Optimized machine learning approaches for identifying vertical temperature gradient on ballastless track in natural environments

An improved machine learning approach for predicting granular flows

Forest inventory with high-density UAV-Lidar: Machine learning approaches for predicting individual tree attributes

Background: Lactic acidosis is the most common cause of anion gap metabolic acidosis in the intensive care unit (ICU), associated with poor outcomes including mortality. We sought to compare machine learning (ML) approaches versus logistic regression analysis for prediction of mortality in lactic acidosis patients admitted to the ICU. Methods: We used the Medical Information Mart for Intensive Care (MIMIC-III) database to identify ICU adult patients with lactic acidosis (serum lactate ≥4 mmol/L). The outcome of interest was hospital mortality. We developed prediction models using four ML approaches consisting of random forest (RF), decision tree (DT), extreme gradient boosting (XGBoost), artificial neural network (ANN), and statistical modeling with forward stepwise logistic regression using the testing dataset. We then assessed model performance using area under the receiver operating characteristic curve (AUROC), accuracy, precision, error rate, Matthews correlation coefficient (MCC), F1 score, and assessed model calibration using the Brier score, in the independent testing dataset. Results: Of 1919 lactic acidosis ICU patients, 1535 and 384 were included in the training and testing dataset, respectively. Hospital mortality was 30%. RF had the highest AUROC at 0.83, followed by logistic regression 0.81, XGBoost 0.81, ANN 0.79, and DT 0.71. In addition, RF also had the highest accuracy (0.79), MCC (0.45), F1 score (0.56), and lowest error rate (21.4%). The RF model was the most well-calibrated. The Brier score for RF, DT, XGBoost, ANN, and multivariable logistic regression was 0.15, 0.19, 0.18, 0.19, and 0.16, respectively. The RF model outperformed multivariable logistic regression model, SOFA score (AUROC 0.74), SAP II score (AUROC 0.77), and Charlson score (AUROC 0.69). Conclusion: The ML prediction model using RF algorithm provided the highest predictive performance for hospital mortality among ICU patient with lactic acidosis.

Aim This study aims to enhance safety in large diameter tunnel construction by integrating robust optimization and machine learning (ML) techniques with Building Information Modeling (BIM). By acquiring and preprocessing various datasets, implementing feature engineering, and using algorithms like SVM, decision trees, ANN, and random forests, the study demonstrates the effectiveness of ML models in risk prediction and mitigation, ultimately advancing safety performance in civil engineering projects. Background Large diameter tunnel construction presents significant safety challenges. Traditional methods often fall short of effectively predicting and mitigating risks. This study addresses these gaps by integrating robust optimization and machine learning (ML) approaches with Building Information Modeling (BIM) technology. By acquiring and preprocessing diverse datasets, implementing feature engineering, and employing ML algorithms, the study aims to enhance risk prediction and safety measures in tunnel construction projects. Objective The objective of this study is to improve safety in large diameter tunnel construction by integrating robust optimization and machine learning (ML) techniques with Building Information Modeling (BIM). This involves acquiring and preprocessing diverse datasets, using feature engineering to extract key parameters, and applying ML algorithms like SVM, decision trees, ANN, and random forests to predict and mitigate risks, ultimately enhancing safety performance in civil engineering projects. Methods The study's methods include acquiring and preprocessing various datasets (geological, structural, environmental, operational, historical, and simulation). Feature engineering techniques are used to extract key safety parameters for tunnels. Machine learning algorithms, such as decision trees, support vector machines (SVM), artificial neural networks, and random forests, are employed to analyze the data and predict construction risks. The SVM algorithm, with a 98.76% accuracy, is the most reliable predictor. Results The study found that the Support Vector Machine (SVM) algorithm was the most accurate predictor of risks in large diameter tunnel construction, achieving a 98.76% accuracy rate. Other models, such as decision trees, artificial neural networks, and random forests, also performed well, validating the effectiveness of ML-based solutions for risk assessment and mitigation. These predictive models enable stakeholders to monitor construction, allocate resources, and implement preventative measures effectively. Conclusion The study concludes that integrating machine learning (ML) approaches with Building Information Modeling (BIM) significantly improves safety in large diameter tunnel construction. The Support Vector Machine (SVM) algorithm, with 98.76% accuracy, is the most reliable predictor of risks. Other models, like decision trees, artificial neural networks, and random forests, also perform well, validating ML-based solutions for risk assessment. Adopting these ML approaches enhances safety performance and resource management in civil engineering projects.

A machine learning approach for the identification of the Lattice Discrete Particle Model parameters

Recently, global climate change discussions have become more prominent, and forests are considered as the ecosystems most at risk by the consequences of climate change. Wildfires are among one of the main drivers leading to losses in forested areas. The increasing availability of free remotely sensed data has enabled the precise locations of wildfires to be reliably monitored. A wildfire data inventory was created by integrating global positioning system (GPS) polygons with data collected from the moderate resolution imaging spectroradiometer (MODIS) thermal anomalies product between 2012 and 2017 for Amol County, northern Iran. The GPS polygon dataset from the state wildlife organization was gathered through extensive field surveys. The integrated inventory dataset, along with sixteen conditioning factors (topographic, meteorological, vegetation, anthropological, and hydrological factors), was used to evaluate the potential of different machine learning (ML) approaches for the spatial prediction of wildfire susceptibility. The applied ML approaches included an artificial neural network (ANN), support vector machines (SVM), and random forest (RF). All ML approaches were trained using 75% of the wildfire inventory dataset and tested using the remaining 25% of the dataset in the four-fold cross-validation (CV) procedure. The CV method is used for dealing with the randomness effects of the training and testing dataset selection on the performance of applied ML approaches. To validate the resulting wildfire susceptibility maps based on three different ML approaches and four different folds of inventory datasets, the true positive and false positive rates were calculated. In the following, the accuracy of each of the twelve resulting maps was assessed through the receiver operating characteristics (ROC) curve. The resulting CV accuracies were 74%, 79% and 88% for the ANN, SVM and RF, respectively.

Machine learning simulation of one-dimensional deterministic water wave propagation

Malaria remains a major public health burden in Nigeria, where climatic variability plays a critical role in shaping transmission dynamics. This study develops and evaluates climate-based predictive models for malaria incidence by integrating historical malaria surveillance data (2018–2023) with key meteorological variables, temperature, precipitation, humidity, and wind speed, across diverse ecological zones. Both traditional statistical and advanced machine learning (ML) approaches were employed to capture linear and nonlinear relationships between climate factors and malaria occurrence. Multiple Linear Regression (MLR) served as the baseline model, while Random Forest (RF), Support Vector Regression (SVR), Artificial Neural Network (ANN), Gradient Boosting Regression (GBR), XGBoost, and Long Short-Term Memory (LSTM) networks represented ML alternatives. Model performance was assessed using RMSE, MAE, R², and MAPE. Results revealed that ensemble-based ML models significantly outperformed MLR, with XGBoost emerging as the best performer (R² = 0.89; RMSE = 27.9; MAPE = 9.8%), followed closely by GBR and RF. The LSTM model effectively captured temporal dependencies (R² = 0.83), while MLR exhibited limited predictive ability (R² = 0.61). Regional analyses indicated that prediction accuracy was higher in areas with stable climatic conditions and reliable data reporting, whereas variability and data gaps in conflict-affected zones reduced performance. The findings highlight the superior predictive power and adaptability of ensemble ML methods for climate-driven malaria forecasting. The study offers an evidence-based framework for integrating these models into Nigeria’s early warning systems, supporting timely and geographically targeted malaria control interventions.

Efficient and high precision orbit prediction is increasingly crucial for improved Space Situational Awareness. Due to the lack of the required information such as space environment conditions and characteristics of Resident Space Objects (RSOs), satellite collisions have happened, partially because that the solely physics-based approaches can fail to achieve the required accuracy for collision avoidance. With the hypothesis that a Machine Learning (ML) approach can learn the underlying pattern of the orbit prediction errors from historical data, in this paper, the Support Vector Machine (SVM) is explored for improving the orbit prediction accuracy. Two publicly available Two-Line Element (TLE) catalog and International Laser Ranging Service (ILRS) catalog are used to validate the proposed ML approach. The position and velocity components of 11 total RSOs maintained at both catalogs are studied. Results of the study demonstrate that the designed dataset structure and SVM model can improve the orbit prediction accuracy with good performance on most cases. The performance on RSOs belonging to different orbit types is analyzed using different sizes of training and testing data. Results of the paper demonstrate the potential of using the proposed ML approach to improve the accuracy of TLE catalog.

A hybrid approach to predict vertical temperature gradient of ballastless track caused by solar radiation

Electroless plating is a chemical process commonly used in semiconductor manufacturing that deposits a uniform metal coating onto a substrate through an auto-catalytic reduction reaction without using electricity. High quality deposition hinges on the precise control of bath composition and operating conditions, which in turn requires accurate and accessible monitoring of the bath chemical concentration. While chemical analyzers present an effective monitoring technique, they are generally limited by high costs, complexity, and maintenance. Time-delayed measurements also impose challenges on real-time operations, and any reduction to the monitoring lag would be highly beneficial. We introduce a data-driven machine learning (ML) approach able to achieve fast concentration predictions directly from operating conditions, and able to compute the prediction uncertainty that is valuable for subsequent robust control and optimization and for improving transparency and trustworthiness of ML tools in manufacturing settings. Notably, our ML procedure overcomes challenges of asynchronous time-series training data with missing values, and where available data are often noisy and sparse. Our ML approach begins with a data preprocessing step to handle asynchronous measurements and missing values by engineering features rooted in the underlying physical processes. Notably, a systematic feature selection is performed to down select features that are most correlated with the prediction target, thereby reduce model overfitting. We then compare a number of regression model architectures for capturing the sequential data relationships, including linear models, random forest, extreme gradient boosting, and fully connected, long short-term memory, and transformer neural networks. We quantify the model uncertainty by training them in a Bayesian manner using scalable Stein variational gradient descent, to compute the posterior probability distributions conditioned on the training data that reflect the uncertainty in the models induced by the quality and quantity of the available observations. We demonstrate the overall ML approach on a real-world dataset from a semiconductor manufacturing plant that exhibits the aforementioned data challenges. The best performing models exhibited 1, 5, 12% accuracy (defined as achieving within a 3% margin) improvements on predicting the metal ion, alkali, reductant concentrations, respectively, over a naive feature extraction technique. It also achieved 13, 10, 32% accuracy improvements over an autoregressive integrated moving average (ARIMA) baseline. These results show the approach’s effectiveness in providing reliable predictions with quantified uncertainty.

Investigation of thermal-hydraulic performance of metal-foam heat sink using machine learning approach

Snow depth estimation with passive microwave (PM) remote sensing is challenged by spatial variations in the Earth’s surface, e.g., snow metamorphism, land cover types, and topography. Thus, traditional static snow depth retrieval algorithms cannot capture snow thickness well. In this study, we present a new operational retrieval algorithm, hereafter referred to as the pixel-based method (0.25° × 0.25° grid-level), to provide more accurate and nearly real-time snow depth estimates. First, the reference snow depth was retrieved using a previously proposed model in which a microwave snow emission model was coupled with a machine learning (ML) approach. In this process, an effective grain size (effGS) value was optimized by utilizing the snow microwave emission model, and then the nonlinear relationship between snow depth and multiple predictive variables, e.g., effGS, longitude, elevation, and brightness temperature (Tb) gradients, was established with the ML technique to retrieve reference snow depth data. To select a robust and well-performing ML approach, we compared the performance of widely used support vector regression (SVR), artificial neural network (ANN) and random forest (RF) algorithms over China. The results show that the three ML models performed similarly in snow depth estimation, which was attributed to the inclusion of effGS in the training samples. In this study, the RF model was used to retrieve the snow depth reference dataset due to its slightly stronger robustness according to our comparison of results. Second, the pixel-based algorithm was built based on the retrieved reference snow depth dataset and satellite Tb observations (18.7 GHz and 36.5 GHz) from Advanced Microwave Scanning Radiometer 2 (AMSR2) during the 2012–2020 period. For the pixel-based algorithm, the fitting coefficients were achieved dynamically pixel by pixel, making it superior to the traditional static methods. Third, the built pixel-based algorithm was verified using ground-based observations and was compared to the AMSR2, GlobSnow-v3.0, and ERA5-land products during the 2012–2020 period. The pixel-based algorithm exhibited an overall unbiased root mean square error (unRMSE) and R2 of 5.8 cm and 0.65, respectively, outperforming GlobSnow-v3.0, with unRMSE and R2 values of 9.2 cm and 0.22, AMSR2, with unRMSE and R2 values of 18.5 cm and 0.13, and ERA5-land, with unRMSE and R2 values of 10.5 cm and 0.33, respectively. However, the pixel-based algorithm estimates were still challenged by the complex terrain, e.g., the unRMSE was up to 17.4 cm near the Tien Shan Mountains. The proposed pixel-based algorithm in this study is a simple and operational method that can retrieve accurate snow depths based solely on spaceborne PM data in comparatively flat areas.

Model predictions are routinely used to help in the decision-making process. For instance, in the oil and gas industry, the accumulation of solid particles, such as sand, and the formation of a bed of solids at the bottom of the pipe can be consequential. Such accumulation may decrease the efficiency of the pipeline due to the increase in the frictional pressure loss; increase the risk of pipeline damage due to erosion; or increase the possibility of pipeline corrosion damage under the bed of solids. In order to transport the solid particles in the pipe, the fluid velocity must exceed the critical velocity required for solid particle transport. Mechanistic models are used to provide a reasonable estimate for the critical velocity needed to transport the particles. However, those models are commonly applicable in their respective ranges of data fitting; and are limited by the applicability of the empirically based closure relations that are a part of such models. On the other hand, the accumulation of experimental data makes possible the application of data-driven methods for characterizing multiphase flow for a broader range of flow conditions. This paper presents a framework to predict the fluid velocity needed to transport solid particles in a pipeline via machine learning (ML) approach. In order to prepare a dataset for training ML models, the critical velocity data are collected from available sources in literature. With the purpose of decreasing the number of input parameters for ML algorithms and to make the model similar for different types of carrying fluids, a set of dimensionless variables has been used. To create the predictive models, three ML algorithms are applied: Random Forest, Support Vector Machine, and Gradient Boosting. The fine-tuned models are compared using statistical analysis to identify the ones that provide the most accurate velocity predictions for different operating conditions. Moreover, the predictive abilities of the models are further validated by comparing their performance with different mechanistic models. The proposed ML approach demonstrates high accuracy in predicting critical velocity across a wide range of flow conditions and inclination angles.

The self-compacting concrete (SCC) mixes were developed using lightweight expandable clay aggregate (LECA) as a partial substitute for coarse aggregate, ground granulated blast-furnace slag (GGBS) as a partial replacement for cement, and combusted bio-medical waste ash (BMWA) as a partial replacement for fine aggregate. The substitution levels for LECA, GGBS, and BMWA were set at 10%, 20%, and 30% of coarse aggregate, cement, and fine aggregate, respectively. M30-grade SCC mixes were designed with two different water-to-binder ratios—0.40 and 0.45—and their compressive strength (CS) was experimentally evaluated. The data entries from the above mix designs and experiments were collected in this research which deals with evaluating the impact of lightweight expandable clay aggregate, metallurgical slag, and combusted bio-medical waste ash on self-compacting concrete. An extensive literature search was used in this project and this produced a global representative database collected from literature. The collected 384 records were divided into training set (300 records = 80%) and validation set (84 records = 20%) in line with the requirements of a more reliable data partitioning. Six advanced machine learning methods such as the Artificial Neural Network (ANN), Support Vector Regression (SVR), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGB), Random Forest (RF), and Adaptive Boosting (AdaBoost) were used to model the concrete behavior. All models were created using “Orange Data Mining” software version 3.36. A combination of error metrics, efficiency metrics and determination/correlation metrics were used to test the models performance and accuracy. Also, the Hoffman and Gardener’s method was used to evaluate the sensitivity analysis of the model variables. At the end of the model work, AdaBoost and KNN excel in predictive accuracy with 97.5%, reducing the margin of error and ensuring precise mix designs for SCC. SVR, XGB, and RF also exhibit strong accuracy (96.5–97%), supporting reliable material selection and proportions. AdaBoost and KNN demonstrate the lowest errors (MAE: 0.65 MPa, RMSE: 0.75 MPa), indicating precise performance, minimizing overdesign or underperformance risks, and optimizing material usage. The Hoffman/Gardener’s sensitivity analysis produced produced GGBS of 31% and Dens of 26% as the highest impact and this is followed by LECA of 21% and BMWA of 20%. This research enables the optimization of self-compacting concrete mix designs using machine learning, reducing experimental trials, enhancing material efficiency, lowering environmental impact, and promoting sustainable construction through the effective reuse of industrial by-products.