Search Results (266)

High-resolution remote sensing (HRRS) imagery enables the extraction of cropland information with high levels of detail, especially when combined with the impressive performance of deep convolutional neural networks (DCNNs) in understanding these images. Comprehending the factors influencing DCNNs’ performance in HRRS cropland extraction is of considerable importance for practical agricultural monitoring applications. This study investigates the impact of classifier selection and different training data characteristics on the HRRS cropland classification outcomes. Specifically, Gaofen-1 composite images with 2 m spatial resolution are employed for HRRS cropland extraction, and two county-wide regions with distinct agricultural landscapes in Shandong Province, China, are selected as the study areas. The performance of two deep learning (DL) algorithms (UNet and DeepLabv3+) and a traditional classification algorithm, Object-Based Image Analysis with Random Forest (OBIA-RF), is compared. Additionally, the effects of different band combinations, crop growth stages, and class mislabeling on the classification accuracy are evaluated. The results demonstrated that the UNet and DeepLabv3+ models outperformed OBIA-RF in both simple and complex agricultural landscapes, and were insensitive to the changes in band combinations, indicating their ability to learn abstract features and contextual semantic information for HRRS cropland extraction. Moreover, compared with the DL models, OBIA-RF was more sensitive to changes in the temporal characteristics. The performance of all three models was unaffected when the mislabeling error ratio remained below 5%. Beyond this threshold, the performance of all models decreased, with UNet and DeepLabv3+ showing similar performance decline trends and OBIA-RF suffering a more drastic reduction. Furthermore, the DL models exhibited relatively low sensitivity to the patch size of sample blocks and data augmentation. These findings can facilitate the design of operational implementations for practical applications. Full article

High energy consumption in Chinese rural residential buildings, caused by rudimentary construction methods and the poor thermal performance of building envelopes, poses a significant challenge to national sustainability and “dual carbon” goals. To address this, this study proposes a comprehensive modeling and analysis framework integrating an improved Bio-inspired Black-winged Kite Optimization Algorithm (IBKA) with Support Vector Regression (SVR). Firstly, to address the limitations of the original B-inspired BKA, such as premature convergence and low efficiency, the proposed IBKA incorporates diversification strategies, global information exchange, stochastic behavior selection, and an NGO-based random operator to enhance exploration and convergence. The improved algorithm is benchmarked against BKA and six other optimization methods. An orthogonal experimental design was employed to generate a dataset by systematically sampling combinations of influencing factors. Subsequently, the IBKA-SVR model was developed for energy consumption prediction and analysis. The model’s predictive accuracy and stability were validated by benchmarking it against six competing models, including GA-SVR, PSO-SVR, and the baseline SVR and so forth. Finally, to elucidate the model’s internal decision-making mechanism, the SHAP (SHapley Additive exPlanations) interpretability framework was employed to quantify the independent and interactive effects of each influencing factor on energy consumption. The results indicate that: (1) The IBKA demonstrates superior convergence accuracy and global search performance compared with BKA and other algorithms. (2) The proposed IBKA-SVR model exhibits exceptional predictive accuracy. Relative to the baseline SVR, the model reduces key error metrics by 37–40% and improves the R² to 0.9792. Furthermore, in a comparative analysis against models tuned by other metaheuristic algorithms such as GA and PSO, the IBKA-SVR consistently maintained optimal performance. (3) The SHAP analysis reveals a clear hierarchy in the impact of the design features. The Insulation Thickness in Outer Wall and Insulation Thickness in Roof Covering are the dominant factors, followed by the Window-wall Ratios of various orientations and the Sun space Depth. Key features predominantly exhibit a negative impact, and a significant non-linear relationship exists between the dominant factors (e.g., insulation layers) and the predicted values. (4) Interaction analysis reveals a distinct hierarchy of interaction strengths among the building design variables. Strong synergistic effects are observed among the Sun space Depth, Insulation Thickness in Roof Covering, and the Window-wall Ratios in the East, West, and North. In contrast, the interaction effects between the Window-wall Ratio in the South and other variables are generally weak, indicating that its influence is approximately independent and linear. Therefore, the proposed bio-inspired framework, integrating the improved IBKA with SVR, effectively predicts and analyzes residential building energy consumption, thereby providing a robust decision-support tool for the data-driven optimization of building design and retrofitting strategies to advance energy efficiency and sustainability in rural housing. Full article

Current temperature prediction methods often focus on time-series information while neglecting the contributions of different meteorological factors and the context of varying time steps. Accordingly, this study developed a Dual-Attention-BiLSTM (a bidirectional long short-term memory network with dual attention mechanisms) network model, which integrates a bidirectional long short-term memory (BiLSTM) network model with random forest-based feature selection and two self-designed attention mechanisms. A sensitivity analysis was conducted to evaluate the influence of the attention mechanisms. This study focuses on Shijiazhuang City, China, which has a temperate continental monsoon climate with significant seasonal and daily variations. The data were sourced from ERA5-Land, comprising hourly near-surface temperature and related meteorological variables for the year of 2022. The results indicate that integrating the two attention mechanisms significantly improves the model’s prediction performance compared to using BiLSTM alone. The mean absolute error between simulation results ranges from 0.80 °C to 1.08 °C, with a reduction of 0.17 °C to 0.39 °C, and the root mean square error ranges from 1.17 °C to 1.37 °C, with a reduction of 0.12 °C to 0.22 °C. Full article

Background: Globally, uncorrected refractive errors are recognized as the primary cause of visual impairment and blindness. According to a report by the World Health Organization (WHO), providing spectacle lenses at an affordable cost remains a significant challenge, particularly for underprivileged populations in developing countries. This challenge contributes to the low compliance with spectacle wear worldwide. However, the benefits of wearing spectacles are influenced by the perceptions of the population regarding spectacle use. Methods: A quantitative, cross-sectional survey-based study was conducted at a superior educative center in Oman, the University of Buraimi. Participants were recruited from the four major colleges, namely, the College of Health Sciences (COHS), College of Business (COB), College of Engineering (COE), and College of Law (COL), and the Center for Foundation Studies (CFS). This study was conducted over the period from 18 December 2022 to 18 December 2023. Essential data were collected using an electronic questionnaire facilitated by the Google platform. The initial section of the questionnaire outlines this study’s objectives and its benefits to the community. The digital survey comprises three sections: the first section addresses the sociodemographic profile of the participants; the second section explores perceptions related to spectacles; and the third section examines visual symptoms associated with spectacle wear. In this study, a pre-tested survey was administered following consultation with a panel of three subject matter experts who reviewed the clarity and content validity of the test items. Data analyses were performed using descriptive statistics, and linear regression was applied to assess the effect of socioeconomic profile on perceptions of spectacles. Additionally, data entry, processing, and analysis were conducted using SPSS 25 software. The overall mean score for spectacle-related visual symptoms was 2.51 ± 0.75, indicating a moderate level of symptom occurrence. Results: A total of 415 participants (N = 415) were included in this study, comprising 133 males (32.0%) and 282 females (68.0%). The most prominent symptoms related to spectacle perception were “light sensitivity” and “eye pain”, with mean values of 3.03 ± 1.30 and 3.04 ± 1.25, respectively. Additionally, 249 participants (60%) reported moderate concern regarding spectacle-related visual symptoms. Among female participants, 118 (41.8%) exhibited little concern about visual symptoms associated with spectacle wear, whereas this was observed in 25.6% of male participants. Descriptive statistics indicated the mean perceived spectacle-related disadvantages score measured on a scale of 0 to 4 was 2.88 ± 1.16 (57.69% ± 23.15% in percentages), reflecting a moderate perception of such disadvantages. The linear regression model demonstrated statistical significance, as indicated by the likelihood ratio chi-square = 199.194 (df = 15, p < 0.001). The most significant predictor was study major (χ² = 72.922, p < 0.001). Conclusions: The present study indicates that undergraduate students generally exhibit a low perception of the disadvantages associated with wearing spectacles. Randomized sampling should be preferred in future studies to the convenience sampling technique. The most frequently reported visual symptoms include “light sensitivity and eye pain” among spectacle wearers. Therefore, it is imperative to implement health education programs and foundational studies across colleges to address these issues among undergraduate university students. Full article

Land Surface Temperature (LST) is a critical parameter for analyzing urban heat islands, surface–atmosphere interactions, and environmental management. This study enhances the temporal resolution of LST data by leveraging machine learning and deep learning models. A novel methodology was developed using Landsat 8 thermal data and Sentinel-2 multispectral imagery to predict LST at finer temporal intervals in an urban setting. Although Sentinel-2 lacks a thermal band, its high-resolution multispectral data, when integrated with Landsat 8 thermal observations, provide valuable complementary information for LST estimation. Several models were employed for LST prediction, including Random Forest Regression (RFR), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) network, and Gated Recurrent Unit (GRU). Model performance was assessed using the coefficient of determination (R²) and Mean Absolute Error (MAE). The CNN model demonstrated the highest predictive capability, achieving an R² of 74.81% and an MAE of 1.588 °C. Feature importance analysis highlighted the role of spectral bands, spectral indices, topographic parameters, and land cover data in capturing the dynamic complexity of LST variations and directional patterns. A refined CNN model, trained with the features exhibiting the highest correlation with the reference LST, achieved an improved R² of 84.48% and an MAE of 1.19 °C. These results underscore the importance of a comprehensive analysis of the factors influencing LST, as well as the need to consider the specific characteristics of the study area. Additionally, a modified TsHARP approach was applied to enhance spatial resolution, though its accuracy remained lower than that of the CNN model. The study was conducted in Tehran, a rapidly urbanizing metropolis facing rising temperatures, heavy traffic congestion, rapid horizontal expansion, and low energy efficiency. The findings contribute to urban environmental management by providing high-temporal-resolution LST data, essential for mitigating urban heat islands and improving climate resilience. Full article

High-precision time synchronization among nodes of the airborne-based pseudolite navigation augmentation positioning system (A-PNAS) is a crucial indicator for ensuring the accuracy of positioning services. Due to the flight characteristics and external factors’ influence, the airborne platform usually undergoes random motion. Therefore, the time-varying effect errors and Doppler effect errors will be introduced into the clock skew measurement results during the time-synchronous processing. In A-PNAS with meter-level positioning accuracy, the time synchronization accuracy (TSA) between nodes usually needs to be within 2 ns. These dynamic errors will have an impact on the TSA between nodes, which cannot be ignored. Based on the analysis of the principle of dynamic error generation and the available sensors, a multi-sensor combination method for correcting dynamic errors is proposed. This method calculates and corrects the dynamic errors based on the motion measurements from sensors. The simulation test results show that the degree of improvement in correcting dynamic errors by this method is basically close to 80%. It can effectively meet the requirements of high-precision time synchronization system and can provide an effective reference for the high-precision time synchronization processing of similar space-based platform collaborative systems. Full article

Designing phosphate adsorbents is often hindered by trial-and-error optimization that overlooks nonlinear coupling between preparation parameters and operational conditions. Here we present a unified, explainable machine-learning framework that links red mud modified biochar bead (RM/CSBC) preparation (red mud dosage, biomass dosage, and pyrolysis temperature) to operating variables (initial pH, reaction temperature, contact time, and initial phosphate concentration) and directly guides condition selection. Using 95 independent experiments, six regressors were trained and compared. Random Forest (RF) model demonstrated strong prediction accuracy, with R² values of 0.916 for the training set and 0.892 for the test set. Support Vector Regression (SVR) model showed superior performance, achieving R² values of 0.984 and 0.967 for training and test sets, respectively, with low RMSE (0.068 and 0.083) and PBIAS (5.41% and 6.86%). Feature importance analysis revealed red mud and biomass doses positively influenced phosphate adsorption, with surface active sites and phosphate concentration gradient playing significant roles. Experimental verification confirmed RF and SVR models provided accurate predictions under three representative conditions, with deviations between predictions and measurements of +0.66, +0.19, and −0.69 mg·g⁻¹ for SVR and −1.08, −0.79, and −1.15 mg·g⁻¹ for RF, offering reliable guidance for phosphate removal in wastewater using RM/CSBC. This work highlights the potential of using machine learning to optimize waste-based adsorbent materials for wastewater treatment, significantly reducing time and experimental costs. Full article

This study proposes a machine learning framework utilizing physical feature dimensionality reduction to address the problem of predicting the maximum excess temperature beneath the tunnel ceiling under the influence of multiple factors. First, theoretical analysis is used to systematically explore the impacts of various factors on the maximum excess temperature, including the heat release rate of the fire source, tunnel height, slope, and ambient air pressure. Physical relationships are established to identify key factors, remove redundant features, and construct a simplified feature vector set. Five typical machine learning models are selected: Random Forest (RF), Support Vector Regression (SVR), Fully Connected Neural Network (FCNN), Multi-Layer Perceptron (MLP), and Bayesian Neural Network (BNN). A hybrid data collection strategy combining scale model tests and CFD numerical simulations constructs a small-sample structured dataset with physical backgrounds. The models are evaluated regarding prediction accuracy, stability, and generalization ability. Results show that the Bayesian Neural Network (BNN) optimized by random search parameter optimization and Bayesian regularization significantly outperforms other comparative models in evaluation indices such as root mean square error (RMSE), and mean absolute error (MAE), and coefficient of determination (R²), making it the optimal model and algorithm combination for such tasks. This study provides a reliable quantitative analysis method for tunnel fire safety assessment and offers a new methodological reference for the research on fire dynamics in underground spaces. Full article

With the continuous acceleration of industrialization, air pollution has become increasingly severe and has, to some extent, contributed to the progression of global climate change. Against this backdrop, accurate temperature forecasting plays a vital role in various fields, including agricultural production, energy scheduling, environmental governance, and public health protection. To improve the accuracy and stability of temperature prediction, this study proposes a hybrid modeling approach that integrates convolutional neural networks (CNNs), Long Short-Term Memory (LSTM) networks, and random forests (RFs). This model fully leverages the strengths of CNNs in extracting local spatial features, the advantages of LSTM in modeling long-term dependencies in time series, and the capabilities of RF in nonlinear modeling and feature selection through ensemble learning. Based on daily temperature, meteorological, and air pollutant observation data from Wuhan during the period 2015–2023, this study conducted multi-scale modeling and seasonal performance evaluations. Pearson correlation analysis and random forest-based feature importance ranking were used to identify two key pollutants (PM_2.5 and O₃) and two critical meteorological variables (air pressure and visibility) that are strongly associated with temperature variation. A CNN-LSTM model was then constructed using the meteorological variables as input to generate preliminary predictions. These predictions were subsequently combined with the concentrations of the selected pollutants to form a new feature set, which was input into the RF model for secondary regression, thereby enhancing the overall model performance. The main findings are as follows: (1) The six major pollutants exhibit clear seasonal distribution patterns, with generally higher concentrations in winter and lower in summer, while O₃ shows the opposite trend. Moreover, the influence of pollutants on temperature demonstrates significant seasonal heterogeneity. (2) The CNN-LSTM-RF hybrid model shows excellent performance in temperature prediction tasks. The predicted values align closely with observed data in the test set, with a low prediction error (RMSE = 0.88, MAE = 0.66) and a high coefficient of determination (R² = 0.99), confirming the model’s accuracy and robustness. (3) In multi-scale forecasting, the model performs well on both daily (short-term) and monthly (mid- to long-term) scales. While daily-scale predictions exhibit higher precision, monthly-scale forecasts effectively capture long-term trends. A paired-sample t-test on annual mean temperature predictions across the two time scales revealed a statistically significant difference at the 95% confidence level (t = −3.5299, p = 0.0242), indicating that time granularity has a notable impact on prediction outcomes and should be carefully selected and optimized based on practical application needs. (4) One-way ANOVA and the non-parametric Kruskal–Wallis test were employed to assess the statistical significance of seasonal differences in daily absolute prediction errors. Results showed significant variation across seasons (ANOVA: F = 2.94, p = 0.032; Kruskal–Wallis: H = 8.82, p = 0.031; both p < 0.05), suggesting that seasonal changes considerably affect the model’s predictive performance. Specifically, the model exhibited the highest RMSE and MAE in spring, indicating poorer fit, whereas performance was best in autumn, with the highest R² value, suggesting a stronger fitting capability. Full article

Flight altitude is a critical parameter influencing both the spatial resolution and operational efficiency of UAV multispectral imaging; however, its quantitative effects on crop monitoring accuracy remain insufficiently characterized. This study investigated maize in the Yuci District, Jinzhong, China, using multispectral imagery and ground measurements of soil moisture, SPAD, leaf water content (LWC), leaf area index (LAI), plant height (PH), and aboveground biomass (AGB) collected at eight altitudes (65–200 m). Correlation analysis and three modeling approaches were applied: stepwise linear regression (SLR), random forest (RF), and back-propagation neural network (BPNN). Accuracy decreased with altitude. At 65–100 m, the correlations were strongest: LAI–NDVI/GNDVI ranged from 0.818 to 0.938, and SPAD–NDVI/GNDVI exceeded 0.816. At 80–100 m, RMSE values for LAI, SPAD, and LWC were 0.05, 10.37, and 0.67, with RE below 15%. At 200 m, the lowest R² dropped to 0.23, with errors rising sharply. RF and BPNN outperformed SLR, with BPNN yielding the highest accuracy for LAI and AGB. Overall, 65–100 m is optimal for precision monitoring, 120–160 m balances accuracy and efficiency, and 180–200 m suits large-scale reconnaissance. These findings provide methodological guidance for UAV flight parameter optimization in precision agriculture. Full article

The anti-slip performance of road surfaces directly affects traffic safety, yet existing evaluation methods based on texture features often suffer from limited interpretability and low accuracy. To overcome these limitations, a portable 3D laser surface analyzer was used to acquire road texture data, while a dynamic friction coefficient tester provided friction measurements. A multi-view fractal dimension index was developed to comprehensively describe the complexity of texture across spatial, cross-sectional, and depth dimensions. Combined with road surface temperature, this index was integrated into an XGBoost-based prediction model to evaluate friction at driving speeds of 10 km/h and 70 km/h. Comparative analysis with linear regression, decision tree, support vector machine, random forest, and backpropagation (BP) neural network models confirmed the superior predictive performance of the proposed approach. The model achieved backpropagation (R²) values of 0.80 and 0.82, with root mean square errors (RMSEs) of 0.05 and 0.04, respectively. Feature importance analysis indicated that fractal characteristics from multiple texture perspectives, together with temperature, significantly influence anti-slip performance. The results demonstrate the feasibility of using non-contact texture-based methods to replace traditional contact-based friction testing. Compared with traditional statistical indices and alternative machine learning algorithms, the proposed model achieved improvements in R² (up to 0.82) and reduced RMSE (as low as 0.04). This study provides a robust indicator system and predictive model to advance road surface safety assessment technologies. Full article

Cemented filling technology is an effective approach to solving tailings accumulation and goaf, with rheological properties serving as key indicators of slurry fluidity. Since slurry rheology is influenced by multiple factors, accurate prediction of its parameters is essential for optimizing filling design. In this study, we developed a model to predict static and dynamic yield stress using the extreme gradient boosting (XGBoost) algorithm, trained on 140 experimental samples (105 for training and 35 for validation, split 75:25). For comparison, adaptive boosting tree (ADBT), gradient boosting decision tree (GBDT), and random forest (RF) algorithms were also applied. Model performance was evaluated using four metrics: coefficient of determination (R²), mean absolute error (MAE), root mean square error (RMSE), and explained variance score (EVS). The Shapley additive explanation (SHAP) method was employed to interpret model outputs. The results show that XGBoost achieved superior predictive accuracy for slurry yield stress compared with other models. Analysis of importance revealed that underflow concentration had the strongest influence on predictions, followed by the binder-to-tailings ratio, while the fine-to-coarse tailings ratio contributed least. These findings highlight the potential of machine learning as a powerful tool for modeling the rheological parameters of filling slurry, offering valuable guidance for engineering applications. Full article

In modern industrial manufacturing, the mechanical properties of large bearing housing castings are critical to equipment reliability and lifespan. Traditional prediction methods relying on experimental testing and empirical formulas face challenges such as high costs, limited samples, and inadequate generalization capabilities. This study presents a machine learning approach for predicting mechanical properties of ZG270-500 cast steel, integrating multivariate data (chemical composition, process parameters) to establish an efficient predictive model. Utilizing real-world production data from a certain foundry and forging plant, the research implemented preprocessing steps including outlier handling, data balancing, and normalization. A systematic comparison was conducted on the performance of four algorithms: Backpropagation Neural Network (BPNN), Support Vector Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The results indicate that under small-sample conditions, the SVR model outperforms other models, achieving a coefficient of determination (R²) between 0.85 and 0.95 on the test set for mechanical properties. The root mean square errors (RMSE) for yield strength, tensile strength, elongation, reduction in area, and impact energy are 7.59 MPa, 7.52 MPa, 0.68%, 1.47%, and 5.51 J, respectively. Experimental validation confirmed relative errors between predicted and measured values below 4%. SHAP value analysis elucidated the influence mechanisms of key process parameters (e.g., pouring speed, normalization holding time) and elemental composition on mechanical properties. This research establishes an efficient data-driven approach for large casting performance prediction and provides a theoretical foundation for guiding process optimization, thereby addressing the research gap in performance prediction for large bearing housing castings. Full article

In the paper, the inverse solution of the heat conduction problem is analysed, which is applied to calculate transient thermal stresses on the internal surface of a thick-walled pipe weakened by a hole. The analysis considered a one-dimensional heat transfer problem when heat is transferred in a radial direction. In the inverse marching method, the measurement of the wall temperature at one point of a thermally insulated pipeline is used. The technique was verified regarding the distance between the point where the wall temperature is measured and the internal surface, the number of finite volumes in the inverse region, and the time step size are selected. The influence of these parameters on the accuracy of the calculated temperature, thermal stresses, heat transfer coefficient on the internal surface of the pipeline and thermal stresses at the hole edge was assessed. The reference values used to verify the technique were those calculated using the analytical method and the direct solution of the heat conduction problem, and the generated ‘measurement data’ were disturbed by random errors. Full article

Each charging/discharging cycle leads to a gradual decrease in the battery’s capacity. The degradation of capacity in lithium-ion batteries represents a non-monotonous process with random jumps. Earlier studies claimed that the instantaneous degradation value of a lithium-ion battery is influenced by the historical dataset with long-range dependence. The existing methods ignore large jumps and long-range dependences in degradation processes. In order to capture long-range-dependent behavior with random jumps, we refer to the fractional Poisson process. We also outline the relationship between the long-range correlation and the Hurst index. The connection between random jumps in capacitance and long-range dependence of the fractional Poisson process is proven. In order to construct the fractional Poisson predictive model, we included fractional Brownian motion as the diffusion term and the fractional Poisson process as the jump term. The proposed approach is implemented on NASA’s dataset for Li-ion battery degradation. We believe that the error analysis for the fractional Poisson process is advantageous compared with that of the fractional Brownian motion, the fractional Levy stable motion, the Wiener model, and the long short-term memory model. Full article