Search Results (80)

Significant wave height (SWH) is a key descriptor of sea state, yet providing accurate, site-specific forecasts at low computational cost remains challenging. This study proposes a transfer-learning-based framework for SWH forecasting that combines Seasonal and Trend decomposition using Loess (STL), a stacked long short-term memory (LSTM) network, and an efficient sliding-window updating scheme. First, STL is applied to decompose the SWH time series into trend, seasonal, and remainder components; the resulting sub-series are then fed into a transfer-learning architecture in which the parameters of the stacked LSTM backbone are kept fixed, and only a fully connected output layer is updated in each window. Using multi-year observations from five National Data Buoy Center (NDBC) buoys, the proposed STL-LSTM-T model is compared with a STL-LSTM configuration that is fully retrained after each STL decomposition. For example, the transfer-learning setup reduces MAE, MSE, and RMSE by up to 11.2%, 19.2%, and 14.5% at buoy 46244, respectively, while reducing the average training time per update to about one-fifth of the baseline. Parameter analyses indicate that a two-layer LSTM backbone and moderate continuous forecast step (6–12 steps) provide a good balance between predictive accuracy, error accumulation, and computational cost, making STL-LSTM-T suitable for SWH forecasting on resource-constrained platforms. Full article

River ecosystems play a crucial role in the global water cycle and regional ecological security, yet they face severe challenges under the dual pressures of human activities and climate change. To systematically assess the spatiotemporal characteristics and driving mechanisms of river ecological impacts, this study proposes a modular and transferable method, which is Quantitative Analysis of Spatiotemporal Variations in Ecological Water-Supplementation Benefits of Rivers Based on Remote Sensing (QASViewSBR). Taking the Yongding River (Beijing section) from 2016 to 2023 as a case study, this research integrates multi-source remote sensing and ground monitoring data to extract river water bodies using an improved Normalized Difference Water Index and Vertical–Horizontal polarization characteristics. The Seasonal and Trend decomposition using Loess (STL) method was employed for time-series trend decomposition, Pearson correlation analysis was applied to identify driving factors of area changes, and the Pelt algorithm was used to quantify the response range of riparian vegetation to changes of river water levels. An integrated analytical framework of “dynamic monitoring—time series analysis—driving factor identification—spatial heterogeneity assessment” was established, enabling standardized end-to-end analysis from data acquisition to evaluation. The results indicate that the river water area in the basin increased significantly after 2019, with enhanced seasonal fluctuations. Under the ecological water supplementation policy, the “human-initiated, natural-response” mechanism was clearly observed, and the ecological responses along both riverbanks exhibited significant spatial heterogeneity due to variations in surface features and topography. QASViewSBR exhibits good universality and transferability, providing methodological support for ecological restoration and management in different river basins. Full article

Understanding the seasonal behaviour of sewer failures is essential for infrastructure reliability and sustainable asset management. This study presents a seasonality-centred, data-driven analysis of monthly sewer failures over a 15-year period (2010–2024) in a major city in south-eastern Poland. The assessment is based exclusively on operational failure records, allowing intrinsic temporal regularities to be extracted without the use of external meteorological covariates. Seasonal Decomposition of Time Series by LOESS (STL), Autocorrelation Function (ACF), Seasonal Index (SI) and the Winter–Summer Index (WSI) were applied to quantify periodicity, seasonal amplitude and long-term variability. The results confirm a pronounced annual cycle, with failures peaking around March and reaching minima in September, supported by a strong autocorrelation at a 12-month lag (r ≈ 0.45). The mean WSI value (1.05) indicates a nearly balanced but still winter-sensitive pattern, while annual WSI values ranged from 0.71 to 1.51. The STL seasonal amplitude remained structurally stable at ≈61 failures throughout the study period, while annual values showed a modest but statistically significant increasing tendency. Trend analysis showed no significant monotonic trend in the deseasonalized series (Z ≈ 0.89, p = 0.37), whereas the raw series exhibited a weak but significant upward trend (τ ≈ 0.33, p < 0.001), largely attributable to short-term operational variability rather than to changes in intrinsic failure rate. The study demonstrates that long-term operational data alone are sufficient to capture seasonal and long-term dynamics in sewer failures. The presented framework supports utilities in integrating seasonality diagnostics into preventive maintenance, resource allocation and resilience planning, even in the absence of detailed climatic datasets. Full article

Highway interchanges are vulnerable components of transport networks, often prone to congestion and crashes. Traditional monitoring methods like loop detectors or travel time queries often fail to capture the granular spatiotemporal distribution of bottlenecks in detail. To address this gap, this study introduces a new approach to quantify congestion and analyze bottleneck dynamics at Atlanta’s Tom Moreland Interchange, one of the nation’s most congested sites. A percent Traffic Congestion (pTC) metric was developed from the Google Maps Traffic Layer for twelve directional routes and validated against observed travel times obtained independently through the Google Maps Routes API. Traffic imagery collected every ten minutes for four months and 746 crash records were analyzed. Findings reveal distinct spatial patterns and temporal dynamics of congestion, with northbound I-85 and eastbound I-285 most affected during afternoon peaks. A quadratic model provided the best fit between pTC and travel times (R² = 0.85), confirming pTC as a reliable congestion indicator. An LSTM model using pTC time series also accurately predicted mobility trends at the I-285 west to I-85 north bottleneck. Additionally, Seasonal-Trend decomposition using LOESS (STL) identified congestion anomalies, and their association was analyzed with crashes. The proposed methodology offers transportation agencies a cost-effective framework for monitoring, measuring, and understanding congestion in complex interchanges. Full article

Time-series anomaly detection is imperative for ensuring reliability and safety in intelligent manufacturing systems. However, real-world environments typically provide only normal operating data and exhibit significant periodicity, noise, imbalance, and domain variability. The present study proposes CL-OCC, a contrastive learning-based one-class framework that integrates seasonal-trend decomposition using loess (STL) for structure-preserving temporal augmentation, a cosine-regularized soft boundary for compact normal-region formation, and variance-preserving regularization to prevent latent collapse. A convolutional recurrent encoder is first pretrained via an autoencoder objective and subsequently optimized through a unified loss that balances contrastive invariance, soft-boundary constraint, and variance dispersion. Experiments on semiconductor equipment data and three public benchmarks demonstrate that CL-OCC provides competitive or superior performance relative to reconstruction-, prediction-, and contrastive-based baselines. CL-OCC exhibits smoother anomaly trajectories, earlier detection of gradual drifts, and strong robustness to noise, window-length variation, and extreme class imbalance. A study of the effects of ablation and interaction on the stability of representations indicates that STL-based augmentation, boundary shaping, and variance regularization contribute complementary benefits to this stability. While the qualitative results indicate limited sensitivity to extremely short impulsive disturbances, the proposed framework delivers a generalizable and stable solution for unsupervised industrial monitoring, with promising potential for extension to multi-resolution analysis and online prognostics and health management (PHM) applications. Full article

By altering aquifer storage capacity, groundwater level (GWL) plays a critical role in driving surface deformation, including ground subsidence and uplift. Groundwater depletion can induce sinkholes or subsidence, whereas recharge can cause surface uplift. These processes pose significant risks to soft grounds composed of soft alluvial sediments, emphasizing the importance of regular monitoring. In this study, we applied the small baseline subset (SBAS) technique to conduct a time-series analysis of surface deformation in Gimhae City, South Korea, where a continuous GWL increase was observed. Seasonal trend decomposition using the Loess (STL) method was employed to isolate the long-term GWL trend by removing seasonal variability. Multi-frequency synthetic aperture radar datasets, including ALOS PALSAR, COSMO-SkyMed, and Sentinel-1, revealed a cumulative surface uplift of approximately 9.2 cm, primarily concentrated along the deepest GWL contour line and confined between two lineament structures. The decomposed velocities from Sentinel-1 highlighted the predominance of vertical displacement over horizontal movement. Time-series analyses consistently showed uplift patterns, whereas correlation analysis demonstrated a strong relationship (R² > 0.75) between surface deformation and GWL changes from 2013 to 2021. These results suggest a significant link between surface uplift and the rising GWL in Gimhae City, providing insights into the hydrogeological processes that influence ground deformation. Furthermore, a time lag between the GWL changes and surface displacement was identified, providing valuable insights into the dynamics of groundwater-related surface deformation. Full article

This study examines long-term trends in maximum (Tmax) and minimum (Tmin) near-surface air temperatures and precipitation across South America, focusing on Brazilian biomes and national capitals, using ERA5 reanalysis data for 1979–2024. To isolate the underlying climate signal, seasonal cycles were removed using Seasonal-Trend decomposition based on Loess (STL), which effectively separates short-term variability from long-term trends. Temperature trends were quantified using ordinary least squares (OLS) regression, allowing consistent estimation of linear changes over time, while precipitation trends were assessed using the non-parametric Mann–Kendall test combined with Theil–Sen slope estimation, a robust approach that minimizes the influence of outliers and serial correlation in hydroclimatic data. Results indicate widespread but spatially heterogeneous warming, with Tmax increasing faster than Tmin, consistent with reduced cloudiness and evaporative cooling. A meridional precipitation dipole is evident, with drying across the Cerrado, Pantanal, Caatinga, and Pampa, contrasted by rainfall increases in northern South America linked to ITCZ shifts. The Pantanal emerges as the most vulnerable biome, showing strong warming (+0.51 °C decade⁻¹) and the steepest rainfall decline (−10.45 mm decade⁻¹). Satellite-based fire detections (2013–2024) reveal rising wildfire activity in the Amazon, Pantanal, and Cerrado, aligning with the “hotter and drier” climate regime. In the capitals, persistent Tmax increases suggest enhanced urban heat island effects, with implications for public health and energy demand. Although ERA5 provides coherent spatial coverage, regional biases and sparse in situ observations introduce uncertainties, particularly in the Amazon and Andes, these do not alter the principal finding that the magnitude and persistence of the 1979–2024 warming lie well above the range of interdecadal variability typically associated with the Atlantic Multidecadal Oscillation (AMO) and the Pacific Decadal Oscillation (PDO). This provides strong evidence that the recent warming is not cyclical but reflects the externally forced secular warming signal. These findings underscore growing fire risk, ecosystem stress, and urban vulnerability, highlighting the urgency of targeted adaptation and resilience strategies under accelerating climate change. Full article

Accurate forecasting of carbon emissions is not only essential for addressing the challenges of climate governance but also provides timely support for dynamic carbon quota adjustments and emergency emission reduction decisions. In this study, we take China’s daily carbon emission data from 2021 to 2024 as the research objects and propose a novel forecasting framework called STL-wLSTM-SVR based on seasonal-trend decomposition with Loess (STL), long short-term memory network (LSTM) and support vector regression (SVR). First, the original carbon emission sequence is decomposed via STL into seasonal, trend and residual components. Subsequently, LSTM is employed to predict the seasonal and trend components with hyper-parameters optimized by whale optimization algorithm (WOA), and SVR is used to predict the residual component with parameters optimized through grid search method. Then, the final results are obtained by accumulating the forecasted values of the three subsequences. The experimental results illustrate that the STL-wLSTM-SVR model achieved a high-precision forecast for China’s total daily carbon emissions (RMSE of 0.1129, MAPE of 0.28%, MAE of 0.0851) and demonstrated remarkable adaptability for five major sectors—from navigating the high volatility of ground transport (MAPE of 0.36%) to effectively handling the dramatic post-pandemic structural break in aviation (MAPE of 0.72%). These findings assess the effectiveness of the hybrid forecasting framework and provide a valuable methodological reference for similar prediction tasks, such as sector-specific pollutant emissions and regional energy consumption. Full article

Air pollution, outstanding particulate matter (PM_2.5), poses severe risks to human health and the environment in densely populated urban areas. Accurate short-term forecasting of PM_2.5 concentrations is therefore crucial for timely public health advisories and effective mitigation strategies. This work proposes a hybrid approach that combines machine learning models with STL decomposition to provide precise short-term PM_2.5 predictions. Daily PM_2.5 series from four major Pakistani cities—Islamabad, Lahore, Karachi, and Peshawar—are first pre-processed to handle missing values, outliers, and variance instability. The data are then decomposed via seasonal-trend decomposition using Loess (STL), which explicitly exploits the symmetric and recurrent structure of seasonal patterns. Each decomposed component (trend, seasonality, and remainder) is modeled independently using an ensemble of statistical and machine learning approaches. Forecasts are combined through a weighted aggregation scheme that balances bias–variance trade-offs and preserves the distributional consistency. The final recombined forecasts provide one-day-ahead PM_2.5 predictions with associated uncertainty measures. The model evaluation employs multiple statistical accuracy metrics, distributional diagnostics, and out-of-sample validation to assess its performance. The results demonstrate that the proposed framework consistently outperforms conventional benchmark models, yielding robust, interpretable, and probabilistically coherent forecasts. This study demonstrates how periodic and recurrent seasonal structure decomposition and probabilistic ensemble methods enhance the statistical modeling of environmental time series, offering actionable insights for urban air quality management. Full article

Considering the limited availability of meteorological data in practice, this paper investigates the short-term photovoltaic output prediction problem based on data decomposition and error correction to further improve prediction accuracy. Firstly, according to the analysis of the variation characteristics of photovoltaic output data, the Seasonal and Trend decomposition using Loess (STL) method is used to decompose the original data into three components: seasonal term, trend term, and residual term. Considering that the variation patterns of different components are different, based on the division of the dataset, temporal convolutional network (TCN)-based prediction models for each component are constructed separately, and the prediction results are superimposed to obtain the predicted value of the photovoltaic output. Secondly, an error dataset is constructed based on the prediction errors of the training set and validation set, and a TCN error prediction model is established. The error prediction value is used as compensation to correct the photovoltaic output prediction value, and the final photovoltaic output prediction value is obtained. Finally, based on the measured photovoltaic output data of a certain region in China, the effectiveness and advancement of the proposed method are demonstrated through the ablation and comparative experiments. Full article

Open-pit mining often induces geological hazards such as slope instability, surface subsidence, and ground fissures. To support sustainable mine operations and safety, high-resolution monitoring and mechanism-based interpretation are essential tools for early warning, risk management, and compliant reclamation. This study focuses on the Baorixile open-pit coal mine in Inner Mongolia, China, where 48 Sentinel-1 images acquired between 3 March 2017 and 23 April 2021 were processed using the Small-Baseline Subset and Distributed-Scatterer Interferometric Synthetic Aperture Radar (SBAS-DS-InSAR) technique to obtain dense and reliable time-series deformation. Furthermore, a Trend–Periodic–Residual Subspace-Constrained Regression (TPRSCR) method was developed to decompose the deformation signals into long-term trends, seasonal and annual components, and residual anomalies. By introducing Distributed-Scatterer (DS) phase optimization, the monitoring density in low-coherence regions increased from 1055 to 338,555 points (approximately 321-fold increase). Deformation measurements at common points showed high consistency ($R^2$ = 0.97, regression slope = 0.88; mean rate difference = −0.093 mm/yr, standard deviation = 3.28 mm/yr), confirming the reliability of the results. Two major deformation zones were identified: one linked to ground compaction caused by transportation activities, and the other associated with minor subsidence from pre-mining site preparation. In addition, the deformation field exhibits a superimposed pattern of persistent subsidence and pronounced seasonality. TPRSCR results indicate that long-term trend rates range from −14.03 to 14.22 mm/yr, with a maximum periodic amplitude of 40 mm. Compared with the Seasonal-Trend decomposition using LOESS (STL), TPRSCR effectively suppressed “periodic leakage into trend” and reduced RMSEs of total, trend, and periodic components by 48.96%, 93.33%, and 89.71%, respectively. Correlation analysis with meteorological data revealed that periodic deformation is strongly controlled by precipitation and temperature, with an approximately 34-day lag relative to the temperature cycle. The proposed “monitoring–decomposition–interpretation” framework turns InSAR-derived deformation into sustainability indicators that enhance deformation characterization and guide early warning, targeted upkeep, climate-aware drainage, and reclamation. These metrics reduce downtime and resource-intensive repairs and inform integrated risk management in open-pit mining. Full article

Accurate prediction of river runoff is significant for flood control, water resource allocation, and basin ecological management. Despite the promise of integrating signal decomposition with deep learning, current decomposition-based hybrid models face critical forward data contamination: decomposition algorithms improperly access future test data in full-series applications, artificially inflating prediction accuracy. In contrast, the stepwise decomposition method currently proposed leads to high computational costs. To address this limitation, we introduce a novel framework integrating segmented decomposition sampling with a multi-input neural network. Specifically, a hybrid forecasting model combining Seasonal-Trend decomposition using Loess (STL) and Convolutional Long Short-Term Memory (CNN-LSTM) networks was implemented for daily runoff estimation. Method reliability was evaluated using historical runoff data from Huaxian Station in China’s Weihe River Basin, with comparative experiments conducted against established single and hybrid models. The results showed that the proposed framework can effectively avoid future information leakage and simultaneously improve prediction accuracy. For 1–3-day-ahead Nash-Sutcliffe efficiency (NSE) at Huaxian Station, the STL-CNN-LSTM model achieved values of 0.96, 0.83, and 0.80, respectively—representing improvements of 5.49%, 5.06%, and 12.68% over the VMD-CNN-LSTM model. This STL-based configuration outperformed the standalone LSTM counterpart by 23.08%, 9.21%, and 17.65% in NSE, respectively. Therefore, the proposed framework, which incorporates the segmented decomposition sampling method and a multi-input neural network, proves to be both practical and reliable. Full article

Nowadays, climate change is one of the significant threats humanity faces. Many researchers have documented its effects on water availability and vulnerable systems. This study examines the long-term precipitation record (1965–2019) from the Tulcea station, located just 4 km from the Danube Delta Biosphere Reserve (DDBR), to evaluate the impact of climate change on precipitation variability, which can significantly affect biodiversity in this protected area. We integrated change point detection (CPD), stationarity tests, trend analysis, and series decomposition to characterize shifts and patterns in the time series. The Lee & Heghinian test detected a change point (CP) in all data series, whereas the Hubert segmentation methods and Cumulative Sum Method (CUSUM) found fewer series that present at least a CP. The Mann–Kendall (MK) trend test and Innovative Trend Analysis (ITA) indicated an increasing trend in the annual, monthly, and October precipitation series. The Seasonal-Trend decomposition using Loess STL decomposition found the highest seasonality indices in June and July. The Ensemble Empirical Mode Decomposition (EEMD) emphasizes a substantial difference in the seasonal cycle. The results indicate a high variability in the precipitation pattern, with periods of high precipitation followed by dry periods. Full article

High energy-consuming industrial parks are characterized by high base-load-to-peak-valley ratios, overlapping production cycles, and megawatt-scale step changes, which significantly complicate short-term load forecasting. To tackle these challenges, this study proposes a novel forecasting framework that combines hierarchical multimodal decomposition with a hybrid deep learning architecture. First, Maximal Information Coefficient (MIC) analysis is applied to identify key input features and eliminate redundancy. The load series is then decomposed in two stages: seasonal-trend decomposition uses the Loess (STL) isolates trend and seasonal components, while variational mode decomposition (VMD) further disaggregates the residual into multi-scale modes. This hierarchical approach enhances signal clarity and preserves temporal structure. A parallel neural architecture is subsequently developed, integrating an Informer network to model long-term trends and a bidirectional gated recurrent unit (BiGRU) to capture short-term fluctuations. Case studies based on real-world load data from a typical industrial park in northeastern China demonstrate that the proposed model achieves significantly improved forecasting accuracy and robustness compared to benchmark methods. These results provide strong technical support for fine-grained load prediction and intelligent dispatch in high energy-consuming industrial scenarios. Full article

Lubricating oil degradation directly impacts friction coefficient, wear rate, and lubrication regime transitions, making precise health quantification essential for predictive tribological maintenance. However, conventional evaluation methods fail to capture subtle tribological changes preceding lubrication failure, often oversimplifying complex multi-parameter relationships critical to friction and wear performance. To address this challenge, this study proposes Seasonal–Trend decomposition using Loess, a Factor Attention Network, a Temporal Convolutional Network, and an Informer with Long Short-Term Memory Variational Autoencoder (SFTI-LVAE) framework for continuous tribological health assessment of diesel engine lubricants. The approach integrates Seasonal–Trend decomposition using Loess (STL) for trend–seasonal separation, a Factor Attention Network (FAN) for multidimensional feature fusion, and a Temporal Convolutional Network (TCN)-enhanced Informer for capturing long-term tribological dependencies. By combining Long Short-Term Memory (LSTM) temporal modeling with Variational Autoencoder (VAE) reconstruction, the method quantifies lubricant health through reconstruction error, establishing a direct correlation between data deviation and tribological performance degradation. Additionally, permutation importance-based feature evaluation and parameter contribution quantification techniques enable deep mechanistic analysis and fault source tracing of lubricant health degradation. Experimental validation using multi-sensor monitoring data demonstrates that SFTI-LVAE achieves a 96.67% fault detection accuracy with zero false alarms, providing early warning 6.47 h before lubrication failure. Unlike traditional anomaly detection methods that only classify conditions as abnormal or normal, the proposed continuous health index reveals gradual tribological degradation processes, capturing subtle viscosity–temperature relationships and wear particle evolution indicating early lubrication regime transitions. The health index correlates strongly with tribological performance indicators, enabling a transition from reactive maintenance to predictive tribological management, providing an innovative solution for equipment health evaluation in the digital tribology era. Full article