Search

In modern warfare, the accurate prediction of the intercept time and intercept point of the interceptor is the key to achieving penetration. Aiming at this problem, firstly, a convolutional neural network (CNN) is used to automatically extract high-level features from the data, and then these features are used as the input of support vector regression (SVR) for regression prediction. The Harris Hawk optimization (HHO) is used to optimize the hyperparameters of SVR, and the HHO-CNN-SVR algorithm is proposed. In order to verify the effectiveness of the algorithm for the prediction of the interception point and interception time, this paper constructs a dataset to test the method of simulating the missile interception maneuvering target. Compared with BP, ELM, SVR, HHO-SVR, and CNN-SVR models, the HHO-CNN-SVR model has outstanding performance in prediction accuracy and stability, especially for the interception time. The error is the smallest, and the error fluctuation is small. The MAE of the prediction result is only 0.0139 s; in the interception point prediction, the error of the range and elevation direction is significantly lower than that of the models used for comparison. The MAE in the range direction is 2.3 m, and the MAE in the elevation direction is 2.01 m, which meet the engineering requirements. The HHO-CNN-SVR model has strong prediction accuracy and stability in interception time and interception point prediction. In addition, different control strategies are used to construct a new prediction set, and noise is added to the prediction set. The HHO-CNN-SVR algorithm can maintain good prediction results. The results show that the HHO-CNN-SVR model proposed in this paper has strong generalization ability and high robustness, which can provide reliable support for penetration decision making and defense system optimization. [ABSTRACT FROM AUTHOR]

This study proposes a novel approach for predicting the output behaviors of the Pepperl+Fuchs 3RG6232-3JS00-PF ultrasonic sensor. The sensor, integrated into the Festo MPS-PA Didactic System, serves to monitor the water level in a tank, facilitating water extraction to bottles delivered via a conveyor belt. This modeling approach represents the initial phase in the creation of a digital twin of the physical sensor, providing the capability for users to observe the sensor's response and forecast its life cycle for maintenance objectives. This study utilizes the Festo MPS-PA Compact Didactic System and support vector regression (SVR) for data acquisition (DAQ), preprocessing, and model training with hyperparameter optimization. The objective of this modeling approach is to establish a digital framework for transition towards Industry 4.0. It holds the potential for creating a digital counterpart of the entire MPS-PA System when combining the proposed sensor modeling technique with computer-assisted design (CAD) software such as Siemens NX in the future. This would enable users to oversee the entire process in a three-dimensional visualization engine, such as Tecnomatix Plant Simulation. This research significantly contributes to the comprehension and application of digital twins in the realm of mechatronics and sensor systems technology. It also underscores the importance of digital twins in enhancing the efficiency and predictability of sensor systems. The method used in this paper involves predicting the rate of change (RoC) of the water level and then integrating this rate to estimate the actual water level, providing a robust approach for sensor data modeling and digital twin creation. The result shows a promising 6.99 % error percentage. [ABSTRACT FROM AUTHOR]

Accurate estimation of soil properties is crucial for reliability-based design in engineering practices. Conventional empirical equations and prevalent data-driven models rarely consider uncertainty quantification in both measurement and modelling processes. This study tailors three uncertainty quantification methods including Bayesian learning, Markov chain Monte Carlo and ensemble learning into data-driven modelling, in which support vector regression is selected as the baseline algorithm. The compression index of clay is adopted as an example for model training and testing. In this context, Bayesian learning and Markov chain quantify uncertainty by considering the distribution of function and hyper-parameters, respectively, while different sampled data are employed to explore model uncertainty. These models are evaluated in terms of accuracy, reliability and cost-effectiveness and also compared with Gaussian process regression, etc. The results reveal that based on built-in structural risk minimization, sparse solution and uncertainty quantification, developed models can capture more accurate and reliable correlations from actual measured data over other methods. Their practicability and generalization ability are also verified on a new creep index database. The proposed probabilistic methods are also compiled into a user-friendly platform, showing a significant potential to enrich the data-driven modelling framework and be applied in other geotechnical properties. [ABSTRACT FROM AUTHOR]

In this research paper, machine learning techniques were applied to a multivariate meteorological time series data for estimating the wheat yield of five districts of Punjab. Wheat yield data and weather parameters over 34 years were collected from the study area and the model was developed using stepwise multi-linear regression (SMLR), artificial neural network (ANN), support vector regression (SVR), random forest (RF) and deep neural network (DNN) techniques. Wheat yield estimation was done at the tillering, flowering, and grain-filling stage of the crop by considering weather variables from 46 to 4th, 46 to 8th, and 46 to 11th standard meteorological week. Weighted and unweighted Meteorological variables and yield data were used to train, test, and validate the models in R software. The evaluation results showed a consistent and promising performance of RF, SVR, and DNN models for all five districts with an overall MAPE and nRMSE value of less than 6% during validation at all three growth stages. These models exhibited outstanding performance during validation for the Faridkot, Ferozpur, and Gurdaspur districts. Based on accuracy parameters MAPE, RMSE, nRMSE, and percentage deviation, the RF model was found better followed by SVR and DNN models and, hence can be used for district-level wheat crop yield estimation at different crop growth stages. [ABSTRACT FROM AUTHOR]

The hydromatereological processes are examined through analysis of temporal rainfall variability. India is an agricultural land and its economy is mainly dependent on timely rains to produce good harvest. The amount of rainfall varies with regional and temporal variation in distribution. The present research has been conducted to predict the temporal variations in rainfall in Udupi district, Karnataka, India using support vector regression (SVR) model and to validate the findings using actual rainfall records. The data has been collected from the statistical department, Udupi district, Government of Karnataka, India. The prediction accuracy of SVR based rainfall prediction model depends on tuning of algorithmic-based parameters. The parameter optimization is performed using grid search to select the optimal values of hyperparameters. The analysis was performed for the year 2018 based on the training dataset from 2000-2017. It is observed that there is a decreasing trend in total annual rainfall in 2018 and it is concluded that the average yearly rainfall has declined during the years 2018 and 2019. The rainfall predicted results were validated with actual records. The SVR based rainfall prediction model will predicts the rainfall accurately for application in agricultural sector. [ABSTRACT FROM AUTHOR]

Carbon emission trading system is one of the important means for China to tackle climate warming and achieve the dual-carbon goals. However, due to the characteristics of the carbon emission trading prices, such as nonlinearity, instability, and complexity of predictor variables, the performance of existing prediction models is relatively poor. In order to solve the above problems, a prediction model considering the predictor variables of carbon emission trading prices is proposed in this paper. The proposed method first analyzes 18 predictor variables in six categories and Lasso is used to select predictor variables as inputs for the prediction model. Secondly, sliding time window technique is adopted to analyze the dynamics and trends in the carbon market. Then, differential evolution (DE) algorithm is utilized to improve the performance of support vector regression (SVR), where SVR is used as the prediction model for carbon emission trading prices. Finally, the carbon emission trading price is taken as a sample set in Hubei Province, together with the selected predictor variables, as input to the prediction model. The experimental results show that the proposed model obtains optimal results in three performance evaluation metrics, including root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). Compared with the basic model, the results decreased by 1.6081, 1.4753 and 5.5418% respectively, which improved the prediction accuracy of the model. And the proposed model has also achieved better performance in predicting the prices of China's carbon emissions trading market. [ABSTRACT FROM AUTHOR]

Wildfires significantly impact water quality in the Western United States, posing challenges for water resource management. However, limited research quantifies post-wildfire stream temperature and turbidity changes across diverse climatic zones. This study addresses this gap by using Random Forest (RF) and Support Vector Regression (SVR) models to predict post-wildfire stream temperature and turbidity based on climate, streamflow, and fire data from the Clackamas and Russian River Watersheds. We selected Random Forest (RF) and Support Vector Regression (SVR) because they handle non-linear, high-dimensional data, balance accuracy with efficiency, and capture complex post-wildfire stream temperature and turbidity dynamics with minimal assumptions. The primary objectives were to evaluate model performance, conduct sensitivity analyses, and project mid-21st century water quality changes under Representative Concentration Pathway (RCP) 4.5 and 8.5 scenarios. Sensitivity analyses indicated that 7-day maximum air temperature and discharge were the most influential predictors. Results show that RF outperformed SVR, achieving an R2 of 0.98 and root mean square error of 0.88 °C for stream temperature predictions. Post-wildfire turbidity increased up to 70 NTU during storm events in highly burned subwatersheds. Under RCP 8.5, stream temperatures are projected to rise by 2.2 °C by 2050. RF's ensemble approach captured non-linear relationships effectively, while SVR excelled in high-dimensional datasets but struggled with temporal variability. These findings underscore the importance of using machine learning for understanding complex post-fire hydrology. We recommend adaptive reservoir operations and targeted riparian restoration to mitigate warming trends. This research highlights machine learning's utility for predicting post-wildfire impacts and informing climate-resilient water management strategies. [ABSTRACT FROM AUTHOR]

Subcritical water extraction (SCWE) has been increasingly studied and applied in recent decades for the extraction of organic pollutants from contaminated soil. However, the efficacy of the SCWE technique for soil remediation depends not only on the operating parameters but also on the soil and pollutant properties. Models for predicting PAHs removal by the SCWE process are highly desirable for the process design and for facilitating a global understanding of the influence of each parameter for optimal remediation without numerous trials. In this study, a support vector regression (SVR) model was developed to predict PAHs removal from contaminated soil based on the SCWE operating parameters and soil and PAHs' properties. Results revealed that the model exhibited a good predictability with the correlation coefficients of 0.99 and 0.93 for the training and testing datasets, respectively. The importance of input variables was in the following order: operating conditions > chemical properties > soil properties. The statistical analysis demonstrated the reliability and robustness of the developed model. Based on our findings, the SVR model is suitable for predicting the removal rate of PAHs by SCWE process. [ABSTRACT FROM AUTHOR]

Accurate power consumption prediction is a crucial part of energy management. Some of the machine learning models that are the focus of this study for the prediction of power use include Support Vector Regression, Adaptive Boosting, and Decision Tree Regression. These models have been improved with the use of some novel optimizers-namely, the Trochoid Search Optimization, Red-Tailed Hawk, and Giant Armadillo Optimization methods-for hyper-parameter tuning to enhance prediction accuracy. When tested against real data, DTGA outperformed with R2 values of 0.9918, 0.9924, and 0.9934 for three zones. This work extends the study on the forecast of power consumption by integrating machine learning and optimization techniques that provide effective energy management strategies. [ABSTRACT FROM AUTHOR]

In structures with reinforced concrete walls, coupling beams join individual walls to produce a rigid assembly that withstands sideways forces. A precise forecasting of the critical shear capacity is essential to avoid early shear failure and attain the desired ductility performance of coupled shear wall systems in earthquake design. This paper examines the ability of Support Vector Regression (SVR) in predicting the shear performance of coupling beams. SVR is a distinguished machine learning regression method that has been positively utilized in former works to forecast the performance of several structural members. Nevertheless, the capability of this regression method deeply relies on picking its best hyperparameters. To handle this, a heuristic optimization procedure named Particle Swarm Optimization (PSO) was merged with SVR to select the optimal hyperparameters. The data of RC coupling beams collected from the previous works were utilized to build the proposed model. Several performance metrics, including RMSE, R2, and MAE, were employed to compare the performance of the optimized model against a baseline SVR model and previous approaches. Analytical results indicate that the new optimized prediction model can assist civil engineers in designing RC coupling beam structures more effectively and outperforms existing models in predicting the shear strength of such beams. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

To address the problem of predicting the state of health (SOH) of lithium-ion batteries, this study develops three models optimized using the particle swarm optimization (PSO) algorithm, including the long short-term memory (LSTM) network, convolutional neural network (CNN), and support vector regression (SVR), for accurate SOH estimation. Key features were extracted by analyzing the temperature, voltage, and current curves of the battery, and health factors with high correlation to SOH were selected as model inputs using the Pearson correlation coefficient. The PSO algorithm was employed to optimize model parameters, resulting in the construction of three predictive models: PSO-LSTM, PSO-CNN, and PSO-SVR. The models were validated using the NASA PCoE battery aging datasets B0005, B0006, and B0007, with prediction accuracy evaluated based on Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R2). Results indicate that the optimized models achieved significant improvements in prediction accuracy, with RMSE and MAE reduced by over 0.5%, a minimum reduction of 38% in MAPE, and R2 exceeding 0.8, demonstrating strong fitting capabilities and validating the effectiveness of the PSO strategy. Among the three models, PSO-LSTM exhibited the best predictive performance, achieving a minimum MAE of 0.67%, RMSE of 0.94%, MAPE of 45.82%, and R2 as high as 0.9298 across the three datasets. These findings suggest that the PSO-LSTM model provides a robust reference for accurate SOH prediction of lithium-ion batteries and shows promising potential for practical applications. [ABSTRACT FROM AUTHOR]

This study presents a quantitative prediction model with an optimal dimensional reduction technique for the first time in the context of shrinkage defects in a compact graphite iron (CGI) engine cylinder head. The model is built on the support vector regression (SVR) machine learning algorithm and the Mahalanobis-Taguchi system (MTS) is incorporated for dimensional reduction purposes. An in-depth analysis of 41 process variables has been conducted to identify the crucial factors influencing the shrinkage defect. The chosen variables were then used to feed the intelligent prediction model. Optimal tuning of SVR hyperparameters was achieved by evaluating adjustments over the root mean square error (RMSE) for training and testing datasets while simultaneously minimizing RMSE when predicting the defect size. Results were experimentally validated through scanning electron microscopy with energy-dispersive X-ray detection (SEM-EDX). [ABSTRACT FROM AUTHOR]

In the present work, the hardness prediction of polypropylene/carbon nanotubes (PP/CNT) and low-density polyethylene/carbon nanotubes (LDPE/CNT) composite materials, processed by microwave technique, has been explored using machine learning models i.e. (Random Forest, Support Vector Regression, K-Nearest Neighbors, Linear Regression, and Neural Network). Four input vectors have been used in the construction of proposed network, such as CNT concentration, power, pressure applied, and exposure time. Hardness prediction is one output that has been evolved from the proposed work. This study presents the prediction of hardness based on machine learning models for both PP/CNT and LDPE/CNT composite materials, and the results show that the Random Forest model consistently performs better than the others models in context with performance metrics like Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Rate of determination (R2) values. Investigations have been performed on resampling strategies, showing that the jackknife approach enhances model precision and robustness in the case of LDPE/CNT composites. For PP/CNT composite material, it has been noticed that Random Forest gives the highest value of R2 (0.94), whereas Random Forest has the lowest R2 value 0.18 for LDPE/CNT composite material. Random Forest is the most reliable model for predicting the characteristics of PP/CNT composite material due to its ability to handle complex datasets. The LDPE/CNT composite material demonstrates superior prediction accuracy, with a maximum error of just 1.61%, making it a better option for high-precision applications due to enhanced mechanical interactions and improved CNT dispersion. [ABSTRACT FROM AUTHOR]

A robust, accurate and reliable approach is essential for not only examining people's acceptance of cloud-based learning management systems in developing nations but also for accurate prediction of factors affecting its implementation and progress. Therefore, in this study, three different soft computing models; Adaptive neuro-fuzzy inference system (ANFIS), Support vector regression (SVR), and Emotional artificial neural network (EANN), were employed for predictions of factors affecting cloud-based learning management systems take-up and progress using data gotten from six Nigerian colleges. The performance of the models was assessed using five arithmetic metrics; MAPE, NSE, RMSE, rRMSE, and RM. All the proposed models forecast the effects of the study inputs on LMS with higher accuracy (NSE > 0.98). However, the SVR model outshone the other models as it increased the performance of the study-reported model by 2% and 4% respectively. Based on the study results, instructors' quality, motivation, and resource availability were found to be the key factors that affect cloud-based learning technologies take-up and progress in the study area. Interestingly, unlike prior studies, this study found system ease of use and usefulness to have insignificant effects on LMS take-up. Finally, the practical implications and limitations of the study were discussed based on the study findings. [ABSTRACT FROM AUTHOR]

Due to the widespread use of point cloud, the demand for compression and transmission is more and more prominent. However, this cause various losses to the point cloud. It is necessary for application to evaluate the quality of point cloud. Therefore, we propose a new point cloud quality assessment (PCQA) metric named statistical information similarity (SISIM). First, we preprocess point cloud (PC) by scaling based on density and then project PC into texture maps and geometry maps. In addition, the SISIM based on Natural Scene Statistics (NSS) is proposed as texture features under the premise of proving that the texture maps meet NSS. Furthermore, we propose to extract geometry features based on local binary patterns (LBP) on account of the phenomenon that LBP maps of geometry images vary with different distortions. Finally, we predict the quality of PCs by fusing texture features with geometry features. Experiments show that our proposed method outperforms the state-of-the-art PCQA metrics on three publicly available datasets. [ABSTRACT FROM AUTHOR]

The shear bearing capacity of confined concrete columns subjected to lateral cyclic loading is an important mechanical property in investigating seismic behavior of concrete buildings. However, it is still difficult to accurately predict shear bearing capacity of confined concrete columns using traditional analysis methods owing to its complex mechanical principle and indeterminate multivariable interrelationship. In this paper, an experimental study of 15 confined concrete columns subjected to lateral cyclic loading was conducted to explore the seismic behavior of confined concrete columns. Moreover, ANN and SVR models were established to accurately estimate the shear bearing capacity of confined concrete columns based on a reliable test database consisting of 121 specimens conducted in this study and published literatures. Nine key parameters were considered as input variables, including cross-sectional area of core concrete, unconfined concrete compressive strength, shear span ratio, axial compression ratio, volumetric ratio of transverse reinforcement, yield strength of transverse reinforcement, longitudinal reinforcement ratio, yield strength of longitudinal reinforcement, and confinement type. Additionally, the model sensitivity analysis was conducted to investigate the impact of parameters on shear bearing capacity of confined concrete columns. Finally, the ANN and SVR models were evaluated by comparing with five existing predicted methods and experimental results indicating that the ANN and SVM models have enough accuracy and reliability in predicting shear bearing capacity of confined concrete columns subjected to lateral cyclic loading. [ABSTRACT FROM AUTHOR]

Copyright of Nonferrous Metals (Mining Section) is the property of Beijing Research Institute of Mining & Metallurgy Technology Group and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Atomic Energy Science & Technology is the property of Editorial Board of Atomic Energy Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Soil texture analysis is critical for advancing agricultural productivity, ensuring environmental sustainability, and maintaining ecosystem balance. Traditional sedimentation-based methods, such as the hydrometer technique, are fast and practical but prone to inaccuracies due to the effects of water-soluble substances. This study focuses on the practical framework of integrating pH (potential of hydrogen) and EC (electrical conductivity), as indicators of dissolved substances that influence soil texture estimation. Using the Ultrasound Penetration-based Digital Soil Texture Analyzer (USTA), this research combined ultrasound time series data with pH and EC measurements to predict sand, silt, and clay ratios through machine learning methods—support vector regression (SVR), Random Forest (RF), and multi-layer perceptron neural network (MLPNN). Simulations showed that RF yielded the best results, improving R2 values to 0.52, 0.33, and 0.31 for sand, silt, and clay, respectively. The enhanced model performance demonstrates the viability of integrating pH and EC with advanced machine learning techniques to improve soil texture analysis accuracy. These findings suggest that automated systems like USTA, with modular pH and EC sensors, can provide cost-effective, efficient alternatives to traditional methods, offering practical implications for soil management and agricultural optimization. [ABSTRACT FROM AUTHOR]

Southern Java Waters contribute significantly to aquatic economy of Indonesia by providing abundant fisheries resources. The understanding of sea state of the waters become a focal point. The aims of this paper are to analyze and to predict time series dataset comprising climate variables such as wind speed, surface temperature (SST), precipitation, and surface pressure of Southern Java waters. The analysis has been done by decomposing the time series dataset to its patterns, trend and seasonality, and calculating the correlation matrix of the dataset. The prediction method employs support vector regression (SVR) algorithm. The performance of the resulted models is computed using mean squared error (MSE). The result shows that wind speed of Southern Java Waters is positively corelated with surface pressure and negatively corelated with SST and total precipitation. The lowest MSE occurs in SST model. Meanwhile, the largest MSE is the total precipitation model. The developed models could be used as prediction tools of climate variables for following years in the Southern Java waters. [ABSTRACT FROM AUTHOR]

China has vast amounts of deep coalbed methane resources but is still in the early stage of deep coalbed methane development; thus, it lacks mature gas exploitation and development theories and technologies, particularly effective methods for evaluating final recoverable reserves. This paper intends to develop a method that can rapidly and accurately predict deep coalbed methane EUR before well spacing to guide the formulation of rational exploitation schemes and full exploitation of geological resources, thus lowering costs and enhancing efficiency. Taking deep coalbed methane in the Daning–Jixian block of the Ordos Basin as the research object, this paper first uses the production decline method to evaluate the EUR of brought-in wells and analyzes the influence of geological conditions and engineering parameters on the EUR. Second, the ADASYN method is used to process the unevenly distributed samples to solve the small number and poor representativeness of the machine learning model samples. After this, the BP neural network, support vector machine, and Gaussian process regression are used to build EUR evaluation models, and the models are compared and the best is selected. Lastly, the selected EUR evaluation model is applied to analyze the influence weights of geological conditions and engineering parameters on EUR. According to the research results, the MAPEs of the BP neural network, support vector machine, and Gaussian process regression models reach 7.03%, 7.23%, and 1.28%, respectively, after ADASYNA oversampling. However, the Gaussian process regression model may bear the risk of overfitting. The model comparison results show that the support vector machine model is superior to the BP neural network model and the Gaussian process regression model. Therefore, the support vector machine is favorably selected to predict EUR in this paper. Feature importance analysis results indicate that engineering parameters (including clusters, horizontal length, fracturing liquid, and proppant) are the major factors influencing the EUR prediction results. This paper establishes a model for predicting the EUR of deep coalbed methane, which provides a reference for the future formulation of well spacing schemes in the surveyed region. [ABSTRACT FROM AUTHOR]

Understanding rock hardness on extraterrestrial planets offers valuable insights into planetary geological evolution. Rock hardness correlates with morphological parameters, which can be extracted from navigation images, bypassing the time and cost of rock sampling and return. This research proposes a machine-learning approach to predict extraterrestrial rock hardness using morphological features. A custom dataset of 1496 rock images, including granite, limestone, basalt, and sandstone, was created. Ten features, such as roundness, elongation, convexity, and Lab color values, were extracted for prediction. A foundational model combining Random Forest (RF) and Support Vector Regression (SVR) was trained through cross-validation. The output of this model was used as the input for a meta-model, undergoing linear fitting to predict Mohs hardness, forming the Meta-Random Forest and Support Vector Regression (MRFSVR) model. The model achieved an R2 of 0.8219, an MSE of 0.2514, and a mean absolute error of 0.2431 during validation. Meteorite samples were used to validate the MRFSVR model's predictions. The model is used to predict the hardness distribution of extraterrestrial rocks using images from the Tianwen-1 Mars Rover Navigation and Terrain Camera (NaTeCam) and a simulated lunar rock dataset from an open-source website. The results demonstrate the method's potential for enhancing extraterrestrial exploration. [ABSTRACT FROM AUTHOR]

Purpose: Ball grid array (BGA) package is prone to failure issues in a thermal vibration-coupled environment, such as deformation and fracture of solder joints. To predict the minimum equivalent stress of solder joints more accurately and optimize the solder joint structure, this paper aims to compare the machine learning method with response surface methodology (RSM). Design/methodology/approach: This paper introduced a machine learning algorithm using Grey Wolf Optimization (GWO) Support Vector Regression (SVR) to optimize solder joint parameters. The solder joint height, spacing, solder pad diameter and thickness were the design variables, and minimizing the equivalent stress of solder joint was the optimization objective. The three dimensional finite element model of the printed circuit board assembly was verified by a modal experiment, and simulations were conducted for 25 groups of models with different parameter combinations. The simulation results were employed to train GWO-SVR to build a mathematical model and were analyzed using RSM to obtain a regression equation. Finally, GWO optimized these two methods. Findings: The results show that the optimization results of GWO-SVR are closer to the simulation results than those of RSM. The minimum equivalent stress is decreased by 8.528% that of the original solution. Originality/value: This study demonstrates that GWO-SVR is more precise and effective than RSM in optimizing the design of solder joints. [ABSTRACT FROM AUTHOR]

The prediction of debris flows is essential for safeguarding infrastructure and minimizing the economic losses associated with the hazards. Traditional empirical and theoretical models, while providing foundational insights, often struggle to capture the complex and nonlinear behaviors inherent in debris flows. This study aims to enhance debris flow prediction by integrating theoretical modeling with data-driven approaches. We model debris flow as a viscoplastic fluid, employing the Herschel–Bulkley rheological model to describe its behavior. By combining the kinematic wave model with lubrication theory, we develop a comprehensive theoretical framework that encapsulates the mechanical physics of debris flows and identifies key governing parameters. Numerical solutions of this theoretical model are utilized to generate an extensive training dataset, which is subsequently used to train a support vector regression (SVR) model. The SVR model targets slide depth and velocity upon impact, using explanatory variables including yield stress, material density, source area depth and length, and slope length. The model demonstrates high predictive accuracy, achieving coefficients of determination R 2 of 0.956 for slide depth and 0.911 for slide velocity at impact. Additionally, the relative residuals σ are primarily distributed within the range of −0.05 to 0.05 for both slide depth and slide velocity upon impact. These results indicate that the proposed hybrid model not only incorporates the fundamental physical mechanisms governing debris flows but also significantly enhances predictive performance through data-driven optimization. This study underscores the critical advantage of merging physical models with machine learning techniques, offering a robust tool for improved debris flow prediction and risk assessment, which can inform the development of more effective early warning systems and mitigation measures. [ABSTRACT FROM AUTHOR]

Abstract In the present work, the hardness prediction of polypropylene/carbon nanotubes (PP/CNT) and low-density polyethylene/carbon nanotubes (LDPE/CNT) composite materials, processed by microwave technique, has been explored using machine learning models i.e. (Random Forest, Support Vector Regression, K-Nearest Neighbors, Linear Regression, and Neural Network). Four input vectors have been used in the construction of proposed network, such as CNT concentration, power, pressure applied, and exposure time. Hardness prediction is one output that has been evolved from the proposed work. This study presents the prediction of hardness based on machine learning models for both PP/CNT and LDPE/CNT composite materials, and the results show that the Random Forest model consistently performs better than the others models in context with performance metrics like Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Rate of determination (R2) values. Investigations have been performed on resampling strategies, showing that the jackknife approach enhances model precision and robustness in the case of LDPE/CNT composites. For PP/CNT composite material, it has been noticed that Random Forest gives the highest value of R2 (0.94), whereas Random Forest has the lowest R2 value 0.18 for LDPE/CNT composite material. Random Forest is the most reliable model for predicting the characteristics of PP/CNT composite material due to its ability to handle complex datasets. The LDPE/CNT composite material demonstrates superior prediction accuracy, with a maximum error of just 1.61%, making it a better option for high-precision applications due to enhanced mechanical interactions and improved CNT dispersion.

Different regression analytics were used to provide a unique approach to testing the compressive strength (CS) of high-performance concrete (HPC) made with blast furnace slag and fly ash. In this study, it was employed the equilibrium optimizer (EO) and the arithmetic optimization algorithm (AOA) to identify key regression method variables (i.e., Support vector regression (SVR)) which could be adjusted to improve performance. The suggested approaches were created utilizing 1030 tests, eight inputs (aggregates, primary mix designs, admixtures, and curing age), and the CS as the forecasting objective. The results were then compared to those in the corpus of already published scientific literature. Estimation outcomes point to the potential benefit of combining EO-SVR with AOA-SVR analysis. The AOA-SVR displayed significantly better R2 (0.9874 and 0.993) and lower RMSE values as compared to the EO-SVR. Comparing the data demonstrates how much better the created AOA-SVR is than anything that has previously been reported. Overall, the suggested technique for determining the CS of HPC augmented with fly ash and blast furnace slag may be used using the AOA-SVR analysis.