Precise Prediction Research Articles

Test-and-FE-based method for obtaining complete stress-strain curves of structural steels including fracture

Ductile fracture is a common limit state of frameworks of steel structures and can be predicted by incorporating models for fracture initiation and propagation in finite element (FE) analyses. However, accurate prediction of fracture relies on unique fracture parameters for a given material, requiring precise predictions of fracture strain and stress states obtained through coupon tests and accompanying FE data analysis. In recent decades, various methods have been proposed to predict ductile fracture initiation, including various design geometries of coupons, test setups and FE analyses, which may lead to inconsistent fracture strains and stress states. Hence, there is a need for proposing a standard procedure for the design, test and accompanying FE-based calibration of fracture parameters, as pursued in this paper. Given that ductile fracture initiates under significant plastic strain, a constitutive model for the full strain range is required, as also proposed in this paper. Moreover, to reduce the experimental and data analytical efforts, an empirical method is proposed that uses only a small number of coupon tests to calibrate the fracture parameters. The method encompasses three levels wherein one, two, or three coupon tests are required. All in all, the paper presents a methodology for determining the full-range true stress-strain curve and the initiation of fracture, including a new post-necking constitutive model and methods for determining the free parameters of the post-necking and fracture initiation models. While applied to steel in this paper, the proposed methodology is potentially also applicable to other metals.

Subclassification of obesity for precision prediction of cardiometabolic diseases.

Obesity and cardiometabolic disease often, but not always, coincide. Distinguishing subpopulations within which cardiometabolic risk diverges from the risk expected for a given body mass index (BMI) may facilitate precision prevention of cardiometabolic diseases. Accordingly, we performed unsupervised clustering in four European population-based cohorts (N ≈ 173,000). We detected five discordant profiles consisting of individuals with cardiometabolic biomarkers higher or lower than expected given their BMI, which generally increases disease risk, in total representing ~20% of the total population. Persons with discordant profiles differed from concordant individuals in prevalence and future risk of major adverse cardiovascular events (MACE) and type 2 diabetes. Subtle BMI-discordances in biomarkers affected disease risk. For instance, a 10% higher probability of having a discordant lipid profile was associated with a 5% higher risk of MACE (hazard ratio in women 1.05, 95% confidence interval 1.03, 1.06, P = 4.19 × 10-10; hazard ratio in men 1.05, 95% confidence interval 1.04, 1.06, P = 9.33 × 10-14). Multivariate prediction models for MACE and type 2 diabetes performed better when incorporating discordant profile information (likelihood ratio test P < 0.001). This enhancement represents an additional net benefit of 4-15 additional correct interventions and 37-135 additional unnecessary interventions correctly avoided for every 10,000 individuals tested.

Biparietal diameter vs crown-rump length as standard parameter for late first-trimester pregnancy dating.

To compare the precision of biparietal diameter (BPD) and crown-rump length (CRL) as predictors of gestational age in the human fetus in the late first and early second trimesters, using a population-based approach. We constructed term and gestational-age prediction curves for first-trimester dating, based on 11 041 pregnancies with 12 260 measurements of CRL and/or BPD from a population-based Norwegian clinical database. We used a population-based approach with local linear quantile regression, combined with a time-to-event strategy that compensates for induced births. Term prediction precision was assessed by estimating and comparing the prediction residual curves using a time-to-event analysis. Individual differences in gestational-age predictions from CRL and BPD were assessed using measurements performed on the same fetus on the same day. A sensitivity analysis was performed to evaluate the effect of not distinguishing between non-spontaneous and spontaneous births. CRL and BPD provided almost identical term prediction precision judged from the residual distribution. In about 51% of examinations, the difference in predicted gestational age was 1 day or less; 24% of examinations had a difference of 2 days, 14% had a difference of 3 days, 7% had a difference of 4 days and only 5% of all examinations had a difference of 5 days or more. Incorrectly removing induced births from the analysis, or treating them as spontaneous, would cause a substantial systematic prediction bias of about 2 days. Based on population data, using comparisons at an individual level, our study found that BPD is as precise as CRL when used for first-trimester dating. BPD has advantages from a clinical point of view, since it is technically less challenging and less time-consuming to measure compared with CRL, and can be measured and assessed throughout the entire pregnancy. © 2024 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Integrated Systematic Framework for Forecasting China’s Consumer Confidence: A Machine Learning Approach

This study aims to introduce a novel approach for predicting China’s consumer confidence index (CCI), a key economic indicator that reflects consumers’ confidence in current and future economic conditions. While traditional statistical models and economic indicators are the primary tools for forecasting CCI, their reliance on linear assumptions limits their ability to capture the complex, dynamic relationships inherent in economic systems. In response, this study proposes a two-step method that integrates social network analysis (SNA) and machine learning (ML) to enhance prediction accuracy by accounting for the nonlinear interactions and systemic interdependencies that drive consumer confidence. The use of SNA enables the identification of critical variables and their interconnected roles in shaping consumer sentiment, while ML models, specifically the gradient boosting decision tree (GBDT), leverage these relationships to provide more precise predictions. Utilizing monthly data from 1999 to 2023, the combined SNA and GBDT approach significantly improves the accuracy of CCI forecasts, particularly during periods of high volatility. The results of this study hold substantial value for policymakers, market analysts, and economists, as they offer a systems-oriented framework for economic forecasting. By demonstrating the effectiveness of combining SNA with ML technologies, this research not only advances the methodological toolkit for economic forecasting, but also provides a new lens through which the complex, adaptive nature of economic systems can be better understood and managed. This integrated approach paves the way for future developments in forecasting models that more accurately reflect the evolving dynamics of consumer confidence in a rapidly changing economic environment.

Research on a Non-Stationary Groundwater Level Prediction Model Based on VMD-iTransformer and Its Application in Sustainable Water Resource Management of Ecological Reserves

The precise forecasting of groundwater levels significantly influences plant growth and the sustainable management of ecosystems. Nonetheless, the non-stationary characteristics of groundwater level data often hinder the current deep learning algorithms from precisely capturing variations in groundwater levels. We used Variational Mode Decomposition (VMD) and an enhanced Transformer model to address this issue. Our objective was to develop a deep learning model called VMD-iTransformer, which aims to forecast variations in the groundwater level. This research used nine groundwater level monitoring stations located in Hangjinqi Ecological Reserve in Kubuqi Desert, China, as case studies to forecast the groundwater level over four months. To enhance the predictive performance of VMD-iTransformer, we introduced a novel approach to model the fluctuations in groundwater levels in the Kubuqi Desert region. This technique aims to achieve precise predictions of the non-stationary groundwater level conditions. Compared with the classic Transformer model, our deep learning model more effectively captured the non-stationarity of groundwater level variations and enhanced the prediction accuracy by 70% in the test set. The novelty of this deep learning model lies in its initial decomposition of multimodal signals using an adaptive approach, followed by the reconfiguration of the conventional Transformer model’s structure (via self-attention and inversion of a feed-forward neural network (FNN)) to effectively address the challenge of multivariate time prediction. Through the evaluation of the prediction results, we determined that the method had a mean absolute error (MAE) of 0.0251, a root mean square error (RMSE) of 0.0262, a mean absolute percentage error (MAPE) of 1.2811%, and a coefficient of determination (R2) of 0.9287. This study validated VMD and the iTransformer deep learning model, offering a novel modeling approach for precisely predicting fluctuations in groundwater levels in a non-stationary context, thereby aiding sustainable water resource management in ecological reserves. The VMD-iTransformer model enhances projections of the water level, facilitating the reasonable distribution of water resources and the long-term preservation of ecosystems, providing technical assistance for ecosystems’ vitality and sustainable regional development.

Research on Non-Destructive Testing of Log Knot Resistance Based on Improved Inverse-Distance-Weighted Interpolation Algorithm

The objective of this paper is to propose a non-destructive resistance detection imaging algorithm for log knots based on improved inverse-distance-weighted interpolation algorithm, i.e., the eccentric circle-based inverse-distance-weighted (ECIDW) method, to predict the size, shape, and position of internal knots of logs; evaluate its precision and accuracy; and both lay a theoretical foundation and provide a scientific basis for predicting and assessing knots in standing trees. Six sample logs with natural knots were selected for this study. Resistance measurements were performed on the log cross-sections using a digital bridge, and resistance tomography was conducted using the improved ECIDW algorithm, which combines the azimuth search method with the eccentric circle search method. The results indicated that both the conventional inverse-distance-weighted (IDW) algorithm and the ECIDW algorithm accurately predicted the positions of the knots. However, neither algorithm was able to predict the shape of the knots with high precision, leading to some discrepancies between the predicted and actual knot shapes. The relative error (Dt1) between the knot areas measured by the IDW algorithm and the actual knot areas ranged from 18.97% to 88.34%. The relative error (Dt2) for the knot areas predicted by the ECIDW algorithm ranged from 1.82% to 74.16%. The average prediction accuracy for the knot areas using the IDW algorithm was 51.58%, compared to 72.90% using the ECIDW algorithm. This indicates that the ECIDW algorithm has higher accuracy in predicting knot areas compared to the conventional IDW algorithm. The ECIDW algorithm proposed in this paper provides a more reasonable and accurate prediction and evaluation of knots inside logs. Compared to the conventional IDW algorithm, the ECIDW algorithm demonstrates greater precision and accuracy in predicting the shape and size of knots. While the resistance method shows significant potential for predicting internal knots in logs and standing trees, further improvements to the algorithm were needed to enhance the imaging effects and the precision and accuracy of knot area and shape predictions.

Improved survival prediction for kidney transplant outcomes using artificial intelligence-based models: development of the UK Deceased Donor Kidney Transplant Outcome Prediction (UK-DTOP) Tool

The UK Deceased Donor Kidney Transplant Outcome Prediction (UK-DTOP) Tool, developed using advanced artificial intelligence (AI), significantly enhances the prediction of outcomes for deceased-donor kidney transplants in the UK. This study analyzed data from the UK Transplant Registry (UKTR), including 29,713 transplant cases between 2008 and 2022, to assess the predictive performance of three machine learning models: XGBoost, Random Survival Forest, and Optimal Decision Tree. Among these, XGBoost demonstrated exceptional performance with the highest concordance index of 0.74 and an area under the curve (AUC) consistently above 0.73, indicating robust discriminative ability and calibration. In comparison to the traditional Kidney Donor Risk Index (KDRI), which achieved a lower concordance index of 0.57, the UK-DTOP model marked a significant improvement, underscoring its superior predictive accuracy. The advanced capabilities of the XGBoost model were further highlighted through calibration assessments using the Integrated Brier Score (IBS), showing a score of 0.14, indicative of precise survival probability predictions. Additionally, unsupervised learning via k-means clustering was employed to identify five distinct clusters based on donor and transplant characteristics, uncovering nuanced insights into graft survival outcomes. These clusters were further analyzed using Bayesian Cox regression, which confirmed significant survival outcome variations across the clusters, thereby validating the model’s effectiveness in enhancing risk stratification. The UK-DTOP tool offers a comprehensive decision-support system that significantly refines pre-transplant decision-making. The study’s findings advocate for the adoption of AI-enhanced tools in healthcare systems to optimize organ matching and transplant success, potentially guiding future developments in global transplant practices.

Enhancing slope stability prediction through integrated PCA-SSA-SVM modeling: a case study of LongLian expressway

China is one of the regions most frequently affected by landslides, which have significant socio-economic impacts. Traditional slope stability analysis methods, such as the limit equilibrium method, limit analysis method, and finite element method, often face limitations due to computational complexity and the need for extensive soil property data. This study proposes a novel approach that combines Principal Component Analysis (PCA), Sparrow Search Algorithm (SSA), and Support Vector Machine (SVM) to improve the accuracy of slope stability prediction. PCA effectively reduces data dimensionality while retaining critical information. SSA optimizes SVM parameters, addressing the limitations of traditional optimization methods. The integrated PCA-SSA-SVM model was applied to a dataset of 257 slope stability samples and validated using five-fold cross-validation to ensure the model’s generalization capability. The results show that the model exhibits superior performance in prediction accuracy, precision, recall, and F1-score, with the test set achieving an accuracy of 84.6%, a recall of 84.7%, a precision of 83.1%, and an F1-score of 84.6%. The model’s robustness was further validated using slope data from the LongLian Expressway, demonstrating high consistency with the actual stability status. These findings indicate that the PCA-SSA-SVM-based slope stability prediction model has significant potential for practical engineering applications, providing a reliable and efficient tool for slope stability forecasting. Classify the training samples through cross-validation, using the accuracy of cross-validation as the fitness of the sparrow individual. Retain the optimal fitness value and position information.

Prognostic role of serum cytokines level in non-small cell lung cancer patients with anti-PD-1 and chemotherapy combined treatment.

Chemotherapy combined with PD-1 inhibitor treatment has revolutionized the standard of care for patients with NSCLC. However, the benefit is not universal, highlighting the need for precise prediction factors. Given their relationship with the immune system and non-invasive nature, serum cytokines are potential candidates for predicting the clinical effects of chemoimmunotherapy. Our study aims to evaluate the association of serum cytokines with the prognosis of patients with NSCLC treated with chemoimmunotherapy. Levels of 10 serum cytokines were detected in 60 NSCLC patients receiving chemotherapy plus PD-1 inhibitor-based treatment. Of these, dynamic samples from 19 patients were collected at baseline and after two treatment cycles. Their association with patients' clinicopathological characteristics, PFS and OS was described and investigated using survival analysis, cox regression and time-dependent ROC analysis. Preliminary evaluation of changes in cytokine levels associated with treatment response was conducted. Patients with lower baseline levels of serum IL-6, IL-5, IL-8, TNF-α and IL-10 had longer PFS, while patients with higher levels of IL-4 had longer PFS. Patients with lower levels of serum IL-6, IL-8, IL-22, TNF-α and IL-10 had longer OS, while patients with higher levels of IL-4 had longer OS. Multivariate analysis suggested that higher IL-6 and IL-5 levels were associated with poorer PFS, and higher IL-6 levels were associated with dismal OS. Additionally, changes in serum cytokine levels could be associated with treatment response. Our study suggests that serum cytokines, specifically IL-6, IL-5, IL-8, TNF-α, IL-10, and IL-4, are potential prognostic factors for patients with NSCLC receiving chemotherapy plus PD-1 inhibitor treatment.

CDO-TCN-BiGRU: An Optimized Hybrid Deep Learning Model for Shared Bicycles Demand Forecasting

&lt;div&gt;Accurate prediction of the demand for shared bicycles is not only conducive to the operation of relevant enterprises, but also conducive to improving the image of the city, facilitating people’s travel, and solving the balance between supply and demand of bicycles in the region. To precisely predict the demand of shared bicycles, a model combining temporal convolution network (TCN) and bidirectional gating recurrent unit (BiGRU) model is proposed, and the Chernobyl disaster optimizer (CDO) is used to optimize its hyperparameters. It has the ability of TCN to extract sequence features and gated recurrent unit (GRU) to mine time series data and combine the characteristics of CDO with fast convergence and high global search ability, so as to reduce the influence of model hyperparameters. This article selects the shared bicycles travel data in Washington, analyzes its multi-characteristics, and trains it as the input characteristics of the model. In the experiments, we performed comparison study and ablation study. The results show that the prediction error of the proposed model is less than other comparative models. Therefore, CDO-TCN-BiGRU model has the characteristics of high prediction precision and good stability.&lt;/div&gt;

Utilization of SYNTAX Score II for Predictive Clinical Outcomes in Patients with Coronary Artery Disease and Chronic Renal Insufficiency Following Percutaneous Coronary Intervention.

The SYNTAX score II (SS II) has earned widespread recognition for use on individuals with coronary artery disease (CAD) due to its reliable predictions of 4-year all-cause mortality (ACM). This research focuses on substantiating the prognostic significance of using the SS II for patients experiencing concurrent chronic renal insufficiency (CRI) and CAD who have undergone percutaneous coronary intervention (PCI). This study retrospectively examined 2468 patients with concurrent CAD and CRI who underwent PCI. Based on their SS II, these participants were sorted into low-, medium-, and high-risk groups and monitored over a median of three years. The evaluation of the predictive precision of different SYNTAX scores for clinical outcomes in patients with CRI after PCI involved using time-dependent receiver operating characteristic (ROC) curves. These included the standard SS (SS), SS II, clinical SS (CSS), and residual SS (rSS). The primary outcomes were ACM and cardiac mortality (CM), while the secondary outcomes covered major adverse cardiovascular and cerebrovascular events (MACCEs), stroke, unplanned revascularization, and myocardial infarction (MI). Higher 5-year cumulative incidences of MACCEs, MI, CM, and ACM were observed significantly in patients in the high SS II category relative to those in the low and medium SS II categories. Multivariable Cox regression analysis confirmed that the SS II independently predicts ACM, CM, MI, and MACCEs as a prognostic marker. Additionally, the analysis of the time-dependent ROC curve demonstrated that the areas under the curve (AUC) for predicting CM and ACM were 0.772 and 0.767, respectively, which are superior to those of other SYNTAX scores (p < 0.05). As an independent predictor, the SS II is notable for its ability to forecast long-term adverse outcomes, including MACCEs, CM, ACM, and MI. For patients with coexisting CAD and CRI undergoing PCI, it provides significantly improved prognostic accuracy for 5-year ACM and CM compared to other SYNTAX scores.

Rolled Thickness Prediction for Titanium/Steel‐Clad Plates Based on Combined Method of Theoretical and Neural Network

To address the issue of low precision in rolled thickness prediction for titanium/steel‐clad plates, theoretical calculation and back propagation (BP) neural network prediction models are established based on the slab method and the rolled measured data, respectively. Furthermore, to solve the model's black‐box problem while also improving thickness prediction accuracy, three combined prediction models are built using the principles of compensating multiplicative error, additive error, and average error based on the model's advantages and features for thickness prediction. During the modeling phase, 1925 groups of manufacturing data for titanium/steel‐clad plate rolling are selected and normalized to form the data set. The trial‐and‐error method is used to determine the optimal network structure for the BP neural network. The model's performance is assessed by calculating the mean square error, mean absolute error, and coefficient of determination (R2) and comparing the relative errors in prediction outcomes across different models. In the results, it is demonstrated that the average error combined model (Combined Model III) performs better and predicts more accurately.

Differential evolution optimization based ensemble framework for accurate cervical cancer diagnosis

Cervical cancer remains a significant global health concern, demanding accurate and efficient diagnostic approaches for early detection and treatment. However, there are situations where a single deep learning model might not be sufficient to adequately capture the pertinent information required for precise disease prediction from intricate datasets. In this paper, we introduce an innovative ensemble learning framework that leverages the Differential Evolution (DE) algorithm to enhance the detection of cervical cancer. Our innovative approach combines the collective strength of a diverse set of base models using feature fusion techniques to achieve precise and robust classification. We have developed three base models, denoted as Fusion 1, Fusion 2, and Fusion 3, where each fusion model incorporates two pre-trained models using a feature fusion technique. To capture sequential dependencies and improve feature attention, we have integrated ConvLSTM layers and Squeeze-and-Excitation (SE) blocks into these base models. Subsequently, we've amalgamated the predictions of each base model using a weighted aggregation scheme, with the weights optimized using the DE algorithm. Our ensemble framework introduces a novel method for dynamic weight adjustment, utilizing advanced fusion techniques to improve cervical cancer detection accuracy. This approach ensures robust diagnostic performance across cancer cells datasets, enhancing patient outcomes and community health. Our evaluation covers two datasets, SIPaKMeD and Mendeley LBC, demonstrating the remarkable performance and robustness of our ensemble model. It consistently outperforms individual base models and even surpasses state-of-the-art methods, achieving an impressive accuracy rate of 98.96 % on the Mendeley LBC dataset and 95.68 % on the SIPaKMeD dataset. The incorporation of ConvLSTM layers, SE blocks, and DE optimization significantly contributes to the model's exceptional accuracy, its ability to generalize effectively, and its adaptability to diverse scenarios. Additionally, we employ Grad-CAM to visualize how the base models focus on crucial regions for accurate predictions, providing insights into the model's decision-making process. Our ensemble model exhibits outstanding Area under the Curve (AUC) values in Receiver Operating Characteristic (ROC) analysis, further confirming its effectiveness. This research represents a significant advancement in cervical cancer detection, underscoring the potential of ensemble learning techniques optimized through DE for enhancing diagnostic accuracy and advancing patient care.

Revolutionizing Patient Safety: Machine Learning and AI for the Early Detection of Adverse Drug Reactions and Drug-Induced Toxicity

Adverse drug reactions and drug-induced toxicity provide significant issues in drug research, jeopardizing patient safety and driving up healthcare costs. Toxicity has a greater potential impact than infectious diseases since it is less visible. Early diagnosis of these difficulties is critical to determining a drug's safety and viability profile. The combination of machine learning and artificial intelligence has marked a watershed moment in the identification of early adverse drug reactions and toxicity. These computational approaches enable rapid, extensive, and precise prediction of likely adverse drug reactions and toxicity even before practical drug manufacture, preclinical testing, and clinical trials. This paradigm change strives to create more efficient and safe drugs, lowering the likelihood of drug withdrawal. This comprehensive review investigates the critical role of machine learning and artificial intelligence in quickly detecting adverse drug reactions and toxicity, including approaches from data mining to deep learning. It lists essential databases, modelling techniques, and software that may be used to model and predict a wide range of toxicities and adverse drug reactions. This review provides a comprehensive overview, outlining recent developments and projecting future opportunities in machine learning and artificial intelligence-driven rapid identification of adverse drug reactions and drug-induced toxicity. It highlights the capabilities of these technologies and their enormous potential to improve patient safety and revolutionize medication discovery.

A novel Tree-augmented Bayesian network for predicting rock weathering degree using incomplete dataset

The precise forecasting of the weathering degree of surrounding rock holds paramount importance for the scientific design and secure execution of tunnel engineering. The apparent features of the surrounding rock serve as critical indicators for evaluating its weathering degree. This paper endeavors to quantify the rock apparent features based on an improved Computer vision model and establish a multi-source heterogeneous dataset encompassing 10 parameters, thereby facilitating data-driven predictions of the weathering degree. Specifically, the rock appearance parameters are quantified and segmented by an improved Tunnel face feature segmentation (TFFSeg) model, which is tailored to the unique characteristics of groundwater, fractures, and interlayers. Concurrently, the TFFSeg model exhibits significantly enhanced performance for these rock features compared to other widely employed Computer vision methods. Subsequently, this multi-source dataset is further enriched by incorporating rock physical and mechanical parameters as well as tunnel design parameters. Nevertheless, the issue of data incompleteness persists within this dataset. To achieve precise prediction of the weathering degree based on this incomplete dataset, a novel Tree-augmented Bayesian network (TAN-BN) is designed, which is capable of learning from incomplete datasets. The predictive outcomes demonstrate that the proposed TAN-BN surpasses other currently utilized meta models and ensemble models, such as ANN, GBRT, and Naive BN. Finally, sensitivity analysis is conducted to determine the importance rankings of the 10 parameters, offering valuable insights for on-site evaluation of the rock weathering degree at the tunnel face.

Deep Learning Empowered Water Quality Assessment: Leveraging IoT Sensor Data with LSTM Models and Interpretability Techniques

Addressing the imperative demand for accurate water quality assessment, this paper delves into the application of deep learning techniques, specifically leveraging IoT sensor datasets for the classification and prediction of water quality parameters. The utilization of LSTM (Long Short-Term Memory) models navigates the intricacies inherent in environmental data, emphasizing the balance between model accuracy and interpretability. This equilibrium is achieved through the deployment of interpretability methods such as LIME, SHAP, Anchor, and LORE. Additionally, the incorporation of advanced parameter optimization techniques focuses on fine-tuning essential parameters like learning rates, batch sizes, and epochs to optimize model performance. This comprehensive approach ensures not only precise predictions but also enhances the transparency and interpretability of the model, addressing the critical need for actionable information in water quality management. The research significantly contributes to the convergence of deep learning, IoT, and environmental science, offering valuable tools for informed decision-making while highlighting the importance of fine-tuning parameters for optimal model performance

Genes in context: path to more precise risk prediction in psychiatry?

This guest editorial describes the importance of converging genetics and psychosocial epidemiology research methods to understand the biopsychosocial etiology of psychiatric phenotypes.

Optimized Machine Learning Model for Predicting Compressive Strength of Alkali-Activated Concrete Through Multi-Faceted Comparative Analysis

Alkali-activated concrete (AAC), produced from industrial by-products like fly ash and slag, offers a promising alternative to traditional Portland cement concrete by significantly reducing carbon emissions. Yet, the inherent variability in AAC formulations presents a challenge for accurately predicting its compressive strength using conventional approaches. To address this, we leverage machine learning (ML) techniques, which enable more precise strength predictions based on a combination of material properties and cement mix design parameters. In this study, we curated an extensive dataset comprising 1756 unique AAC mixtures to support robust ML-based modeling. Four distinct input variable schemes were devised to identify the optimal predictor set, and a comparative analysis was performed to evaluate their effectiveness. After this, we investigated the performance of several popular ML algorithms, including random forest (RF), adaptive boosting (AdaBoost), gradient boosting regression trees (GBRTs), and extreme gradient boosting (XGBoost). Among these, the XGBoost model consistently outperformed its counterparts. To further enhance the predictive accuracy of the XGBoost model, we applied four state-of-the-art optimization techniques: the Gray Wolf Optimizer (GWO), Whale Optimization Algorithm (WOA), beetle antennae search (BAS), and Bayesian optimization (BO). The optimized XGBoost model delivered superior performance, achieving a remarkable coefficient of determination (R2) of 0.99 on the training set and 0.94 across the entire dataset. Finally, we employed SHapely Additive exPlanations (SHAP) to imbue the optimized model with interpretability, enabling deeper insights into the complex relationships governing AAC formulations. Through the lens of ML, we highlight the benefits of the multi-faceted synergistic approach for AAC strength prediction, which combines careful input parameter selection, optimal hyperparameter tuning, and enhanced model interpretability. This integrated strategy improves both the robustness and scalability of the model, offering a clear and reliable prediction of AAC performance.

Data-Efficient Dimensionality Reduction and Surrogate Modeling of High-Dimensional Stress Fields

Abstract Tensor datatypes representing field variables like stress, displacement, velocity, etc., have increasingly become a common occurrence in data-driven modeling and analysis of simulations. Numerous methods [such as convolutional neural networks (CNNs)] exist to address the meta-modeling of field data from simulations. As the complexity of the simulation increases, so does the cost of acquisition, leading to limited data scenarios. Modeling of tensor datatypes under limited data scenarios remains a hindrance for engineering applications. In this article, we introduce a direct image-to-image modeling framework of convolutional autoencoders enhanced by information bottleneck loss function to tackle the tensor data types with limited data. The information bottleneck method penalizes the nuisance information in the latent space while maximizing relevant information making it robust for limited data scenarios. The entire neural network framework is further combined with robust hyperparameter optimization. We perform numerical studies to compare the predictive performance of the proposed method with a dimensionality reduction-based surrogate modeling framework on a representative linear elastic ellipsoidal void problem with uniaxial loading. The data structure focuses on the low-data regime (fewer than 100 data points) and includes the parameterized geometry of the ellipsoidal void as the input and the predicted stress field as the output. The results of the numerical studies show that the information bottleneck approach yields improved overall accuracy and more precise prediction of the extremes of the stress field. Additionally, an in-depth analysis is carried out to elucidate the information compression behavior of the proposed framework.

A study on hyperspectral soil total nitrogen inversion using a hybrid deep learning model CBiResNet-BiLSTM

Rapid, accurate and non-destructive acquisition of soil total nitrogen (TN) content in the black soil zone is significant for achieving precise fertilization. In this study, the soil types of corn and soybean fields in Jilin Agricultural University, China, were selected as the study area. A total of 162 soil samples were collected using a five-point mixed sampling method. Then, spectral data were obtained and the noisy edge were initially eliminated. Subsequently, the denoised spectral data underwent smoothing by using the Savitzky–Golay (SG) method. After performing the first-order difference (FD) and second-order difference (SD) transformations on the data, it was input to the model. In this study, a hybrid deep learning model, CBiResNet-BiLSTM, was designed for precise prediction of soil TN content. This model was optimized based on ResNet34, and its capabilities were enhanced by incorporating CBAM in the residual module to facilitate additional eigenvalue extraction. Also, Bidirectional Long Short-Term Memory (BiLSTM) was integrated to enhance model accuracy. Besides, partial least squares regression (PLSR), random forest regression (RFR), support vector machine regression (SVR), and back propagation neural network (BP), as well as ResNet(18, 34, 50, 101, 152) models were taken for comparative experiments. The results indicated that the traditional machine learning model PLSR achieved good performance, with R2 of 0.883, and the hybrid deep learning model CBiResNet-BiLSTM had the best inversion capability with R2 of 0.937, with the R2 being improved by 5.4%, compared with the PLSR model. On this basis, we present the LUCAS dataset to demonstrate the generalisability of the model. Therefore, the CBiResNet-BiLSTM model is a fast and feasible hyperspectral estimation method for soil TN content.Graphical abstract