Search Results (238)

Accurate forecasting of wind power is essential for maintaining the stability and efficiency of power networks as renewable energy sources become more integrated. This study proposes a multi-level spatial–temporal graph convolution network (MLAGCN) that combines a multi-level adaptive graph convolution (MLAGC) and a temporal transformer module (TTM) for wind power forecasting. Specifically, MLAGC first extracts spatial representations for each turbine at every time step by dynamically modeling local, global, and structural interactions. These spatial embeddings are then organized as temporal sequences and fed into TTM, which captures both short-term fluctuations and long-term temporal dependencies via self-attention. MLAGC is constructed using three adaptive graphs: a local-aware graph, a global-aware graph, and a structure-aware graph. These components form a flexible graph structure that effectively represents dynamic spatial interactions, while TTM learns short- and long-term sequential patterns. Experiments on real wind farm datasets demonstrated that the proposed model outperforms existing baselines. The model achieved improved prediction accuracy and generalization, as indicated by a lower composite score (defined as the average of MAE and RMSE) of 43.44, and a forecast loss of 0.22. These results demonstrate the effectiveness of temporal modeling and multi-level attention-based adaptive graph learning for high-resolution wind power forecasting. Full article

The randomness and volatility of wind power pose significant challenges for short-term forecasting, requiring the model to capture both temporal dynamics and the spatial correlations among turbines. To address this issue, this paper proposes a Spatio-Temporal Adaptive Graph Convolutional Recurrent Network (STAGCRN). The proposed method dynamically constructs and updates the spatial relationship graph through node adaptive parameter learning (NAPL) and a data adaptive graph generation (DAGG) module, enabling more accurate modeling of spatio-temporal dependencies in wind power data. In addition, a spatio-temporal self-attention mechanism is introduced to enhance the model’s ability to capture both short-term fluctuations and long-term temporal patterns. By stacking multiple spatio-temporal adaptive graph convolutional recurrent layers, the model is capable of extracting complex nonlinear characteristics in wind power sequences. Experimental results based on real wind farm data demonstrate that the proposed method achieves significantly improved prediction accuracy and robustness compared with existing approaches in short-term wind power forecasting tasks. Full article

The prompt and precise detection of road damage is vital for effective infrastructure management, forming the foundation for intelligent transportation systems and cost-effective pavement maintenance. While current convolutional neural network (CNN)-based methodologies have made progress, they are fundamentally limited by treating damages as independent, isolated entities, thereby ignoring the intrinsic spatial symmetry and topological organization inherent in complex damage patterns like alligator cracking. This conceptual asymmetry in modeling leads to two major deficiencies: “context blindness,” which overlooks essential structural interrelations, and “temporal inconsistency” in video analysis, resulting in unstable, flickering predictions. To address this, we propose a Spatio-Temporal Graph Mamba You-Only-Look-Once (STG-Mamba-YOLO) network, a novel architecture that introduces a symmetry-informed, hierarchical reasoning process. Our approach explicitly models and integrates contextual dependencies across three levels to restore a holistic and consistent structural representation. First, at the pixel level, a Mamba state-space model within the YOLO backbone enhances the modeling of long-range spatial dependencies, capturing the elongated symmetry of linear cracks. Second, at the object level, an intra-frame damage Graph Network enables explicit reasoning over the topological symmetry among damage candidates, effectively reducing false positives by leveraging their relational structure. Third, at the sequence level, a Temporal Graph Mamba module tracks the evolution of this damage graph, enforcing temporal symmetry across frames to ensure stable, non-flickering results in video streams. Comprehensive evaluations on multiple public benchmarks demonstrate that our method outperforms existing state-of-the-art approaches. STG-Mamba-YOLO shows significant advantages in identifying intricate damage topologies while ensuring robust temporal stability, thereby validating the effectiveness of our symmetry-guided, multi-level contextual fusion paradigm for structural health monitoring. Full article

This study investigated a typical mining area with overlapping uranium and coal resources within the northern Ordos Basin. Based on the hydrogeologic conditions and spatial overlapping relationship of uranium and coal resources, we analyzed critical constraints on coordinated mining of uranium and coal. Using the Groundwater Modeling System, we established a numerical model of the groundwater flow field for coordinated mining of uranium and coal. Accordingly, we characterized the impacts of coal mining on the groundwater level in the uranium area, followed by quantitative prediction of the relationship between the coal mining avoidance distance and the groundwater level in the uranium mining area. Regarding the impacts on the groundwater level, this study proposed priority zones and their time sequence for coal mining. Additionally, based on the time when coal mining avoidance scenarios would influence the groundwater level in the uranium mining area, this study proposed priority zones and their time sequence for uranium mining. By developing an avoidance scheme for coordinated mining of uranium and coal from temporal and spatial aspects, this study provides a theoretical basis for the scientific, coordinated mining of uranium and coal resources. Full article

The kiln head temperature of a rotary kiln is a core process parameter in cement clinker production, and its accurate prediction coupled with uncertainty quantification is crucial for process optimization, energy consumption control, and safe operation. To tackle the prediction challenges arising from strong multi-variable coupling and nonlinear time series characteristics, this paper proposes a prediction approach integrating feature selection, heterogeneous model ensemble, and probabilistic interval estimation. Firstly, the Relief algorithm is adopted to select key features and construct a time series feature set with high discriminability. Then, a hierarchical architecture encompassing deep feature extraction, heterogeneous model fusion, and probabilistic interval quantification is devised. CNN is utilized to extract spatial correlation features among multiple variables, while BiLSTM is employed to bidirectionally capture the long-term and short-term temporal dependencies of the temperature sequence, thereby forming a deep temporal–spatial feature representation. Subsequently, RF is introduced to establish a heterogeneous model ensemble mechanism, and dynamic weight allocation is implemented based on the Mean Absolute Error of the validation set to enhance the modeling capability for nonlinear coupling relationships. Finally, Gaussian probabilistic regression is leveraged to generate multi-confidence prediction intervals for quantifying prediction uncertainty. Experiments on the real rotary kiln dataset demonstrate that the R² of the proposed model is improved by up to 15.5% compared with single CNN, BiLSTM and RF models, and the Mean Absolute Error is reduced by up to 27.7%, which indicates that the model exhibits strong robustness to the dynamic operating conditions of the rotary kiln and provides both accuracy guarantee and risk quantification basis for process decision-making. This method offers a new paradigm integrating feature selection, adaptive heterogeneous model collaboration, and uncertainty quantification for industrial multi-variable nonlinear time series prediction, and its hierarchical modeling concept is valuable for the intelligent perception of complex process industrial parameters. Full article

Time Series Classification (TSC) plays a crucial role in machine learning applications across domains such as healthcare, finance, and industrial systems. In these domains, TSC requires accurate predictions and reliable explanations, as misclassifications may lead to severe consequences. In addition, scalability issues, including training time and memory consumption, are critical for practice usage. To address these challenges, we propose ProtoPGTN, a prototype-based interpretable framework that unifies gated transformers with prototype reasoning for scalable time series classification. Unlike existing prototype-based interpretable TSC models which rely on recurrent structure for sequence processing and Euclidean distance for similarity computation, ProtoPGTN adapts Gated Transformer Networks (GTN), which uses an attention mechanism to capture both temporal and spatial long-range dependencies in time series data and integrates the prototype learning framework from ProtoPNet with cosine similarity to enhance metric consistency and interpretability. Extensive experiments are conducted on 165 publicly available datasets from the UCR and UEA repositories, covering both univariate and multivariate tasks. Results show that ProtoPGTN obtains at least the same performance as existing prototype-based interpretable models on both multivariate and univariate datasets. The average accuracy on multivariate and univariate datasets stands at 67.69% and 76.99%, respectively. ProtoPGTN achieves up to 20× faster training and up to 200× lower memory consumption than existing prototype-based interpretable models. Full article

Wind energy is a clean but intermittent and volatile energy source, and its large-scale integration into power systems poses great challenges to ensuring safe and stable operation and achieving scheduling optimization and effective energy planning of the power systems. Accurate wind power forecasting is an effective way to mitigate the impact of wind power instability on power systems. However, wind power data are often in the form of multivariate time series. Existing wind power forecasting research often directly models the temporal and spatial characteristics of coupled wind power time-series data, ignoring the heterogeneity of time and space, thereby limiting the model’s expressive power. To address the above problems, we propose a triple-flow dynamic graph convolutional network (TFDGCN) for short-term wind power forecasting. The proposed TFDGCN is a symmetric dynamic graph neural network with three branches. It decouples and learns features of three different dimensions: within a wind power variable sequence, between sequences, and between wind turbines. The proposed TFDGCN constructs dynamic sparse graphs based on cosine similarities within variable sequences, between variable sequences, and between wind turbine nodes, and feeds them into their respective dynamic graph convolution modules. Afterwards, TFDGCN utilizes linear attention encoders which fuse local position encoding (LePE) and rotational position encoding (RoPE) to learn global dependencies within variable sequences, between sequences, and between wind turbines, and provide prediction results. Extensive experimental results on two real-world datasets demonstrate that the proposed TFDGCN outperforms other state-of-the-art methods. On the SDWPF and SD23 datasets, the proposed TFDGCN achieved mean absolute error values of 37.16 and 14.63, respectively, as well as root mean square error values of 44.84 and 17.56, respectively. Full article

Alloy gradient-grained structures (represented by copper as a typical single-phase face-centered cubic (FCC) metal), known for their superior mechanical properties such as enhanced strength, ductility, and fatigue resistance, have become increasingly important in aerospace and automotive industries. These alloys are often fabricated using advanced processing techniques such as laser welding, electron beam melting, and controlled cooling, which induce spatial gradients in grain size and optimize material properties by overcoming the traditional strength–ductility trade-off. In this study, a deep learning-based inversion framework combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks is proposed to efficiently predict key constitutive parameters, such as the initial critical resolved shear stress and hardening modulus, in alloy gradient-grained structures. The model integrates spatial features extracted from strain-field sequences and grain morphology images with temporal features from loading sequences, providing a comprehensive solution for path-dependent mechanical behavior modeling. Trained on high-fidelity Crystal Plasticity Finite Element Method (CPFEM) simulation data, the proposed framework demonstrates high prediction accuracy for the constitutive parameters. The model achieves an error margin of less than 5%. This work highlights the potential of deep learning techniques for the efficient and physically consistent identification of constitutive parameters in alloy gradient-grained structures, offering valuable insights for alloy design and optimization. Full article

Methyl jasmonic acid (MeJA) is a vital phytohormone that plays a key role in plant growth and adaptation to various environmental stresses. In the present study, on the basis of the longan genome, we identified a total of seven versatile putative abscisic acid-insensitive genes, which are the key players in plant growth and stress response. On the basis of bioinformatics analysis, transcriptome data, exogenous treatment experiments, and RT-qPCR findings, a comprehensive evolutionary pattern of ABI genes in different plant species and the effect of different MeJA treatments during early somatic embryogenesis in D. longan was carried out. The phylogeny results revealed that the seven DlABI genes evolved independently in monocots and dicots, having high protein sequence similarity, especially with Arabidopsis ABI genes. The comparative findings of gene structure, motif prediction, and synteny analysis suggest that DlABI genes disperse mainly through duplication events rather than localized tandem repeats. Furthermore, the correlations among the expressions of DlABI genes propose that the organization of the cis-regulatory elements in the promoter regions may regulate the temporal and spatial transcription activation of these genes. The qRT-PCR results revealed that the 50 µM MeJA treatment significantly upregulated the expression of DlABI3, followed by DlABI1, DlABI2, DlABI5, DlABI4, and DlABI8, respectively. The ROS findings clearly revealed that MeJA distinctly elevated the SOD, POD, and H₂O₂ activities while reducing catalase and MDA contents. The subcellular localization of DlABI3 further confirmed its presence in the nucleus, suggesting its predicated transcriptional regulatory role in MeJA-mediated early SE in longan. Our findings reveal that the ABI genes are integral to the mechanism of MeJA-induced early somatic embryogenesis in longan by maintaining the ROS activity. Full article

Accurate cooling load forecasting in chiller units is critical for building energy optimization, yet remains challenging due to non-stationary nonlinear dynamics driven by coupled external weather variability (solar radiation, ambient temperature) and internal thermal loads. Conventional models fail to capture the spatiotemporal coupling inherent in load time series, violating their stationarity assumptions. To address this, this research proposes OptiNet, a spatiotemporal forecasting framework integrating patch-specific dynamic filtering with graph neural networks. OptiNet partitions multi-sensor data into non-overlapping time patches to develop a dynamic spatiotemporal graph. A learnable routing mechanism then performs adaptive dependency filtering to capture time-varying temporal–spatial correlations, followed by graph convolution for load prediction. Validated on long-term industrial logs (52,075 multi-sensor samples at 20 min; district cooling plant in Zhangjiang, Shanghai, with multiple chillers, towers, pumps, building meters, and a weather station), OptiNet achieves consistently lower MAE and MSE than Graph WaveNet across 6–144-step horizons and sampling frequencies of 20–60 min; among 30 set-tings it leads in 26, with MSE reductions up to 27.8% (60 min, 72-step) and typical long-horizon (72–144 steps) gains of ≈2–18% MSE and ≈1–15% MAE. Crucially, the model provides interpretable spatial-temporal dependencies (e.g., “Zone B solar radiation influences Unit 2 load with 4-h lag”), enabling data-driven chiller sequencing strategies that reduce electricity consumption by 12.7% in real-world deployments—directly advancing energy-efficient building operations. Full article

Accurate traffic flow prediction is vital for intelligent transportation systems, yet strong spatiotemporal coupling and multi-scale dynamics make modelling difficult. Existing methods often rely on static adjacency and short input windows, limiting adaptation to time-varying spatial relations and long-term patterns. To address these issues, we propose the Pre-trained Trend-aware Dynamic Graph Convolutional Network (PT-TDGCN), a two-stage framework. In the pre-training stage, a Transformer-based masked autoencoder learns segment-level temporal representations from historical sequences. In the prediction stage, three designs are integrated: (1) dynamic graph learning parameterized by tensor decomposition; (2) convolutional trend-aware attention that adds 1D convolutions to capture local trends while preserving global context; and (3) spatial graph convolution combined with lightweight fusion projection for aligning pre-trained, spatial, and temporal representations. Extensive experiments on four real-world datasets demonstrated that PT-TDGCN consistently outperformed 14 baseline models, achieving superior predictive accuracy and robustness. Full article

Background/Objectives: Bacterial blight (BB) represents one of the most devastating diseases threatening global rice production. Exploring and characterizing disease resistance (R) genes provides an effective strategy for controlling BB and enhancing rice resilience. Common wild rice (Oryza rufipogon) serves as a valuable reservoir of genetic diversity and disease resistance resources. In this study, we identified and functionally characterized a novel NLR gene, YPR1, from common wild rice (Oryza rufipogon), which exhibited significant spatial, temporal, and tissue-specific expression patterns. Methods: Using a combination of conventional PCR, RT-PCR, bioinformatics, transgenic analysis, and CRISPR/Cas9 gene-editing approaches, the full-length YPR1 sequence was successfully cloned. Results: The gene spans 4689 bp with a coding sequence (CDS) of 2979 bp, encoding a 992-amino acid protein. Protein domain prediction revealed that YPR1 is a typical CNL-type NLR protein, comprising RX-CC_like, NB-ARC, and LRR domains. The predicted molecular weight of the protein is 112.43 kDa, and the theoretical isoelectric point (pI) is 8.36. The absence of both signal peptide and transmembrane domains suggests that YPR1 functions intracellularly. Furthermore, the presence of multiple phosphorylation sites across diverse residues implies a potential role for post-translational regulation in its signal transduction function. Sequence alignment showed that YPR1 shared 94.02% similarity with Os09g34160 and up to 96.47% identity with its closest homolog in the NCBI database, confirming that YPR1 is a previously unreported gene. To verify its role in disease resistance, an overexpression vector (Ubi–YPR1) was constructed and introduced into the BB-susceptible rice cultivar JG30 via Agrobacterium tumefaciens-mediated transformation. T₁ transgenic lines were subsequently inoculated with 15 highly virulent Xanthomonas oryzae pv. oryzae (Xoo) strains. The transgenic plants exhibited strong resistance to eight strains (YM1, YM187, C1, C5, C6, T7147, PB, and HZhj19), demonstrating a broad-spectrum resistance pattern. Conversely, CRISPR/Cas9-mediated knockout of YPR1 in common wild rice resulted in increased susceptibility to most Xoo strains. Although the resistance of knockout lines to strains C7 and YM187 was comparable to that of the wild type (YP^WT), the majority of knockout plants exhibited more severe symptoms and significantly lower YPR1 expression levels compared with YP^WT. Conclusions: Collectively, these findings demonstrate that YPR1 plays a crucial role in bacterial blight resistance in common wild rice. As a novel CNL-type NLR gene conferring specific resistance to multiple Xoo strains, YPR1 provides a promising genetic resource for the molecular breeding of BB-resistant rice varieties. Full article

Manufacturing workshops operate in dynamic and complex environments, where multiple orders are processed simultaneously through interdependent stages. This complexity makes it challenging to accurately predict the remaining completion time of ongoing orders. To address this issue, this paper proposes a data-driven prediction approach that analyzes key features extracted from multi-source manufacturing data. The method involves collecting heterogeneous production data, constructing a comprehensive feature dataset, and applying feature analysis to identify critical influencing factors. Furthermore, a deep learning optimization model based on a Convolutional Neural Network (CNN)–Bidirectional Long Short-Term Memory (BiLSTM)–Attention architecture is designed to handle the temporal and structural complexity of workshop data. The model integrates spatial feature extraction, temporal sequence modeling, and adaptive attention-based refinement to improve prediction accuracy. This unified framework enables the model to learn hierarchical representations, focus on salient temporal features, and deliver accurate and robust predictions. The proposed deep learning predictive model is validated on real production data collected from a discrete manufacturing workshop equipped with typical machines. Comparative experiments with other predictive models demonstrate that the CNN–BiLSTM–Attention model outperforms existing approaches in both accuracy and stability for predicting order remaining completion time, offering strong potential for deployment in intelligent production systems. Full article

Accurate prediction of structural displacements in hydropower stations is essential for the safety and long-term stability of large-scale water-related infrastructure. To address this challenge, this study proposes an AI-assisted monitoring framework that integrates Convolutional Neural Networks (CNNs) for spatial feature extraction with Gated Recurrent Units (GRUs) for temporal sequence modeling. The framework leverages long-sequence prototype monitoring data, including reservoir level, temperature, and displacement, to capture complex spatiotemporal interactions between environmental conditions and dam behavior. A parameter optimization strategy is further incorporated to refine the model’s architecture and hyperparameters. Experimental evaluations on real-world hydropower station datasets demonstrate that the proposed CNN–GRU model outperforms conventional statistical and machine learning methods, achieving an average determination coefficient of R² = 0.9582 with substantially reduced prediction errors (RMSE = 4.1121, MAE = 3.1786, MAPE = 3.1061). Both qualitative and quantitative analyses confirm that CNN–GRU not only provides stable predictions across multiple monitoring points but also effectively captures sudden deformation fluctuations. These results underscore the potential of the proposed AI-assisted framework as a robust and reliable tool for intelligent monitoring, safety assessment, and early warning in large-scale hydropower facilities. Full article

To address the challenge of high wind speed variability in wind farm planning, a small-sample-based spatio-temporal fusion and compression deep residual point prediction model, STiCDRS (Spatio-Temporal integration and Compression Deep Residual), is proposed. This model is designed to deeply explore the spatial and temporal characteristics within wind speed sequences to enhance the accuracy of point predictions. Initially, the spatio-temporal integration and compression deep residual network is employed to obtain point prediction results. Subsequently, an innovative hybrid model, STiCDRS-NKDE (STiCDRS-Nonparametric Kernel Density Estimation), is introduced to achieve interval predictions, thereby providing more reliable probabilistic forecasts of wind speed. The hyper-parameters of the model are optimized using Bayesian optimization, ensuring efficient and automated tuning. Finally, a case study involving wind speed forecasting at a wind farm in Inner Mongolia, China, is conducted, comparing the performance of the STiCDRS model with traditional models. Experimental results demonstrate that in comparison to other models, the proposed STiCDRS-NKDE model delivers superior point prediction accuracy, appropriate interval predictions, and reliable probabilistic forecasting outcomes, fully showcasing its significant potential in the domain of wind speed forecasting. Full article