Search Results (554)

Climate-driven hydrological extremes and anthropogenic interventions are increasingly altering streamflow regimes worldwide. While prior studies have explored climate or regulation effects separately, few have integrated multiple teleconnection indices and reservoir chronologies within a cross-basin comparative framework. This study addresses this gap by assessing long-term streamflow nonstationarity and its drivers at two key stations—Khabarovsk on the Amur River and Datong on the Yangtze River—representing distinct hydroclimatic settings. We utilized monthly discharge records, meteorological data, and large-scale climate indices to apply trend analysis, wavelet transform, percentile-based extreme diagnostics, lagged random forest regression, and slope-based attribution. The results show that Khabarovsk experienced an increase in winter baseflow from 513 to 1335 m³/s and a notable reduction in seasonal discharge contrast, primarily driven by temperature and cold-region reservoir regulation. In contrast, Datong displayed increased discharge extremes, with flood discharges increasing by +71.9 m³/s/year, equivalent to approximately 0.12% of the mean flood discharge annually, and low discharges by +24.2 m³/s/year in recent decades, shaped by both climate variability and large-scale hydropower infrastructure. Random forest models identified temperature and precipitation as short-term drivers, with ENSO-related indices showing lagged impacts on streamflow variability. Attribution analysis indicated that Khabarovsk is primarily shaped by cold-region reservoir operations in conjunction with temperature-driven snowmelt dynamics, while Datong reflects a combined influence of both climate variability and regulation. These insights may provide guidance for climate-responsive reservoir scheduling and basin-specific regulation strategies, supporting the development of integrated frameworks for adaptive water management under climate change. Full article

Forestry carbon sinks play a crucial role in mitigating climate change and protecting ecosystems, significantly contributing to the development of carbon trading systems. Remote sensing technology has become increasingly important for monitoring carbon sinks, as it allows for precise measurement of carbon storage and ecological changes, which are vital for forecasting carbon prices. Carbon prices fluctuate due to the interaction of various factors, exhibiting non-stationary characteristics and inherent uncertainties, making accurate predictions particularly challenging. To address these complexities, this study proposes a method for predicting carbon trading prices influenced by multiple factors. We introduce a Decomposition (DECOMP) module that separates carbon price data and its influencing factors into trend and cyclical components. To manage non-stationarity, we propose the KAN with Multi-Domain Diffusion (KAN-MD) module, which efficiently extracts relevant features. Furthermore, a Wave-MH attention module, based on wavelet transformation, is introduced to minimize interference from uncertainties, thereby enhancing the robustness of the model. Empirical research using data from the Hubei carbon trading market demonstrates that our model achieves superior predictive accuracy and resilience to fluctuations compared to other benchmark methods, with an MSE of 0.204% and an MAE of 0.0277. These results provide reliable support for pricing carbon financial derivatives and managing associated risks. Full article

Motor imagery (MI) electroencephalograms (EEGs) are pivotal cortical potentials reflecting cortical activity during imagined motor actions, widely leveraged for brain-computer interface (BCI) system development. However, effectively decoding these MI EEG signals is often overshadowed by flawed methods in signal processing, deep learning methods that are clinically unexplained, and highly inconsistent performance across different datasets. We propose BCINetV1, a new framework for MI EEG decoding to address the aforementioned challenges. The BCINetV1 utilizes three innovative components: a temporal convolution-based attention block (T-CAB) and a spectral convolution-based attention block (S-CAB), both driven by a new convolutional self-attention (ConvSAT) mechanism to identify key non-stationary temporal and spectral patterns in the EEG signals. Lastly, a squeeze-and-excitation block (SEB) intelligently combines those identified tempo-spectral features for accurate, stable, and contextually aware MI EEG classification. Evaluated upon four diverse datasets containing 69 participants, BCINetV1 consistently achieved the highest average accuracies of 98.6% (Dataset 1), 96.6% (Dataset 2), 96.9% (Dataset 3), and 98.4% (Dataset 4). This research demonstrates that BCINetV1 is computationally efficient, extracts clinically vital markers, effectively handles the non-stationarity of EEG data, and shows a clear advantage over existing methods, marking a significant step forward for practical BCI applications. Full article

Accurate short-term weather forecasting plays a vital role in disaster response, agriculture, and energy management, where timely and reliable predictions are essential for decision-making. Graph neural networks (GNNs), known for their ability to model complex spatial structures and relational data, have achieved remarkable success in meteorological forecasting by effectively capturing spatial dependencies among distributed weather stations. However, most existing GNN-based approaches rely on pairwise station connections, limiting their capacity to represent higher-order spatial interactions. Moreover, their dependence on supervised learning makes them vulnerable to spatial heterogeneity and temporal non-stationarity. This paper introduces a novel spatial–temporal pretraining framework, Hypergraph-enhanced Meteorological Pretraining (HyMePre), which combines hypergraph neural networks with self-supervised learning to model high-order spatial dependencies and improve generalization across diverse climate regimes. HyMePre employs a two-stage masking strategy, applying spatial and temporal masking separately, to learn disentangled representations from unlabeled meteorological time series. During forecasting, dynamic hypergraphs group stations based on meteorological similarity, explicitly capturing high-order dependencies. Extensive experiments on large-scale reanalysis datasets show that HyMePre outperforms conventional GNN models in predicting temperature, humidity, and wind speed. The integration of pretraining and hypergraph modeling enhances robustness to noisy data and improves generalization to unseen climate patterns, offering a scalable and effective solution for operational weather forecasting. Full article

This study analyzes air pollution time-series big data to assess stationarity, seasonal patterns, and the performance of machine learning models in forecasting PM2.5 concentrations. Fifty-two low-cost sensors (LCS) were deployed across Krakow city and its surroundings (Poland), collecting hourly air quality data and generating nearly 20,000 observations per month. The network captured both spatial and temporal variability. The Kwiatkowski–Phillips–Schmidt–Shin (KPSS) test confirmed trend-based non-stationarity, which was addressed through differencing, revealing distinct daily and 12 h cycles linked to traffic and temperature variations. Additive seasonal decomposition exhibited time-inconsistent residuals, leading to the adoption of multiplicative decomposition, which better captured pollution outliers associated with agricultural burning. Machine learning models—Ridge Regression, XGBoost, and LSTM (Long Short-Term Memory) neural networks—were evaluated under high spatial and temporal variability (winter) and low variability (summer) conditions. Ridge Regression showed the best performance, achieving the highest $R^2$ (0.97 in winter, 0.93 in summer) and the lowest mean squared errors. XGBoost showed strong predictive capabilities but tended to overestimate moderate pollution events, while LSTM systematically underestimated PM2.5 levels in December. The residual analysis confirmed that Ridge Regression provided the most stable predictions, capturing extreme pollution episodes effectively, whereas XGBoost exhibited larger outliers. The study proved the potential of low-cost sensor networks and machine learning in urban air quality forecasting focused on rare smog episodes (RSEs). Full article

The spread of COVID-19 is influenced by multiple factors, including control policies, virus characteristics, individual behaviors, and environmental conditions, exhibiting highly complex nonlinear dynamic features. The time series of new confirmed cases shows significant nonlinearity and non-stationarity. Traditional prediction methods that rely solely on one-dimensional case data struggle to capture the multi-dimensional features of the data and are limited in handling nonlinear and non-stationary characteristics. Their prediction accuracy and generalization capabilities remain insufficient, and most existing studies focus on single-step forecasting, with limited attention to multi-step prediction. To address these challenges, this paper proposes a multi-module fusion prediction model—TSMixer-BiKSA network—that integrates multi-feature inputs, Variational Mode Decomposition (VMD), and a dual-branch parallel architecture for 1- to 3-day-ahead multi-step forecasting of new COVID-19 cases. First, variables highly correlated with the target sequence are selected through correlation analysis to construct a feature matrix, which serves as one input branch. Simultaneously, the case sequence is decomposed using VMD to extract low-complexity, highly regular multi-scale modal components as the other input branch, enhancing the model’s ability to perceive and represent multi-source information. The two input branches are then processed in parallel by the TSMixer-BiKSA network model. Specifically, the TSMixer module employs a multilayer perceptron (MLP) structure to alternately model along the temporal and feature dimensions, capturing cross-time and cross-variable dependencies. The BiGRU module extracts bidirectional dynamic features of the sequence, improving long-term dependency modeling. The KAN module introduces hierarchical nonlinear transformations to enhance high-order feature interactions. Finally, the SA attention mechanism enables the adaptive weighted fusion of multi-source information, reinforcing inter-module synergy and enhancing the overall feature extraction and representation capability. Experimental results based on COVID-19 case data from Italy and the United States demonstrate that the proposed model significantly outperforms existing mainstream methods across various error metrics, achieving higher prediction accuracy and robustness. Full article

Understanding the impacts of the spatial non-stationarity of environmental factors on surface soil moisture (SSM) in different seasons is crucial for effective environmental management. Yet, our knowledge of this phenomenon remains limited. This study introduces an interpretable machine learning framework that combines the SHapley Additive exPlanations (SHAP) method with two-step clustering to unravel the spatial drivers of SSM across Iran. Due to the limited availability of in situ SSM data, the performance of three global SSM datasets—SMAP, MERRA-2, and CFSv2—from 2015 to 2023 was evaluated using agrometeorological stations. SMAP outperformed the others, showing the highest median correlation and the lowest Root Mean Square Error (RMSE). Using SMAP, we estimated SSM across 609 catchments employing the Random Forest (RF) algorithm. The RF model yielded R² values of 0.89, 0.83, 0.70, and 0.75 for winter, spring, summer, and autumn, respectively, with corresponding RMSE values of 0.076, 0.081, 0.098, and 0.061 m³/m³. SHAP analysis revealed that climatic factors primarily drive SSM in winter and autumn, while vegetation and soil characteristics are more influential in spring and summer. The clustering results showed that Iran’s catchments can be grouped into five categories based on the SHAP method coefficients, highlighting regional differences in SSM controls. Full article

As the global energy system accelerates its transition toward a low-carbon economy, renewable energy sources (RESs), such as wind and photovoltaic power, are rapidly replacing traditional fossil fuels. These RESs are becoming a critical element of deeply decarbonized power systems (DDPSs). However, the inherent non-stationarity, multi-scale volatility, and uncontrollability of RES output significantly increase the risk of source–load imbalance, posing serious challenges to the reliability and economic efficiency of power systems. Scenario generation technology has emerged as a critical tool to quantify uncertainty and support dispatch optimization. Nevertheless, conventional scenario generation methods often fail to produce highly credible wind and solar output scenarios. To address this gap, this paper proposes a novel renewable energy scenario generation method based on a multi-resolution diffusion model. To accurately capture fluctuation characteristics across multiple time scales, we introduce a diffusion model in conjunction with a multi-scale time series decomposition approach, forming a multi-stage diffusion modeling framework capable of representing both long-term trends and short-term fluctuations in RES output. A cascaded conditional diffusion modeling framework is designed, leveraging historical trend information as a conditioning input to enhance the physical consistency of generated scenarios. Furthermore, a forecast-guided fusion strategy is proposed to jointly model long-term and short-term dynamics, thereby improving the generalization capability of long-term scenario generation. Simulation results demonstrate that MDDPM achieves a Wasserstein Distance (WD) of 0.0156 in the wind power scenario, outperforming DDPM (WD = 0.0185) and MC (WD = 0.0305). Additionally, MDDPM improves the Global Coverage Rate (GCR) by 15% compared to MC and other baselines. Full article

A geographically and temporally weighted regression (GTWR) model is an effective tool for dealing with spatial heterogeneity and temporal non-stationarity simultaneously. As an important characteristic of spatiotemporal data, spatiotemporal autocorrelation should be considered when constructing spatiotemporally varying coefficient models. The proposed local autoregressive geographically and temporally weighted regression (GTWRLAR) model can simultaneously handle spatiotemporal autocorrelations among response variables and the spatiotemporal heterogeneity of regression relationships. The two-stage weighted least squares (2SLS) estimation can effectively reduce computational complexity. However, the weighted least squares estimation is essentially a Nadaraya–Watson kernel-smoothing approach for nonparametric regression models, and it suffers from a boundary effect. For spatiotemporally varying coefficient models, the three-dimensional spatiotemporal coefficients (longitude, latitude, and time) inherently exhibit larger boundaries than one-dimensional intervals. Therefore, the boundary effect of the 2SLS estimation of GTWRLAR will be more serious. A local–linear geographically and temporally weighted 2SLS (GTWRLAR-L) estimation is proposed to correct the boundary effect in both the spatial and temporal dimensions of GTWRLAR and simultaneously improve parameter estimation accuracy. The simulation experiment shows that the GTWRLAR-L method reduces the root mean square error (RMSE) of parameter estimates compared to the standard GTWRLAR approach. Empirical analyses of carbon emissions in China’s Yellow River Basin (2017–2021) show that GTWRLAR-L enhances the adjusted $R^2$ from 0.888 to 0.893. Full article

To address the challenges of weak fault features and strong non-stationarity in early-stage vibration signals, this study proposes a novel fault diagnosis method combining enhanced variational mode decomposition (VMD) with a structurally improved GoogLeNet. Specifically, an improved wild horse optimizer (IWHO) with tent chaotic mapping is employed to automatically optimize critical VMD parameters, including the number of modes K and the penalty factor α, enabling precise decomposition of non-stationary signals to extract weak fault features. The vibration signal is decomposed, and the top five intrinsic mode functions (IMFs) are selected based on the kurtosis criterion. Time–frequency features are then extracted from these IMFs and input into a modified GoogLeNet classifier. The GoogLeNet structure is improved by replacing standard n × n convolution kernels with cascaded 1 × n and n × 1 kernels, and by substituting the ReLU activation function with a parameterized TReLU function to enhance adaptability and convergence. Experimental results on two public rolling bearing datasets demonstrate that the proposed method effectively handles non-stationary signals, achieving 99.17% accuracy across four fault types and maintaining over 95.80% accuracy under noisy conditions. Full article

Reliable damage detection in operational offshore wind turbines (OWTs) remains challenging due to the inherent non-stationarity of environmental excitations and signal degradation from noise-contaminated partial measurements. To address these limitations, this study proposes a robust damage detection method for OWTs under non-stationary ambient excitations using partial measurements with strong noise resistance. The method is first developed for a scenario with known non-stationary ambient excitations. By reformulating the time-domain equation of motion in terms of non-stationary cross-correlation functions, structural stiffness parameters are estimated using partially measured acceleration responses through the extended Kalman filter (EKF). To account for the more common case of unknown excitations, the method is enhanced via the extended Kalman filter under unknown input (EKF-UI). This improved approach enables the simultaneous identification of the physical parameters of OWTs and unknown non-stationary ambient excitations through the data fusion of partial acceleration and displacement responses. The proposed method is validated through two numerical cases: a frame structure subjected to known non-stationary ground excitation, followed by an OWT tower under unknown non-stationary wind and wave excitations using limited measurements. The numerical results confirm the method’s capability to accurately identify structural damage even under significant noise contamination, demonstrating its practical potential for OWTs’ damage detection applications. Full article

Iron ore sintering is a critical process in steelmaking, where the produced sinter is the main raw material for blast furnace ironmaking. The quality and yield of sinter ore directly affect the cost and efficiency of iron and steel production. Accurately predicting the burn-through point (BTP) temperature is of paramount importance for controlling quality and yield. Traditional BTP temperature prediction only utilizes data from bellows, neglecting the information contained in sinter images. This study combines color temperature information extracted from the cross-sectional frame at the discharge end with bellows data. Due to the non-stationarity of the BTP temperature, a hybrid prediction model of the BTP temperature integrating bidirectional long short-term memory and extreme gradient boosting is presented. By combining the advantages of deep learning and tree ensemble learning, a hybrid prediction model of the BTP temperature is established using the color temperature information in the cross-sectional frame at the discharge end and time-series data. Experiments were conducted with the actual running data in an iron and steel enterprise and show that the proposed method has higher accuracy than existing methods, achieving an approximately 4.3% improvement in prediction accuracy. The proposed method can provide an effective reference for decision-making and for the optimization of operating parameters in the sintering process. Full article

Accurately forecasting karst spring discharge remains a significant challenge due to the inherent nonstationarity and multi-scale hydrological dynamics of karst hydrological systems. This study presents a physics-informed variational mode decomposition long short-term memory (VMD-LSTM) model, enhanced with an attention mechanism and Monte Carlo dropout for uncertainty quantification. Hourly discharge data (2013–2018) from the Zhaidi karst spring in southern China were decomposed using VMD to extract physically interpretable temporal modes. These decomposed modes, alongside precipitation data, were input into an attention-augmented LSTM incorporating physics-informed constraints. The model was rigorously evaluated against a baseline standalone LSTM using an 80% training, 15% validation, and 5% testing data partitioning strategy. The results demonstrate substantial improvements in prediction accuracy for the proposed framework compared to the standard LSTM model. Compared to the baseline LSTM, the RMSE during testing decreased dramatically from 0.726 to 0.220, and the NSE improved from 0.867 to 0.988. The performance gains were most significant during periods of rapid conduit flow (the peak RMSE decreased by 67%) and prolonged recession phases. Additionally, Monte Carlo dropout, using 100 stochastic realizations, effectively quantified predictive uncertainty, achieving over 96% coverage in the 95% confidence interval (CI). The developed framework provides robust, accurate, and reliable predictions under complex hydrological conditions, highlighting substantial potential for supporting karst groundwater resource management and enhancing flood early-warning capabilities. Full article

Underwater sonar target recognition is crucial in fields such as national defense, navigation, and environmental monitoring. However, it faces issues such as the complex characteristics of ship-radiated noise, imbalanced data distribution, non-stationarity, and bottlenecks of existing technologies. This paper proposes the MultiFuseNet-AID network, aiming to address these challenges. The network includes the TriFusion block module, the novel lightweight attention residual network (NLARN), the long- and short-term attention (LSTA) module, and the Mamba module. Through the TriFusion block module, the original, differential, and cumulative signals are processed in parallel, and features such as MFCC, CQT, and Fbank are fused to achieve deep multi-domain feature fusion, thereby enhancing the signal representation ability. The NLARN was optimized based on the ResNet architecture, with the SE attention mechanism embedded. Combined with the long- and short-term attention (LSTA) and the Mamba module, it could capture long-sequence dependencies with an O(N) complexity, completing the optimization of lightweight long sequence modeling. At the same time, with the help of feature fusion, and layer normalization and residual connections of the Mamba module, the adaptability of the model in complex scenarios with imbalanced data and strong noise was enhanced. On the DeepShip and ShipsEar datasets, the recognition rates of this model reached 98.39% and 99.77%, respectively. The number of parameters and the number of floating point operations were significantly lower than those of classical models, and it showed good stability and generalization ability under different sample label ratios. The research shows that the MultiFuseNet-AID network effectively broke through the bottlenecks of existing technologies. However, there is still room for improvement in terms of adaptability to extreme underwater environments, training efficiency, and adaptability to ultra-small devices. It provides a new direction for the development of underwater sonar target recognition technology. Full article

Methane (CH₄) emissions from dairy farming represent a substantial yet under-quantified share of agricultural greenhouse gas emissions. This study provides an in-depth, satellite-based fingerprinting analysis of methane emissions from Canada’s dairy sector, using Sentinel-5P/TROPOMI data. We utilized a robust quasi-experimental design, pairing 14 dairy-intensive zones with eight non-dairy reference regions, to analyze methane emissions from 2019 to 2024. A dynamic, region-specific baseline approach was implemented to remove temporal non-stationarity and isolate dairy-specific methane signals. Dairy regions exhibited consistently higher methane concentrations than reference areas, with an average methane anomaly of 17.4 ppb. However, this concentration gap between dairy and non-dairy regions notably narrowed by 57.23% (from 24.42 ppb in 2019 to 10.44 ppb in 2024), driven primarily by accelerated methane increases in non-dairy landscapes and a pronounced one-year contraction during 2022–2023 (−39.29%). Nationally, atmospheric methane levels rose by 3.83%, revealing significant spatial heterogeneity across provinces. Notably, an inverse relationship between the initial methane concentrations in 2019 and subsequent growth rates emerged, indicating spatial convergence. The seasonal analysis uncovered consistent spring minima and fall–winter maxima across regions, reflecting the combined effects of seasonal livestock management practices, atmospheric transport dynamics, and biogeochemical processes. The diminishing dairy methane anomaly suggests complex interplay of intensifying background methane emissions from climate-driven wetland fluxes, increasing fossil fuel extraction activities, and diffuse agricultural emissions. These findings underscore the emerging challenges in attributing sector-specific methane emissions accurately from satellite observations, highlighting both the capabilities and limitations of current satellite monitoring approaches. Full article