Search Results (174)

As the world’s largest loess deposit region, the Loess Plateau’s vegetation dynamics are crucial for its regional water–heat balance and ecosystem functioning. Leaf Area Index (LAI) serves as a key indicator bridging canopy architecture and plant physiological activities. Existing studies have made significant advancements in simulating LAI, yet accurate LAI simulation remains challenging. To address this challenge and gain deeper insights into the environmental controls of LAI, this study aims to accurately simulate LAI in the Loess Plateau using deep learning models and to elucidate the spatiotemporal influence of soil moisture and temperature on LAI dynamics. For this purpose, we used three deep learning models, namely Artificial Neural Network (ANN), Long Short-Term Memory (LSTM), and Interpretable Multivariable (IMV)-LSTM, to simulate LAI in the Loess Plateau, only using soil moisture and temperature as inputs. Results indicated that our approach outperformed traditional models and effectively captured LAI variations across different vegetation types. The attention analysis revealed that soil moisture mainly influenced LAI in the arid northwest and temperature was the predominant effect in the humid southeast. Seasonally, soil moisture was crucial in spring and summer, notably in grasslands and croplands, whereas temperature dominated in autumn and winter. Notably, forests had the longest temperature-sensitive periods. As LAI increased, soil moisture became more influential, and at peak LAI, both factors exerted varying controls on different vegetation types. These findings demonstrated the strength of deep learning for simulating vegetation–climate interactions and provided insights into hydrothermal regulation mechanisms in semiarid regions. Full article

The Complementary Relationship (CR) principle of evapotranspiration provides an efficient approach for estimating actual evapotranspiration (ET_a), owing to its simplified computation and effectiveness in utilizing meteorological factors. Accurate estimation of actual evapotranspiration (ET_a) is crucial for understanding surface energy and water cycles, especially in permafrost regions. This study aims to evaluate the applicability of two Complementary Relationship (CR)-based methods—Bouchet’s in 1963 and Brutsaert’s in 2015—for estimating ETa on the Qinghai–Tibetan Plateau (QTP), using observations from Eddy Covariance (EC) systems. The potential evapotranspiration (ET_p) was calculated using the Penman equation with two wind functions: the Rome wind function and the Monin–Obukhov Similarity Theory (MOST). The comparison revealed that Bouchet’s method underestimated ET_a during frozen soil periods and overestimated it during thawed periods. In contrast, Brutsaert’s method combined with the MOST yielded the lowest RMSE values (0.67–0.70 mm/day) and the highest correlation coefficients (r > 0.85), indicating superior performance. Sensitivity analysis showed that net radiation (Rn) had the strongest influence on ET_a, with a daily sensitivity coefficient of up to 1.35. This study highlights the improved accuracy and reliability of Brutsaert’s CR method in cold alpine environments, underscoring the importance of considering freeze–thaw dynamics in ET modeling. Future research should incorporate seasonal calibration of key parameters (e.g., ε) to further reduce uncertainty. Full article

Computational Fluid Dynamics (CFD) is regarded as an important tool for analyzing the flow field, thermal environment, and air quality around the built environment. However, for built environment applications, the high computational cost of CFD hinders large-scale scenario simulation and efficient design optimization. In the field of built environment research, surrogate modeling has become a key technology to connect the needs of high-fidelity CFD simulation and rapid prediction, whereas the low-dimensional nature of traditional surrogate models is unable to match the physical complexity and prediction needs of built flow fields. Therefore, combining machine learning (ML) with CFD to predict flow fields in built environments offers a promising way to increase simulation speed while maintaining reasonable accuracy. This review briefly reviews traditional surrogate models and focuses on ML-based surrogate models, especially the specific application of neural network architectures in rapidly predicting flow fields in the built environment. The review indicates that ML accelerates the three core aspects of CFD, namely mesh preprocessing, numerical solving, and post-processing visualization, in order to achieve efficient coupled CFD simulation. Although ML surrogate models still face challenges such as data availability, multi-physics field coupling, and generalization capability, the emergence of physical information-driven data enhancement techniques effectively alleviates the above problems. Meanwhile, the integration of traditional methods with ML can further enhance the comprehensive performance of surrogate models. Notably, the online ministry of trained ML models using transfer learning strategies deserves further research. These advances will provide an important basis for advancing efficient and accurate operational solutions in sustainable building design and operation. Full article

Task-oriented medical dialogue systems face two fundamental challenges: the explosion of state-action space caused by numerous diseases and symptoms and the sparsity of informative signals during interactive diagnosis. These issues significantly hinder the accuracy and efficiency of automated clinical reasoning. To address these problems, we propose MA-HRL, a multi-agent hierarchical reinforcement learning framework that decomposes the diagnostic task into specialized agents. A high-level controller coordinates symptom inquiry via multiple worker agents, each targeting a specific disease group, while a two-tier disease classifier refines diagnostic decisions through hierarchical probability reasoning. To combat sparse rewards, we design an information entropy-based reward function that encourages agents to acquire maximally informative symptoms. Additionally, medical knowledge graphs are integrated to guide decision-making and improve dialogue coherence. Experiments on the SymCat-derived SD dataset demonstrate that MA-HRL achieves substantial improvements over state-of-the-art baselines, including +7.2% diagnosis accuracy, +0.91% symptom hit rate, and +15.94% symptom recognition rate. Ablation studies further verify the effectiveness of each module. This work highlights the potential of hierarchical, knowledge-aware multi-agent systems for interpretable and scalable medical diagnosis. Full article

This study investigates how university students adopt large language models (LLMs) for online consumption of sustainable products, integrating perceived value theory with the technology acceptance model (TAM). Cross-sectional survey data were analyzed using structural equation modeling (SEM) and artificial neural networks (ANNs). SEM results reveal partial mediation. Performance expectancy value (PEV) and information quality value (IQV) directly shape continue using intention (CUI). They also influence CUI indirectly through perceived ease of use (PEU) and perceived usefulness (PU). Green self-identity value (GSV) influences CUI both directly and via PEU, while trust transfer value (TTV) and green perceived value (GPV) affect CUI only via PEU. ANN findings confirm this hierarchy, as PU (86.7%) and PEU (85.7%) are the strongest predictors of CUI, followed by GSV (73.7%). Convergent evidence from both methods indicates that instrumental utility, effortless interaction, and sustainability identity congruence drive sustained LLM use in the context of online consumption of green products, whereas credibility cues and sustainability incentives play secondary roles. This study extends TAM by incorporating multidimensional value constructs and offers design recommendations for engaging and high-utility AI shopping platforms. Full article

In composites, fiber–matrix thermal mismatch induces stress heterogeneity that is beyond the resolution of macroscopic approaches. The asymptotic expansion homogenization method is used to create a multi-scale thermo-mechanical coupling model that predicts the elastic modulus, thermal expansion coefficients, and thermal conductivity of ceramic matrix composites at both the macro- and micro-scales. These predictions are verified to be accurate with a maximum relative error of 9.7% between the measured and predicted values. The multi-scale analysis method is then used to guide the vane’s thermal stress analysis, and a macro–meso–micro multi-scale model is created. The thermal stress distribution and stress magnitudes of the guide vane under a transient high-temperature load are investigated. The results indicate that the temperature and thermal stress distributions of the guide vane under the homogenization and lamination theory models are rather comparable, and the locations of the maximum thermal stress are predicted to be reasonably close to one another. The homogenization model allows for the rapid and accurate prediction of the guide vane’s thermal stress distribution. When compared to the macro-scale stress values, the meso-scale predicted stress levels exhibit excellent accuracy, with an inaccuracy of 11.7%. Micro-scale studies reveal significant stress concentrations at the fiber–matrix interface, which is essential for the macro-scale fatigue and fracture behavior of the guide vane. Full article

Reliable rainfall thresholds are critical for effective early warning and mitigating the risks of rainfall-induced landslides. Traditional statistical models have limitations in multi-variable modeling, while machine learning models face interpretability challenges. Explainable machine learning methods can address these challenges, but they are rarely applied to rainfall threshold modeling. In this study, we compared the performance of an empirical statistical model and machine learning models for predicting rainfall-induced landslides in Italy. Based on the optimal model, we visualized refined rainfall thresholds at three probability levels and employed SHAP (Shapley Additive Explanations) to enhance model explainability by quantifying the contribution of each input variable to the predictions. The results demonstrated that the XGBoost model achieved a good performance (AUC = 0.917 ± 0.026) with well-balanced sensitivity (0.792 ± 0.075) and specificity (0.812 ± 0.033) in landslide susceptibility modeling. Hydrological factors, particularly total rainfall, were identified as the dominant triggering mechanisms, with SHAP analysis confirming their substantially greater contribution compared to environmental factors in rainfall threshold modeling. The developed visualized threshold maps revealed distinct spatial variations in landslide-triggering rainfall thresholds across Italy, characterized by lower thresholds in gentle slope areas with moderate annual precipitation and higher thresholds in steep slope and mid-to-low-elevation regions, while these regional differences decreased under high-probability scenarios. This study offered a modeling approach for regional rainfall threshold assessment by integrating multi-variable modeling with explainable methods, contributing to the development of landslide early warning systems. Full article

As a crucial component of account protection system evaluation and intrusion detection, the advancement of password guessing technology encounters challenges due to its reliance on password data. In password guessing research, there is a conflict between the traditional models’ need for large training samples and the limitations on accessing password data imposed by privacy protection regulations. Consequently, security researchers often struggle with the issue of having a very limited password set from which to guess. This paper introduces a small-sample password guessing technique that enhances cross-domain features. It analyzes the password set using probabilistic context-free grammar (PCFG) to create a list of password structure probabilities and a dictionary of password fragment probabilities, which are then used to generate a password set structure vector. The method calculates the cosine similarity between the small-sample password set B from the target area and publicly leaked password sets $A_i$ using the structure vector, identifying the set $A_{max}$ with the highest similarity. This set is then utilized as a training set, where the features of the small-sample password set are enhanced by modifying the structure vectors of the training set. The enhanced training set is subsequently employed for PCFG password generation. The paper uses hit rate as the evaluation metric, and Experiment I reveals that the similarity between B and $A_i$ can be reliably measured when the size of B exceeds 150. Experiment II confirms the hypothesis that a higher similarity between $A_i$ and B leads to a greater hit rate of $A_i$ on the test set of B, with potential improvements of up to 32% compared to training with B alone. Experiment III demonstrates that after enhancing the features of $A_{max}$, the hit rate for the small-sample password set can increase by as much as 10.52% compared to previous results. This method offers a viable solution for small-sample password guessing without requiring prior knowledge. Full article

The present investigation systematically elucidates the distinct functional specialization within the M1–M3 midgut sections of the significant agricultural pest, Nezara viridula. Employing an integrated transcriptomic analysis, three pivotal discoveries were achieved: (1) each midgut segment possesses unique gene expression signatures; (2) metabolic and signal transduction pathways exhibit coordinated regulatory patterns; and (3) parallel expression changes occur between neuroreceptor (e.g., TACR/HTR) and metabolic enzyme (e.g., GLA/NAGA) genes within identical midgut segments. These data reveal that the M1 region is primarily enriched in metabolic processes and neural signaling; the M2 region emphasizes cellular junctions and immune responses, while the M3 region is mainly responsible for cellular senescence and renewal. These discoveries advance the understanding of feeding adaptation mechanisms in Hemipteran insects and propose a “metabolism–defense–regeneration” functional model for the midgut. The established multi-level analytical framework provides a robust methodology for subsequent dissection of complex biological systems, identification of key molecular targets for functional validation, and for the development of novel pest control strategies. Full article

The escalating industrial emissions have dramatically increased airborne particulate matter (PM), particularly submicron particles (PM0.3), creating substantial health risks through respiratory system penetration. Current fiber-based filtration systems predominantly relying on electrostatic adsorption mechanisms suffer from critical limitations, including insufficient efficiency, potential secondary contamination, and performance degradation in humid environments. We develop a flexible silica composite aerogel to overcome these challenges with customizable and exceptional superamphiphobicity. This composite aerogel exhibits high porosity of ~95% and robust compression Young’s modulus that reaches ~220 kPa at 50% strain even after 1000 cycles. These features enable it to maintain a high filtration efficiency of ~98.52% for PM0.3, even after 50 cycles under traditional artificial simulation conditions. Significantly, a competitive filtration efficiency of ~97.9% is still performed in our composite aerogel at high humidity (water mist), high temperatures (50–250 °C), and corrosive solutions or atmospheres environments, revealing potential industrial applications. This work is expected to replace conventional air filtration materials and pave the way for various human protection and industrial production applications. Full article

Role-playing games (RPGs) set in ancient architecture have emerged as a digital tool for enhancing engagement with ancient architectural cultural heritage. This study examines how RPG elements (immersion, narrative, cognitive engagement) influence sustainable tourism outcomes at ancient architectural heritage sites and develops a stimulus–organism–response (SOR)-based framework model to explore their affective and behavioral effects. The results demonstrate that immersion, narrative, and cognitive engagement in RPGs significantly enhance tourists’ affective engagement. Affective engagement, in turn, enhances tourists’ willingness to travel to and support for heritage conservation sites. Mediation analyses indicated that affective engagement partially mediated the effects of immersion and narrative on the willingness to travel and fully mediated the effects of cognitive engagement. Affective engagement positively predicted support for heritage preservation, whereas willingness to travel alone did not exhibit this relationship. Emotional engagement is therefore a critical mechanism by which digital role-playing game experiences drive sustainable tourism behaviors, resulting in outcomes that go beyond individual behaviors to include broader sustainability impacts. By fostering immersive, narrative-rich, and engaging cognitive experiences, RPGs set in ancient architecture can stimulate willingness to visit heritage sites and encourage conservation awareness, providing valuable insights into sustainable tourism and the management of ancient architectural heritage. Full article

Enhancing the safety standards of autonomous ships is a shared objective of all stakeholders involved in the maritime industry. Since the existing hazard analysis work for autonomous ships often exhibits a degree of subjectivity, in the absence of data support, the verification of hazard analysis results has become increasingly challenging. In this study, a formal verification method in a risk-based assessment framework is proposed to verify the hazard analysis results for autonomous ships. To satisfy the characteristics of high time sensitivity, time automata are adopted as a formal language while model checking based on the formal verification tool UPPAAL is used to complete the automatic verification of the liveness of system modeling and correctness of hazard analysis results derived from extended System-Theoretic Process Analysis (STPA) by traversing the finite state space of the system. The effectiveness of the proposed method is demonstrated through a case study involving a remotely controlled ship. The results indicate that the timed automata network model for remotely controlled ships, based on the control structure, has no deadlocks and operates correctly, which demonstrates its practicability and effectiveness. By leveraging the verification of risk analysis results based on model checking, the framework enhances the precision and traceability of these inputs into RBAT. The results disclose the significance of the collaborative work between safety and system engineering in the development of autonomous systems under the definition of human–computer interaction mode transformation. These findings also hold reference value for other intelligent systems with potential hazards. Full article

Seeing is a key factor affecting the image quality of astronomical observations and can be quantitatively described by the Fried parameter $r_0$. The larger the $r_0$ value (in unit of cm), the better the seeing conditions. Currently, daytime seeing measurements are primarily conducted using the Solar Differential Image Motion Monitor (SDIMM) or the spectral ratio method. In this work, we propose a neural network model for estimating daytime $r_0$. The experimental results of the training set and the test set show that this model can currently estimate $r_0$ with an accuracy exceeding $99\%$. Using this model, we estimate the $r_0$ of the Huairou Solar Observing Station (HSOS) in 22 consecutive years from 1989 to 2010. The median $r_0$ of HSOS in 22 consecutive years was around 2.5 cm, and the best seeing condition was in April and September of one year. This result confirmed the long-term stability of seeing conditions. In addition, we conducted an error analysis comparing the seeing measured by SDIMM and the results obtained by the spectral ratio method both under domeless and domed conditions. The results indicate a significant correlation between the SDIMM results and the spectral ratio method results, with first-order fitting coefficients of 2.2 and 2.9, respectively. Full article

The harvesting of green Sichuan pepper remains heavily reliant on manual field operations, but automation can enhance the efficiency, quality, and sustainability of the process. However, challenges such as intertwined branches, dense foliage, and overlapping pepper clusters hinder intelligent harvesting by causing inaccuracies in target recognition and localization. This study compared the performance of multiple You Only Look Once (YOLO) algorithms for recognition and proposed a cluster segmentation method based on K-means++ and a cutting-point localization strategy using geometry-based iterative optimization. A dataset containing 14,504 training images under diverse lighting and occlusion scenarios was constructed. Comparative experiments on YOLOv5s, YOLOv8s, and YOLOv11s models revealed that YOLOv11s achieved a recall of 0.91 in leaf-occluded environments, marking a 21.3% improvement over YOLOv5s, with a detection speed of 28 Frames Per Second(FPS). A K-means++-based cluster separation algorithm (K = 1~10, optimized via the elbow method) was developed and was combined with OpenCV to iteratively solve the minimum circumscribed triangle vertices. The longest median extension line of the triangle was dynamically determined to be the cutting point. The experimental results demonstrated an average cutting-point deviation of 20 mm and a valid cutting-point ratio of 69.23%. This research provides a robust visual solution for intelligent green Sichuan pepper harvesting equipment, offering both theoretical and engineering significance for advancing the automated harvesting of Sichuan pepper (Zanthoxylum schinifolium) as a specialty economic crop. Full article

The transcription and replication of the genome of influenza A virus (IAV) take place in the nucleus of infected cells, which is catalyzed by the viral ribonucleoprotein (vRNP) complex. The nuclear import of the vRNP complex and its component proteins is essential for the efficient replication of IAV and is therefore prone to be targeted by host restriction factors. Herein, we found that host cellular protein keratin 6A (KRT6A) is a negative regulator of IAV replication because siRNA-mediated knockdown of KRT6A expression increased the growth titers of IAV, whereas exogenous overexpression of KRT6A reduced viral yields. The nuclear import of incoming vRNP complexes and newly synthesized nucleoprotein (NP) was significantly impaired when KRT6A was overexpressed. Further studies showed that KRT6A interacts with the four vRNP complex proteins—polymerase basic protein 1 (PB1), polymerase basic protein 2 (PB2), polymerase acidic protein (PA), and NP. Notably, the interaction between KRT6A and vRNP complex proteins had no effect on the nuclear import of PB2 or the PB1-PA heterodimer but impaired the interaction between NP and the nuclear import adaptor importin α3, thereby inhibiting the nuclear import of incoming vRNP complexes and newly synthesized NP. Moreover, KRT6A was further shown to suppress the assembly of the vRNP complex and consequently reduce viral polymerase activity. Together, our data uncover a novel role of KRT6A in counteracting the nuclear import and functions of the vRNP complex, thereby restricting the replication of IAV. Full article