Search Results (2,725)

Social and economic growth in developing countries has heightened the awareness of environmental challenges, with carbon emissions emerging as a particularly pressing concern. However, the impact of economic development on carbon emission intensity has rarely been considered from the perspective of economic agglomeration, and the relationships and mechanisms between the two remain poorly understood. We analyzed the impact of economic agglomeration on carbon emission intensity and its spatial spillover effect in Guangdong Province, the most economically advantaged province of China, based on a spatial weight matrix generated using geographic proximity, exploratory spatial data analysis (ESDA), and the spatial Durbin model. Between 2000 and 2019, economic agglomeration and carbon emission intensity in Guangdong Province exhibited persistent upward trajectories, whereas between 2016 and 2019, carbon emission intensity gradually approached zero. Further, 80% of the province’s economic output was concentrated in the Pearl River Delta region. Strong spatial autocorrelation was observed between economic agglomeration and carbon emission intensity in the cities, and the economic agglomeration of the province had a parabolic influence on carbon emission intensity. Carbon emission intensity peaked at an economic agglomeration level of 1.2416 × 10⁹ yuan/km² and then gradually decreased. The spatial spillover effect of the openness degree on carbon emission intensity was positive, while GDP per capita and industrial structure had negative effects. Further, the economic agglomeration effects of Guangdong Province increased the carbon emission intensity of major cities and smaller neighboring cities. The stacking effect of economic agglomeration between cities also affected the carbon emission intensity of neighboring cities in the region. During the period of rapid urban development, industrial development and population agglomeration increased resource and energy consumption, and positive externalities such as the scale effect and knowledge spillover were not well reflected, resulting in greater overall negative environmental externalities relative to positive environmental externalities. Full article

This paper proposes a transformer temperature early warning method based on an adaptive sliding window and stacking ensemble learning algorithm, aiming to improve the accuracy and robustness of temperature prediction. The transformer temperature early warning system is crucial for ensuring the safe operation of the power system, and temperature prediction, as the foundation of early warning, directly affects the early warning effectiveness. This paper analyzes the characteristics of transformer temperature using support vector regression, random forest, and gradient boosting regression as base learners and ridge regression as the meta-learner to construct a stacking model. At the same time, Bayesian optimization is used to automatically adjust the sliding window size, achieving adaptive sliding window processing. The experimental results indicate that the temperature prediction method based on adaptive sliding window and stacking significantly reduces prediction errors, enhances the model’s adaptability and generalization ability, and provides more reliable technical support for transformer fault warning. Full article

In the field of ensemble learning, bagging and stacking are two widely used ensemble strategies. Bagging enhances model robustness through repeated sampling and weighted averaging of homogeneous classifiers, while stacking improves classification performance by integrating multiple models using meta-learning strategies, taking advantage of the diversity of heterogeneous classifiers. However, the fixed weight distribution strategy in traditional bagging methods often has limitations when handling complex or imbalanced datasets. This paper combines the concept of heterogeneous classifier integration in stacking with the weighted averaging strategy of bagging, proposing a new adaptive weight distribution approach to enhance bagging’s performance in heterogeneous ensemble settings. Specifically, we propose three weight generation functions with “high at both ends, low in the middle” curve shapes and demonstrate the superiority of this strategy over fixed weight methods on two datasets. Additionally, we design a specialized neural network, and by training it adequately, validate the rationality of the proposed adaptive weight distribution strategy, further improving the model’s robustness. The above methods are collectively called func-bagging. Experimental results show that func-bagging has an average 1.810% improvement in extreme performance compared to the base classifier, and is superior to stacking and bagging methods. It also has better dataset adaptability and interpretability than stacking and bagging. Therefore, func-bagging is particularly effective in scenarios with class imbalance and is applicable to classification tasks with imbalanced classes, such as anomaly detection. Full article

To evaluate the accuracy of Discrete Wavelet Transform (DWT) in monitoring the chlorophyll (CHL) content of maize canopies based on RGB images, a field experiment was conducted in 2023. Images of maize canopies during the jointing, tasseling, and grouting stages were captured using unmanned aerial vehicle (UAV) remote sensing to extract color, texture, and wavelet features and to construct a color and texture feature dataset and a fusion of wavelet, color, and texture feature datasets. Backpropagation neural network (BP), Stacked Ensemble Learning (SEL), and Gradient Boosting Decision Tree (GBDT) models were employed to develop CHL monitoring models for the maize canopy. The performance of these models was evaluated by comparing their predictions with measured CHL data. The results indicate that the dataset integrating wavelet features achieved higher monitoring accuracy compared to the color and texture feature dataset. Specifically, for the integrated dataset, the BP model achieved an R² value of 0.728, an RMSE of 3.911, and an NRMSE of 15.24%; the SEL model achieved an R² value of 0.792, an RMSE of 3.319, and an NRMSE of 15.34%; and the GBDT model achieved an R² value of 0.756, an RMSE of 3.730, and an NRMSE of 15.45%. Among these, the SEL model exhibited the highest monitoring accuracy. This study provides a fast and reliable method for monitoring maize growth in field conditions. Future research could incorporate cross-validation with hyperspectral and thermal infrared sensors to further enhance model reliability and expand its applicability. Full article

This paper describes the Weather On-Demand (WOD) forecasting framework which is a software stack used to run operational and on-demand weather forecasts. The WOD framework is a distributed system for the following: (1) running the Weather Research and Forecast (WRF) model for data assimilation and forecasts by triggering either scheduled or on-demand jobs; (2) gathering upstream weather forecasts and observations from a wide variety of sources; (3) reducing output data file sizes for permanent storage; (4) making results available through Application Programming Interfaces (APIs); (5) making data files available to custom post-processors. Much effort is put into starting processing as soon as the required data become available, and in parallel where possible. In addition to being able to create short- to medium-range weather forecasts for any location on the globe, users are granted access to a plethora of both global and regional weather forecasts and observations, as well as seasonal outlooks from the National Oceanic and Atmospheric Administration (NOAA) in the USA through WOD integrated-APIs. All this information can be integrated with third-party software solutions via WOD APIs. The software is maintained in the Git distributed version control system and can be installed on suitable hardware, bringing the full flexibility and power of the WRF modelling system to the user in a matter of hours. Full article

An intelligent prediction model for rice yield in small-scale cultivation areas can provide precise forecasting results for farmers, rice planting enterprises, and researchers, holding significant importance for agricultural industries and crop science research within small regions. Although machine learning can handle complex nonlinear problems to enhance prediction accuracy, further improvements in models are still needed to accurately predict rice yields in small areas facing complex planting environments, thereby enhancing model performance. This study employs four rice phenotypic traits, namely, panicle angle, panicle length, total branch length, and grain number, along with seven machine learning methods—multiple linear regression, support vector machine, MLP, random forest, GBR, XGBoost, and LightGBM—to construct a yield prediction model group. Subsequently, the top three models with the best performance in individual model predictions are integrated using voting and stacking ensemble methods to obtain the optimal integrated model. Finally, the impact of different rice phenotypic traits on the performance of the stacked ensemble model is explored. Experimental results indicate that the random forest model performs best after individual machine learning modeling, with RMSE, R², and MAPE values of 0.2777, 0.9062, and 17.04%, respectively. After model integration, Stacking–3m demonstrates the best performance, with RMSE, R², and MAPE values of 0.2483, 0.9250, and 6.90%, respectively. Compared to the performance after random forest modeling, the RMSE decreased by 10.58%, R² increased by 1.88%, and MAPE decreased by 0.76%, indicating improved model performance after stacking ensemble. The Stacking–3m model, which demonstrated the best comprehensive evaluation metrics, was selected for model validation, and the validation results were satisfactory, with MAE, R², and MAPE values of 8.3384, 0.9285, and 0.2689, respectively. The above research findings demonstrate that this integrated model possesses high practical value and fills a gap in precise yield prediction for small-scale rice cultivation in the Yunnan Plateau region. Full article

The effectiveness of data-driven landslide susceptibility mapping relies on data integrity and advanced geospatial analysis; however, selecting the most suitable method and identifying key regional factors remains a challenging task. To address this, this study assessed the performance of six machine learning models, including Convolutional Neural Networks (CNNs), Random Forest (RF), Categorical Boosting (CatBoost), their CNN-based hybrid models (CNN+RF and CNN+CatBoost), and a Stacking Ensemble (SE) combining CNN, RF, and CatBoost in mapping landslide susceptibility along the Karakoram Highway in northern Pakistan. Twelve geospatial factors were examined, categorized into Topography/Geomorphology, Land Cover/Vegetation, Geology, Hydrology, and Anthropogenic Influence. A detailed landslide inventory of 272 occurrences was compiled to train the models. The proposed stacking ensemble and hybrid models improve landslide susceptibility modeling, with the stacking ensemble achieving an AUC of 0.91. Hybrid modeling enhances accuracy, with CNN–RF boosting RF’s AUC from 0.85 to 0.89 and CNN–CatBoost increasing CatBoost’s AUC from 0.87 to 0.90. Chi-square (χ²) values (9.8–21.2) and p-values (<0.005) confirm statistical significance across models. This study identifies approximately 20.70% of the area as from high to very high risk, with the SE model excelling in detecting high-risk zones. Key factors influencing landslide susceptibility showed slight variations across the models, while multicollinearity among variables remained minimal. The proposed modeling approach reduces uncertainties, enhances prediction accuracy, and supports decision-makers in implementing effective landslide mitigation strategies. Full article

As the climate emergency escalates, the role of forests in carbon sequestration is paramount. This paper proposes a framework that integrates local capacities, multi-source remote sensing data, and meta-learning to enhance forest carbon assessment methodologies in data-scarce regions. By integrating multi-source optical and radar remote sensing data alongside community forest inventories, we applied a meta-modelling approach using stacked generalization ensemble to estimate forest above-ground carbon (AGC). We also conducted a Kruskal–Wallis test to determine significant differences in AGC among different tree species. The Kruskal–Wallis test (p = 1.37 × 10⁻¹³) and Dunn post-hoc analysis revealed significant differences in carbon stock potential among tree species, with Afzelia quanzensis ($\tilde{x}$= 12 kg/ha, P-holm-adj. = 0.05) and the locally known species M’buta ($\tilde{x}$ = 6 kg/ha, P-holm-adj. = 5.45 × 10⁻⁹) exhibiting a significantly higher median AGC. Our results further showed that combining optical and radar remote sensing data substantially improved prediction accuracy compared to single-source remote sensing data. To improve forest carbon assessment, we employed stacked generalization, combining multiple machine learning algorithms to leverage their complementary strengths and address individual limitations. This ensemble approach yielded more robust estimates than conventional methods. Notably, a stacking ensemble of support vector machines and random forest achieved the highest accuracy (R² = 0.84, RMSE = 1.36), followed by an ensemble of all base learners (R² = 0.83, RMSE = 1.39). Additionally, our results demonstrate that factors such as the diversity of base learners and the sensitivity of meta-leaners to optimization can influence stacking performance. Full article

The interaction of sodium phytate hydrate C₆H₁₈O₂₄P₆·xNa·yH₂O (phytNa) with Cu(OAc)₂·H₂O and 1,10-phenanthroline (phen) led to the anionic tetranuclear complex [Cu₄(H₂O)₄(phen)₄(phyt)]·2Na⁺·2NH₄⁺·32H₂O (1), the structure of the latter was determined by X-ray diffraction analysis. The phytate 1 is completely deprotonated; six phosphate⁻ fragments (with atoms P1–P6) are characterized by different spatial arrangements relative to the cyclohexane ring (1a5e conformation), which determines two different types of coordination to the complexing agents—P1 and P3, P4, and P6 have monodentate, while P2 and P5 are bidentately bound to Cu²⁺ cations. The molecular structure of the anion complex is stabilized by a set of strong intramolecular hydrogen bonds involving coordinated water molecules. Aromatic systems of phen ligands chelating copper ions participate in strong intramolecular and intermolecular π-π interactions, further contributing to their association. At the supramolecular level, endless stacks are formed, in the voids of which sodium and ammonium cations and water molecules are present. The stability of 1 in the presence of human serum albumin (HSA) was investigated using Electron Paramagnetic Resonance (EPR) spectroscopy. Continuous wave (CW) EPR spectra in water/glycerol frozen solution clearly indicate a presence of an exchange-coupled Cu(II)-Cu(II) dimeric unit, as well as a Cu(II) monomer-like signal arising from spins sufficiently distant from each other, with comparable contributions of two types of signals. In the presence of albumin at a 1:1 ratio (1 to albumin), the EPR spectrum changes significantly, primarily due to the reduced contribution of the S = 1 fraction showing dipole–dipole splitting. The biological activity of 1 in vitro against the non-pathogenic (model for Mycobacterium tuberculosis) strain of Mycolicibacterium smegmatis is comparable to the first-line drug for tuberculosis treatment, rifampicin. Full article

Accurate prediction of natural gas purchase volumes is crucial for both the economy and the environment. It not only facilitates the rational allocation of resources for companies but also helps to reduce operational costs. Although existing prediction methods have achieved some success in addressing the nonlinear relationships in natural gas purchases, there remains potential for further improvement. To address this issue, a stacking ensemble learning model was developed to enhance the ability to handle complex nonlinear problems. This model integrates diverse algorithms and incorporates weather factors, while regionalizing characteristics of natural gas usage, thereby achieving accurate forecasts of natural gas purchase volumes. We selected three distinctly different base models—Informer, multiple linear regression (MLR), and support vector regression (SVR)—for our research. By conducting four different feature combination experiments for each base model, including weather, time, regional, and usage features, we constructed 12 foundational models. Subsequently, we integrated these base models using a meta-learner to form the final stacking ensemble model. The experimental results indicate that the stacking ensemble model outperforms individual models across key metrics, including $R^2$, MRE, and RMSE. Notably, the $R^2$ values improved by 4–15% compared to the 12 base models. The model was subsequently applied to predict natural gas purchase volumes in Pi County, Chengdu, China. In November 2024, a side-by-side comparison of the predicted and actual data revealed a maximum error of just 5.39%. This exceptional accuracy effectively meets forecasting requirements, underscoring the model’s predictive strength in the energy sector. Full article

This study addresses the challenges of tomato maturity recognition in natural environments, such as occlusion caused by branches and leaves, and the difficulty in detecting stacked fruits. To overcome these issues, we propose a novel YOLOv8n-CA method for tomato maturity recognition, which defines four maturity stages: unripe, turning color, turning ripe, and fully ripe. The model is based on the YOLOv8n architecture, incorporating the coordinate attention (CA) mechanism into the backbone network to enhance the model’s ability to capture and express features of the tomato fruits. Additionally, the C2f-FN structure was utilized in both the backbone and neck networks to strengthen the model’s capacity to extract maturity-related features. The CARAFE up-sampling operator was integrated to expand the receptive field for improved feature fusion. Finally, the SIoU loss function was used to solve the problem of insufficient CIoU of the original loss function. Experimental results showed that the YOLOv8n-CA model had a parameter count of only 2.45 × 10⁶, computational complexity of 6.9 GFLOPs, and a weight file size of just 4.90 MB. The model achieved a mean average precision (mAP) of 97.3%. Compared to the YOLOv8n model, it reduced the model size slightly while improving accuracy by 1.3 percentage points. When compared to seven other models—Faster R-CNN, YOLOv3s, YOLOv5s, YOLOv5m, YOLOv7, YOLOv8n, YOLOv10s, and YOLOv11n—the YOLOv8n-CA model was the smallest in size and demonstrated superior detection performance. Full article

Stacking fermentation is critical in sauce-flavor Baijiu production, but winter production often sees abnormal fermentations, like Waistline and Sub-Temp fermentation, affecting yield and quality. This study used three machine learning models (Logistic Regression, KNN, and Random Forest) combined with multi-omics (metagenomics and flavoromics) to develop a classification model for abnormal fermentation. SHAP analysis identified 13 Sub-Temp Fermentation and 9 Waistline microbial biomarkers, along with 9 Sub-Temp Fermentation and 12 Waistline flavor biomarkers. Komagataeibacter and Gluconacetobacter are key for normal fermentation, while Ligilactobacillus and Lactobacillus are critical in abnormal cases. Excessive acid and ester markers caused unbalanced aromas in abnormal fermentations. Additionally, ecological models reveal the bacterial community assembly in abnormal fermentations was influenced by stochastic factors, while the fungal community assembly was influenced by deterministic factors. RDA analysis shows that moisture significantly drove Sub-Temp fermentation. Differential gene analysis and KEGG pathway enrichment identify metabolic pathways for flavor markers. This study provides a theoretical basis for regulating stacking fermentation and ensuring Baijiu quality. Full article

The structure of thermoset composite laminated plates is made by stacking layers of plies with different fiber orientations. Similarly, the stiffened panel structure is assembled from components with varying ply configurations, resulting in thermal residual stresses and processing-induced deformations (PIDs) during manufacturing. To mitigate the residual stresses caused by the geometric features of corner structures and the mismatch between the stiffener-skin ply orientations, which lead to PIDs in composite-stiffened panels, this study proposes a multi-objective stacking optimization strategy based on an improved adaptive genetic algorithm (IAGA). The viscoelastic constitutive model was employed to describe the modulus variation during the curing process to ensure computational accuracy. In this study, the IAGA was proposed to optimize the ply-stacking sequence of L-shaped stiffeners in composite laminated structures. The results demonstrate a reduction in the spring-in angle to 0.12°, a 50% improvement compared to symmetric balanced stacking designs, while the buckling eigenvalues were improved by 20%. Additionally, the IAGA outperformed the traditional non-dominated sorting genetic algorithm (NSGA), achieving a threefold increase in the Pareto solution diversity under identical constraints and reducing the convergence time by 70%. These findings validate the effectiveness of asymmetric ply design and provide a robust framework for enhancing the structural performance and manufacturability of composite laminates. Full article

In this study, the solution of the buckling problem of axially loaded laminated cylindrical shells consisting of functionally graded (FG) nanocomposites in elastic and thermal environments is presented within extended first-order shear deformation theory (FOST) for the first time. The effective material properties and thermal expansion coefficients of nanocomposites in the layers are computed using the extended rule of mixture method and molecular dynamics simulation techniques. The governing relations and equations for laminated cylindrical shells consisting of FG nanocomposites on the two-parameter elastic foundation and in thermal environments are mathematically modeled and solved to find the expression for the axial buckling load. The numerical results of the current analytical approach agree well with the existing literature results obtained using a different methodology. Finally, some new results and interpretations are provided by investigating the influences of different parameters such as elastic foundations, thermal environments, FG nanocomposite models, shear stress, and stacking sequences on the axial buckling load. Full article

With the widespread adoption of electric vehicles, the power converter, as a key component, plays a crucial role. Traditional fault detection methods often face challenges in real-time performance and computational efficiency, making it difficult to meet the demands of electric vehicle power converters for efficient and accurate fault diagnosis. To address this challenge, this paper proposes a novel fault detection model—SpikingShuffleNet. This paper first designs an efficient SpikingShuffle Unit that integrates grouped convolutions and channel shuffle techniques, effectively reducing the model’s computational complexity by optimizing feature extraction and channel interaction. Next, by appropriately stacking SpikingShuffle Units and refining the network architecture, a complete lightweight diagnostic network is constructed for real-time fault detection in electric vehicle power converters. Finally, the Mixed Local Channel Attention mechanism is introduced to address the potential limitations in feature representation caused by grouped convolutions, further enhancing fault detection accuracy and robustness by balancing local detail preservation and global feature integration. Experimental results show that SpikingShuffleNet exhibits excellent accuracy and robustness in the fault detection task for power converters, fulfilling the real-time fault diagnosis requirements for low-power embedded devices. Full article