Search

In recent years, machine learning (ML) algorithms have gained substantial recognition for ecological modeling across various temporal and spatial scales. However, little evaluation has been conducted for the prediction of soil organic carbon (SOC) on small data sets commonly inherent to long-term soil ecological research. In this context, the performance of ML algorithms for SOC prediction has never been tested against traditional process-based modeling approaches. Here, we compare ML algorithms, calibrated and uncalibrated process-based models as well as multiple ensembles on their performance in predicting SOC using data from five long-term experimental sites (comprising 256 independent data points) in Austria. Using all available data, the ML-based approaches using Random forest and Support vector machines with a polynomial kernel were superior to all process-based models. However, the ML algorithms performed similar or worse when the number of training samples was reduced or when a leave-one-site-out cross validation was applied. This emphasizes that the performance of ML algorithms is strongly dependent on the data-size related quality of learning information following the well-known curse of dimensionality phenomenon, while the accuracy of process-based models significantly relies on proper calibration and combination of different modeling approaches. Our study thus suggests a superiority of ML-based SOC prediction at scales where larger datasets are available, while process-based models are superior tools when targeting the exploration of underlying biophysical and biochemical mechanisms of SOC dynamics in soils. Therefore, we recommend applying ensembles of ML algorithms with process-based models to combine advantages inherent to both approaches. • We evaluated process-based (PB) and machine-learning (ML) models for SOC prediction. • Random forest & support vector machine predicted SOC superior to PB models. • Reduced data availability and quality significantly weakened ML model performance. • ML-assisted PB model ensembles strongly improved model performance. [ABSTRACT FROM AUTHOR]

The estimation of material performance plays a crucial role in practical life, enabling the rational allocation of time and resources while enhancing the practical application of materials. Therefore, this study investigates the analytical and predictive capabilities of five machine learning (ML) algorithms (the Random Forest algorithm – RF, the Adaboost algorithm – AB, the Gradient Boosting algorithm – GB, the Extra Trees algorithm – ET and linear models – LM) for comprehensive performance parameters of wood ceramics (ammonia nitrogen adsorption quantity - Q , open porosity - P , burn-off , and hardness). In the analysis of model prediction capabilities, five key statistical parameters (Root Mean Square Error - RMSE , Mean Square Error - MSE , Coefficient of Correlation - R , Determination Coefficient - R 2 , and Mean Absolute Relative Error - MARE) were calculated. The results indicate the following: (1) Among various ML models, the GB model exhibits the most superior performance with an R 2 ≥ 0.9594. (2) However, in predicting the four performance parameters of wood ceramics, the AB model with an R 2 ranging from 0.0078 to 0.45, indicating notably poor predictive capabilities. Despite integrating the Support Vector Regression (SVR) module, no enhancement in predictive accuracy was observed. (3) While forecasting the four performance parameters of wood ceramics, the LM model demonstrates predictive accuracy relatively akin to that of the RF and ET models among the ML models. (4) Though the feature importance scores vary across distinct input variable models, there is a consistent trend of change. (5) Variables B and D exhibit some level of correlation with other variables. In summary, the results of this study suggest that, for the analysis and prediction of wood ceramic performance, the GB model among the five regression models demonstrates outstanding simulation performance. [ABSTRACT FROM AUTHOR]

The present study provided the first-time comprehensive evaluation of 12 advanced statistical and machine learning (ML) algorithms for the Soil Moisture (SM) estimation from dual polarimetric Sentinel-1 radar backscatter. The ML algorithms namely support vector machine (SVM) with linear, polynomial, radial and sigmoid kernel, random forest (RF), multi-layer perceptron (MLP), radial basis function (RBF), Wang and Mendel's (WM), subtractive clustering (SBC), adaptive neuro fuzzy inference system (ANFIS), hybrid fuzzy interference system (HyFIS), and dynamic evolving neural fuzzy inference system (DENFIS) were used. Extensive field samplings were performed for collection of in-situ SM data and other parameters from the selected sites for seven different dates and at two different locations (Varanasi and Guntur District, India), concurrent to Sentinel-1 overpasses. The backscattering coefficients were considered as input variables and SM as output variable for the training, validation and testing of the ML algorithms. The site at Varanasi was used for the training, validation and testing of the models. On the other hand, the Guntur site was used as an independent site for checking the model performance, before finalizing the algorithms. The performances of different trained algorithms were evaluated in terms of correlation coefficient (r), root mean square error (RMSE) (in m3/m3) and bias (in m3/m3). The study identified the RF, SBC and ANFIS as the top three best performing models with comparable and promising SM estimation. In order to test the robustness of these best models (RF, SBC and ANFIS), further performance analysis was performed to the independent datasets of the Varanasi and Guntur test sites, which indicates that the performance of these three models were consistent and SBC can be recommended as the best among all for SM estimation. [ABSTRACT FROM AUTHOR]

In recent years, there has been a notable surge in the prevalence of cardiovascular diseases (CVD), presenting a significant global public health challenge and a leading cause of mortality worldwide. Among the myriad complications stemming from CVD, heart failure stands out as a critical concern. Addressing heart failure through surgical means poses considerable challenges. The primary objective of this research is to identify pivotal attributes linked to heart failure and employ diverse machine learning methodologies to predict its occurrence, thereby enabling early estimation of mortality rates associated with heart failure. Leveraging a heart failure dataset, we conducted comprehensive model construction using pre-processing techniques such as feature scaling and correlation analysis. The Extreme Gradient Boosting (XGBoost) method was instrumental in evaluating feature relevance, leading to the selection of two distinct datasets: the whole dataset and the XGBoost dataset. In conclusion, we employed thirteen machine learning methods to predict the occurrence of death events within these datasets. Fine-tuning hyperparameters significantly enhanced model performance. Notably, our model demonstrated exceptional performance on this dataset, achieving the highest accuracy of 85.23% with Random Forest on the whole dataset and 86.36% with Flexible Discriminant Analysis on the XGBoost dataset. [Display omitted] • This research addresses the rising global prevalence of cardiovascular diseases, focussing heart failure. • The study aims to predict heart failure occurrence, enabling early estimation of mortalityrates. • Employing model, feature scaling and correlation analysis method to identify pivotal attributes linked to heart failure. [ABSTRACT FROM AUTHOR]

U.S. background ozone is defined as ground-level ozone in the absence of any domestic anthropogenic emissions. It plays an important role in the U.S. regulatory framework, as it corresponds to the theoretical minimum ozone that can be achieved at a location. Although some studies estimated background ozone from observations, it cannot be measured directly, and therefore air quality models have been used to estimate its levels across different parts of the country. These estimates are uncertain given the inherent uncertainty in air quality modeling. Recently data fusion techniques have been used to improve those estimates using ground-level ozone observations and satellite data. Here, we used two adjustment methods to improve on air quality model-derived estimates of background ozone: a Multi-Variate Linear Regression (MVLR) model and a machine learning (ML) algorithm, called Random Forest (RF), with a focus on thirteen urban areas in the U.S. These adjustments regress observed ozone on the simulated background and anthropogenic ozone (by a regional air quality model) and their combinations with spatial and temporal variables. The RF-ML algorithm showed the biggest improvement in model performance, compared to MVLR and the base air quality model predictions. Applying the MVLR adjustment, the background ozone estimates increased in most locations. Furthermore, applying the RF ML model adjustment increased background ozone estimates even more, highlighting the enhanced contribution of background ozone in recent years that constitutes a larger portion of total ozone and exceeds NAAQS in some regions. Our results are consistent with other observational and modeling studies in that the highest background ozone levels were estimated in the western U.S. and over higher elevations. • We first estimated background ozone in the U.S. using air quality models. • We used data fusion methods and machine learning to adjust the background ozone. • Adjustment methods improved the air quality model performance for total ozone. • Applying adjustment methods increased background ozone estimates in most locations. • The highest background ozone levels were estimated in the western U.S. [ABSTRACT FROM AUTHOR]

In this paper, three machine learning algorithms (Random Forest (RF), Support Vector Regression (SVR), and Long Short Term Memory (LSTM)) were used to predict and compare the thermodynamic performance of a 1 kW Organic Rankine Cycle (ORC) system under cryogenic operating conditions (i.e., cold source temperature < −160 °C). The cryogenic ORC system uses liquid nitrogen as the cold source, hot water as the heat source, and propane as the working fluid. Ten key operating parameters were selected as input parameters through Variable Importance Measures, and the output work of the expander, the cold exergy efficiency, and the system exergy destruction were used as output parameters. Moreover, the multi-objective optimization of this experimental system was conducted by applying the Non-dominated Sorting Genetic Algorithm III. The results showed that the RF algorithm was the most suitable algorithm among the three machine learning algorithms. According to the optimal results of the prediction model, the maximum error was 5.0251%, which was relatively small compared to the optimal results under experimental conditions. The related results demonstrate the feasibility of machine learning for cryogenic ORC data prediction, which can guide the design and improvement of ORC systems under low-temperature cold source conditions. • Performance of a 1 kW-scale cryogenic Organic Rankine Cycle (ORC) is predicted. • Three machine learning algorithms are used for prediction and system optimization. • Random Forest is more suitable for predicting output work and exergy destruction. • Support Vector Regression is more suitable for predicting cold exergy efficiency. • Maximum error for predicted optimal results and experimental results is 5.0251%. [ABSTRACT FROM AUTHOR]

• Factors influencing drinking water intake in swine buildings are not fully understood. • Monitoring and evaluating drinking water are crucial for farm profitability. • Statistical and machine learning models were developed for drinking water estimation. • The accuracy of the random forest model was higher than other tested models. • Body mass and feed intake mostly influence the drinking water intake in pigs. Effective monitoring and management of drinking water in swine buildings is a crucial aspect for promoting pigs' health and productivity. Therefore, this study aimed to quantify and model drinking water intake (DWI) in growing-finishing pigs by providing them with three concentrated diets in experimental pig barns. Two independent experiments were conducted in three experimental barns between 2021 and 2022. One statistical (multiple linear regression) and four machine learning algorithms (elastic net, random forest regression, support vector regression, and multilayer perceptron) were employed, with feed intake (FI), mass of pigs (MP), pigs' body temperature (PBT), room temperature (RT), CO 2 concentration (RCO 2), and temperature-humidity index (RTHI) as input parameters. The results revealed that pigs with a body mass of 30 to 60 kg consumed approximately 3.58 L of drinking water and 2.10 kg of concentrated diet per day. Additionally, strong positive correlations were observed between MP, FI, and DWI (correlation coefficient (r) > 90) during both experimental periods. The findings indicated that the random forest regression algorithm performed the best, explaining over 90% and 80% of the observed and predicted data during the training and testing phases, respectively. However, during the testing phase, the multiple linear regression methods performed the worst (R2 < 0.79 and RMSE > 0.89 L pig−1 day−1) when compared to the other models. Sensitivity analysis indicated that among all the variables, MP had the greatest impact on predicting DWI, followed by FI, RCO 2 , RTHI, and RT. The study concluded that random forest regression could predict DWI precisely, which can assist pig farmers in enhancing their water monitoring capabilities and promptly assessing the availability of drinking water. [ABSTRACT FROM AUTHOR]

• The accuracy of machine learning algorithms to predict injury locations were evaluated. • 16,878 construction accident records were analyzed. • Significant contributing factors were identified using permutation importance method. The construction industry is a hazardous industry with significant injuries and fatalities. Few studies have used data-driven analysis to investigate injuries due to construction accidents. This study aims to deploy machine learning (ML) models to predict four injury types (ITs): Upper limbs, lower limbs, head/neck, and back/trunk. A total of 16,878 construction accident records in Australia were collected and fed into several ML algorithms, including fine trees, ensemble of boosted trees, xgboost, random forest, two types of support vector machines, and logistic regression. Six performance metrics of precision, recall, accuracy, F1 score, the area under the receiver operating curve (AUROC), and the area under precision recall curve (AUPRC) were used to evaluate modeling outputs. Random forest showed superior performance in predicting injury types (accuracy 79.3%; recall 78.0%; F1 score 78.5%; precision 77.1%; AUROC 0.98; and AUPRC 0.78). The critical features of injury types were analyzed using the feature importance method and accident nature and mechanism had significant impacts. The study's findings contribute to safety enhancement by providing quantitative prediction models of injury types and subsequent development of safety controls in construction. [ABSTRACT FROM AUTHOR]

• The factors influencing the carbon emissions of tunnel construction were analyzed. • Propose carbon emission prediction model for tunnel construction. • The potential to lower carbon emissions from tunnel construction was examined. Excessive carbon dioxide emission leads to climate change and severely threaten social sustainability. A novel model for evaluating carbon dioxide emission in slurry shield tunneling is presented. Firstly, the carbon dioxide emission from a slurry shield tunnel during construction was calculated using the emission coefficient method. Then, for predicting carbon dioxide emission in slurry shield tunneling, a support vector regression integrated sparrow search algorithm model was proposed. Random forest is used to select the input variables of the model. The predicted model accuracy is validated by comparing it to multiple machine learning models. The results show that the model can accurately predict carbon dioxide emission in the shield tunneling with acceptable errors. The influencing factors for carbon dioxide emission in the slurry shield tunneling are disscussed. The recommendations for low-carbon tunnel construction are given. This study provides reference for guiding the low-carbon tunnel construction. [ABSTRACT FROM AUTHOR]

Age estimation has become inordinately significant for human beings for many reasons, such as detecting legal and criminal responsibility and other social events like a marriage license, birth certificate, etc. This paper aims to decide on the most desirable machine learning algorithm (from conventional machine learning algorithms to deep learning) for dental age estimation based on buccal bone level. The database consisted of 150 CBCT images (73 males and 77 females) from an existing base of the Faculty of Dental Medicine with Clinics, University of Sarajevo, aged 20-69. Results were obtained using the Waikato Environment for Knowledge Analysis (Weka), machine learning software in Java. Left and Right Buccal Alveolar Bone Levels are increasing with age, so they showed to be the most important attributes, especially the latter. Random Forest classifier provided the greatest result with the correlation coefficient of 0.803 and the mean absolute error of 6.022. We have also shown that considering sinus-related features can be a significant addition to the databases. Our paper is probably one of the first studies where regression algorithms based on the Support Vector Machines and Random Forest were utilized. [ABSTRACT FROM AUTHOR]

• New information on the frost prediction for forest. • Frost forecasting from spatial data. • Machine learning algorithms to classify frost risk probability. • High prediction performance using Random Forest classifier. • Transferability of the predictive approach for other agricultural plantations. Brazil is one of the leading timber producers in the world. However, in South Brazil, frost events frequently cause damage and reduce yield in forest plantations, a situation predicted to become more common under global change scenarios. This raises the need for low cost and efficient tools, such as machine learning algorithms to improve forecasting of frost risk. This study used machine learning algorithms to create zoning classifications forecasting frost risk for forest plantations located in the south-central region of Rio Grande do Sul State, Brazil. For this, we gathered and processed data from a local geodatabase (i.e. high-spatial-resolution contour lines, hydrography, and forest stands limits) comprising 30 management units with consistent historical data of frost occurrence. Then, we generated possible local-scale predictors of frost occurrence, which included longitude, latitude, elevation, relative altitude, relief orientation, and Euclidean distance from hydrography. We carried out tests of three machine learning classifiers (Random Forest – RF; Support Vector Machine-SVM and Multi-layer Perceptron-MLP) in order to determine which would most accurately predict frost occurrence. We found that RF provided the highest accuracy (> 90%), as well as the smallest percentages of class-specific errors (i.e. commission and omission errors), when compared to SVM and MLP. Latitude was the most important predictor of frost occurrence when using RF. Conversely, MLP performed worst, especially for classifying frost occurrence versus non-occurrence, and therefore had the highest percentage of class-specific errors. Our findings lead us to conclude that RF is the most proficient algorithm for forecasting frost occurrence from local-scale geomorphological data, without the need for high-cost investment in micro-meteorological sensors to monitor climate frost events linking temperature to plant damage. With increasing global climate extreme events, accurate risk zoning is essential for planning strategies of plantation at the landscape scale. [Display omitted] [ABSTRACT FROM AUTHOR]

• Three common cultivars of Euodiae Fructus were separated by an integrated approach. • The origin of processed products could be tracked by the orthogonal partial least squares-discriminant analysis model. • Five chemical markers were selected by the evaluation of mean decrease Gini. • The chemical markers were quantitatively analyzed in different cultivars. • The classification thresholds were derived from eXtreme Gradient Boosting algorithm. Euodiae Fructus (EF, the fruit of Tetradium ruticarpum) belongs to the family Rutaceae which has a complex genetic background, making classification a challenge. In order to classify the three closely related cultivars (small flower EF, medium flower EF, and big flower EF) and simplify the identification procedure in the future, an approach integrating ultra-high performance liquid chromatography-ultraviolet spectrum-hybrid quadrupole-Orbitrap high resolution mass spectrometry (UHPLC-UV-Q-Orbitrap HRMS) with machine learning algorithms was developed. Orthogonal partial least squares-discriminant analysis (OPLS-DA) and random forest (RF) were used to assort the processed EF products and select the chemical markers to differentiate among the three EF cultivars, respectively. Then the thresholds of classification were determined using the eXtreme Gradient Boosting (XGboost) model based on the quantitative data of chemical markers by the UHPLC-Q-Orbitrap HRMS. The results demonstrated that the approach successfully discriminated among three closely related cultivars of EF, and five chemical markers (neochlorogenic acid, (+)-catechin, chlorogenic acid, dehydroevodiamine, and limonin) were selected. Thresholds were obtained to classify the three cultivars. If the content of neochlorogenic acid was greater than 7.52 mg/g, the sample belonged to small flower EF, otherwise, it belonged to medium flower EF or big flower EF. Furthermore, if the content of dehydroevodiamine was greater than 3.84 mg/g, the sample was medium flower EF, otherwise, it was big flower EF. In general, this research provides a novel strategy for the discrimination of Euodiae Fructus cultivars to avoid misapplication and possible side effects. [ABSTRACT FROM AUTHOR]

• TBM parameters were predicted using seven different machine learning methods. • The 30 most influential TBM operating parameters were selected for each model. • The calculation times and prediction accuracy of all methods were determined. • The random forest model provides the best balance of calculation accuracy and time. The operating parameters of a tunnel boring machine (TBM) reflect its geological conditions and working status and are accordingly critical data for ensuring safe and efficient tunnel construction. The accurate prediction of the advance rate, rotation speed, thrust, and torque indicators based on the operating parameters can guide the control and application of a TBM. In this study, we analyzed the relationships between the TBM operating parameters and daily collected TBM data. We used the smoothing method and outlier detection to process this data, and determined the stable values of four different TBM indicators in the ascending phase of a complete TBM operational segment. Then, we evaluated the application of five different statistical and ensemble machine learning methods (Bayesian ridge regression (BR), nearest neighbors regression, random forests, gradient tree boosting (GTB), and support vector machine) and two different deep neural networks (a convolutional neural network (CNN) and long short-term memory network (LSTM)) to establish prediction models. The GTB method provided the best prediction accuracy and the BR method provided the least calculation time of the five different statistical and ensemble machine learning methods evaluated. The LSTM method provided a higher prediction accuracy than the CNN model. The ensemble machine learning methods were found to be the most accurate for the relatively limited data sets used in this study, suggesting that sufficient data must be present before the advantages of deep neural networks can be truly realized. The successful application of statistical, ensemble, and deep neural network machine learning methods to predict TBM indicators in this study suggests the promise of machine learning in this application. [ABSTRACT FROM AUTHOR]

• To improve the classification accuracy and lower classification time in diagnosing coronary artery disease as compared to the state-of-the-art techniques. • Random Forest based Boruta feature selection algorithm and SVM feature importance is employed. • The heterogeneous ensemble algorithm is proposed for diagnosing and prediction of CAD using the Z-Alizadeh Sani dataset. • A highest classification accuracy of 98.97% for the original dataset and an accuracy of 100% for the balanced dataset is achieved in the diagnosis of CAD. Background and Objective: Coronary artery disease (CAD) is considered one of the most prominent health issues causing high mortality in the world population. Hence, earlier diagnosis and prediction of CAD is essential for the proper medication of patients. The objective of this study is to develop a machine learning algorithm that will help in accurate diagnosis of CAD. Methods: In this paper, we have proposed a novel heterogeneous ensemble method combining three base classifiers viz., K-Nearest Neighbour, Random Forest, and Support Vector Machine for effective diagnosis of CAD. The results of base classifiers are combined using ensemble voting technique based on average-voting (AVEn), majority-voting (MVEn), and weighted-average voting (WAVEn) for prediction of CAD. The random forest-based Boruta wrapper feature selection algorithm and feature importance of SVM are used for relevant feature selection based on attribute importance and rank. Results: The proposed ensemble algorithm is developed using 5 features selected based on the feature importance and the performance of the algorithm is evaluated using the Z-Alizadeh Sani dataset. Further, the dataset is balanced using Synthetic Minority Over-sampling Technique and its performance is evaluated. The result analysis shows that the WAVEn algorithm achieves better classification accuracy, sensitivity, specificity and precision of 98.97%, 100%, 96.3% and 98.3% respectively for the original dataset. The WAVEn algorithm applied on the balanced dataset achieves 100% accuracy, sensitivity, specificity and precision in diagnosing CAD. To the best of author's knowledge, the accuracy achieved by WAVEn is the highest accuracy when compared with the state-of-the-art algorithms in the literature for both original and balanced dataset. Conclusions: The statistical results prove the robustness of the WAVEn algorithm in reliably discriminating the CAD patients from healthy ones with high precision, and therefore it can be used for developing a decision support system for diagnosing CAD at an early stage. [ABSTRACT FROM AUTHOR]