Search

Acute psychological stress (APS) is a complex and multifactorial phenomenon that affects metabolism, necessitating real-time detection and interventions to mitigate its effects on glycemia in people with type 1 diabetes. This study investigates the detection of APS using physiological variables measured by the Empatica E4 wristband and employs explainable machine learning to evaluate the importance of the physiological signals. The extreme gradient boosting model is developed for classification of APS and non-stress (NS) with weighted training, achieving an overall accuracy of 99.93%. The Shapley additive explanations (SHAP) technique is employed to interpret the global importance of the physiological signals, determining the order of importance for the variables from most to least as galvanic skin response (GSR), heart rate (HR), skin temperature (ST), and motion sensors (accelerometer readings). The increase in GSR and HR are positively correlated with the occurrence of APS as indicated by high positive SHAP values. The SHAP technique is also used to explain the local signal importance for particular instances of misclassified samples. The detection of APS can inform multivariable automated insulin delivery systems to intervene to counteract the APS-induced glycemic excursions in people with type 1 diabetes.

Summary: Precise estimation of the shear strength of concrete‐filled steel tubes (CFSTs) is a crucial requirement for the design of these members. The existing design codes and empirical equations are inconsistent in predicting the shear strength of these members. This paper provides a data‐driven approach for the shear strength estimation of circular CFSTs. For this purpose, the authors evaluated and compared the performance of nine machine learning (ML) methods, namely linear regression, decision tree (DT), k‐nearest neighbors (KNN), support vector regression (SVR), random forest (RF), bagging regression (BR), adaptive boosting (AdaBoost), gradient boosting regression tree (GBRT), and extreme gradient boosting (XGBoost) in estimating the shear strength of CFSTs on an experimental database compiled from the results of 230 shear tests on CFSTs in the literature. For each model, hyperparameter tuning was performed by conducting a grid search in combination with k‐fold cross‐validation (CV). Comparing the nine methods in terms of several performance measures showed that the XGBoost model was the most accurate in predicting the shear strength of CFSTs. This model also showed superior accuracy in predicting the shear strength of CFSTs when compared to the formulas provided in design codes and the existing empirical equations. The Shapley Additive exPlanations (SHAP) technique was also used to interpret the results of the XGBoost model. Using SHAP, the features with the greatest impact on the shear strength of CFSTs were found to be the cross‐sectional area of the steel tube, the axial load ratio, and the shear span ratio, in that order. [ABSTRACT FROM AUTHOR]

Aims: Heart failure with reduced ejection fraction (HFrEF) poses significant challenges for clinicians and researchers, owing to its multifaceted aetiology and complex treatment regimens. In light of this, artificial intelligence methods offer an innovative approach to identifying relationships within complex clinical datasets. Our study aims to explore the potential for machine learning algorithms to provide deeper insights into datasets of HFrEF patients. Methods: To this end, we analysed a cohort of 386 HFrEF patients who had been initiated on sodium‐glucose co‐transporter‐2 inhibitor treatment and had completed a minimum of a 6‐month follow‐up. Results: In traditional frequentist statistical analyses, patients receiving the highest doses of beta‐blockers (BBs) (chi‐square test, P =.036) and those newly initiated on sacubitril‐valsartan (chi‐square test, P =.023) showed better outcomes. However, none of these pharmacological features stood out as independent predictors of improved outcomes in the Cox proportional hazards model. In contrast, when employing eXtreme Gradient Boosting (XGBoost) algorithms in conjunction with the data using Shapley additive explanations (SHAP), we identified several models with significant predictive power. The XGBoost algorithm inherently accommodates non‐linear distribution, multicollinearity and confounding. Within this framework, pharmacological categories like 'newly initiated treatment with sacubitril/valsartan' and 'BB dose escalation' emerged as strong predictors of long‐term outcomes. Conclusions: In this manuscript, we not only emphasize the strengths of this machine learning approach but also discuss its potential limitations and the risk of identifying statistically significant yet clinically irrelevant predictors. [ABSTRACT FROM AUTHOR]

The tomato as a raw material for processing is globally important and is pivotal in dietary and agronomic research due to its nutritional, economic, and health significance. This study explored the potential of machine learning (ML) for predicting tomato quality, utilizing data from 48 cultivars and 28 locations in Hungary over 5 seasons. It focused on °Brix, lycopene content, and colour (a/b ratio) using extreme gradient boosting (XGBoost) and artificial neural network (ANN) models. The results revealed that XGBoost consistently outperformed ANN, achieving high accuracy in predicting °Brix (R² = 0.98, RMSE = 0.07) and lycopene content (R² = 0.87, RMSE = 0.61), and excelling in colour prediction (a/b ratio) with a R² of 0.93 and RMSE of 0.03. ANN lagged behind particularly in colour prediction, showing a negative R² value of −0.35. Shapley additive explanation's (SHAP) summary plot analysis indicated that both models are effective in predicting °Brix and lycopene content in tomatoes, highlighting different aspects of the data. SHAP analysis highlighted the models' efficiency (especially in °Brix and lycopene predictions) and underscored the significant influence of cultivar choice and environmental factors like climate and soil. These findings emphasize the importance of selecting and fine-tuning the appropriate ML model for enhancing precision agriculture, underlining XGBoost's superiority in handling complex agronomic data for quality assessment. [ABSTRACT FROM AUTHOR]

Objectives: Radiomics‐based eXtreme gradient boosting (XGBoost) model was developed to differentiate benign thyroid nodules from malignant thyroid nodules and to prevent unnecessary thyroid biopsies, including positive and negative effects. Methods: The study evaluated a data set of ultrasound images of thyroid nodules in patients retrospectively, who initially received ultrasound‐guided fine‐needle aspiration biopsy (FNAB) for diagnostic purposes. According to ACR TI‐RADS, a total of five ultrasound feature categories and the maximum size of the nodule were determined by four radiologists. A radiomics score was developed by the LASSO algorithm from the ultrasound‐based radiomics features. An interpretative method based on Shapley additive explanation (SHAP) was developed. XGBoost was compared with ACR TI‐RADS for its diagnostic performance and FNAB rate and was compared with six other machine learning models to evaluate the model performance. Results: Finally, 191 thyroid nodules were examined from 177 patients. The radiomics score were calculated using 8 features, which were selected among 789 candidate features generated from the ultrasound images. The model yielded an AUC of 93% in the training cohort and 92% in the test cohort. It outperformed traditional machine learning models in assessing the nature of thyroid nodules. Compared with ACR TI‐RADS, the FNAB rate decreased from 34% to 30% in training and from 35% to 41% in test. Conclusions: The radiomics‐based XGBoost model proposed could distinguish benign and malignant thyroid nodules, thereby reduced significantly the number of unnecessary FNAB. It was effective in making preoperative decisions and managing selected patients using the SHAP visual interpretation tools. [ABSTRACT FROM AUTHOR]

The active ingredient group is a prominent feature reflecting the inherent characteristics of plant-based functional foods. Chinese hawthorn leaf (CHL), a tea substitute possessing intrinsic nutritional properties in anti-hyperlipidemia, was first found to be adulterated with Malus doumeri leaf (MDL) owing to similar commercial labels. In this context, the above-mentioned two contrasting species were explored through phytochemical profiling and activity assessment. The amelioration effect of CHL on free fatty acids-elicited lipid deposition in HepG2 cells was significantly better than that of MDL. Molecular networking-based metabolic profiles identified 68 and 67 components in CHL and MDL, with 33 shared components. Extreme gradient boosting (XGBoost) algorithm with outstanding performance was selected to screen candidate components contributing to hypolipidemic activity, and the output was later interpreted by Shapley additive explanations (SHAP) method. Twelve and eight components were separately screened as hyperlipidemic inhibitors in CHL and MDL, while only four constituents were shared. The bioactivity evaluation of selected ingredients and combinations further confirmed their anti-hyperlipidemia capacity. These findings emphasized the feasibility of filtering bioactivity-related compounds using interpretable machine learning approaches and illustrated that related species may contain different hypolipidemic contributors, even if shared constituents existed. [ABSTRACT FROM AUTHOR]

Eco-friendly concrete is in great demand, and as a consequence, the necessity to find sustainable alternatives to ordinary cement has become critical. In recent years, there has been considerable interest in the potential benefits of utilizing rice husk ash (RHA) as a cement substitute in concrete. Evaluating concrete properties in a laboratory setup like compressive strength (CS) is a time-consuming and expensive process. The development of trustworthy and precise models for CS estimation might be a better strategy. To determine the CS of RHA concrete, this research used boosting ensemble algorithms, namely gradient boosting (GB), AdaBoost regressor (ABR), and extreme gradient boosting (XGB), over a vast literature database. The estimation models were validated using statistical measures, error distribution by plotting violin graphs, and k-fold analysis. Furthermore, SHapley Additive exPlanations (SHAP) analysis was utilized to assess the importance of contributing elements. The results showed that XGB had the greatest performance in estimating the CS of RHA concrete out of the three methods tested. While the GB and ABR models both had R2 values of 0.90 and 0.94, respectively, the XGB model achieved a value of 0.96. The violin graphs indicated that the average absolute error values for the GB, ABR, and XGB were 5.82, 4.65, and 3.53 MPa, implying the higher precision of the XGB model in estimating the CS of RHA concrete. The SHAP study demonstrated that the three most influential factors in increasing the strength were cement, specimen age, and rice husk ash. The construction sector may benefit from the application of such technologies by facilitating the development of quick and low-cost methods for identifying material qualities and the influence of input parameters.

The tomato as a raw material for processing is globally important and is pivotal in dietary and agronomic research due to its nutritional, economic, and health significance. This study explored the potential of machine learning (ML) for predicting tomato quality, utilizing data from 48 cultivars and 28 locations in Hungary over 5 seasons. It focused on °Brix, lycopene content, and colour (a/b ratio) using extreme gradient boosting (XGBoost) and artificial neural network (ANN) models. The results revealed that XGBoost consistently outperformed ANN, achieving high accuracy in predicting °Brix (R² = 0.98, RMSE = 0.07) and lycopene content (R² = 0.87, RMSE = 0.61), and excelling in colour prediction (a/b ratio) with a R² of 0.93 and RMSE of 0.03. ANN lagged behind particularly in colour prediction, showing a negative R² value of −0.35. Shapley additive explanation’s (SHAP) summary plot analysis indicated that both models are effective in predicting °Brix and lycopene content in tomatoes, highlighting different aspects of the data. SHAP analysis highlighted the models’ efficiency (especially in °Brix and lycopene predictions) and underscored the significant influence of cultivar choice and environmental factors like climate and soil. These findings emphasize the importance of selecting and fine-tuning the appropriate ML model for enhancing precision agriculture, underlining XGBoost’s superiority in handling complex agronomic data for quality assessment.

Liver cirrhosis is a terminal pathological result of chronic liver damage, illicit drugs, hepatotoxicity, and non-alcoholic steatohepatitis. Assessment of liver cirrhosis via non-invasive methods in order to circumvent the limitations of liver biopsy. This research builds upon the growing body of knowledge in liver cirrhosis assessment by examining a dataset comprising cases of primary biliary cirrhosis. Prior research has primarily concentrated on comparative analyses and development of machine learning models integrating imaging modalities such as ultrasound, magnetic resonance imaging (MRI), and elastography, with limited focus on serum biomarkers. This research endeavors to address the neglected aspects of liver cirrhosis assessment by leveraging Explainable AI algorithm to bridge the gap between AI models and human comprehension via providing insights into the intricate decision-making process of the proposed machine learning model, thus enhancing transparency and trustworthiness. This novel approach aims to overcome the limitations of previous works and contribute to improved liver cirrhosis diagnosis.

The use of machine learning (ML) models for streamflow forecasting has recently proved highly successful. However, ML is typically criticized for a lack of interpretability. Here, we develop an interpretable ML model for 1-month-ahead streamflow forecasting using extreme gradient boosting (XGBoost) and Shapley additive explanations (SHAP). In addition to a performance evaluation of XGBoost compared to regression tree and random forest approaches, the effects of input variables, including local weather, streamflow lag, and global climate, on streamflow were interpreted in terms of SHAP total effect values, main effect values, interaction values, and loss values. The experimental results at two catchments in the contiguous USA are significant in four ways. First, XGBoost was superior to the other two models in terms of Nash–Sutcliffe efficiency, mean absolute error, root mean square error, and correlation coefficient. Second, by aggregating SHAP values, we found that the contributions of these variables to streamflow differed according to the investigated local perspectives, including streamflow at different months, low streamflow, medium streamflow, high streamflow, and peak streamflow. Third, the SHAP main effect and interaction values revealed that nonmonotonic relationships may occur between the input variables and streamflow, and the strength of variable interaction effects might be related to the variable values rather than their correlations. Fourth, variable drifts in the testing set were deduced from SHAP loss values. These findings exhibit positive significance for understanding ML for monthly streamflow forecasting. [ABSTRACT FROM AUTHOR]

Abstract The stable operation of strip rolling mill is the key factor to ensure the stability of product quality. The design capability of existing domestic imported and self-developed strip rolling mills cannot be fully developed, and the frequent occurrence of mill vibration and operation instability problems seriously restrict the equipment capacity and the production of high-end strip products. The vibration prediction analysis method for hot strip mill based on eXtreme gradient boosting (XGBoost) and Bayesian optimization (BO) is proposed. First, an XGBoost prediction model is developed based on a self-built data set to construct a complex functional relationship between process parameters and rolling mill vibration. Second, the important hyperparameters and parameters of XGBoost are optimized using Bayesian optimization algorithm to improve the prediction accuracy, computational efficiency, and stability of the model. Third, a comprehensive comparison is made between the prediction model in this paper and other well-known machine learning benchmark models. Finally, the prediction results of the model are interpreted using the SHapley Additive exPlanations (SHAP) method. The proposed model outperforms existing models in terms of prediction accuracy, computational speed and stability. At the same time, the degree of influence of each feature on rolling mill vibration is also obtained.

The stable operation of strip rolling mill is the key factor to ensure the stability of product quality. The design capability of existing domestic imported and self-developed strip rolling mills cannot be fully developed, and the frequent occurrence of mill vibration and operation instability problems seriously restrict the equipment capacity and the production of high-end strip products. The vibration prediction analysis method for hot strip mill based on eXtreme gradient boosting (XGBoost) and Bayesian optimization (BO) is proposed. First, an XGBoost prediction model is developed based on a self-built data set to construct a complex functional relationship between process parameters and rolling mill vibration. Second, the important hyperparameters and parameters of XGBoost are optimized using Bayesian optimization algorithm to improve the prediction accuracy, computational efficiency, and stability of the model. Third, a comprehensive comparison is made between the prediction model in this paper and other well-known machine learning benchmark models. Finally, the prediction results of the model are interpreted using the SHapley Additive exPlanations (SHAP) method. The proposed model outperforms existing models in terms of prediction accuracy, computational speed and stability. At the same time, the degree of influence of each feature on rolling mill vibration is also obtained. [ABSTRACT FROM AUTHOR]

Scouring at bridge piers is a crucial issue that risks bridge collapses, causing economic losses and endangering public safety. Classic models struggle to accurately estimate equilibrium scour depth (d se) due to the complex scouring mechanism. This study combines Bayesian optimization (BO) with support vector machine (SVM) and extreme gradient boosting (XGBoost) to improve d se estimates. These models predict d se around round-nosed, square, and sharp-nosed bridge piers using field and laboratory data. The results demonstrate that the BO algorithm can effectively optimize the hyperparameters of SVM and XGBoost and ameliorate their d se estimates. For the square, sharp-nosed, and round-nosed piers, BO–XGBoost achieves the lowest mean absolute error (MAE) of 0.37 m, 0.35 m, and 0.36 m, the lowest root mean square error (RMSE) of 0.52 m, 0.60 m, and 0.56 m, and the highest coefficient of determination (R2) of 0.85, 0.80, and 0.84, respectively. Accurate estimation of d se is essential to balance safety and affordability of the bridge designs. Underestimating d se can lead to bridge failure, posing significant safety risks. Conversely, overestimating d se can result in unnecessary construction expenses. Finally, the impact of independent variables on d se estimates is analyzed using Shapley additive explanations (SHAP). • Traditional models struggle with accurate equilibrium scour depth (d se) predictions due to complex scouring mechanisms. • Bayesian optimization combined with SVM and XGBoost improves d se estimation accuracy. • Models predict d se for round, square, and sharp-nosed piers using field and lab data. • BO–XGBoost demonstrated the most accurate results with low MAE and RMSE and high R2 for various pier shapes. • SHAP analysis reveals the impact of different variables on d se estimates. [ABSTRACT FROM AUTHOR]

This study proposes a machine learning-driven approach for the analysis of the feature importance of seismic parameters on tunnel damage and seismic fragility prediction. The Incremental Dynamic Analysis (IDA) method serves as the fundamental database for vulnerability analysis. Strength and deformation yield criteria are chosen to comprehensively assess the impact of different seismic parameters on the vulnerability of tunnels to seismic events. Three machine learning algorithms, namely Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Machine (SVM), are utilized to develop models for classifying and regressing tunnel damage under seismic conditions. Following parameter tuning, the models' performance in multi-classification, binary classification, and regression prediction is assessed, with XGBoost and RF models exhibiting outstanding performance. Feature importance analysis of seismic parameters in XGBoost and RF models for multi-classification, binary classification, and regression is performed using Shapley additive explanations (SHAP). The correlation analysis between SHAP-based feature values and predictions reveals that Peak Ground Displacement (PGD) has the highest influence in the regression model. Utilizing the interaction dependencies among crucial features in the regression model, fragility curves for tunnels based on these key features are effectively derived. The predicted fragility curves closely align with those derived from IDA, illustrating the time-saving and high-performance capabilities of machine learning in nonlinear dynamic computations. [ABSTRACT FROM AUTHOR]

Machine learning techniques provide an effective and cost-efficient solution for estimating solar radiation for solar energy utilization. However, the reported machine learning-based solar radiation models fail to offer comprehensive explanations for their outputs. Therefore, this study aims to tackle this issue by developing machine learning models that are both accurate and interpretable. To achieve the objective, this study evaluated the performance of tree-based ensemble algorithms, using optimized combinations of model input parameters for different climate zones in China. The results showed that the extreme gradient boosting (XGBoost) models demonstrated the highest overall accuracy, model stability, and generalization ability. At the national scale, the developed XGBoost models yielded an average R2, MAE, and RMSE of 0.939, 1.226 MJ/m2, and 1.663 MJ/m2, respectively, showing significant improvements of 2.13–27.78% in RMSE compared to recently reported models. Most importantly, the state-of-the-art SHapley Additive exPlanations (SHAP) technique was integrated with the developed XGBoost models to enhance model interpretability in terms of global and local feature importance, as well as the interaction effects between model features. The results of the SHAP value analysis demonstrated the robustness of sunshine duration in modeling global solar radiation, revealing thresholds where its values undergo a shift from negative to positive effects on model output. SHAP interaction values illustrated the interaction effects among features in the developed solar radiation model, uncovering the model's complex non-linear relationships. Additionally, this study provided explanations for individual instances based on the SHAP method. Overall, this study provided an accurate, reliable, and transparent machine learning model and an enlightening framework for modeling global solar radiation at sites without observations. • An interpretable framework is proposed using tree-based ensemble models and SHAP. • More accurate and explanatory models are developed for solar radiation estimation. • XGBoost achieves the highest averaged model precision and generalization ability. • XGBoost models are interpreted based on global and local feature SHAP values. • Elucidation of interaction effects between solar radiation model features. [ABSTRACT FROM AUTHOR]

[Display omitted] • KGCatboost outperforms other benchmark models from multiple datasets. • The favorable multi-step ahead prediction capability of the KGCatboost model is verified. • The conclusions derived from explainable artificial intelligence (XAI) align with the actual physics laws. • pH and water temperature have the most significant impact on dissolved oxygen concentration. • A regulation mechanism is applied to alleviate the disasters caused by low dissolved oxygen concentration. Accurate water quality prediction is crucial for effective environmental management and decision-making. However, previous studies have solely relied on historical data to simulate water quality, overlooking the potential discrepancies between predicted values and actual observations. Additionally, the opacity of machine learning models has posed challenges to the credibility of their predictions. Hence, considering the excellent nonlinear fitting ability of ensemble tree models, especially the Categorical Boosting (Catboost) model, this study proposes a knowledge-guided Catboost (KGCatboost) model for predicting the dissolved oxygen concentration, one of the vital water quality indicators, in 15 river sections of the Yangtze River Basin in Yunnan Province, China. Furthermore, to enhance the model's interpretability, we employ the SHapley Additive exPlanations (SHAP) method to analyze the contributions of each input variable within the water body. The results demonstrate that on the test set of each dataset, the mean Nash-Sutcliffe Efficiency (NSE) value of KGCatboost is 0.874, which has improved by 0.34% and 3.07% compared to Catboost and eXtreme Gradient Boosting (Xgboost). In addition, this study reveals that pH has the most significant impact on DO concentrations. Specifically, as the pH increased, the DO concentration increased significantly. A regulatory mechanism has also been developed to alleviate the hazards caused by low DO concentrations. The KGCatboost model can provide valuable guidance for water resource management processes. [ABSTRACT FROM AUTHOR]

Developing fuel resources is strategically crucial for Armenia. Far more than any other fossil fuel resource, coal roughly generates half the nation’s electricity. Although coal could play a critical role, no vast data is available about Armenia coal properties. Using robust modeling of energy indexes such as coal gross calorific value (GCV) by considering trivial existing datasets could be an essential clue for ensuring sustainable development. For the first time, this investigation is going to model GCV for Armenia coal samples. For this purpose, SHAP (SHapley Additive exPlanations) as a novel explainable artificial intelligence will be introduced. SHAP enables understanding the magnitude of relationships between each individual input record and its representative output and ranks input variables based on their effectiveness. SHAP was coupled by extreme gradient boosting (xgboost) as the most recently generated powerful predictive machine learning tool (SHAP-Xgboost). SHAP-Xgboost could accurately (R2=0.99) model GCV based on proximate and ultimate variables of Armenia coal samples. These significant outcomes open a new window for developing high interpretability models to assess coal properties and pinpoint the influential parameters.

Background and Aim: Risk stratification beyond the endoscopic classification of esophageal varices (EVs) to predict first episode of variceal bleeding (VB) is currently limited in patients with compensated advanced chronic liver disease (cACLD). We aimed to assess if machine learning (ML) could be used for predicting future VB more accurately. Methods: In this retrospective analysis, data from patients of cACLD with EVs, laboratory parameters and liver stiffness measurement (LSM) were used to generate an extreme‐gradient boosting (XGBoost) algorithm to predict the risk of VB. The performance characteristics of ML and endoscopic classification were compared in internal and external validation cohorts. Bleeding rates were estimated in subgroups identified upon risk stratification with combination of model and endoscopic classification. Results: Eight hundred twenty‐eight patients of cACLD with EVs, predominantly related to non‐alcoholic fatty liver disease (28.6%), alcohol (23.7%) and hepatitis B (23.1%) were included, with 455 (55%) having the high‐risk varices. Over a median follow‐up of 24 (12–43) months, 163 patients developed VB. The accuracy of machine learning (ML) based model to predict future VB was 98.7 (97.4–99.5)%, 93.7 (88.8–97.2)%, and 85.7 (82.1–90.5)% in derivation (n = 497), internal validation (n = 149), and external validation (n = 182) cohorts, respectively, which was better than endoscopic classification [58.9 (55.5–62.3)%] alone. Patients stratified high risk on both endoscopy and model had 1‐year and 3‐year bleeding rates of 31–43% and 64–85%, respectively, whereas those stratified as low risk on both had 1‐year and 3‐year bleeding rates of 0–1.6% and 0–3.4%, respectively. Endoscopic classification and LSM were the major determinants of model's performance. Conclusion: Application of ML model improved the performance of endoscopic stratification to predict VB in patients with cACLD with EVs. [ABSTRACT FROM AUTHOR]

This study merges macroscale and microscale analyses with interpretable machine learning (ML) algorithm to explore the effect of particle size distribution (PSD) on the small-strain shear modulus (G 0) of gap-graded granular mixtures. For this purpose, a database containing 610 groups of data samples was generated by conducting numerical triaxial compression simulations using the discrete element method (DEM). The simulations were carried out using the well-recognized DEM program PFC3D. The influence of isotropic confining pressure (p ′), void ratio (e), non-plastic fines content (FC), particle size ratio (R d), particle size ratio of coarse particles (D max / D min) and particle size ratio of fine particles (d max / d min) on the G 0 were discussed in detail. Furthermore, the eXtreme Gradient Boosting (XGBoost) algorithm was utilized, and it was enhanced through a hyperparameter tuning process known as Bayesian optimization (BO) to improve the predictive accuracy of G 0 model. Finally, the predictive outcomes of the BO-XGBoost model were interpreted using the SHapley Additive exPlanations (SHAP) method, addressing the technical gap associated with the lack of interpretability in ML models. Meanwhile, the local and global feature variable importance in nonlinear models was also elucidated to provide intuitive insight for the user. The analysis demonstrates that the outcomes from both macroscale and microscale assessments correlate well with the findings obtained through the BO-XGBoost-SHAP approach, facilitating the incorporation of ML model predictions into decision-making processes. • The effects of FC and R d on the G 0 were investigated by adopting DEM. • Numerical results show that FC and R d have a coupled effect on the G 0. • A G 0 predictive model based on BO-XGBoost algorithm was established and validated. • The outcomes of the predictive model were interpreted using the SHAP method. [ABSTRACT FROM AUTHOR]

Long-term exposure to geogenic arsenic (As)-contaminated groundwater poses a severe threat to public health problems. Generally, elevated As concentrations have been observed with high amounts of ammonium in groundwater of floodplains. An extreme gradient boosting algorithm was conducted to develop a probability model based on hydrogeochemical data, which predicted the occurrence rates of groundwater As on a regional scale. Results showed that concentrations of NH 4 +, Eh, K, Cl−, SO 4 2−, and NO 3 − were powerful predictive variables of As exposure. The model revealed the co-enrichment of As with NH 4 +, suggesting that the mineralization of nitrogen-containing organic matter promoted the reduction of As-bearing iron-oxides. The predicted distribution of high-As groundwater showed high consistency with known spatial distribution of As contamination, and the model also accurately predicted As concentrations in Jiangbei Plain of China and typical As-affected floodplains of Southeast Asia. The model can serve as a low-cost and rapid virtual sensor for detecting As concentrations in private or newly drilled wells, thereby providing critical information for informed management decisions, environmental protection and public health safety. [Display omitted] • A XGB model to predict groundwater arsenic contamination risk in floodplains. • The co-enrichment of As with NH 4 + as a key factor influencing As concentrations. • The model demonstrates robust transferability across various floodplains. [ABSTRACT FROM AUTHOR]

We apply explainable artificial intelligence (xAI) to a large dataset of global equity funds. Our approach combines the XGBoost model with Shapley values; the former is a machine learning framework that enhances model fitness while the latter is an xAI method that provides informed explanations regarding the direction and significance of predictors. Based on macro-finance and fund-level factors, our fund performance evaluation of G10 countries uncovers novel insights into the diversification of country portfolios: both over- and under-diversification are associated with poor performance. Our analysis establishes consistency through a benchmark linear regression model and robustness at country level. • Non-linear machine learning models and xAI improve fund performance analysis. • First xAI study to examine the influence of HHI on fund performance. • xAI shows over/under-diversification on portfolios is associated with underperformance. • Results are robust across countries. [ABSTRACT FROM AUTHOR]

Hypereutrophy of water bodies is an undesirable phenomenon due to the influence of a complex of environmental factors. The aim of the work was to predict the responsibility of environmental factors in changing water quality from eutrophic to hypereutrophic states. Hypereutrophy was defined as exceeding the concentration of chlorophyll a of 56 μg/L according to the Trophic State Index (TSI). The study was conducted on the Vistula Lagoon in the southern Baltic Sea. The work was carried out using the prediction and explanation ensemble XGBoost with SHAP modelling. On the global scale of the whole basin and at local sites, the importance of a number of physicochemical, nutritional and phytoplankton factors for hypereutrophy was calculated using mean Shapley values. High concentrations of organic carbon and nitrogen forms and, to a lesser extent, high water temperature mainly caused hypereutrophy. In the case of cyanobacterial biomass, the strong effect of low values of this factor maintains the eutrophic state more stable than higher values maintain hypereutrophy. XGBoost- SHAP modelling as an explanatory tool for the interpretation of water monitoring results can be useful for better management of coastal and inland waters. [Display omitted] • Resposibility of factors for water state change to hypereutrophy was modelled. • Case study was located on Vistula Lagoon in the southern Baltic Sea. • Predictive and explanatory ensemble XGBoost with SHAP modelling were used. • Importance of factors for hypereutrophy was calculated using mean Shapley values. • High concentrations of carbon and nitrogen organic forms mainly caused hypereutrophy. [ABSTRACT FROM AUTHOR]

• The constructed eXtreme gradient boosting model could individually assess central cervical lymph node metastasis in patients with papillary thyroid carcinoma. • SHapley Additive exPlanations provided a rational explanation for predicting central cervical lymph node metastasis, including positive and negative effects. • Due to visualization advantages, the prediction performance of the eXtreme gradient boosting model was better than traditional machine-learning models. Central cervical lymph node metastasis (CLNM) is considered a risk factor for recurrence in patients with papillary thyroid carcinoma (PTC). Traditional machine learning models suffered from "black-box" problems, which could not exactly explain the interactive effects of the risk factors. We aimed to develop an eXtreme Gradient Boosting (XGBoost) model to assess CLNM, including positive and negative effects. 1,122 patients with PTC admitted at Tianjin First Central Hospital from 2016 to 2020 were retrospectively selected. They were randomly divided into the training and test datasets with an 8:2 ratio. 108 patients with PTC admitted at Binzhou Medical University Hospital in 2020 served as the validation dataset. The XGBoost model was used to assess CLNM. The 10-fold cross-validation was utilized for model selection, and the metric used to evaluate classification performance was the average area under the curve (AUC) of 10-fold cross-validation. Interpretation and transparency of the "black-box" problem were performed. SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanation (LIME) were used to ensure the stability and reliability of the model. The XGBoost model based on ultrasound and dual-energy computed tomography images of the solitary primary lesion had an excellent performance for assessing CLNM, with average AUCs of 0.918, 0.903, and 0.881 in the training, test, and validation datasets, respectively. SHAP plots showed the influence of each parameter on the XGBoost model, including positive (i.e., capsular invasion, diameter, iodine concentration in the venous phase, and calcification) and negative (i.e., sex and age) impacts. For all cases, the capsular invasion prediction weight was the highest; for individual cases, different predictors were assigned different weights. Moreover, the performance of the XGBoost model was better than classical machine-learning models. This study developed and validated an XGBoost model for assessing CLNM in patients with PTC. The ability to visually interpret the positive and negative effects made the XGBoost model an effective tool for guiding clinical treatment. [Display omitted] [ABSTRACT FROM AUTHOR]

• Eight machine learning models were used to predict damage-state of steel frames. • Performance of eight machine learning models was examined and compared. • Synthetic minority oversampling technique was used to resolve imbalance of dataset. • Effects of input variables were explored using Shapley additive explanations. • The graphical user interface was created for easy access of practical engineers. The damage state assessment of buildings after an earthquake is an essential and urgent task that typically requires significant manpower and time for the resilience of a city-scale society. This study aims to develop machine learning (ML) models for the rapid seismic damage-state assessment of steel moment frames, which was never tried before to the authors' knowledge. Eight ML models were examined for this purpose, including K-nearest neighbors, naïve Bayes, decision tree, random forest (RF), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), light gradient boosting, and category boosting. The combination of 468 steel moment frames from the database in DesignSafe cyberinfrastructure and 240 ground motions yielded a total of 112,320 data points. The steel moment frames have a wide variety of geometric configurations (e.g., number of stories from 1 to 19, number of bays from 1 to 5, bay width from 6.1 to 12.19 m), and applied loads (i.e., three cases of dead load and two cases of live load). Nonlinear time history analyses were conducted using OpenSees to produce a comprehensive dataset for the training and testing of the ML models. A reliable procedure to define the damage states of steel moment frames was suggested based on pushover analysis. Damage states of steel moment frames were categorized following the tag definitions (i.e., green, yellow, and red) in ATC-20. Spectral accelerations at five selected periods (1, 2, 3, 4, and 5 s) for the given ground motions and at the first three natural periods of the steel frames were used as input variables for the ML models. From the results, the RF model is suggested for the prediction of the seismic damage states of steel moment frames. The RF model could accurately predict 98% of the assigned tags in the testing dataset. In contrast, the AdaBoost (88%) and naïve Bayes (90%) models displayed the lowest performance. Among the four boosting methods considered, the XGBoost model (97%) exhibited the highest performance. Furthermore, Shapley additive explanations (SHAP) method was used to inspect the importance of input variables on the prediction. It was found that the spectral accelerations at 1 and 2 s strongly influence the prediction, likely because the first natural periods of the considered steel frames fall in the range of 1–2 s. Finally, to provide convenient access to engineers, a graphical user interface based on the developed RF model was created. This study places a pioneering step for the application of machine learning to the rapid damage assessment of building structures. [ABSTRACT FROM AUTHOR]

• Explainable machine learning-based approach is developed for interface shear strength prediction of cold joints; • The XGBoost model has high accuracy for interface shear strength prediction; • The XGBoost model is superior over conventional empirical models; • The most important input variable is the reinforcement ratio followed by the surface type. Accurate prediction of the shear strength of the interface between old and new concrete (cold joints) is essential for the design or assessment of precast and retrofitted concrete structures. However, the shear mechanism of the interface under shear loading is complicated and many factors can affect the shear strength. The conventional empirical models developed based on specific and limited dataset cannot well predict the interface shear strength. This study adopts the machine learning-based approaches and Shapley Additive exPlanations technique to develop an explainable ML-model for interface shear strength prediction of the cold joints. A comprehensive interface shear strength database consisting of 217 cold joints with variant design attributes and two types of interfaces (rough and smooth) were developed. The eXtreme Gradient Boosting (XGBoost) algorithm was selected to develop the predictive model. The model performance of the XGBoost model was thoroughly compared with three additional ML-models (DT, RF, ANN) and six empirical models (ACI, AASHTO, CSA, Kahn and Mitchell, Patnaik, Mattock). Four quantitative measures (R2, RMSE, MAE, and MAPE) were utilized to evaluate the prediction accuracy and the results show that the XGBoost model has the best model performance among the four ML-models. Meanwhile the XGBoost model is superior to the empirical models. The most significant parameter affecting the predictions of the XGBoost model is the reinforcement ratio. The surface type, section width of the interface and concrete strength can significantly affect the shear strength. [ABSTRACT FROM AUTHOR]

• Development of an XGBoost predictive model of maximum axial load-carrying capacity of FRP-RC columns. • Interpretation of XGBoost prediction model using SHAP values. • Verification of XGBoost prediction model with empirical and code-based models. • Demonstration of the capability of machine learning models to predict the axial load-carrying capacity of FRP-RC columns. This study presents a new approach for predicting the load-carrying capacity of reinforced concrete (RC) columns reinforced with fiber-reinforced polymer (FRP) bars with an eXtreme Gradient Boosting (XGBoost) algorithm. The proposed XGBoost model was developed based on a comprehensive database containing experimental data for 283 FRP-RC columns collected from the literature. The SHapley Additive exPlanations (SHAP) framework was used to interpret the output of the model. Furthermore, the efficiency and accuracy of the XGBoost model were evaluated and compared with design codes and equations in the literature. The results show that the proposed prediction model performed extremely well and was suitable for predicting the load-carrying capacity of FRP-RC columns. Moreover, the XGBoost model outperformed other numerical equations. For short columns, the mean R2 and MAPE values for the XGBoost model were 0.98% and 5.3%, respectively. In addition, the most significant input variables for predicting the maximum axial load-carrying capacity of FRP-RC columns were the eccentricity ratio, gross sectional area, compressive strength of concrete, slenderness ratio, and spacing or pitch of transversal reinforcement. Lastly, this study demonstrates the capability of machine learning models to predict the axial load-carrying capacity of FRP-RC columns. The proposed XGBoost model can provide an alternative method to existing mechanics-based models for design practice. [ABSTRACT FROM AUTHOR]

• An ensemble of machine learning models is developed for predicting the PHL of rectangular RC columns. • The proposed ensemble model outperformed the predictions of existing models and guideline equations. • The SHAP approach is used to explain the predictions of the model. • The most significant factors are highlighted using SHAP values. It is critical to properly define the plastic hinge region (the region that is exposed to maximum plastic deformation) of reinforced concrete (RC) columns to assess their performances in terms of ductility and energy dissipation capacity, implement retrofitting techniques, and control damages under lateral loads. The plastic hinge length (PHL) is used to define the extent of damages/plastic deformation in a structural element. However, accurate determination of the plastic hinge length remains a challenge. This study leveraged the power of ensemble machine learning algorithms by combining the performances of different base models and proposed a robust ensemble learning model to predict the PHL. The prediction of the proposed model is compared with those of existing empirical models and guideline equations for the PHL. The proposed model outperformed the predictions of all models and resulted in a superior prediction with a coefficient of determination ( R 2) between the experimental and predicted values for PHL of 98 %. Furthermore, the SHapley Additive exPlanations (SHAP) approach is used to explain the predictions of the model and highlight the most significant factors that influence the PHL of rectangular RC columns. [ABSTRACT FROM AUTHOR]