Search Results (4,536)

Severe leaf galling by the jujube gall midge Dasineura jujubifolia (Diptera: Cecidomyiidae) compromises photosynthesis and yield in arid-zone jujube orchards, yet Xinjiang-specific evidence to guide biological control has been scarce. Here we provide the first systematic characterization in Xinjiang (Hami, China) of D. jujubifolia and its parasitoid complex, integrating region-specific field surveys with gall dissection and laboratory assays. We documented five parasitoid wasps, including two species newly recorded in China—Pseudotorymus samsatensis (Hymenoptera: Torymidae) and Baryscapus adalia (Hymenoptera: Eulophidae). In Hami, the host completed 4–5 generations per year with a 19–24-day generation time. Functional roles were partitioned: P. samsatensis (dominant), Systasis parvula (Hymenoptera: Pteromalidae), and B. adalia were larval ectoparasitoids, whereas Aprostocetus sp. (Hymenoptera: Eulophidae) and Synopeas sp. (Hymenoptera: Platygastridae) were endoparasitoids. Time-series data revealed tight temporal synchrony between P. samsatensis and host peaks. Controlled experiments quantified daily emergence rhythms, diet-dependent adult longevity, and sex ratios, providing parameters to inform release timing and conservation in biological control programs. Collectively, these findings establish management-ready baselines for D. jujubifolia and its parasitoids in arid jujube systems and support conservation-oriented, reduced-pesticide integrated pest management (IPM). Full article

One of the key limitations of AI chatbots is the lack of human-like nonverbal communication. Although there are many research studies on video or audio emotion recognition for detecting human emotions, there is no research that combines video, audio, and ontology methods to develop an AI chatbot with human-like communication. Therefore, this research aims to develop an audio-video emotion recognition model and an emotion-ontology-based chatbot engine to improve human-like communication with emotion detection. This research proposed a novel model of cluster-based audiovisual emotion recognition for improving emotion detection with both video and audio signals and compared it with existing methods using video or audio signals only. Twenty-two audio features, the Mel spectrogram, and facial action units were extracted, and the last two were fed into a cluster-based independent transformer to learn long-term temporal dependencies. Our model was validated on three public audiovisual datasets: RAVDESS, SAVEE, and RML. The results demonstrated that the accuracy scores of the clustered transformer model for RAVDESS, SAVEE, and RML were 86.46%, 92.71%, and 91.67%, respectively, outperforming the existing best model with accuracy scores of 86.3%, 75%, and 60.2%, respectively. An emotion-ontology-based chatbot engine was implemented to make inquiry responses based on the detected emotion. A case study of the HKU Campusland metaverse was used as proof of concept of the emotional AI chatbot for nonverbal communication. Full article

Unconventional reservoirs are critical for future energy supply, but present major challenges for predictions of production due to their ultra-low permeability, strong pressure sensitivity, and non-Darcy flow. Mechanistically grounded physics-based models depend on uncertain parameters derived from laboratory tests or empirical correlations, limiting their field reliability. A data-enhanced variable start-up pressure gradient framework is developed herein, integrating flow physics with physics-informed neural networks (PINNs), surrogate models, and Bayesian optimization. The framework adaptively refines key parameters to represent spatial and temporal variability in reservoir behavior. Validation with field production data shows significantly improved accuracy and robustness compared to baseline physics-based and purely data-driven approaches. Sensitivity and uncertainty analyses confirm the physical consistency of the corrected parameters and the model’s stable predictive performance under perturbations. Comparative results demonstrate that the data-enhanced model outperforms conventional models in accuracy, generalization, and interpretability. This study provides a unified and scalable approach that bridges physics and data, offering a reliable tool for prediction, real-time adaptation, and decision support in unconventional reservoir development. Full article

Accurate fault detection for Permanent Magnet Synchronous Motors (PMSMs) prevents costly failures and improves overall reliability. This paper presents a hybrid one-dimensional convolutional neural network (1DCNN)–bidirectional gated recurrent unit (BiGRU) deep learning model for PMSM fault detection. Inverter-driven short-circuit, open-circuit, and thermal faults, as well as stator faults, can cause electrical and thermal disturbances that affect PMSMs. Significant harmonic distortions, current and voltage peaks, and transient fluctuations are introduced by these faults. The proposed architecture utilizes handcrafted features, including statistical analysis, fast Fourier transform (FFT), and Discrete Wavelet Transform (DWT), extracted from the raw PMSM signals to efficiently capture these faults. 1DCNN effectively extracts local and high-frequency fault-related patterns that encode the effects of peaks and harmonic distortions, while the BiGRU of this enriched representation models complex temporal dependencies, including global asymmetries across phase currents and long-term fault evolution trends seen in stator faults and thermal faults. The proposed model reveals the highest metrics for inverter-driven and stator winding fault datasets compared to the other approaches, achieving an accuracy of 99.44% and 99.98%, respectively. As a result, the study with realistic and comprehensive datasets guarantees high accuracy and generalizability not only in the laboratory but also in industry. Full article

This study analyzed how external forcings, such as meteorological conditions and inflows, influence the average water surface temperature (WST) of the urban Lake Paranoá, Brasília-Brazil, using both in situ measurements and remote sensing estimates over a 40-year period. The temperature model calibrated for Lake Paranoá with no time lag (0-day delay) presented the following metrics: R² = 0.92, RMSE = 0.59 °C, demonstrating the feasibility of obtaining reliable thermal estimates from remote sensing even in urban water bodies. Simple and multiple regression analyses were applied to identify the main external drivers of WST across different temporal scales. A warming trend of 0.036 °C/yr in lake surface temperature was observed, higher than the concurrent increase in air temperature (0.026 °C/yr), suggesting enhanced thermal stratification that may impact water quality. The most influential variables on WST were air temperature, relative humidity, and wind speed, with varying degrees of influence depending on the time scale considered (daily, monthly, annual or seasonal). Remote sensing proved to be essential for overcoming the limitations of traditional monitoring, such as temporal gaps and limited spatial coverage, and allowed detailed mapping of thermal patterns throughout the lake. Integrating these data into hydrodynamic models enhances their diagnostic, predictive, and decision-support capabilities in the context of climate change. Full article

Ship-radiated noise (SRN) recognition is vital for underwater acoustics, with applications in both military and civilian fields. Traditional manual recognition by sonar operators is inefficient and error-prone, motivating the development of automated recognition systems. However, most existing deep learning approaches demand high computational resources, limiting their deployment on resource-constrained edge devices. To overcome this challenge, we propose LW-MS-LFTFNet, a lightweight model informed by time-frequency analysis of SRN that highlights the critical role of low-frequency components. The network integrates a multi-scale depthwise separable convolutional backbone with CBAM attention for efficient spectral representation, along with two LSTM-based modules to capture temporal dependencies in low-frequency bands. Experiments on the DeepShip dataset show that LW-MS-LFTFNet achieves 75.04% accuracy with only 0.85 M parameters, 0.38 GMACs, and 3.27 MB of storage, outperforming representative lightweight architectures. Ablation studies further confirm that low-frequency temporal modules contribute complementary gains, improving accuracy by 2.64% with minimal overhead. Guided by domain-specific priors derived from time-frequency pattern analysis, LW-MS-LFTFNet achieves efficient and accurate SRN recognition with strong potential for edge deployment. Full article

A shallow, seasonal snowpack is rarely homogeneous in depth, layer characteristics, or surface structure throughout an entire winter. Aerodynamic roughness length ($z_0$) is typically considered a static parameter within hydrologic and atmospheric models. Here, we present observations showing $z_0$ as a dynamic variable that is a function of snow depth ($d_s$). This has a significant impact on sublimation modeling, especially for shallow snowpacks. Terrestrial LiDAR data were collected at nine different study sites in northwest Colorado from the 2019 to 2020 winter season to measure the spatial and temporal variability of the snowpack surface. These data were used to estimate the geometric $z_0$ from 91 site visits. Values of $z_0$ decrease during initial snow accumulation, as the snow conforms to the underlying terrain. Once the snowpack is sufficiently deep, which depends on the height of the ground surface roughness features, the surface becomes more uniform. As melt begins, $z_0$ increases, when the snow surface becomes more irregular. The correlation value of $z_0$ was altered by human disturbance at several of the sites. The $z_0$ versus $d_s$ correlation was almost constant, regardless of the initial roughness conditions that only affected the initial $z_0$. Full article

Background: Hyperphosphorylated tau accumulation and neurofibrillary tangles (NFTs) are hallmarks of tauopathies, including Alzheimer’s disease (AD), and are strongly associated with cognitive decline. The rTg4510 mouse model, which expresses mutant human tau (P301L), develops progressive tauopathy in the absence of amyloid-β pathology, providing a valuable tool for investigating tau-driven neurodegeneration. Previous studies have demonstrated spatial and object-recognition memory deficits at six months of age, which can be prevented by doxycycline (DOX)-mediated suppression of tau expression. However, it remained unclear whether non-spatial hippocampal learning, particularly temporal associative learning, would be similarly affected. Methods: We evaluated six-month-old rTg4510 mice with or without DOX treatment. To control for potential motor confounds, we first assessed spontaneous home cage activity. We then tested hippocampus-dependent non-spatial learning using two paradigms: trace eyeblink conditioning (500-ms trace interval) and contextual fear conditioning. Results: General motor function remained intact; however, rTg4510 mice without DOX treatment exhibited increased rearing behavior. These mice demonstrated significant deficits in trace eyeblink conditioning acquisition, with particularly clear impairment on the final day of training. Contextual fear conditioning showed milder deficits. Analysis of response peak latency revealed subtle temporal processing abnormalities during early learning. Two months of DOX treatment initiated at four months of age prevented these learning deficits, confirming their association with tau overexpression. Conclusions: Our findings demonstrate that rTg4510 mice exhibit deficits in non-spatial temporal associative learning alongside previously reported spatial and object-recognition impairments. Trace eyeblink conditioning serves as a sensitive behavioral assay for detecting tau-related hippocampal dysfunction, and the prevention of learning deficits by DOX treatment highlights its potential utility as a translational biomarker for evaluating tau-targeted interventions. Full article

Accurate load forecasting of central air conditioning (CAC) systems is crucial for enhancing energy efficiency and minimizing operational costs. However, the complex nonlinear correlations among meteorological factors, water system dynamics, and cooling demand make this task challenging. To address these issues, this study proposes a novel hybrid forecasting model termed IWOA-BiTCN-BiGRU-SA, which integrates the Improved Whale Optimization Algorithm (IWOA), Bidirectional Temporal Convolutional Networks (BiTCN), Bidirectional Gated Recurrent Units (BiGRU), and a Self-attention mechanism (SA). BiTCN is adopted to extract temporal dependencies and multi-scale features, BiGRU captures long-term bidirectional correlations, and the self-attention mechanism enhances feature weighting adaptively. Furthermore, IWOA is employed to optimize the hyperparameters of BiTCN and BiGRU, improving training stability and generalization. Experimental results based on real CAC operational data demonstrate that the proposed model outperforms traditional methods such as LSTM, GRU, and TCN, as well as hybrid deep learning benchmark models. Compared to all comparison models, the root mean square error (RMSE) decreased by 13.72% to 56.66%. This research highlights the application potential of the IWSO-BiTCN-BiGRU-Attention framework in practical load forecasting and intelligent energy management for large-scale CAC systems. Full article

Background: While host immune responses to SARS-CoV-2 vaccination are routinely assessed through IgG measurements, less is known about the temporal dynamics of vaccine-induced cellular immunity, particularly in individuals who fail to develop detectable IgG antibodies after COVID-19 vaccination. Objective: To investigate the development and timing of T-cell immunity following SARS-CoV-2 vaccination in antibody-non-responders to COVID-19 vaccination. Methods: A cross-sectional analysis was conducted on COVID-19-naive individuals who had received full SARS-CoV-2 vaccination, categorized by SARS-CoV-2 IgG serostatus. T-cell response was evaluated using the IGRA methodology T-SPOT^®.COVID (Oxford Immunotec, Abingdon, Oxfordshire, UK). T-cell response rates and levels were compared between SARS-CoV-2 seropositive and seronegative groups, and a temporal cutoff analysis was applied to examine trends in T-cell response over time. Results: Within the seronegative group, IgG levels showed a strong negative correlation with time since vaccination (Spearman ρ = −0.65, p < 0.001), while T-cell response levels exhibited a weak positive time-dependent trend (ρ = 0.15, p = 0.019). Temporal cutoff analysis identified a critical time-point beginning at 80 days post-vaccination, after which both T-cell response rates and levels were significantly higher. Specifically, individuals tested after 80 days showed increased median T-cell response levels (U = 4205, p < 0.001) and higher positive T-cell response rate (67% vs. 38%, Χ² = 17.06, p < 0.001). Conclusions: Cellular immunity response against SARS-CoV-2 may emerge later than expected in antibody-non-responders to COVID-19 vaccination, with the 80-day post-vaccination mark emerging as a critical time point. Our results support the inclusion of cellular assays in post-vaccination monitoring and emphasize the need to reconsider the timing and criteria for evaluating vaccine response. Full article

Recent advancements in deep learning have significantly improved fault diagnosis methods. However, challenges such as insufficient feature extraction, limited long-range dependency modeling, and environmental noise continue to hinder their effectiveness. This paper presents a novel mixture of multi-view convolutional (MOM-Conv) layers integrating the Mixture of Experts (MOE) mechanism. This design effectively captures and fuses both local and contextual information, thereby enhancing feature extraction and representation. This proposed approach aims to improve prediction accuracy under varying noise conditions, particularly in rolling ball bearing systems characterized by noisy signals. Additionally, we propose the Mamba-enhanced adaptive self-attention long short-term memory (MASA-LSTM) model, which effectively captures both global and local dependencies in ultra-long time series data. This model addresses the limitations of traditional models in extracting long-range dependencies from such signals. The architecture also integrates a multi-step temporal state fusion mechanism to optimize information flow and incorporates adaptive parameter tuning, thereby improving dynamic adaptability within the LSTM framework. To further mitigate the impact of noise, we transform vibration signals into denoised multi-channel representations, enhancing model stability in noisy environments. Experimental results show that our proposed model outperforms existing state-of-the-art approaches on both the Paderborn and Case Western Reserve University bearing datasets, demonstrating remarkable robustness and effectiveness across various noise levels. Full article

Pasture systems, typically composed of grasses, legumes, and forage crops, are vital livestock nutrition sources. The quality of these pastures depends on various factors, including species composition and growth stage, which directly impact livestock productivity. Remote sensing (RS) technologies offer powerful, non-invasive means for large-scale pasture monitoring and classification, enabling efficient assessment of pasture health across extensive areas. However, traditional supervised classification methods require labelled datasets that are often expensive and labour-intensive to produce, especially over large grasslands. This study explores unsupervised clustering as a cost-effective alternative for identifying pasture types without the need for labelled data. Leveraging spatiotemporal data from the Sentinel-2 mission, we propose a clustering framework that classifies pastures based on their temporal growth dynamics. For this, the pasture segments are first created with quick-shift segmentation, and spectral time series for each segment are grouped into clusters using time-series distance-based clustering techniques. Empirical analysis shows that the dynamic time warping (DTW) distance measure, combined with K-Medoids and hierarchical clustering, delivers promising pasture mapping with normalised mutual information (NMI) of 86.28% and 88.02% for site-1 and site-2 (total area of approx. 2510 ha), respectively, in New South Wales, Australia. This approach offers practical insights for improving pasture management and presents a viable solution for categorising pasture and grazing systems across landscapes. Full article

Accurate and timely precipitation forecasting is critical for climate risk management, agriculture, and hydrological regulation. However, this task remains challenging due to the dynamic evolution of atmospheric systems, heterogeneous environmental factors, and frequent missing data in multi-source observations. To address these issues, we propose DAHG, a novel long-term precipitation forecasting framework based on dynamic augmented heterogeneous graphs with reinforced graph generation, contrastive representation learning, and long short-term memory (LSTM) networks. Specifically, DAHG constructs a temporal heterogeneous graph to model the complex interactions among multiple meteorological variables (e.g., precipitation, humidity, wind) and remote sensing indicators (e.g., NDVI). The forecasting task is formulated as a dynamic spatiotemporal regression problem, where predicting future precipitation values corresponds to inferring attributes of target nodes in the evolving graph sequence. To handle missing data, we present a reinforced dynamic graph generation module that leverages reinforcement learning to complete incomplete graph sequences, enhancing the consistency of long-range forecasting. Additionally, a self-supervised contrastive learning strategy is employed to extract robust representations of multi-view graph snapshots (i.e., temporally adjacent frames and stochastically augmented graph views). Finally, DAHG integrates temporal dependency through long short-term memory (LSTM) networks to capture the evolving precipitation patterns and outputs future precipitation estimations. Experimental evaluations on multiple real-world meteorological datasets show that DAHG reduces MAE by $\stackrel{\sim }{3}$% and improves R² by $\stackrel{\sim }{0}$.02 over state-of-the-art baselines (p < 0.01), confirming significant gains in accuracy and robustness, particularly in scenarios with partially missing observations (e.g., due to sensor outages or cloud-covered satellite readings). Full article

The integration of photovoltaic (PV) energy into the power grid requires precise forecasting due to its dependence on the variability of weather conditions. This study explores the effectiveness of neural network models for predicting PV energy generation using historical meteorological and temporal data from Austria over a two-year period. We implement and compare multiple neural machine learning approaches, including Multilayer Perceptrons (MLPs), Recurrent Neural Networks (RNNs), and Convolutional Neural Networks (CNNs), against traditional statistical models such as Decision Trees (DTs), Linear Regression (LR), and Random Forest (RF). Our methodology introduces novel data preprocessing techniques, including cyclical encoding of time features, to improve prediction accuracy. Results demonstrate that RNN models outperform other architectures in single-step forecasting, achieving a Mean Squared Error (MSE) of 0.045 and a Mean Absolute Error (MAE) of 0.0427, while CNNs prove superior for multi-step predictions. These findings highlight the potential benefits of applying predictive deep learning techniques for optimal PV energy management, contributing to grid stability and sustainability. This study systematically compares the effectiveness of traditional and deep learning models for photovoltaic energy prediction under the same data preprocessing conditions, including the cyclical encoding of temporal features that provides a continuous representation of the time frame allowing its use as an input feature. This study identifies the specific strengths of each model (RNN for single-step prediction, CNN for multi-step prediction) for Central European climates, validated on Austria’s unique meteorological dataset. Full article

Detection of changes in remote sensing relies on clean multi-temporal images, but cloud cover may considerably degrade image quality. Cloud removal, a critical image-restoration task, demands effective modeling of long-range spatial dependencies to reconstruct information under cloud occlusions. While Transformer-based models excel at handling such spatial modeling, their quadratic computational complexity limits practical application. The recently proposed Mamba, a state space model, offers a computationally efficient alternative for long-range modeling, but its inherent 1D sequential processing is ill-suited to capturing complex 2D spatial contexts in images. To bridge this gap, we propose the multi-pattern scanning Mamba (MPSM) block. Our MPSM block adapts the Mamba architecture for vision tasks by introducing a set of diverse scanning patterns that traverse features along horizontal, vertical, and diagonal paths. This multi-directional approach ensures that each feature aggregates comprehensive contextual information from the entire spatial domain. Furthermore, we introduce a dynamic path-aware (DPA) mechanism to adaptively recalibrate feature contributions from different scanning paths, enhancing the model’s focus on position-sensitive information. To effectively capture both global structures and local details, our MPSM blocks are embedded within a U-Net architecture enhanced with multi-scale supervision. Extensive experiments on the RICE1, RICE2, and T-CLOUD datasets demonstrate that our method achieves state-of-the-art performance while maintaining favorable computational efficiency. Full article