2023. A multi-dimensional evaluation system comprising 29 indicators across water resources, ecological environment, economy, society, and coordination subsystems was established. The Entropy Weight Method was applied to determine indicator weights and calculate a comprehensive index (CI) to quantify carrying pressure. A Random Forest model identified dominant influencing factors, and an autoregressive integrated moving average model projected trends from 2024 to 2028. The results show the provincial mean CI increased from 0.49 to 0.91, indicating intensifying pressure and a shift toward mild overload. Spatially, pressure exhibits a stable west–east gradient, with the highest levels persistently in western prefectures like Jiuquan, Jinchang, and Baiyin. In contrast, Gannan and Longnan in the south maintain lower pressure but show high interannual variability, indicating ecological sensitivity. The Random Forest model demonstrated strong performance, with training R² values exceeding 0.88 across all regions and mean absolute error mostly below 0.10. Projections suggest continued high pressure from 2024 to 2028 in the west, while central and southern regions show stable or slightly decreasing trends. These findings provide a quantitative basis for establishing differentiated, zoned water resource management and sustainable demand-side regulation strategies in water-limited regions. 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

Short-term wind speed forecasting plays a critical role in enabling the reliable integration of renewable energy and supporting the sustainable operation of power systems. However, traditional dual-frequency decomposition methods oversimplify wind speed dynamics by separating them into only high-frequency disturbances and low-frequency trends, making it difficult to capture intermediate-frequency transitional dynamics. Additionally, single models struggle to adapt to multi-scale temporal features, limiting forecasting performance. To address these issues, this paper proposes a tri-band frequency-aware heterogeneous expert collaboration framework. First, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is employed for signal denoising, followed by Particle Swarm Optimization-Time Varying Filtering-based Empirical Mode Decomposition (PSO-TVF-EMD) for multi-scale signal disentanglement. Then, Permutation Entropy (PE) is used to construct a tri-band structure consisting of high-, intermediate-, and low-frequency components. A frequency-aware expert routing mechanism assigns Bayesian Optimization Long Short-Term Memory (BO-LSTM), an improved Markov model, and Auto-Regressive Integrated Moving Average (ARIMA) to the corresponding frequency bands. Finally, a reliability-aware cooperative aggregation strategy integrates predictions from multiple experts. Experimental results show that representative baseline models, including BO-LSTM, Markov, ARIMA, Gated Recurrent Unit (GRU) and Convolutional Neural Network Long Short-Term Memory (CNN-LSTM), achieve MAE values ranging from 0.308 to 0.429, while the proposed framework reduces the Mean Absolute Error (MAE) to 0.193 and Root Mean Square Error (RMSE) to 0.274, with a Mean Absolute Percentage Error (MAPE) of 7.35% and R² of 0.927. Compared with the dual-frequency decomposition scheme (MAE = 0.266), the proposed tri-band framework achieves an average improvement of approximately 28.1%. The results suggest that explicitly modeling intermediate-frequency dynamics and aligning model inductive biases with multi-scale signal characteristics can effectively enhance short-term wind speed forecasting performance. Full article

Missing data remains a pervasive challenge in air quality data analysis, where inappropriate imputation techniques can introduce hidden biases and compromise the reliability of time-series models such as AutoRegressive Integrated Moving Average (ARIMA). This paper examines the impact of linear interpolation and mean/median imputation on the performance of the ARIMA model and biases in the prediction of fine particulate matter 2.5 (PM2.5) concentration, together with a detailed analysis of ARIMA generated error metrics and their implications for the accuracy and reliability of the prediction. The findings reveal that package-default imputation significantly influences ARIMA forecasts, while mean/median imputation consistently delivers superior predictive performance, highlighting its robustness for handling missing environmental data. Moreover, imputation during the data transformation stage exerts a greater influence on model outcomes than methods applied at later analysis stages. 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

Workplace accidents pose a serious threat to people’s lives and property and hinder social and economic development. Among these accidents, fire accidents are typical due to their sudden occurrence and severe consequences. To better understand accident evolution laws and improve risk prevention, this study analyzes the characteristics of typical national fire accidents based on 2015–2024 accident statistics. A linear-nonlinear combined Autoregressive Integrated Moving Average-Long Short-Term Memory (ARIMA-LSTM) model is established to predict trends of the number of national overall workplace accidents, deaths, injuries, and direct economic losses, and it is compared with Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Seasonal Autoregressive Integrated Moving Average (SARIMA), and Seasonal Autoregressive Integrated Moving Average-Long Short-Term Memory (SARIMA-LSTM) models. The results show that the ARIMA-LSTM model integrates the strengths of linear fitting and nonlinear learning, with stronger explanatory power and higher prediction accuracy, as reflected by lower Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) values. This study provides technical support for the precise prevention and control of fire accidents, trend prediction of work safety accidents, and helps to establish a scientific and forward-looking safety risk prevention and control system. Full article

Real-time precise point positioning (RT-PPP) has enabled a wide range of high-precision positioning and navigation applications, while its reliability strongly depends on the availability and continuity of precise satellite clock products. In the third-generation BeiDou Navigation Satellite System (BDS-3), interruptions or gaps in real-time precise clock products can significantly degrade the continuity and performance of precise positioning services. Therefore, accurate and robust satellite clock bias (SCB) prediction is essential for supporting reliable RT-PPP applications under product outage conditions. To address this problem, this study proposes a hybrid physics-informed and data-driven framework for BDS-3 SCB prediction. The proposed method sequentially integrates a physics-informed neural network (PINN) and a long short-term memory (LSTM) network. Specifically, the PINN is used to model and extrapolate the physically consistent trend component of SCB increments by embedding clock dynamical constraints through automatic differentiation, while the LSTM is employed to learn and predict the residual sequence containing short-term stochastic variations that cannot be fully captured by the physical model. The final SCB prediction is obtained by reconstructing the trend and residual components and recovering the original clock bias series. The proposed framework is evaluated using BDS-3 precise clock products and compared with conventional models, including quadratic polynomial (QP), autoregressive integrated moving average (ARIMA), convolutional neural network–long short-term memory (CNN-LSTM), and attention-enhanced long short-term memory (LSTM-Attention). Experimental results show that the proposed PINN-LSTM framework consistently achieves superior prediction accuracy and stability at both 12 h and 24 h forecasting horizons. Specifically, compared with QP, ARIMA, CNN-LSTM, and LSTM-Attention, the proposed method improves prediction accuracy by 18.4%, 52.8%, 32.3%, and 33.8%, respectively, for the 12 h forecasting task, and by 34.8%, 58.5%, 41.8%, and 43.8%, respectively, for the 24 h forecasting task. The results further demonstrate reduced long-horizon error accumulation, improved robustness across satellites equipped with different atomic clock types, and stronger generalization across observation days. These findings indicate that the proposed framework can provide effective support for maintaining the continuity and reliability of BDS-3 precise clock products and has strong potential for improving real-time precise positioning applications. Full article

Hydropower-dominated electricity systems are increasingly exposed to hydroclimatic variability, making anticipatory streamflow information essential for energy security, operational resilience, and sustainable planning. This study develops a transparent monthly early-warning framework for the Paute River basin, Ecuador, a strategically important hydrological system for national hydropower generation. Using a 42-year series of observed and compiled monthly streamflow records from 1984 to 2025 (n = 504), the framework derives seasonal low-flow thresholds (P20 warning and P10 critical) and fits a Seasonal Autoregressive Integrated Moving Average model to log-transformed flows. The resulting lognormal predictive distribution provides point forecasts, prediction intervals, and probabilities of low-flow events. Predictive skill was assessed through a 2016–2025 rolling-origin validation with 120 one-step-ahead forecasts and benchmarks against Error–Trend–Seasonal Holt–Winters and seasonal naive models. The SARIMA-log specification achieved the best point accuracy (MAE = 38.80 m³/s, RMSE = 47.62 m³/s, sMAPE = 32.63%) and modest but useful probabilistic skill (CRPSS = 0.069; Brier Skill Score = 0.169 for Q < P20 and 0.274 for Q < P10). A threshold-sensitivity analysis showed that the 0.15 and 0.30 alert thresholds represent a deliberate trade-off between early detection and false-alarm reduction. For 2026, August displayed the highest low-flow probability (P(Q < P20) = 0.303), triggering a moderate Hydropower Low-Flow Risk Traffic-Light category. The contribution is not a new forecasting algorithm but an operationally auditable integration of seasonal thresholds, probabilistic forecasting, verification, and risk communication for hydropower energy-security governance in the tropical Andes. Full article

Against the backdrop of the “dual carbon” goals, carbon emission trading prices serve as a core signal of market operational efficiency. Accurately predicting carbon prices facilitates scientific decision-making, and model optimization is key to improving prediction accuracy. This study takes five major carbon trading pilots in China—Shenzhen, Guangdong, Hubei, Beijing, and Shanghai—as the research objects. An indicator system is constructed from four dimensions: macroeconomy, energy prices, climate and environment, and international markets. The Least Absolute Shrinkage and Selection Operator (LASSO) algorithm is employed to identify the key influencing factors of carbon prices across different markets. Among them, “WTI crude oil price” and “EUA futures closing price” are consistently significant factors common to all five pilots. On this basis, four models—Autoregressive Integrated Moving Average with Exogenous Variables (ARIMAX), Convolutional Neural Network (CNN), Gated Recurrent Unit (GRU), and Transformer—are constructed for multi-method prediction comparison. The results show that ARIMAX and GRU achieve the best prediction performance among the four models. To further enhance prediction accuracy, hybrid optimization models are respectively developed: Support Vector Regression (SVR) is used to optimize the nonlinear residuals of ARIMAX (SVR-ARIMAX), and Genetic Algorithm (GA) is used to optimize the key hyperparameters of GRU (GA-GRU). The hybrid models significantly reduce prediction errors in most markets. Specifically, SVR-ARIMAX shows particularly notable improvements in Beijing and Hubei, while GA-GRU outperforms standard GRU in Guangdong, Shenzhen, Shanghai, and Hubei. Based on the optimized models, 12-month-ahead forecasts indicate that the Shenzhen market exhibits high volatility and greatest uncertainty; Guangdong remains relatively stable; Hubei, Beijing, and Shanghai are characterized by narrow-range fluctuations. The findings provide empirical support for corporate emission reduction decision-making, carbon market risk management, and price mechanism improvement. Full article

The growing use of electric vehicles (EVs) has created a strong need for smart, data-driven charging management systems that can support large-scale and sustainable infrastructure. This study introduces a modular cloud-based framework that combines artificial intelligence and machine learning to provide predictive insights for energy demand and station expansion. The system mainly consists of two complementary models. The first is an AutoRegressive Integrated Moving Average (ARIMA) model that forecasts charging energy demand using transactional data from Palo Alto. The second is a Light Gradient Boosting Machine (LightGBM) model that predicts optimal charging-station locations using spatial data from the U.S. Department of Energy’s Alternative Fuels Data Center (AFDC). Both models were deployed as scalable containerized microservices and were validated for accuracy and efficiency within the cloud environment. This proposed framework establishes a predictive link between energy-demand trends and infrastructure planning. It demonstrates the viability of cloud-native, AI-enabled systems to proactively manage EV charging networks and future smart-grid applications. Full article

Viticulture is a globally significant economic activity; however, the scientific literature lacks in-depth, long-term studies integrating historical trends with future market concentration projections. This study fills this gap by analyzing global grape production dynamics and market structure over a 63-year period (1961–2023). The detection of structural breaks and the forecasting of yield trajectories using AutoRegressive Integrated Moving Average with Exogenous Variables (ARIMAX) models are crucial for the strategic planning of agricultural resources and enhancing viticultural resilience. Results indicate that while the global population increased 2.58-fold (1961–2023), grape production rose only 1.69-fold, leading to a decline in per capita availability. Although traditional leaders remain dominant, the combined share of the top five producers fell from 60% to 51.8%. The market concentration analysis Herfindahl-Hirschman Index (HHI) = 0.092; the Concentration Ratio (CR₅) = 53.65%) for 2024–2030 suggests a monopolistic competition structure. The arithmetic mean of annual global production for the 2024–2030 period is projected to reach 79.42 million tons. China is expected to lead (23.11%), followed by Italy, the United States, France, and Spain. These findings highlight the necessity of precision viticulture and modern technology to stabilize yields and enhance competitiveness in high-value horticultural markets. Full article