Search Results (101)

With the rapid advancement of digitalization and intelligence in power systems, SF₆ high-voltage circuit breakers, as the core switching devices in power grid protection systems, have become critical components in high-voltage networks of 110 kV and above due to their superior insulation performance and exceptional arc-quenching capability. Their operational status directly impacts the reliability of power system protection. Therefore, real-time condition monitoring and accurate assessment of SF₆ circuit breakers along with science-based maintenance strategies derived from evaluation results hold significant engineering value for ensuring secure and stable grid operation and preventing major failures. In recent years, the frequency of extreme weather events has been increasing, necessitating a comprehensive consideration of both internal and external factors in the operational status prediction of SF₆ high-voltage circuit breakers. To address this, we propose an operational status assessment model for SF₆ high-voltage circuit breakers based on an Integrated Attribute-Weighted Risk Model Based on the Branch–Trunk Rule (IAR-BTR), which integrates internal and environmental influences. Firstly, to tackle the issues of incomplete data and feature imbalance caused by irrelevant attributes, this study employs missing value elimination (Drop method) on the fault record database. The selected dataset is then normalized according to the input feature matrix. Secondly, conventional risk factors are extracted using traditional association rule mining techniques. To improve the accuracy of these rules, the filtering thresholds and association metrics are refined based on seasonal distribution and the importance of time periods. This allows for the identification of spatiotemporally non-stationary factors that are strongly correlated with circuit breaker failures in low-probability seasonal conditions. Finally, a quantitative weighting method is developed for analyzing branch-trunk rules to accurately assess the impact of various factors on the overall stability of the circuit breaker. The DFP-Growth algorithm is applied to enhance the computational efficiency of the model. The case study results demonstrate that the proposed method achieves exceptional accuracy (95.78%) and precision (97.22%) and significantly improves the predictive performance of SF₆ high-voltage circuit breaker operational condition assessments. Full article

As a renewable and clean energy source with abundant reserves, the development of wave energy relies on accurate predictions of significant wave height (Hs). The fluctuation of Hs is a non-stationary process influenced by seasonal variations in marine climate conditions, which poses significant challenges for accurate predictions. This study proposes a deep learning method based on buoy datasets collected from four research locations in China’s offshore waters over three years (2021–2023, 3-hourly). The hybrid modal decomposition CEEMDAN-VMD is employed for reducing non-stationarity of the Hs sequence, with peak information incorporated as a data augmentation strategy to enhance the performance of deep learning. A probabilistic deep learning model, QRCNN-BiLSTM, was developed using quantile regression, achieving 12-, 24-, and 36-h interval predictions of Hs based on 12 days of historical data with three input features (Hs and wave velocities only). Furthermore, an optimization algorithm that integrates the proposed innovative enhancement strategies is used to automatically adjust the network parameters, making the model more lightweight. Results demonstrate that under a 0.95 prediction interval nominal confidence (PINC), the prediction interval coverage probability (PICP) reaches 100% for at least 6 days across all datasets, indicating that the developed system exhibits superior performance in short-term wave forecasting. Full article

With the growing demand for global energy transition, integrated energy systems (IESs) have emerged as a key pathway for sustainable development due to their deep coupling of multi-energy flows. Accurate load forecasting is crucial for IES optimization and scheduling, yet conventional methods struggle with complex spatio-temporal correlations and long-term dependencies. This study proposes ST-ScaleFusion, a multi-scale time–frequency complementary hybrid model to enhance comprehensive energy load forecasting accuracy. The model features three core modules: a multi-scale decomposition hybrid module for fine-grained extraction of multi-time-scale features via hierarchical down-sampling and seasonal-trend decoupling; a frequency domain interpolation forecasting (FI) module using complex linear projection for amplitude-phase joint modeling to capture long-term patterns and suppress noise; and an FI sub-module extending series length via frequency domain interpolation to adapt to non-stationary loads. Experiments on 2021–2023 multi-energy load and meteorological data from the Arizona State University Tempe campus show that ST-ScaleFusion achieves 24 h forecasting MAE values of 667.67 kW for electric load, 1073.93 kW/h for cooling load, and 85.73 kW for heating load, outperforming models like TimesNet and TSMixer. Robust in long-step (96 h) forecasting, it reduces MAE by 30% compared to conventional methods, offering an efficient tool for real-time IES scheduling and risk decision-making. Full article

Accurate traffic forecasting is challenging due to the complex spatial-temporal interdependencies of large road networks and sudden speed changes caused by unexpected events. Traditional models often struggle with the non-stationary and volatile characteristics of traffic time series. While existing sequence decomposition methods can capture stable long-term trends and periodic information, they fail to address complex fluctuation patterns. To tackle this issue, we propose the Spatial-Temporal traffic flow prediction with residual and trend Decomposition Transformer (STDformer), which decomposes time series into different components, thus enabling more accurate modeling of both short-term and long-term dependencies. Our method processes the time series in parallel using the Trend Decomposition Block and the Spatial-Temporal Relation Attention. The Spatial-Temporal Relation Attention captures dynamic spatial correlations across the road network, while the Trend Decomposition Block decomposes the series into trend, seasonal, and residual components. Each component is then independently modeled by the Temporal Modeling Block to capture its unique temporal dynamics. Finally, the outputs from the Temporal Modeling Block are fused through a selective gating mechanism, combined with the Spatial-Temporal Relation Attention output to produce the final prediction. Extensive experiments on PEMS traffic datasets demonstrate that STDformer consistently outperforms state-of-the-art traffic flow prediction methods, particularly under volatile conditions. These results validate STDformer’s practical utility in real-world traffic management, highlighting its potential to assist traffic managers in making informed decisions and optimizing traffic efficiency. Full article

This study proposes an extension of Seasonal Autoregressive Integrated Moving Average models with exogenous regressors (SARIMAX) by incorporating skew-normal and zero-inflated skew-normal error structures to better accommodate asymmetry and excess zeros in time series data. The proposed framework demonstrates improved flexibility and robustness compared to traditional Gaussian-based models. Simulation experiments reveal that the skewness parameter significantly affect forecasting accuracy, with reductions in mean absolute error (MAE) and root mean square error (RMSE) observed across both positively and negatively skewed scenarios. Notably, in negative-skew contexts, the model achieved an MAE of 0.40 and RMSE of 0.49, outperforming its symmetric-error counterparts. The inclusion of zero-inflation probabilities further enhances model performance in sparse datasets, yielding superior values in goodness-of-fit criteria such as the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC). To illustrate the practical value of the methodology, a real-world case study is presented involving the modeling of optical density (OD₆₀₀) data from Escherichia coli during stationary-phase growth. A SARIMAX(1,1,1) model with skew-normal errors was fitted to 200 time-stamped absorbance measurements, revealing significant positive skewness in the residuals. Bootstrap-derived confidence intervals confirmed the significance of the estimated skewness parameter ($\alpha =14.033$ with 95% CI [12.07, 15.99]). The model outperformed the classical ARIMA benchmark in capturing the asymmetry of the stochastic structure, underscoring its relevance for biological, environmental, and industrial applications in which non-Gaussian features are prevalent. Full article

The Japanese sardine (Sardinops sagax), a key economic species in the Northwest Pacific Ocean (NWPO), has shown significant increases in both population abundance and catch volume over the past decade. To understand its spatiotemporal dynamics under climate change, this study analyzed light purse seine fishery data (2014–2021) from the NWPO. The results showed that the primary fishing season spans March to December, with peak catches concentrated in 40–43° N, 149–155° E. Annual catches grew steadily, accelerating notably in 2021. The fishing grounds’ center shifted northeastward annually and seasonally (southwest-to-northeast trajectory), driven by directional aggregation. Spatial clustering with global positive autocorrelation was observed, weakening as distance thresholds increased. Resource hotspots migrated northeast, narrowing from 40–42° N (2016) to 42–44° N (2017–2021), while coldspots showed complementary fluctuations. Generalized additive model (GAM) analysis revealed that the catch per unit effort (CPUE) of Japanese sardine in the high seas of the NWPO was governed by temporal–spatial drivers and multivariate environmental determinants. Analytical findings substantiate the significant climate-driven impacts on the spatiotemporal distribution and population dynamics of Japanese sardine. The non-stationary interannual and seasonal patterns of fishing grounds highlight the need for adaptive management strategies. Full article

This study examines variations in personal exposure to PM_2.5 and NO₂ while commuting by bicycle, vehicle, and walking during heating and non-heating seasons in Gliwice, an industrial city in Upper Silesia, Poland. Understanding these variations is crucial for assessing health risks and developing effective mitigation strategies. Personal exposure was measured using low-cost sensors, while stationary measurements provided comparative background concentrations. The results indicate statistically significant seasonal differences in pollutant concentrations. NO₂ levels were higher during the heating season (mean: 30.84 µg/m³, median: 25.60 µg/m³) than in the non-heating season (mean: 22.61 µg/m³, median: 20.37 µg/m³; p = 0.025). In contrast, PM_2.5 concentrations were higher in the non-heating season (mean: 12.1 µg/m³) compared to the heating season (mean: 9.5 µg/m³; p = 0.032). Inhaled doses instead of concentrations evaluated the exposure of participants. The inhaled doses of NO₂ and PM_2.5 per km were significantly higher for walking (mean: 141.3 and 30.7 µg/km for the male participant; 77.9 and 31.6 µg/km for the female participant) than for bicycle and walking (p < 0.05). These findings underscore the impact of transport mode and seasonality on air pollution exposure, highlighting the necessity for targeted mitigation strategies to reduce commuters’ exposure to traffic-related pollutants. Full article

Understanding tidal changes and their potential forcing mechanisms enables a better assessment of non-stationary tidal effects for projecting extreme sea levels and nuisance flooding. In this study, we investigate the seasonal and interannual changes in the M₂ tidal current off the Guangdong coast using currents observed via two different types of high-frequency radar from 2019 to 2022. The results indicate significant seasonal changes in the M₂ tidal current in the coastal areas of the Pearl River Estuary and Cape Maqijiao, with the largest relative deviations occurring in summer, reaching 10–20%. Observations of thermohaline profiles from 2006 to 2007 and 1978 to 1988 show that runoff in summer can reach these two areas and change the stratification of seawater, in turn affecting tidal currents. A comparative analysis of the two areas suggests that the greater the runoff, the wider the area where the M₂ tidal current experiences significant seasonal variation. No significant interannual changes in the M₂ tidal current were detected offshore of Guangdong during the observation period. However, an abrupt change occurred in the coastal area of Shantou in 2021, primarily caused by the distortion of the antenna patterns. Full article

Accurate prediction of Global Navigation Satellite System-derived precipitable water vapor (GNSS-PWV), which is a crucial indicator for climate change monitoring, holds significant scientific value for climate disaster prevention and mitigation. In the study of GNSS-PWV prediction, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm within a decomposition–integration framework effectively addresses the non-stationarity and complexity of PWV sequences, enhancing prediction accuracy. However, residual noise and pseudo-modes from decomposition can distort signals, reducing the predictor system’s reliability. Additionally, independent modeling of all decomposed components decreases computational efficiency. To address these challenges, this paper proposes a hybrid model combining the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), autoregressive integrated moving average (ARIMA), and long short-term memory (LSTM) networks. Enhanced by local mean optimization and adaptive noise regulation, the ICEEMDAN algorithm effectively suppresses pseudo-modes and minimizes residual noise, enabling its decomposed intrinsic mode functions (IMFs) to more accurately capture the multi-scale features of GNSS-PWV. Sample entropy (SE) is used to quantify the complexity of IMFs, and components with similar entropy values are reconstructed into the following three sub-sequences: high-frequency, low-frequency, and trend. This process significantly reduces modeling complexity and improves computational efficiency. We propose different modeling strategies tailored to the dynamics of various subsequences. For the nonlinear and non-stationary high-frequency components, the LSTM network is used to effectively capture their complex patterns. The LSTM’s gating mechanism and memory cell design proficiently address the long-term dependency issue. For the stationary and weakly nonlinear low-frequency and trend components, linear patterns are extracted using ARIMA. Differencing eliminates trends and moving average operations capture random fluctuations, effectively addressing periodicity and trends in the time series. Finally, the prediction results of the three components are linearly combined to obtain the final prediction value. To validate the model performance, experiments were conducted using measured GNSS-PWV data from several stations in Hong Kong. The results demonstrate that the proposed model reduces the root mean square error by 56.81%, 37.91%, and 13.58% at the 1 h scale compared to the LSTM, EMD-LSTM, and ICEEMDAN-SE-LSTM benchmark models, respectively. Furthermore, it exhibits strong robustness in cross-month forecasts (accounting for seasonal influences) and multi-step predictions over the 1–6 h period. By improving the accuracy and efficiency of PWV predictions, this model provides reliable technical support for the real-time monitoring and early warning of extreme weather events in Hong Kong while offering a universal methodological reference for multi-scale modeling of geophysical parameters. Full article

A key feature in sheep biology is reproduction seasonality which concerns the cyclical occurrence of natural breeding, which therefore does not take place throughout the year. Since sheep are short-day breeders, the amount of daylight has an impact on their reproductive activity. The melatonin receptor subtype 1A (MTNR1A) gene is the primary gene that has been linked with seasonality. Nonetheless, information regarding the potential genetic association between other loci and the seasonality of sheep reproduction is scarce. Genome-wide association study (GWAS) is considered a cutting-edge methodology for comprehending the genetic architecture of complex traits since it enables the discovery of many markers linked to different features. In the present study, three indigenous Greek sheep breeds were investigated using GWAS—two of which presented strict patterns of reproduction seasonality, i.e., the Florina and Karagkouniko breeds, while the third one, i.e., the Chios breed had the ability to exhibit estrus throughout the year—in an attempt to detect the genetic loci linked with reproduction seasonality. All three breeds of investigated animals were purebred with Chios and Florina breeds originating from the Greek national stationary stock, whereas Karagkouniko originated from a commercial farm. Interestingly, a significant genetic differentiation of the national stationary stock groups was suggested by principal component analysis, phylogenetic analysis, and admixture and spatial point patterns, with these two breeds being less heterogeneous. This finding highlights the value of stationary stocks towards the maintenance of genetic integrity in indigenous sheep, demonstrating the Greek station’s critical role in the conservation of native sheep breeds. On the other hand, according to the GWAS data analysis, no genetic loci were correlated with reproduction seasonality, emphasizing the MTNR1A gene as the main determinant of the seasonality in native non genetically improved breeds. Full article

This paper introduces an integrated inventory model that employs customized neural networks to tackle the challenge of non-stationary demand for newsvendor-type products, such as vegetables and fashion items. In this newsvendor context, demand is intertemporal-dependent and influenced by external factors such as prices, promotions, and holidays. Contrary to traditional machine-learning-based inventory models that assume stationary and independent demand, our method accounts for the temporal dynamics and the impact of external factors on demand. Our customized neural network model integrates demand estimation with inventory optimization, circumventing the potential suboptimality of sequential estimation and optimization methods. We conduct a case study on optimizing the vegetable ordering decisions for a supermarket. The findings indicate the proposed model’s effectiveness in enhancing ordering decisions, thereby reducing inventory costs by up to 21.14%. By customizing an integrated neural network, this paper presents a precise and cost-effective inventory management solution to address real-world complexities of demand, like seasonality and external factor dependency. The proposed approach is particularly beneficial for retailers in industries dealing with perishable items and market volatility, enabling them to mitigate waste (e.g., unsold vegetables) and stockouts (e.g., seasonal fashion items). This directly confronts challenges related to sustainability and profitability. Furthermore, the integrated framework provides a methodological inspiration for adapting neural networks to other time-sensitive supply chain problems. Full article

With the rapid development of industrialization and urbanization, air pollution is becoming increasingly serious. Accurate prediction of PM_2.5 concentration is of great significance to environmental protection and public health. Our study takes Nanning urban area, which has unique geographical, climatic and pollution source characteristics, as the object. Based on the dual-time resolution raster data of the China High-resolution and High-quality PM_2.5 Dataset (CHAP) from 2012 to 2023, the PM_2.5 concentration prediction study is carried out using SARIMA, Prophet and LightGBM models. The study systematically compares the performance of each model from the spatial and temporal dimensions using indicators such as mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R²). The results show that the LightGBM model has a strong ability to mine complex nonlinear relationships, but its stability is poor. The Prophet model has obvious advantages in dealing with seasonality and trend of time series, but it lacks adaptability to complex changes. The SARIMA model is based on time series prediction theory and performs well in some scenarios, but has limitations in dealing with non-stationary data and spatial heterogeneity. Our research provides a multi-dimensional model performance reference for subsequent PM_2.5 concentration predictions, helps researchers select models reasonably according to different scenarios and needs, provides new ideas for analyzing concentration change patterns, and promotes the development of related research in the field of environmental science. Full article

The recent success of emission reduction policies in China has significantly lowered sulfur dioxide (SO₂) levels. However, accurately forecasting these concentrations remains challenging due to their inherent non-stationary tendency. This study introduces an innovative hybrid deep learning model, RF-VMD-Seq2Seq, combining the Random Forest (RF) algorithm, Variational Mode Decomposition (VMD), and the Sequence-to-Sequence (Seq2Seq) framework to improve SO₂ concentration forecasting in five coastal cities of northern China. Our results show that the predicted SO₂ concentrations closely align with observed values, effectively capturing fluctuations, outliers, and extreme events—such as sharp declines the Novel Coronavirus Pneumonia (COVID-19) pandemic in 2020—along with the upper 5% of SO₂ levels. The model achieved high coefficients of determination (>0.91) and Pearson’s correlation (>0.96), with low prediction errors (RMSE < 1.35 μg/m³, MAE < 0.94 μg/m³, MAPE < 15%). The low-frequency band decomposing from VMD showed a notable long-term decrease in SO₂ concentrations from 2013 to 2020, with a sharp decline since 2018 during heating seasons, probably due to the ‘Coal-to-Natural Gas’ policy in northern China. The input sequence length of seven steps was recommended for the prediction model, based on high-frequency periodicities extracted through VMD, which significantly improved our model performance. This highlights the critical role of weekly-cycle variations in SO₂ levels, driven by anthropogenic activities, in enhancing the accuracy of one-day-ahead SO₂ predictions across northern China’s coastal regions. The results of the RF model further reveal that CO and NO₂, sharing common anthropogenic sources with SO₂, contribute over 50% to predicting SO₂ concentrations, while meteorological factors—relative humidity (RH) and air temperature—contribute less than 20%. Additionally, the integration of VMD outperformed both the standard Seq2Seq and Ensemble Empirical Mode Decomposition (EEMD)-enhanced Seq2Seq models, showcasing the advantages of VMD in predicting SO₂ decline. This research highlights the potential of the RF-VMD-Seq2Seq model for non-stationary SO₂ prediction and its relevance for environmental protection and public health management. Full article

Accurate prediction of the on-orbit positions of Low Earth Orbit (LEO) satellites is essential for mission success, operational efficiency, and safety. Nevertheless, the non-stationary nature of orbital data and sensor noise presents significant challenges for accurate prediction. To address these challenges, we propose a novel forecasting model, EMD-ICA-DLinear, which combines trend-residual representation with EMD-ICA in an innovative manner. By integrating the TSR (Trend, Seasonality, and Residual) framework with the EMD-ICA dual perspective, this approach provides a comprehensive understanding of time series data and outperforms traditional models in capturing subtle nonlinear relationships. When predicting the orbital position of the Fengyun-3C satellite, the model uses MSE and MAE as evaluation metrics. Experimental results indicate that the proposed EMD-ICA-DLinear hybrid model achieves MSE and MAE values of 0.1101 and 0.1567, respectively, when predicting the orbital position of the Fengyun-3C satellite 6 h in advance, representing reductions of 37.87% and 19.85% compared to the best baseline model, TimesNet. This advancement enhances satellite orbit prediction accuracy, supports operational stability, and enables timely adjustments, thereby improving mission efficiency and safety. Full article

This research applies continuous wavelet analysis and seasonal correlation analysis to tree-ring data from Três Barras National Forest (FLONA Três Barras), revealing diverse influences on growth, including climate, solar activity, and external factors. The methodology involved tree-ring collection and subsequent wavelet and seasonal analyses to unveil the non-stationary characteristics of and multifaceted influences on growth. Key findings include the subtle effects of El Niño events on tree-ring development, the sensitivity of Araucaria angustifolia to temperature changes, the significant influence of precipitation during drought periods, and the intricate relationship between tree growth and solar cycles. The El Niño–Southern Oscillation (ENSO) emerges as a primary climatic driver during specific intervals, with external factors (precipitation, temperature, and solar cycle–solar irradiance) influencing tree response between 1936 and 1989. Additionally, the seasonal correlation analysis highlighted the importance of sub-annual climate variability, capturing specific intervals, such as a 3-month season ending in March of the previous year, that significantly impacted tree-ring growth. The study underscores the importance of protecting the endangered Araucaria angustifolia for climatic studies and local communities. Historically, in Brazil, Araucaria angustifolia seeds played a vital role in sustaining indigenous populations, which in turn helped to disperse and propagate forests, creating anthropogenic landscapes that highlight the interconnected relationship between humans and the preservation of these forests. Full article