MAE Values Research Articles

A panorama-based technique to estimate sky view factor and solar irradiance considering transmittance of tree canopies

Street-view-based techniques for assessing the sky view factor (SVF) and solar irradiance under trees are gaining attention as tools for evaluating trees as nature-based solutions to mitigate urban heat risks. Although these metrics significantly depend on the morphology of trees and resulting canopy transmittance, an existing approach, termed the Solid Canopy Method (SCM), assumes zero transmission and has not accounted for these variations. This paper advances the computation of both metrics, improving their accuracy and application — we developed the Transmissive Canopy Method (TCM), a panorama-based approach that integrates semantic segmentation and binarization to evaluate SVF and solar irradiance while accounting for transmittance of tree canopies. Using a study area on a university campus in Singapore, we collected data on solar irradiance and 360°imagery to validate our method. The results indicated improved accuracy with MAE, RMSE, and R2 values of 77.8 Wm−2, 105.0 Wm−2 and 0.90, respectively — significantly outperforming the SCM. We showcased two use cases of our method: (1) high-resolution mapping of SVF and solar irradiance in a field with trees, and (2) walking route optimization considering sunlight exposure. Our findings highlight the strong capability of our TCM to evaluate the effects of trees in mitigating urban heat more accurately than the existing method. Additionally, the TCM has potential applications in urban planning and management, enabling strategic tree planting prioritizing areas lacking sufficient shading and developing tools for optimizing walking routes to minimize sunlight exposure.

Tide level prediction during typhoons based on variable topology in graph convolution recurrent neural networks

Accurate tide level prediction is crucial for storm surge prevention and mitigation. In this study, we propose a regional multi-station tide-level prediction model (RMSTL) based on a graph convolution recurrent network that utilizes spatial and temporal information from historical tide levels and meteorological data to predict tide levels at multiple stations. Six stations in Changjiang Estuary, China, were selected for this case study. We explored the change in the accuracy of forecasting the tide-level during typhoons under a distinct topology of the tidal station network and the weights of the stations. The results showed that: (1) the prediction accuracy of RMSTL model behaved better than that of the other three widely used models; (2) the RMSTL model can be made more accurate by adding the weights of the edges or the number of edges of the topology; the value of RMSE decreased from 0.369 to 0.278, and the value of MAE decreased from 0.260 to 0.189; (3) when the dataset was limited, increasing the weights of the edges had a slightly better effect than increasing the weights of the edges in terms of improving the accuracy of the prediction results. The proposed method opens new avenues for forecasting storm surges.

Forecasting of meteorological drought using ensemble and machine learning models

This study highlights drought forecasting for understanding the semi-arid area in India, where drought phenomena play vital role in the irrigation, drinking water supplies, and sustaining the ecological with economic balance for every nation. Therefore, drought forecasting is important for the future drought planning based on the machine learning (ML) models. Hence, The Standardized Precipitation Index (SPI) at 3- and 6-month periods have been selected and used for future drought forecasting scenarios in area. The combinations of ten inputs SPI-1- and SPI-10 were used for predicting modeling for SPI-3 and SPI-6 timescales, that modeling developed based on the historical SPI datasets from 1989 to 2019 years. The SPI-3 and SPI-6 maximum and minimum values are shown SPI-3 (2.03 and -5.522) and SPI-6 (1.94 and -6.93). The SPI is a popular method for estimating the drought analysis and has been used everywhere at global level. The developed models have been compared with each other, with the best combination of input variables selected using subset regression models and sensitivity studies. After that, the active input parameters were used for forecasting of SPI-3 and SPI-6 values to understanding of drought in semi-arid area. The finest input variables combination have been used in the Ml models and established the novel five models such as robust linear regression, bagged trees, boosted trees, support vector regression (SVM-Linear), and Matern Gaussian Process Regression (Matern GPR) models. Such kind of models first time has been applied for the forecasting of future drought conditions. Whole models were fine and improved modeling by using hyperparameters tuning, bagging, and boosting models. Entire ML models’ accuracy was compared using different statistical metrics. Compared with five ML models accuracy, we have found that the Matern GPR model better accuracy than other ML models. The best model accuracy is R2 = 0.95 and 0.93, RMSE, MSE, MAE, MARE, and NSE values, respectively, for predicting SPI-3 and SPI-6 values in the area. Therefore, the Matern GPR model was identified as the finest ML algorithm for predicting SPI-3 and SPI-6 associated with other algorithms. This research demonstrates the Matern GPR model's efficacy in predicting multiscale SPI-3 and SPI-6 under climate variations. It can be helpful in soil and water resource conservation planning and management and understanding droughts in the entire basin areas of the country India.

Enhancing stock market Forecasting: A hybrid model for accurate prediction of S&P 500 and CSI 300 future prices

This paper investigates the challenging domain of stock market prediction, a significant aspect of financial markets. It focuses on developing predictive models to forecast stock prices accurately, vital for mitigating losses and maximizing gains amidst the inherent unpredictability and volatility of the market. The study comprehensively analyzes various predictive models, including time series analysis and advanced machine learning techniques. It highlights the superiority of ensemble or hybrid models in enhancing prediction reliability. Central to this research is the development of a model incorporating detailed data collection, thorough analysis, and state-of-the-art machine learning methods, achieving notable predictive accuracy. This approach underscores the benefits of data-centric strategies in today’s rapidly evolving business environment and the widespread applicability of predictive analytics. The model outperforms conventional methods by decomposing time series into simpler components and optimizing hyperparameters, thereby enhancing prediction accuracy, as demonstrated by performance testing on the S&P 500 and CSI 300 indices. The RMSE, MAE, and R2 values of the MEME-AO-LSTM model are 27.12, 19.43, and 0.992, respectively, which serve as evidence of this. The model’s generalizability and high performance are demonstrated by its efficacy in a variety of major markets, including the NASDAQ 100, Nikkei 225, FTSE, DAX, SSE, and KOSPI. Additionally, the model’s adaptability under diverse market conditions is demonstrated through its evaluation of its robustness in response to significant events, such as the economic stimulus responses to the COVID-19 pandemic and the geopolitical tensions resulting from the tension and conflict between Russia and Ukraine. Consequently, the proposed methodology has the potential to help investors achieve substantial and advantageous returns.

Research on multi-parameter precise prediction of borehole gas extraction under negative pressure drive

Accurate prediction of multi-parameter gas extraction in mines is vital for intelligent gas extraction regulation. This study establishes a linear and nonlinear multi-parameter prediction model to address excessive prediction residuals resulting from parameter interactions. Initially, a combined linear-nonlinear model is constructed using ARIMA and RBFNN. Real-time multi-parameter data under varying negative pressures is collected via a custom experimental platform. After preprocessing and inspection, the linear models is obtained: ARIMA (0,1,1) for gas concentration, ARIMA (0,1,1) for flow rate, ARIMA (2,1,2) for air leakage volume. Finally, the prediction residuals were optimised using RBFNN to obtain the combined model predictions. Results demonstrate closer proximity of combined model predictions to actual values, with gas extraction multi-parameter R2 surpassing 0.7. Additionally, negligible values of MAE、MSE and MAPE attest to the model’s robust performance, laying theoretical groundwork for dynamic gas extraction regulation and control.

Enhancing Stock Price Prediction in the Indonesian Market: a Concave LSTM Approach with RunReLU

This study addresses the pressing need for improved stock price prediction models in the financial markets, focusing on the Indonesian stock market. It introduces an innovative approach that utilizes the custom activation function RunReLU within a Concave Long Short Term Memory (LSTM) framework. The primary objective is to enhance prediction accuracy, ultimately assisting investors and market participants in making more informed decisions. The research methodology used historical stock price data from ten prominent companies listed on the Indonesia Stock Exchange, covering the period from July 6, 2015, to October 14, 2021. Evaluation metrics such as RMSE, MAE, MAPE, and R2 were employed to assess model performance. The results consistently favored the RunReLU-based model over the ReLU-based model, showcasing lower RMSE and MAE values, higher R2 values, and notably reduced MAPE values. These findings underscore the practical applicability of custom activation functions for financial time series data, providing valuable tools for enhancing prediction precision in the dynamic landscape of the Indonesian stock market.

Investigating the influencing parameters with automated scour severity detection using Bayesian neural networks

ABSTRACT This research proposes a novel approach leveraging deep learning techniques to enhance scour severity prediction that aims to analyse various parameters’ effects on scour severity and scour patterns around piers under different bed conditions. The methodology involves integrating deep learning techniques, including Linear Discriminant Analysis-t-Distributed Stochastic Neighbour Embedding (LDA-t-SNE) and Bayesian Neural Networks (BNNs), to extract features, reduce dimensionality, and improve detection accuracy. This study conducted correlation analysis to understand the relationships between parameters such as drainage area, stream slope, pier characteristics, flow dynamics, and sediment properties and their influence on scour severity. Additionally, sensitivity analysis was performed to assess the impact of different pier shapes and bed conditions on scour severity. Our results demonstrate the effectiveness of the proposed approach, with metrics such as RMSE (%) values of 0.025 and MAE (%) values of 0.011 and 0.01, respectively, outperforming traditional scour detection methods, achieving an accuracy of 98% consistently affirming the superior accuracy and reliability of the model. This research provides valuable insights into proactive scour management and infrastructure resilience, offering practical solutions for safeguarding hydraulic structures against scour-induced risks in civil engineering applications.

Machine learning-based q-RASAR predictions of the bioconcentration factor of organic molecules estimated following the organisation for economic co-operation and development guideline 305

In this study, we utilized an innovative quantitative read-across (RA) structure-activity relationship (q-RASAR) approach to predict the bioconcentration factor (BCF) values of a diverse range of organic compounds, based on a dataset of 575 compounds tested using Organisation for Economic Co-operation and Development Test Guideline 305 for bioaccumulation in fish. Initially, we constructed the q-RASAR model using the partial least squares regression method, yielding promising statistical results for the training set (R2 =0.71, Q2LOO=0.68, mean absolute error [MAE]training=0.54). The model was further validated using the test set (Q2F1=0.77, Q2F2=0.75, MAEtest=0.51). Subsequently, we explored the q-RASAR method using other regression-based supervised machine-learning algorithms, demonstrating favourable results for the training and test sets. All models exhibited R2 and Q2F1 values exceeding 0.7, Q2LOO values greater than 0.6, and low MAE values, indicating high model quality and predictive capability for new, unidentified chemical substances. These findings represent the significance of the RASAR method in enhancing predictivity for new unknown chemicals due to the incorporation of similarity functions in the RASAR descriptors, independent of a specific algorithm.

Utilizing TGAN and ConSinGAN for Improved Tool Wear Prediction: A Comparative Study with ED-LSTM, GRU, and CNN Models

Developing precise deep learning (DL) models for predicting tool wear is challenging, particularly due to the scarcity of experimental data. To address this issue, this paper introduces an innovative approach that leverages the capabilities of tabular generative adversarial networks (TGAN) and conditional single image GAN (ConSinGAN). These models are employed to generate synthetic data, thereby enriching the dataset and enhancing the robustness of the predictive models. The efficacy of this methodology was rigorously evaluated using publicly available milling datasets. The pre-processing of acoustic emission data involved the application of the Walsh-Hadamard transform, followed by the generation of spectrograms. These spectrograms were then used to extract statistical attributes, forming a comprehensive feature vector for model input. Three DL models—encoder-decoder long short-term memory (ED-LSTM), gated recurrent unit (GRU), and convolutional neural network (CNN)—were applied to assess their tool wear prediction capabilities. The application of 10-fold cross-validation across these models yielded exceptionally low RMSE and MAE values of 0.02 and 0.16, respectively, underscoring the effectiveness of this approach. The results not only highlight the potential of TGAN and ConSinGAN in mitigating data scarcity but also demonstrate significant improvements in the accuracy of tool wear predictions, paving the way for more reliable and precise predictive maintenance in manufacturing processes.

Scientific preparation for JRT: Wind pressure prediction model for large radio telescope based on real data from multi-sensors

Jingdong 120-meter radio telescope (JRT) is poised to become the world's largest single-aperture fully steerable medium-low frequency radio telescope. However, like other large-aperture radio telescopes, the JRT is vulnerable to wind loads, which can cause structural deformation and pointing errors. Addressing this challenge requires the ability to predict dynamic winds in real-time. This study developed a wind pressure preprocessing and prediction model using sensor data collected from the Kunming 40-meter radio telescope (KRT), enabling real-time prediction of wind pressure on the telescope. The model employs adaptive noise and Variational Mode Decomposition (VMD) techniques to eliminate random noise from the original wind pressure data. Subsequently, wind pressure predictions are made using a Bidirectional Long Short-term Memory (BiLSTM) model. By conducting predictions under various stabilization conditions and conducting a thorough analysis of measurement data from five sensors, the study has achieved impressive results in predicting wind pressure on the KRT reflector surface. The proposed model demonstrates the lowest MAE, RMSE, and MAPE, while achieving the highest R2 across various data sets. Where the average R2 of the proposed model is 0.9392 at 45° pitch angle attitude and the RMSE, MAE and MAPE values are 1.4923, 1.2377 and 1.82% respectively. This model helps wind load monitoring of real-time wind pressure monitoring of the telescope surface, to study the effects of wind load on pointing accuracy. By adjusting the control parameters to reduce wind load interference, to ensure the high-precision work of a large radio telescope, such as JRT.

Wind power prediction method based on Attention-LSTM

Abstract Under the background of realizing the goal of “double carbon”, precise short-term wind power prediction can offer a scientific foundation for the effective integration of wind energy into the grid and the secure and steady functioning of the electricity system. However, the unpredictability of weather conditions causes wind power to be volatile, which makes prediction more difficult. Aiming at this problem, a short-term wind power prediction technique that combines LSTM neural network and attention is suggested, which can make the predictive model more effective in processing the inputs of relevant influencing factors. The outcomes demonstrate the higher accuracy of the Attention-LSTM prediction method., with the mean value of RSME of 6.12, the mean value of MAE of 4.51, and the mean value of MAPE of 18%, when the prediction model is trained with real data.

Machine-Learning-Based Path Loss Prediction for Vehicle-to-Vehicle Communication in Highway Environments

Vehicle-to-vehicle (V2V) communication, which plays an important role in intelligent transportation systems, has been statistically proven to improve traffic efficiency and reduce the probability of accidents. In real-world applications, it is critical to accurately estimate the path loss parameter in communication channels due to the variable and complex propagation environments often encountered in inter-vehicle communication scenarios. This paper presents a study on various machine learning methods to improve path loss estimation in V2V communication using a dataset (192,000 observations) obtained from field measurements of highway environments in the Trabzon and Gümüşhane provinces in Türkiye. For this purpose, path loss estimation was carried out with different machine learning algorithms such as Artificial Neural Networks, Random Forest, Linear Regression, Gradient Boosting, Support Vector Regression, and AdaBoost by using various environmental and system features. Then, performance comparisons were conducted between machine learning methods and traditional empirical approaches such as log-distance, two-ray, and log-ray. Examining the outputs reveals that machine learning methods outperform traditional methods and yield results quickly. As a result, the Random Forest and Gradient Boosting methods demonstrated the highest prediction performances, with R2 values of 0.97 and 0.96, MAE values of 0.0557 and 0.0701, and RMSE values of 0.0774 and 0.0964, respectively, outperforming both empirical methods, other machine learning techniques, and the existing studies based on V2V. Overall, our study provides significant contributions to the existing literature by providing a comprehensive parameter set for highway environments, examining the path loss prediction performance of machine learning models with different capabilities, and comparing them with traditional methods. This study not only fills a critical gap in the existing literature but also highlights the necessity, efficiency, and originality of machine learning approaches for improving reliable V2V communication systems.

GREEN BOND INDEX PRICE FORECASTING: COMPARATIVE ANALYSIS OF MACHINE LEARNING MODELS

Today, green financial products have garnered recognition and are consequently regarded as alternative assets. Green bonds exclusively allocate their funds to environmentally sustainable initiatives. Green bonds facilitate companies in enhancing both their financial and environmental performance by promoting innovations stemming from green initiatives and long-term green investments. This study focused on predicting the price of the green bond index in Japan. The input factors for price prediction in Japan include Nikkei225, USD/JPY, and crude oil price assets, which are seen as alternative investment options for Japanese investors. The study utilized a dataset spanning 693 days, from 06.05.2021 to 02.05.2024. The acquired data is partitioned into two distinct sets: one for training and one for testing. 80% of the data was allocated for training purposes, while the remaining 20% was designated for testing. The study utilized various prediction approaches including RF, MLP, GBR, XGBoost, LSTM, SVR, Catboost, and Linear Regression. The performance of these models was compared using evaluation metrics such as MSE, RMSE, MAE, MAPE, and R2 values. The research revealed that the GBR model exhibited the highest performance on the training data set, whereas the XGBoost and RF models yielded superior prediction results on the test data set.

Uncertainty analysis of photovoltaic power generation system and intelligent coupling prediction

Accurate prediction of photovoltaic power generation is essential to promoting the active consumption and low-carbon protection. The complex uncertainty of the photovoltaic system itself leads to the deviation in the photovoltaic power prediction. Therefore, we propose a new prediction model for coupled intelligence optimization. First, the photovoltaic power is decomposed into effective mode components using VMD optimized by GWO. Statistical techniques were used to analyze multidimensional uncertainty and extract features, then, optimize the performance of the coupled model. Second, the Zebra optimization (ZOA) establishes an appropriate balance between exploration and utilization to achieve the optimization of the model parameters. In addition, the CNN is used to extract complex features and enhance the correlation between input values and output values. Finally, the power was predicted using the BiLSTM. The results show that applying the statistical technique to the coupled prediction model not only reveals the uncertainty of photovoltaic systems but reduces the prediction error. Among them, the R2 increased by 0.42 %, the values of MAPE, MSE, RMSE, and MAE were reduced to different degrees. It can better optimize the allocation and reasonable consumption of renewable energy, which provides the decision basis for the adjustment of renewable energy structure.

Spatial attention guided cGAN for improved salient object detection

Recent research shows that Conditional Generative Adversarial Networks (cGANs) are effective for Salient Object Detection (SOD), a challenging computer vision task that mimics the way human vision focuses on important parts of an image. However, implementing cGANs for this task has presented several complexities, including instability during training with skip connections, weak generators, and difficulty in capturing context information for challenging images. These challenges are particularly evident when dealing with input images containing small salient objects against complex backgrounds, underscoring the need for careful design and tuning of cGANs to ensure accurate segmentation and detection of salient objects. To address these issues, we propose an innovative method for SOD using a cGAN framework. Our method utilizes encoder-decoder framework as the generator component for cGAN, enhancing the feature extraction process and facilitating accurate segmentation of the salient objects. We incorporate Wasserstein-1 distance within the cGAN training process to improve the accuracy of finding the salient objects and stabilize the training process. Additionally, our enhanced model efficiently captures intricate saliency cues by leveraging the spatial attention gate with global average pooling and regularization. The introduction of global average pooling layers in the encoder and decoder paths enhances the network's global perception and fine-grained detail capture, while the channel attention mechanism, facilitated by dense layers, dynamically modulates feature maps to amplify saliency cues. The generated saliency maps are evaluated by the discriminator for authenticity and gives feedback to enhance the generator's ability to generate high-resolution saliency maps. By iteratively training the discriminator and generator networks, the model achieves improved results in finding the salient object. We trained and validated our model using large-scale benchmark datasets commonly used for salient object detection, namely DUTS, ECSSD, and DUT-OMRON. Our approach was evaluated using standard performance metrics on these datasets. Precision, recall, MAE and Fβ score metrics are used to evaluate performance. Our method achieved the lowest MAE values: 0.0292 on the ECSSD dataset, 0.033 on the DUTS-TE dataset, and 0.0439 on the challenging and complex DUT-OMRON dataset, compared to other state-of-the-art methods. Our proposed method demonstrates significant improvements in salient object detection, highlighting its potential benefits for real-life applications.

Segmentation and Estimation of Fetal Biometric Parameters using an Attention Gate Double U-Net with Guided Decoder Architecture

The fetus's health is evaluated with the biometric parameters obtained from the low-resolution ultrasound images. The accuracy of biometric parameters in existing protocols typically depends on conventional image processing approaches and hence, is prone to error. This study introduces the Attention Gate Double U-Net with Guided Decoder (ADU-GD) model specifically crafted for fetal biometric parameter prediction. The attention network and guided decoder are specifically designed to dynamically merge local features with their global dependencies, enhancing the precision of parameter estimation. The ADU-GD displays superior performance with Mean Absolute Error of 0.99 mm and segmentation accuracy of 99.1 % when benchmarked against the well-established models. The proposed model consistently achieved a high Dice index score of about 99.1 ± 0.8, with a minimal Hausdorff distance of about 1.01 ± 1.07 and a low Average Symmetric Surface Distance of about 0.25 ± 0.21, demonstrating the model's excellence. In a comprehensive evaluation, ADU-GD emerged as a frontrunner, outperforming existing deep-learning models such as Double U-Net, DeepLabv3, FCN-32s, PSPNet, SegNet, Trans U-Net, Swin U-Net, Mask-R2CNN, and RDHCformer models in terms of Mean Absolute Error for crucial fetal dimensions, including Head Circumference, Abdomen Circumference, Femur Length, and BiParietal Diameter. It achieved superior accuracy with MAE values of 2.2 mm, 2.6 mm, 0.6 mm, and 1.2 mm, respectively.

Enhancing smart grid load forecasting: An attention-based deep learning model integrated with federated learning and XAI for security and interpretability

Smart grid is a transformative advancement that modernized the traditional power system for effective electricity management, and involves optimized energy distribution by load forecasting. Precise load forecasting provides the best utilization of energy resources and increases sustainability. Dynamic changes of several connected factors, such as temporal and geographical variability, pose challenges to accurate load prediction. Integrating Artificial Intelligence (AI) in the smart grid can enhance the performance of the forecasting process by capturing these changes. This study investigated load forecasting tasks on four different datasets. Several preprocessing and augmentation techniques are applied to increase the data quality. An attention-based 1D-CNN-GRU model is proposed to capture the temporal patterns from the time-series data, and the hyperparameters of the model are optimized using a particle swarm optimization (PSO) algorithm that also accelerates the convergence and results in an efficient training session. Empirical evaluations highlight that the proposed model substantially minimizes the loss, reflecting the ability to make accurate predictions. It obtains MAE values of 0.12, 0.8, 16.48, and 82.64 for the four datasets. Moreover, the explainable AI (XAI) technique is applied using Shapley Additive explanations (SHAP) to interpret the model prediction, providing the feature ranking based on their prediction score. Moreover, this study utilizes federated learning, enables collaborative training, maintains the privacy of the grid data, and secures the process comprehensively. The aggregation mechanism in federated learning is modified using pruning-based methods that reduce the parameters and computational cost, resulting in a more efficient framework. Integrating all these approaches provides valuable insights for developing a load forecasting model and outlines potential contributions in the smart grid domain.

Prediction of runoff characteristics in permeable pavements using experimental data and intelligent models.

Considering the growing use of permeable pavements, the prediction of runoff passing through this pavement model is of considerable importance. The prediction of rainfall-runoff relationships can be a challenge because of several factors including data uncertainty, non-linear relationships, and high temporal and spatial variability. To deal with these challenges, intelligent algorithms are often used to predict such complex phenomena. In this research, runoff control parameters were investigated in two types of permeable pavements (permeable interlocking concrete pavement (PICP) and high strength clogging resistant permeable pavement (CRP)) using support vector machine (SVM), support vector machine-bat (SVM-BA) and support vector machine-grasshopper (SVM-GOA). Variables used in the models included percentage of coverage by permeable pavement (A), rainfall intensity (I), slope (S), and pavement type coefficient (K) as input data, and runoff coefficient (C), time to runoff (Tr), and peak discharge (Qp) as output data. In this research, from the total of 108 data extracted from the experimental results, 86 data were used in the training period, and 22 data were used in the test period. The results of the test period show that the SVM-BA model has the best performance with values of MAE = 0.010 in predicting C, MAE = 1.330 min in predicting Tr, and MAE = 0.029 lit/min in predicting Qp. The SVM-GOA model is ranked second with values of MAE = 0.051 in predicting C, MAE = 3.285 min in predicting Tr, and MAE = 0.097 lit/min in predicting Qp. Also, the SVM model is ranked third with values of MAE = 0.063 in predicting C, MAE = 4.470 min in predicting Tr, and MAE = 0.121 lit/min in predicting Qp. In summary, the SVM-BA algorithm showed the best performance and the SVM algorithm showed the weakest performance in predicting runoff characteristics in permeable pavements.

Efficient predictive modeling of resilient modulus in stabilized clayey soil using automated machine learning

Pavement subgrade design relies on the resilient modulus (Mr) to analyze structural response to vehicle-like loading. Adding stabilizers to the soil subgrade makes estimating Mr difficult and resource-intensive. This study uses an automated machine learning (ML) strategy to predict the Mr of stabilized clayey soil using recycled plastic waste. The proposed method automates model selection and hyperparameter tuning, making it a feasible alternative to tedious ML modeling and costly laboratory testing. From extensive laboratory investigation involving 3285 experimental data points, the automated ML model using Bayesian optimization evaluates ensembles, support vector machine (SVM), neural network (NET), decision trees, (TREE), and Gaussian process (GP) regression models, identifying the best model based on cross-validation mean squared error (MSE). Bayesian optimization explores hyperparameter spaces to find optimal configurations, enhancing the accuracy, scalability, and reliability of the prediction model. The optimization process yielded the best results for the ensemble least square boost (LSBoost) model with a cross-validation mean squared error (MSE) value of 6.723×10−29. The optimized ML model’s performance is measured using R2 and adjusted R2. The LSboost model’s R2 and adjusted R2 values of 0.9999 suggested overfitting, prompting further investigations using performance metrics like root mean squared error (RMSE), mean absolute error (MSE), and probability density function (PDF) for normalized absolute error (NAE) for training and testing datasets for the predictive ML model. The small RMSE and MAE (0.0049 and 0.0005) values and symmetrical NAE distribution of the proposed ML model demonstrate its high accuracy and generalization capabilities. The proposed model was subsequently tested on the new, unseen data and achieved predictions with an error rate of 0.24 %. This confirms the proposed ML model’s superiority over conventional deformation models, making it ideal for reliable geotechnical engineering applications.

State of Health Estimation of Lithium-Ion Battery for Electric Vehicle Based on VMD-DBO-SVR Model

State-of-health (SOH) of lithium-ion batteries is an important indicator for measuring performance and remaining life. We propose an innovative prediction model that integrates variational mode decomposition (VMD), Dung Beetle optimizer (DBO), and support vector regression (SVR) algorithms. We extracted relevant features from the discharge characteristic curve and incremental capacity curve. We used Pearson and Spearman correlation coefficient methods for correlation analysis on the extracted health factors (HFs), selecting those that significantly impact SOH as input features. A DBO-SVR model was constructed to establish a nonlinear correlation between HFs and SOH, and the DBO algorithm was used to globally search and optimize the hyperparameters of the SVR model to improve its prediction accuracy. To reduce the impact of noise in battery signals on model performance, VMD technology was introduced to decompose battery signals into multiple intrinsic mode components, to extract useful features and remove noise to further improve prediction accuracy. The proposed method was validated using the NASA battery dataset and compared with other algorithm models. Results showed that the prediction model was significantly better than other models, with a maximum RMSE value of 0.84%, a maximum MAE value of 0.71%, and a stable prediction error value within 1%.