Predictive Capability Of Model Research Articles

MGT: Machine Learning Accelerates Performance Prediction of Alloy Catalytic Materials.

The application of deep learning technology in the field of materials science provides a new method for predicting the adsorption energy of high-performance alloy catalysts in hydrogen evolution reactions and material discovery. The activity and selectivity of catalytic materials are mainly influenced by the properties and positions of active sites and adsorption sites. However, current deep learning models have not sufficiently focused on the importance of active atoms and adsorbates, instead placing more emphasis on the overall structure of the catalytic materials. In this paper, the overall molecular graph and a masked graph, which ignores fixed atoms, are separately input into the Masked Graph Transformer (MGT) network to enhance the model's ability to recognize key sites in catalytic reactions. Second, we introduce a nonlinear message-passing mechanism to improve the dot-product attention in the Transformer and capture the directional information on the relative positions of nodes by integrating molecular geometric information through deep tensor products. Subsequently, we constructed the NLMP-TransNet framework, which combines MPNN and Transformer and optimizes the model's learning and prediction capabilities through weight sharing and residual connections. The MGT achieves an error rate of 0.5447 eV on the small data set OC20-Ni, surpassing existing technologies. Ablation studies confirm the necessity of focusing on site features for accurate adsorption energy prediction. Code is available at https://github.com/KristinSun/OCP-MGT.git.

An exploratory machine learning model for predicting advanced liver fibrosis in autoimmune hepatitis patients: A preliminary study.

Advanced fibrosis is a crucial stage in the progression of autoimmune hepatitis (AIH), where fibrosis can either regress or advance. This study aims to leverage machine learning (ML) models for the assessment of advanced liver fibrosis in AIH patients using routine clinical features. A total of 233 patients diagnosed with AIH and underwent liver biopsy were included in the discovery cohort. The dataset was randomly split into training and testing sets. Patients were categorized into groups with no/minimal/moderate fibrosis and advanced fibrosis. Six ML models were employed to identify the optimal model. Subsequently, the predictive capability of the best ML model was validated in an additional cohort (n = 33) and compared with conventional noninvasive fibrosis scores. Three key clinical features, including prothrombin time (PT), albumin (ALB), and ultrasound spleen thickness (UTST), were analyzed by least absolute shrinkage and selection operator (LASSO) regression. In the training set, the random forest (RF) model showed the highest diagnostic performance in predicting advanced fibrosis stage (AUC=0.951). In the testing cohort and validation cohort, the RF model maintained high accuracy (AUC = 0.863 and AUC = 0.843). Additionally, the random forest model outperformed the conventional noninvasive fibrosis scores. ML models, particularly the RF model, can help improve the discrimination of advanced liver fibrosis in patients with AIH.

Energy-based approach to the assessment of traffic flow

This article focuses on modeling vehicle acceleration noise in different road conditions, emphasizing urban, highway, and rural roads in Ukraine. Acceleration noise, which refers to the fluctuations in a vehicle's acceleration, is a critical factor in vehicle safety, fuel efficiency, and driving comfort. The research aims to improve current vehicle dynamics models by integrating multi-body dynamics and machine learning algorithms, allowing for more precise predictions of acceleration variability in real-time. The study is based on the existing literature, showing that road surface quality significantly affects acceleration noise. With frequent stop-and-go traffic, urban roads produce moderate but irregular noise patterns. Highways show stable acceleration noise at moderate speeds, but noise increases sharply as vehicles approach higher speeds due to aerodynamic forces. Rural roads, especially those in poor condition, exhibit the highest variability in acceleration noise, even at low speeds. The proposed model has been validated using real-world data. It demonstrates a strong correlation between the predictions and actual vehicle behavior on various road types. One of the key innovations in this research is the use of machine learning to adjust model parameters in real-time dynamically. This adaptive approach enhances the model’s accuracy and applicability, especially in intelligent transport systems. The model can inform traffic management strategies, allowing for real-time adjustments to speed limits, traffic signals, and routing decisions based on road conditions. This contributes to safer, more efficient, and sustainable transport systems, particularly in regions with inconsistent road infrastructure. The research concludes that integrating acceleration noise modeling into intelligent transport systems can significantly improve traffic flow and vehicle safety. Future research will expand the dataset to include a broader range of vehicle types and road conditions, further refining the model's predictive capabilities.

Essential Structural Profile of Novel Adenosine Derivatives as Antiplatelet Aggregation Inhibitors based on 3D-QSAR Analysis

Aims: In this research, 3D-QSAR evaluation on a set of fresh purinoid compounds that we produced was conducted. This analysis aims to illustrate the correlation between the structure of purine and its ability to prevent platelet aggregation. Our findings could pave the way to discovering novel antithrombotic medications. Background: The incidence of cardiovascular disease triggered by the clumping of platelets poses a significant danger to human health. Purine derivatives are important molecules with antiplatelet aggregation activity. Objective: The objectives of this research are to establish the correlation between the structure of purine and its ability to prevent platelet aggregation. Such a correlation could aid in the development of innovative antithrombotic medications. Methods: In this study, 3D-QSAR investigation on a collection of 75 new purine derivatives, which we synthesized, was conducted, utilizing Comparative molecular field analysis (CoMFA) and comparative molecular similarity indices analysis (CoMSIA). Results: Significant correlation coefficients (CoMFA, q2= 0.843, r2= 0.930, F value= 266.755, SEE= 0.165; CoMSIA, q2= 0.869, r2= 0.918, F value= 222.571, SEE= 0.179) were obtained, and assessed the model's predictive capabilities by validating it with the test set. Conclusion: Our findings indicate that the introduction of an appropriately sized structure at position 2 of the compound yields significant benefits. Conversely, the attachment of an excessively large group is detrimental. Direct attachment of a bulky substituent at C-6 of the compound is not feasible, and its activity increases when the structure with low electron cloud density is added. Moreover, the presence of a voluminous functional group at the 5' position of the compound is advantageous, and its activity will be further increased by the presence of hydrogen bond receptors in this region. These discoveries furnish significant comprehension for the formation of innovative structures with heightened efficacy.

Cross-Seasonal Effect on Tropical Pacific Precipitation: Implication of South Pacific Quadrupole Simulation in CMIP6

Abstract The tropical Pacific convergence zone plays a crucial role in the global climate system. Previous research studies emphasized the cross-seasonal influence of the South Pacific quadrupole (SPQ) mode on the tropical Pacific climate. This study assesses the relationship between austral summer SPQ and austral winter tropical precipitation in phase 6 of the Coupled Model Intercomparison Project (CMIP6) models. The analysis emphasizes the historical experiments conducted within this time frame, spanning from 1979 to 2014. Our findings reveal that the SPQ is accurately represented in all CMIP6 models, but the connection between SPQ and precipitation is inadequately simulated in most models. To investigate the reasons behind these intermodel differences in reproducing SPQ-related processes, we categorize models into two groups. The comparisons demonstrate that the fidelity of model simulations in replicating the SPQ–tropical precipitation relationship hinges significantly on their capacity to reproduce the positive wind–evaporation–sea surface temperature (WES; SST) feedback over both the southwestern Pacific (25°–10°S; 150°E–160°W) and the southeastern Pacific (30°–10°S; 140°–80°W). This positive WES feedback propagates the SPQ signal into the tropics, intensifying the meridional gradient of SST anomaly in the tropical western-central Pacific, which consequently amplifies convection and rainfall in that area. In the group of models that failed to simulate this relationship accurately, the weakened WES feedback can be traced back to biases in wind speed and its variation. Furthermore, this WES feedback establishes a connection between SPQ and El Niño–Southern Oscillation (ENSO). A better rendition of the SPQ–tropical rainfall connection tends to result in a better simulation of the onset of SPQ-related ENSO events. As a result, this study advances our comprehension of extratropical impacts on the tropics, with the potential to enhance the accuracy of tropical climate simulation and prediction. Significance Statement Tropical rainfall plays an important role in the global climate system. Beyond the well-known influence of El Niño–Southern Oscillation (ENSO) on the tropical rainfall, the sea surface temperature (SST) anomaly in the South Pacific has a cross-seasonal impact on the precipitation over the tropical Pacific via air–sea coupled processes. Such SST anomaly pattern shows a quadrupole structure in the extratropical South Pacific, known as the South Pacific quadrupole (SPQ) mode. However, the relationship between SPQ and tropical precipitation remains poorly simulated in most state-of-the-art climate models. One primary reason for this gap between observed and simulated relationships is the underestimation of wind speed and its variation over the south tropical Pacific in these models. This limitation undermines their ability to accurately represent the air–sea interactions that drive tropical precipitation patterns, leading to inaccuracies in simulations. Our study aims to bridge this knowledge gap by enhancing our understanding of the extratropical effects on the tropical Pacific. By exploring the mechanisms underlying the SPQ–precipitation connection, we expect to improve the simulation and prediction capabilities of tropical climate models, thereby enhancing our ability to forecast and adapt to future climatic changes.

Prediction Model and Knowledge Discovery for Roof Stress in Mined-Out Areas Integrating 3D Scanning Image Features

The accurate prediction of roof stress in mined-out areas is crucial for ensuring mine safety. However, existing study methods often overlook the increasingly available image data and fail to balance the model predictive capability with interpretability. To address these issues, this study innovatively integrates 3D laser scanning image features into the prediction of roof stress in mined-out areas. Image features are extracted using pre-trained deep-learning models and combined with traditional geological parameters to construct multiple machine-learning models for prediction. The experimental results demonstrate that models incorporating image features significantly outperform traditional models that rely solely on geological parameters in terms of prediction accuracy, interpretability, and complexity, revealing the critical role of image features in stress prediction. Furthermore, the use of SHapley Additive exPlanations (SHAP) to interpret the random forest model uncovers new domain knowledge, such as the relationship between spatial patterns and stress concentration. This study theoretically validates the effectiveness of image data and effectively balances the predictive capability and interpretability of the model, facilitating knowledge discovery in the field. On a practical level, it also provides guidance for mine safety management.

Accounting for Natural Disasters Using Risk of Information Security

Objective: The harm that can be done to an information technology system is referred to as "information security risk" (IS). Data breaches, administrative actions, financial expenses, and reputational harm are just a few of the many possible dangers that fall under the broad category of information systems risks. IS hazards include hostile assaults, spam, viruses, human error, hardware and software malfunctions, and natural disasters like floods, hurricanes, and fires. Methods: Key security controls for applications are identified, evaluated, and implemented through security risk assessments. Another priority is to avoid security gaps and defects in software. This article analyzes documented historical research on natural disaster accounting. Based on the results of 35 publications on general topics, economic history, and accounting, 11 papers were selected and reviewed. By analyzing the scattered literature, emerging themes, investigated disasters, investigated time periods, and main contributions of published research were identified. Result: To compare the predictive capabilities of the machine learning models and validate the landslide, flood, and wildfire hazard maps, the area under the curve (AUC) was calculated. For the landslide, flood, and wildfire hazard maps, the RF model provided the highest AUC values (0.81, 0.85, and 0.94, respectively).

Use and Evaluation of GANs for Synthetic Data Generation in Pharmacogenetics.

Pharmacogenetics (PGx) explores the influence of genetic variability on drug efficacy and tolerability. Synthetic Data Generation (SDG) has emerged as a promising alternative to the labor-intensive process of collecting real-world PGx data, which is required for high-qualitative prediction models. This study investigates the performance of two Generative Adversarial Network (GAN) models, CTGAN and CTAB-GAN+, in generating synthetic PGx data. The benchmarking is based on utility metrics (Hellinger distance and Random Forest accuracy) and ϵ-identifiability. Results demonstrate that synthetic data generated by CTAB-GAN+ can surpass the original dataset in terms of utility. For instance, CTAB-GAN+ achieves higher Random Forest accuracy compared to the original data, indicating better predictive performance. These improvements suggest that synthetic data not only capture the essential patterns of the original data but also enhance model generalization and prediction capabilities, providing a more robust training ground for machine learning models. Consequently, SDG offers a promising solution to address data scarcity and imbalance in pharmacogenetic research.

Numerical modeling of concrete beams subjected to partial wetting and drying cycles

Concrete structures are commonly subjected to cycles of wetting and drying, which can have a significant impact on their behavior. However, experimental data on the effects of wetting and drying on concrete beams are scarce. This study presents the results of a 4-year experimental program on 2.5 m span concrete beams with heights of 100 mm, 150 mm, and 200 mm subjected to one-sided wetting and drying cycles. Vertical deflection of the beams was monitored throughout the experiment, and moisture mass balance was measured on companion specimens.The behavior of the specimens was experimentally assessed, and subsequently numerical models using coupled hygromechanical finite element simulations were developed. The purpose of the simulations was to verify the prediction capabilities of the established constitutive models for moisture transport and creep and shrinkage of concrete and, if needed, to propose necessary corrections to the constitutive models.

Testing the prediction capability of trained models: sildenafil citrate solubility in propylene glycol and 1-propanol mixtures at different temperatures

ABSTRACT This study investigates the thermodynamic characteristics, equilibrium solubility, and solvation dynamics of sildenafil citrate within binary solvent systems composed of propylene glycol and 1-propanol. Utilizing both determination and computational approaches, the solubility patterns of sildenafil citrate were quantitatively assessed, revealing direct proportionality with increments in temperature and the concentration of propylene glycol. A comparative analysis using three distinct mathematical models to represent the solid–liquid phase equilibrium was conducted. Among these, the Jouyban-Acree-van’t Hoff model yielded the most comprehensive correlation by covering the effects of both temperature and solvent composition variations on the solubility, with a mean relative deviation (MRD%) of 6.4%, suggesting a robust alignment between the modelled and experimental solubility data. Previously trained models were tested to predict the solubility of the drug in mono- and mixed-solvents at various temperatures where accurate predictions were obtained with the MRD% of 19.1% (for mono-solvents), 8.1 and 14.4% (for mixed solvent systems).

Challenges with Literature-Derived Data in Machine Learning for Yield Prediction: A Case Study on Pd-Catalyzed Carbonylation Reactions.

The application of machine learning (ML) to predict reaction yields has shown remarkable accuracy when based on high-throughput computational and experimental data. However, the accuracy significantly diminishes when leveraging literature-derived data, highlighting a gap in the predictive capability of the current ML models. This study, focusing on Pd-catalyzed carbonylation reactions, reveals that even with a data set of 2512 reactions, the best-performing model reaches only an R2 of 0.51. Further investigations show that the models' effectiveness is predominantly confined to predictions within narrow subsets of data, closely related and from the same literature sources, rather than across the broader, heterogeneous data sets available in the literature. The reliance on data similarity, coupled with small sample sizes from the same sources, makes the model highly sensitive to inherent fluctuations typical of small data sets, adversely impacting stability, accuracy, and generalizability. The findings underscore the inherent limitations of current ML techniques in leveraging literature-derived data for predicting chemical reaction yields, highlighting the need for more sophisticated approaches to handle the complexity and diversity of chemical data.

Application of Bayesian Neural Networks in Healthcare: Three Case Studies

This study aims to explore the efficacy of Bayesian Neural Networks (BNNs) in enhancing predictive modeling for healthcare applications. Advancements in artificial intelligence have significantly improved predictive modeling capabilities, with BNNs offering a probabilistic framework that addresses the inherent uncertainty and variability in healthcare data. This study demonstrates the real-world applicability of BNNs through three key case studies: personalized diabetes treatment, early Alzheimer’s disease detection, and predictive modeling for HbA1c levels. By leveraging the Bayesian approach, these models provide not only enhanced predictive accuracy but also uncertainty quantification, a critical factor in clinical decision making. While the findings are promising, future research should focus on optimizing scalability and integration for real-world applications. This work lays a foundation for future studies, including the development of rating scales based on BNN predictions to improve clinical outcomes.

Multi-Algorithm Approach to Enhancing Social Assistance Efficiency Through Accurate Poverty Classification

The determination of poverty status in Lombok Utara district depends on criteria such as income, access to health and education services, and housing conditions. These factors are crucial for assessing the level of community welfare and guiding the allocation of social assistance by the district government. The purpose of this study is to address the gap by utilizing advanced data mining techniques to improve the accuracy of poverty status classification in North Lombok, thereby informing more effective social assistance policies. The method used in this research is the Random Forest (RF), K-Nearest Neighbor (KNN) and Naïve Bayes with split data 80% data training and 20% data testing. The finding indicated that the machine learning model the RF algorithm, which achieved an accuracy rate of 82.56%, proved to play an important role in this process by effectively distinguishing between different categories of poverty based on these criteria. In comparison, the KNN algorithm achieved an accuracy of 70.94% and the Naïve Bayes model achieved an accuracy of 53.47%. It means that the machine learning model using the RF algorithm has more accurate accuracy than the KNN and Naïve Bayes algorithm in predicting or recommending Recipients of Social Assistance from the District Government. The implication is that RF machine learning can help the role of social service officers in predicting the economic status of the community. The high accuracy of the RF algorithm enhances its role in informing targeted policy decisions and optimizing the effectiveness of social assistance programs. Nonetheless, continuous improvement is essential to refine the model's predictive capabilities and ensure the accuracy and reliability of poverty assessments. These continuous improvements are essential to effectively alleviate poverty and break the cycle of socio-economic disparities in the region.

Evaluate Multi-Objective Optimization Model for Product Supply Chain Inventory Control Based on Grey Wolf Algorithm

Enterprise supply chain inventory control plays a critical role in modern enterprise management. Yet achieving multi-objective optimization remains challenging. This paper proposes a deep learning integrated model based on grey wolf optimization (GWO-DLIM) aimed at optimizing inventory holding costs, stockout costs, and order costs. The model integrates multi-layer perceptron (MLP), DeBERTa, and GWO, leveraging the powerful predictive and feature extraction capabilities of deep learning models, combined with the global optimization ability of the grey wolf algorithm, to achieve multi-objective optimization. These results demonstrate that the GWO-DLIM model significantly outperforms other comparative models across all metrics, exhibiting lower prediction errors and root mean square errors, as well as higher service levels. This study provides an effective multi-objective optimization solution for supply chain inventory management, holding significant theoretical and practical implications.

Damage mechanism and energy evolution of frozen soil under coupled compression–shear impact loading

In cold region engineering, the impact of coupled compression–shear loading on frozen soil foundations is a critical issue that urgently needs to be addressed, as it often significantly reduces bearing capacity and can cause structural failures. Accurately characterizing the mechanical behavior of frozen soil under dynamic coupled compression–shear loading is essential for enhancing the safety and stability of cold region engineering projects. This study prepared four frozen-soil specimens with varying tilting angles to investigate failure mechanisms and energy evolution under coupled compression–shear impact loading. The impact-compression experiments were conducted on the specimens under different loading strain rates and temperature conditions using a split Hopkinson pressure bar. The results indicated that the strength of frozen soil was effectively enhanced by higher strain rates and lower temperatures, while it was reduced by increased tilting angle. The fracturing morphology of frozen soil was analyzed from both microscopic and macroscopic perspectives to reveal its failure mechanisms. To quantify the strength characteristics of the frozen soil under various loading conditions, damage variables were defined from an energy-based perspective and incorporated into the Zhu–Wang–Tang viscoelastic constitutive model. Hence, a dynamic constitutive model for frozen soil under coupled compression–shear loading was developed. The model's predictive capability was validated through comparisons with the experimental data, which revealed a high level of agreement. The results of this study provide practical insights into the failure mechanisms and construction design of frozen soil foundations under coupled compression–shear impact loading in cold region engineering.

DeepAge: Harnessing Deep Neural Network for Epigenetic Age Estimation From DNA Methylation Data of Human Blood Samples

Accurate prediction of biological age from DNA methylation data is a critical endeavor in understanding the molecular mechanisms of aging and developing age-related disease interventions. Traditional epigenetic clocks rely on linear regression or basic machine learning models, which often fail to capture the complex, non-linear interactions within methylation data. This study introduces DeepAge, a novel deep learning framework utilizing Temporal Convolutional Networks (TCNs) to enhance the prediction of biological age from DNA methylation profiles using selected CpGs by a Dual-Correlation based apparoach. DeepAge leverages a sequence-based approach with dilated convolutions to effectively capture long-range dependencies between CpG sites, addressing the limitations of prior models by incorporating advanced network architectures including residual connections and dropout regularization. The dual correlation feature selection enhances our model's predictive capabilities by identifying the most age-relevant CpG sites. Our model outperforms existing epigenetic clocks across multiple datasets, offering significant improvements in accuracy and providing deeper insights into the epigenetic determinants of aging. The proposed method not only sets a new standard in age estimation but also highlights the potential of deep learning in biologically relevant feature extraction and interpretation, contributing to the broader field of computational biology and precision medicine.

WS-BiTM: Integrating White Shark Optimization with Bi-LSTM for enhanced autism spectrum disorder diagnosis

Autism Spectrum Disorder (ASD) is a multifaceted neurodevelopmental condition marked by challenges in social communication, sensory processing, and behavioral regulation. The delayed diagnosis of ASD significantly impedes timely interventions, which can exacerbate symptom severity. With approximately 62 million individuals affected worldwide, the demand for efficient diagnostic tools is critical. This study introduces a novel framework that combines a White Shark Optimization (WSO)-based feature selection method with a Bidirectional Long Short-Term Memory (Bi-LSTM) classifier for enhanced autism classification. Utilizing the WSO technique, we identify key features from autism screening datasets, which markedly improves the model's predictive capabilities. The optimized feature set is then processed by the Bi-LSTM classifier, enhancing its efficiency in handling sequential data. We comprehensively address methodological challenges, including overfitting, generalization, interpretability, and computational efficiency. Furthermore, we conduct a comparative analysis against baseline algorithms such as Neural Networks, Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks, while also employing Particle Swarm Optimization (PSO) for feature selection validation. We evaluate performance metrics, including accuracy, F1-score, specificity, precision, and sensitivity across three ASD datasets: Toddlers, Adults, and Children. Our results demonstrate that the WS-BiTM model significantly outperforms baseline methods, achieving accuracies of 97.6 %, 96.2 %, and 96.4 % on the respective datasets. Additionally, we implemented leave-one-dataset cross-validation and confirmed the statistical significance of our findings through a paired t-test, supplemented by an ablation study to detail the contributions of individual model components. These findings highlight the potential of the WS-BiTM model as a robust tool for ASD classification.

Research on imaging biomarkers for chronic subdural hematoma recurrence.

This study utilizes radiomics to explore imaging biomarkers for predicting the recurrence of chronic subdural hematoma (CSDH), aiming to improve the prediction of CSDH recurrence risk. Analyzing CT scans from 64 patients with CSDH, we extracted 107 radiomic features and employed recursive feature elimination (RFE) and the XGBoost algorithm for feature selection and model construction. The feature selection process identified six key imaging biomarkers closely associated with CSDH recurrence: flatness, surface area to volume ratio, energy, run entropy, small area emphasis, and maximum axial diameter. The selection of these imaging biomarkers was based on their significance in predicting CSDH recurrence, revealing deep connections between postoperative variables and recurrence. After feature selection, there was a significant improvement in model performance. The XGBoost model demonstrated the best classification performance, with the average accuracy improving from 46.82% (before feature selection) to 80.74% and the AUC value increasing from 0.5864 to 0.7998. These results prove that precise feature selection significantly enhances the model's predictive capability. This study not only reveals imaging biomarkers for CSDH recurrence but also provides valuable insights for future personalized treatment strategies.

Evaluation of the Predictive Capability of CMA Climate Prediction System Model for Summer Surface Heat Source on the Tibetan Plateau

Surface heat source (SHS) is a crucial factor affecting local weather systems. Particularly SHS on the Tibetan Plateau (TP) significantly influences East Asian atmospheric circulation and global climate. Accurate prediction of summer SHS on the TP is of urgent demand for economic development and local climate change. To evaluate the performance of SHS on the TP, the observed SHS data from the eleven sites on the TP verified against CRA40-land (CRA) is evidenced significantly better than ERA5-land (ERA5), another widely used reanalysis. The predictive capability of the CMA Climate Prediction System Model (CMA-CPS) for SHS on the TP was assessed using multiple scoring methods, including the anomaly correlation coefficient and temporal correlation coefficient, among others. Furthermore, relative variability and trend analysis were conducted. Finally, based on these assessments, the causes of the biases were preliminarily discussed. The CMA-CPS demonstrates a reasonable ability to predict the spatial distribution patterns of SHS, sensible heat (SH), and latent heat (LH) on the TP in summer. Specifically, the prediction results of SHS and LH exhibit an “east-high and west-low” distribution, while the distribution of the predicted SH is opposite. Nevertheless, the predicted values are generally lower than CRA, particularly in interannual variations and trends. Among the predictions, LH exhibits the highest temporal correlation coefficients, consistently above 0.6, followed by SHS, while SH predictions are less accurate. The spatial distribution and skill scores indicate that LH on the TP contributes more significantly to SHS than SH in summer. Furthermore, discrepancies in the predictions of surface temperature gradients, ground wind speed, and humidity on the TP may partly explain the biases in SHS and their components.

Thermodynamic calculation-assisted design of 500 MPa high performance steel by machine learning

In order to rationally design Q500 low-alloy wind power steel with stable microstructure and properties within a large cooling rate range, this study proposed a design system that utilizes thermodynamic database, machine learning (ML), and the multi-objective genetic optimization algorithm (MOGA). Thermodynamic calculation has been used to obtain a large amount of data on phase fractions and mechanical properties for various chemical composition at different cooling rates. By comparing the predictive capabilities of different ML models, the deep neural network (DNN) and MOGA were combined to design Q500 wind power steel. Subsequently, three groups of designed chemical compositions were appropriately selected for verification. The results indicate that the yield strength of the experimental steel was over 500 MPa, and the maximum error in microstructure and mechanical property prediction was 5.0%. The prediction results demonstrated the rationality of the composition design framework. Meanwhile, the method of combining the material database and ML proposed in this study can also be applied to the design of other low-alloy steels.