Proposed Prediction Model Research Articles

Fast Magnetic Field Prediction Based on Hybrid Subdomain Method and Multiobjective Optimization Design for Interior Permanent Magnet Synchronous Machines

Benefiting from the prosperity of new energy industry, interior permanent magnet synchronous machines (IPMSM) have ushered in unprecedented development opportunities. To further suppress defects and enhance engineering practicality, fast magnetic field prediction based on hybrid subdomain method and multiobjective optimization design for IPMSM are studied. First, fast no-load magnetic field prediction model based on hybrid subdomain method for IPMSM is innovatively proposed. By combining master/slave subdomain division method and lumped parameter magnetic equivalent circuit, complex rotor structure and saturation effects of magnetic bridges and cores can be comprehensively considered. Prediction model has extremely high calculation accuracy and speed. After that, based on the proposed prediction model, a multiobjective optimization model combining Taguchi method and nondominated sorting genetic algorithm II (NSGA-II) is implemented. Model optimization efficiency has been greatly improved scientifically and effectively. Finally, the efficiency, advancement, innovation, and engineering practicability of studied prediction and optimization models are well verified through a series of finite element analysis (FEA) and prototype experiments. In addition, the generality and universality of this study are verified for other types of IPMSM.

Intelligent Trust Ranking Security Preserving Model for B5G/6G

Trust assessment is a crucial parameter in the next generation WCN (Wireless Communication Network) for the secure collaboration of nodes with each other and the detection of the possible security menaces in the network. The trust ranking of nodes especially in the platforms of defense networks and healthcare networks is of vital importance to the security threats inside the network. In this paper, we have suggested an RM dataset based on the current possible attacks along with advanced authentication attributes for the next generation WCN (B5G/6G). Further, we proposed a trust-ranking model based on the SVM machine learning technique to define the trust ranks of the users present in the network. The model consists of five trust rankings. The fifth trust rank is defined as the highest level of trust and the first trust rank designates the lowest level of trust. The attained rank of trust determines the specific services offered to the corresponding node. The proposed prediction model based on the SVM (Support Vector Machine) algorithm maintains the triple-off balance between the computational time, accuracy, and security. The simulation results indicate that the proposed SVM-based trust ranking model intelligently identifies possible malicious threats and provides an advancement in network security.

Prediction Model of Pigsty Temperature Based on ISSA-LSSVM

The internal temperature of the pigsty has a great impact on the pigs. Keeping the temperature in the pigsty within a certain range is a pressing problem in environmental control. The current pigsty temperature regulation method is based mainly on manual and simple automatic control. There is rarely intelligent control, and such direct methods have problems such as low control accuracy, high energy consumption and untimeliness, which can easily lead to the occurrence of heat stress conditions. Therefore, this paper proposed an improved sparrow search algorithm (ISSA) based on a multi-strategy improvement to optimize the least squares support vector machine (LSSVM) to form a pigsty temperature prediction model. In the optimization process of the sparrow search algorithm (SSA), the initial position of the sparrow population was first generated by using the reverse good point set; secondly, the population number update formula was proposed to automatically adjust the number of discoverers and followers based on the number of iterations to improve the search ability of the algorithm; finally, the adaptive t-distribution was applied to the discoverer position variation to refine the discoverer population and further improve the search ability of the algorithm. Tests were conducted using 23 benchmark functions, and the results showed that ISSA outperformed SSA. By comparing it with the LSSVM models optimized by four standard algorithms, the prediction effect of the ISSA-LSSVM model was tested. In the end, the ISSA-LSSVM temperature prediction model had MSE of 0.0766, MAE of 0.2105, and R2 of 0.9818. The results showed that the proposed prediction model had the best prediction performance and prediction accuracy, and can provide accurate data support for the prediction and control of the internal temperature of the pigsty.

A Deep Learning-Based Multi-objective Optimization Model for PM2.5 Prediction

Air pollution caused by particulate matter with a diameter of less than 2.5 μm (PM2.5) poses a serious threat to human health and the environment. Predicting PM2.5 concentrations and controlling emissions are crucial for pollution prevention and control. This study proposes a comprehensive solution based on weight-sharing deep learning and multi-objective optimization. The proposed approach first utilizes a model that combines the Convolutional Neural Network and Long Short-Term Memory Neural Network to analyze data from 13 air quality monitoring stations in Xi'an City. By simultaneously inputting data from different monitoring stations, the model can extract highly correlated spatiotemporal features, enabling accurate predictions of PM2.5 concentrations for specific monitoring stations using LSTM. In addition, a multi-objective optimization model is established with the primary goal of achieving maximum total emission reduction. This model takes into account four key factors: the total emission reduction, the task of emission reduction, the government subsidy, and the total cost of emission reduction. To obtain the emission reduction of PM2.5 concentration at 13 monitoring stations, 5 classical intelligence algorithms are employed to solve the model. Experimental results demonstrate the effectiveness of the proposed prediction model, with an average Root Mean Square Error (RMSE) of 12.820 and a fitting coefficient (R2) of 0.907, outperforming all comparison models. The proposed model exhibits strong generalization ability, making it applicable to different time and space conditions. Furthermore, it can be adapted for calculating emission reduction of other air pollutants. Lastly, the multi-objective optimization model achieves significant success in terms of total emission reduction. This study provides a new reference in the field of artificial intelligence and its application to air pollution control. The findings hold great significance for promoting public health and environmental protection.

Effects of corrosion morphology on the fatigue life of corroded Q235B and 42CrMo steels: Numerical modelling and proposed design rules

This study presents a detailed numerical analysis to examine the effects of corrosion morphology on the fatigue life of corroded Q235B and 42CrMo steels. To obtain the actual corrosion morphologies, a 3D digital model of Q235B and 42CrMo steels after indoor accelerated corrosion was obtained using the three-dimensional (3D) scanning method. After that, the corrosion morphologies of the test specimens were extracted and then stored in a database for further parametric study, and the specimens with different corrosion morphologies can be obtained by randomly selecting and combining the morphology meshes from the database. Finite element (FE) models were then developed, and validated against the experimental results reported by the authors previously. A parametric study was carried out to investigate the influence of different corrosion morphologies on the fatigue properties of Q235B and 42CrMo steels. Finally, the fatigue life prediction model was proposed in this study, which can establish the relationship between the exposure time and the fatigue life of the corroded steels. The numerical results suggested that the average cross-section area and thickness have a significant effect on the fatigue properties of Q235B and 42CrMo steels. The newly proposed prediction model can provide accurate predictions for predicting the fatigue life of corroded Q235B and 42CrMo steels.

A deep learning approach to predict and optimise energy in fish processing industries

The fish processing sector is experiencing increased pressure to reduce its energy consumption and carbon footprint as a response to (a) an increasingly stringent energy regulatory landscape, (b) rising fuel prices, and (c) the incentives to improve social and environmental performance. In this paper, a standalone forecasting computational platform is developed to optimise energy usage and reduce energy costs. This short-term forecasting model is achieved using an artificial neural network (ANN) to predict power and temperature at thirty-minute intervals in two cold rooms of a fish processing plant. The proposed ANN function is optimised by genetic algorithms (GA) with simulated annealing algorithms (SA) to model the relationships between future temperature and power and the system variables affecting them. To assess the accuracy of the proposed method, extensive experiments were conducted using real-world data sets. The results of the experiments indicate that the proposed ANN model performs with higher accuracy than (a) the long short-term memory (LSTM) as an artificial recurrent neural network (RNN) architecture, (b) peephole-LSTM, and (c) the gated recurrent unit (GRU). This paper finds that using GA & SA algorithms; ANN parameters can be optimised. The RMSE obtained by the ANN compared with the second-ranked method GRU was consequently 16% and 4% less for the predicted temperature and power. The results in one particular site demonstrate energy cost savings in the range of 15%–18% after applying the forecast-optimiser approach. The proposed prediction model is used in a fish processing plant for energy management and is scalable to other sites.

An innovative model fusion algorithm to improve the recall rate of peer-to-peer lending default customers

Peer-to-peer (P2P) lending is a fintech innovation that provides loans to individuals and businesses without the need for additional intermediaries. However, if the borrower fails to repay the loan on time, the bank suffers a financial loss due to the borrower's default. At present, many studies are trying to improve the accuracy of credit default risk prediction models to reduce the risk of financial institutions' loan business, but it is also a meaningful study to focus on improving the recall rate of model prediction results. In the related research field of credit default risk prediction, improving the recall rate is crucial for banks and other lending institutions. The recall rate refers to the proportion of all true positive examples that are correctly identified as positive examples. In credit default risk prediction, true positive cases refer to the cases where borrowers default, while being correctly identified as positive cases means that the model can accurately predict which borrowers may default. If banks' risk prediction models can improve recall rates, this can help them better assess risk, formulate appropriate lending policies, and minimize default losses. This study aims to further improve the recall and AUC metrics (area under the ROC curve) of P2P credit default prediction using the lending dataset from Lending Club using an improved machine learning model fusion algorithm. Our proposed algorithm consists of two machine learning algorithms. The improved LightGBM algorithm and the improved XGBoost algorithm are used for model fusion to obtain the LGB-XGB-Stacking model. By optimizing the evaluation metrics in the training phase of these two algorithms, we have achieved significant improvement in results, especially in the recall rate of defaulted customers and the overall AUC metrics. After comparing the predictive performance of the models, our proposed predictive model is improved in the following aspects. First, the recall of our proposed prediction model is significantly better than other models. Second, it also outperforms other machine learning models on the AUC metric. Among them, the recall rate of the positive sample (default customer) is 24.43% higher than that of the XGBoost model, and the overall AUC index is 6.71% higher. In the end, it was found that XGBoost, LightGBM, and CatBoost models performed very well in terms of accuracy rate improvement. The accuracy rates of these three models are very close, and they are all higher than other models. Therefore, it is found that machine learning models are still an effective method for credit default prediction research, especially tree models. Although the accuracy of our model is slightly lower than the above models, our proposed model outperforms the above models in identifying defaulting customers. Our model can more accurately identify defaulting customers and minimize the risk of bad debts for financial institutions.

A Combined Wind Forecasting Model Based on SSA and WNN: Application on Real Case of Ningbo Zhoushan Port

Wind energy is an effective way to reduce emissions in ports. However, port wind power generation exhibits strong intermittency and randomness. Predicting port wind speed enables timely scheduling of port operations and improves wind energy utilization efficiency. To achieve high accuracy and rapid prediction of port wind speed, this paper proposes a wind speed prediction model based on the Sparrow Search Algorithm (SSA) optimized Wavelet Neural Network (WNN). Firstly, the SSA is used to optimize the Mean Squared Error (MSE) as the fitness function during the training process of the WNN model, obtaining the optimal fitness value corresponding to the network parameters. Then, the obtained parameters are used as the network model parameters of WNN for wind speed prediction. To validate the effectiveness of the proposed method, the model is validated using the measured wind speed data from the Chuanshan Port Area of Ningbo-Zhoushan Port throughout 2022, and its performance is compared with three other models: SSA–BP, SSA–LSTM, and WNN. The results demonstrate that the proposed prediction model exhibits good performance in port wind speed prediction and outperforms the other comparative models in terms of prediction accuracy and convergence speed.

A spatial-temporal feature fusion network for order remaining completion time prediction in discrete manufacturing workshop

The enterprises of the make-to-order production mode are required to make accurate judgments and reasonable decisions when dealing with the disturbance factors in the manufacturing process to ensure the timely completion of orders. Order remaining completion time (ORCT) prediction can quantify the production process and is an important basis to ensure the delivery date of orders. However, an accurate prediction model of the ORCT is challenging because of the spatial and temporal (ST) characteristics of the manufacturing process. An ST features-based prediction method is proposed to solve this problem. Firstly, the ST data sets are established on the basis of analysing ST characteristics of the manufacturing process. Secondly, the spatial feature extraction network and temporal feature extraction network are built to make a more comprehensive analysis. Finally, the prediction model of the ORCT is proposed by fusing the spatial and temporal features and validated in a practical workshop. Experimental results show that considering the spatial and temporal characteristics of the manufacturing process can significantly improve the prediction model’s performance, and the proposed prediction model is superior to graph convolutional neural network, gated recurrent unit network, deep auto-encoder, deep neural network, and back propagation neural network.

Network traffic prediction model based on linear and nonlinear model combination

AbstractWe propose a network traffic prediction model based on linear and nonlinear model combination. Network traffic is modeled by an autoregressive moving average model, and the error between the measured and predicted network traffic values is obtained. Then, an echo state network is used to fit the prediction error with nonlinear components. In addition, an improved slime mold algorithm is proposed for reservoir parameter optimization of the echo state network, further improving the regression performance. The predictions of the linear (autoregressive moving average) and nonlinear (echo state network) models are added to obtain the final prediction. Compared with other prediction models, test results on two network traffic datasets from mobile and fixed networks show that the proposed prediction model has a smaller error and difference measures. In addition, the coefficient of determination and index of agreement is close to 1, indicating a better data fitting performance. Although the proposed prediction model has a slight increase in time complexity for training and prediction compared with some models, it shows practical applicability.

Phase-field fracture coupled elasto-plastic constitutive model for 3D printed thermoplastics and composites

Understanding the mechanical behavior and failure of 3D printed components is vital for their application. Recently, many experimental studies have demonstrated that the fracture in these types of materials depends on the printing parameters. This study aims to develop numerical models for predicting the constitutive behavior and fracture of 3D printed thermoplastics and 3D printed short fiber reinforced composites. A small-strain elasto-plastic anisotropic phase field fracture approach has been proposed for a class of 3D printed thermoplastics; further a finite strain elasto-plastic cohesive zone based phase field model has been proposed to model the fracture in 3D printed short fiber reinforced composites. Experiments are also performed in 3D printed thermoplastic parts to investigate the fracture mechanisms in detail. It is observed that the fracture pattern varies with the printing orientations for the thermoplastics as well as for the composites. Hence the printing orientation influences the peak load and the fracture toughness of the printed parts. The proposed model predictions have been validated against the experimental data for both the 3D printed thermoplastics and composites.

Analysis and Optimization of Tensile Strength for Loess Stabilized by Calcium Carbide Residue

Calcium carbide residue (CCR) can be reutilized to solidify the loess for road construction as a base or subbase due to its rich Ca(OH)2 facilitating pozzolanic reaction with water and soil particles. This study examines the effect of curing time, CCR contents, and dry unit weights on the tensile strength (Rt) of CCR-stabilized loess through the splitting tensile test. Aiming to predict the Rt values, the ratio of porosity (n) controlled by compacted effort and initial volumetric CCR content (Liv), namely n/Liv, was chosen as a prediction parameter and then modified to n/Liv0.064 for compatible variation rate with Rt values. A prediction model for the splitting tensile strength of CCR-treated soil was proposed considering the modified ratio n/Liv0.064 and curing days. The results indicate that Rt values showed a nearly linear positive correlation with CCR contents and dry unit weights, logarithmic increase with the extension of curing time, but no apparent relationship with the ratio n/Liv. The modified ratio n/Liv0.064 can reflect the trend of Rt values at different curing days since the coefficients of determination were almost greater than 0.90 except for the specimens cured for seven days. The proposed prediction model had a good fit for laboratory data with 97% acceptability and close to 3% error. It can be applied for estimating the Rt values of CCR-stabilized loess using curing time and an optimized ratio of porosity and initial volumetric CCR content. From the aspect of practical engineering, the reutilization of CCR can reduce construction costs, waste disposal costs, and environmental pollution.

A decomposition and ensemble model based on GWO and Differential Evolution algorithm for PM2.5 concentration forecasting

Accurate and reliable prediction of PM2.5 concentrations is the basis for appropriate warning measures, and a single prediction model is often ineffective. In this paper, we propose a novel decomposition-and-ensemble model to predict the concentration of PM2.5. The model utilizes Ensemble Empirical Mode Decomposition (EEMD) to decompose PM2.5 series, Support Vector Regression (SVR) to predict each Intrinsic Mode Function (IMF), and a hybrid algorithm based on Differential Evolution (DE) and Grey Wolf Optimizer (GWO) to optimize SVR parameters. The proposed prediction model EEMD-SVR-DEGWO is employed to forecast the concentration of PM2.5 in Guangzhou, Wuhan, and Chongqing of China. Compared with six prediction models, the proposed EEMD-SVR-DEGWO is a reliable predictor and has achieved competitive results.

Reconstruction of Missing Well-Logs Using Facies-Informed Discrete Wavelet Transform and Time Series Regression

Summary Geophysical logging is widely used in lithofacies identification, reservoir parameter prediction, and geological modeling. However, it is common to have well-log sections with low-quality and/or missing segments. Repeating the well-log measurements is not only expensive but might also be impossible depending on the condition of the borehole walls. In these situations, reliable and accurate well-log prediction is, therefore, necessary in different stages of the geomodeling workflow. In this study, we propose a time series regression model to predict missing well-log data, incorporating facies information as an additional geological input and using discrete wavelet transform (DWT) to denoise the input data set. The main contributions of this work are threefold: (i) We jointly use facies information with well logs as the input data set; (ii) we use DWT to denoise the input data and consequently improve the signal-to-noise ratio of the input data; and (iii) we regard the depth domain as the time domain and use a time series regression algorithm for log reconstruction modeling. We show a real application example in two distinct scenarios. In the first, we predict missing well-log intervals. In the second, we predict complete well logs. The experimental results show the ability of the proposed prediction model to recover missing well-log data with high accuracy levels.

Automatic prediction of hepatic arterial infusion chemotherapy response in advanced hepatocellular carcinoma with deep learning radiomic nomogram.

Hepatic arterial infusion chemotherapy (HAIC) using the FOLFOX regimen (oxaliplatin plus fluorouracil and leucovorin) is a promising option for advanced hepatocellular carcinoma (Ad-HCC). As identifying patients with Ad-HCC who would obtain objective response (OR) to HAIC preoperatively remains a challenge, we aimed to develop an automatic and non-invasive model for predicting HAIC response. A total of 458 patients with Ad-HCC who underwent HAIC were retrospectively included from three hospitals (310 for training, 77 for internal validation, and 71 for external validation). The deep learning and radiomic features were extracted from the automatically segmented liver region on contrast-enhanced computed tomography images. Then, a deep learning radiomic nomogram (DLRN) was constructed by integrating deep learning scores, radiomic scores, and significant clinical variables with multivariate logistic regression. Model performance was assessed by AUC and Kaplan-Meier estimator. After automatic segmentation, only a few modifications were needed (less than 30min for 458 patients). The DLRN achieved an AUC of 0.988 in the training cohort, 0.915 in the internal validation cohort, and 0.896 in the external validation cohort, respectively, outperforming other models in HAIC response prediction. Moreover, survival risk stratification was also successfully performed by the DLRN. The overall survival (OS) of the predictive OR group was significantly longer than that of the predictive non-OR group (median OS: 26.0 vs. 12.3months, p < 0.001). The DLRN provided a satisfactory performance for predicting HAIC response, which is essential to identify Ad-HCC patients for HAIC and may potentially benefit personalized pre-treatment decision-making. This study presents an accurate and automatic method for predicting response to hepatic arterial infusion chemotherapy in patients with advanced hepatocellular carcinoma, and therefore help in defining the best candidates for this treatment. • Deep learning radiomic nomogram (DLRN) based on automatic segmentation of CECT can accurately predict hepatic arterial infusion chemotherapy (HAIC) response of advanced HCC patients. • The proposed prediction model can perform survival risk stratification and is an easy-to-use tool for personalized pre-treatment decision-making for advanced HCC patients.

Prediction of Contact Angle for Oriented Hydrophobic Surface and Experimental Verification by Micro-Milling

The rectangular microgroove surfaces have obvious anisotropy, which can control the movement of water droplets in parallel and vertical directions. Based on such a property, anisotropic functional surfaces are expected to have potential applications in the fields of droplet-oriented delivery and microfluidics. Micro-milling can accurately adjust the dimension of microstructures, which is convenient to explore the optimal micro-structural parameters. In this study, the non-composite and composite state prediction models of contact angle on the oriented hydrophobic surface were established based on minimum Gibbs free energy, and the effect of micro-structural dimension parameters on contact angle was investigated. Then, the rectangular microgroove structure on 316 L stainless steel was prepared using micro-milling. The composite state prediction model of contact angle was found to be more consistent with the actual situation, and reducing the width of the convex platform was beneficial to increasing the contact angle. In particular, the contact angle in the parallel direction reached 146.5° when the width of the convex platform was 60 μm, and the accuracy of the prediction model was 98.4%. The proposed prediction models of contact angle provide a theoretical basis for designing and preparing oriented hydrophobic surfaces.

Contrastive Learning for Preoperative Early Recurrence Prediction of Hepatocellular Carcinoma with Liver CT Image and Tumor Mask.

High early recurrence (ER) rate is the main factor leading to the poor outcome of patients with hepatocellular carcinoma (HCC). Accurate preoperative prediction of ER is thus highly desired for HCC treatment. Many radiomics solutions have been proposed for the preoperative prediction of HCC using CT images based on machine learning and deep learning methods. Nevertheless, most current radiomics approaches extract features only from segmented tumor regions that neglect the liver tissue information which is useful for HCC prognosis. In this work, we propose a deep prediction network based on CT images of full liver combined with tumor mask that provides tumor location information for better feature extraction to predict the ER of HCC. While, due to the complex imaging characteristics of HCC, the image-based ER prediction methods suffer from limited capability. Therefore, on the one hand, we propose to employ supervised contrastive loss to jointly train the deep prediction model with cross-entropy loss to alleviate the problem of intra-class variation and inter-class similarity of HCC. On the other hand, we incorporate the clinical data to further improve the prediction ability of the model. Experiments are extensively conducted to verify the effectiveness of our proposed deep prediction model and the contribution of liver tissue for prognosis assessment of HCC.

Vibration Prediction and Evaluation System of the Pumping Station Based on ARIMA–ANFIS–WOA Hybrid Model and D-S Evidence Theory

Research on the vibration response prediction and safety early warning is of great significance to the operation and management of pumping station engineering. In the current research, a hybrid prediction method was proposed to predict vibration responses of the pumping station based on a single model of autoregressive integrated moving average (ARIMA), a combined model of the adaptive network-based fuzzy inference system (ANFIS) and whale optimization algorithm (WOA). The performance of the developed models was studied based on the effective stress vibration data of the blades in a shaft tubular pumping station. Then, the D-S evidence theory was adopted to perform safety early warning of the operation state by integrating the displacement, velocity, acceleration and stress indicators of the vibration responses of the pumping station. The research results show that the proposed prediction model ARIMA–ANFIS–WOA exhibited better accuracy in obtaining both linear and nonlinear characteristics of vibration data than the single prediction model and hybrid model with different optimization algorithms. The D-S evidence fusion results quantitatively demonstrate the safe operation state of the pumping station. This research could provide a scientific basis for the real-time analysis and processing of data in pumping station operation and maintenance systems.

An approach towards building robust neural networks models using multilayer perceptron through experimentation on different photovoltaic thermal systems

The study is aimed at training an artificial neural network to determine the specific Photo voltaic thermal (PV/T) system that will function optimally in a specific environmental situation by optimizing the input parameters. In this regard, four different PV/T systems based on the arrangement of the tubes and the presence of the copper absorber sheet, namely, vertically oscillating tube, vertically oscillating sheet tube, rectangular spiral tube and horizontally oscillating tube PV/T’s were considered. In the experimental study, wind velocity, solar irradiation, ambient temperature, relative humidity, and inlet temperature to the PV/T are considered the influencing factors. The response factors for evaluating the performance of the PV/T system were temperature outlet and power output. Water was used as the working fluid for the thermal management of the systems for all four test cases. The investigation discloses that the rectangular spiral tube photovoltaic thermal system is the best among the studied systems as it maintains both average thermal efficiency and average electrical efficiency at 50.7% and 12.15%, respectively, considering the trade-off between electrical and thermal efficiency. The ideal design can then be selected for a specific area that will be more appropriate with its environmental fluctuations by approximating the production for each scenario. The artificial neural network was designed to be capable of being successfully trained for this application based on Artificial Neural Network (ANN), Multilayer Perceptron using Levenberg Marquardt learning algorithm through MATLAB software based on the experimental data. The ANN model for the rectangular spiral tube PV/T system achieved an exceptional overall R-value of 0.99843 among the proposed prediction models. For the artificial neural network model formulated for vertically oscillating tube, vertically oscillating sheet tube and horizontally oscillating tube PV/T system, the R-value was found to be 0.99807, 0.9943, and 0.99593, respectively. In the training phase, the MSE for vertically oscillating tube, vertically oscillating sheet tube, rectangular spiral tube and horizontally oscillating tube PV/T’s using the multilayer perceptron artificial neural network models were found to be 1.1328, 3.5082, 0.3134 and 1.1328, respectively. For the same PV/T’s models, the MSE values for Cross validation phase were found to be 1.8497, 3.9072, 5.1419, and 4.6402, respectively. Finally, the suggested linear prediction models assist in quickly and easily determining the ideal conditions for every solar system while lowering the error in furcating future results.

Ensemble learning-based applied research on heavy metals prediction in a soil-rice system

Accurate prediction of heavy metal accumulation in soil ecosystems is crucial for maintaining healthy soil environments and ensuring high-quality agricultural products, as well as a challenging scientific task. In this study, we constructed a dataset containing 490 sets of multidimensional environmental covariate data and proposed prediction models for heavy metal concentrations (HMC) in a soil–rice system, EL-HMC (including RF-HMC and GBM-HMC), based on Random Forest (RF) and Gradient Boosting Machine (GBM) ensemble learning (EL) techniques. To reasonably evaluate the effectiveness of each model, Multiple linear and Bayesian regressions were selected as benchmark models (BM), and mean absolute error (MAE), root mean square error (RMSE), and determination coefficient R2 were selected as evaluation indicators. In addition, sensitivity and spatial autocorrelation (SAC) analyses were used to examine the robustness of the model. The results showed that the R2 values of RF-HMC and GBM-HMC for modeling available cadmium (Cd) concentrations in soil were 0.654 and 0.690, respectively, with an average increase of 48.0 % compared to the BMs. The R2 values of RF-HMC and GBM-HMC for predicting Cd, lead (Pb), chromium (Cr), and mercury (Hg) concentrations in rice ranged from 0.618 to 0.824 and 0.645 to 0.850, respectively, with an average increase of 58.2 % compared with the BMs. The corresponding MAEs and RMSEs of RF-HMC and GBM-HMC had low error levels. Sensitivity analysis of the input features and the SAC of the prediction bias showed that the EL-HMC models have excellent robustness. Therefore, the EL technology-based prediction models for HMCs proposed herein are practical and feasible, demonstrating better accuracy and stability than the traditional model. This study verifies the application potential of EL technology in pollution ecology and provides a new perspective and solution for sustainable management and precise prevention of heavy metal pollution in farmland soil at the regional scale.