Search

This study estimates both hourly and daily Downward Surface Solar Radiation (SSR) in Istanbul while determining the importance of variables on SSR using tree-based machine learning methods, namely Decision Tree (DT), Random Forest (RF), and Gradient Boosted Regression Tree (GBRT). The hourly and daily data of climatic factors for the period between January 2016 and December 2020 are gathered from the European Centre for Medium-Range Weather Forecasts' (ECMWF) ERA5 reanalysis data sets. In addition to the meteorology data, hourly data of selected aerosols are obtained from the Ministry of Environment, Urbanization and Climate Change. Temperature, cloud coverage, ozone level, precipitation, pressure, and two components of wind speeds, PM10, PM2.5, and SO2 are utilized to train and test the established models. The model performances are determined with the out-of-bag errors by calculating R-squared, MSE, RMSE, and MBE. The GBRT model is found to be the most accurate model with the lowest error rates. Furthermore, this study provides the variable importance in determining the SSR. Although all models provide different values for the variable importance; temperature, ozone level, cloud coverage, and precipitation are found to be the most important variables in estimating daily SSR. For the hourly estimation, the time of day (hour) becomes the most important factor in addition to temperature, ozone level, and cloud coverage. Finally, this study shows that the tree-based machine learning methods used with these variables to estimate hourly and daily SSR results are very accurate when it is not possible to measure the SSR values directly. [ABSTRACT FROM AUTHOR]

Short-term load forecasting (STLF) plays a vital role in ensuring the safe, efficient, and economical operation of power systems. Accurate load forecasting provides numerous benefits for power suppliers, such as cost reduction, increased reliability, and informed decision-making. However, STLF is a complex task due to various factors, including non-linear trends, multiple seasonality, variable variance, and significant random interruptions in electricity demand time series. To address these challenges, advanced techniques and models are required. This study focuses on the development of an efficient short-term power load forecasting model using the random forest (RF) algorithm. RF combines regression trees through bagging and random subspace techniques to improve prediction accuracy and reduce model variability. The algorithm constructs a forest of trees using bootstrap samples and selects random feature subsets at each node to enhance diversity. Hyperparameters such as the number of trees, minimum sample leaf size, and maximum features for each split are tuned to optimize forecasting results. The proposed model was tested using historical hourly load data from four transformer substations supplying different campus areas of the University of Beira Interior, Portugal. The training data were from January 2018 to December 2021, while the data from 2022 were used for testing. The results demonstrate the effectiveness of the RF model in forecasting short-term hourly and one day ahead load and its potential to enhance decision-making processes in smart grid operations. [ABSTRACT FROM AUTHOR]

Context: As evaluation of carcass components is costly and time consuming, models for prediction of broiler carcass components are useful. Aims: The aim was to investigate the feasibility of machine learning methods in the prediction of carcass components from measurements on live birds during the rearing period. Methods: Three machine learning methods, including regression tree, random forest and gradient-boosting trees, were applied to predict carcass yields, and benchmarked against classical linear regression. Two scenarios were defined for prediction. In the first scenario, carcass yields were predicted by live bodyweight, shank length and shank diameter features, recorded at 2, 3 and 4 weeks of age. In the second scenario, predictor features recorded at 5, 6 and 7 weeks of age were used. The two scenarios were reanalysed by including effective single-nucleotide polymorphisms associated with bodyweight, shank length and shank diameter as new predictor features. Key results: The correlation coefficient between predicted and observed values for predicting weight of carcass traits ranged from 0.50 for wing to 0.59 for thigh in the first scenario, and from 0.63 for wing to 0.74 for carcass in the second scenario. These predictions for the percentage of carcass components ranged from 0.30 for wing to 0.39 for carcass and breast in the first scenario, and from 0.34 for thigh to 0.43 for carcass in the second scenario when random forest was used. Conclusions: Predictive accuracy in the first scenario was lower than in the second scenario for all prediction methods. Including single-nucleotide polymorphisms as predictor features in either scenario did not increase the accuracy of the prediction. Implications: In general, random forest had the best performance among machine learning methods, and classical linear regression in two scenarios, suggesting that it may be considered as an alternative to conventional linear models for prediction of carcass traits in broiler chickens. Evaluation of carcass component yields is costly and time consuming, thus models for the prediction of broiler carcass yields are useful. Three advanced predictive models were applied to predict carcass component yields, and benchmarked against the classical linear regression. Random forest had the best performance among machine learning methods, suggesting that it may be considered as an alternative to conventional linear models for prediction of carcass yields in broiler chickens. In all of the predictive model tested in this study, inclusion of single-nucleotide polymorphisms as predictor features lowered the predictive performance of the model. [ABSTRACT FROM AUTHOR]

Ensemble methods, such as Bagging, Boosting, or Random Forests, often enhance the prediction performance of single learners on both classification and regression tasks. In the context of regression, we propose a gradient boosting‐based algorithm incorporating a diversity term with the aim of constructing different learners that enrich the ensemble while achieving a trade‐off of some individual optimality for global enhancement. Verifying the hypotheses of Biau and Cadre's theorem (2021, Advances in contemporary statistics and econometrics—Festschrift in honour of Christine Thomas‐Agnan, Springer), we present a convergence result ensuring that the associated optimization strategy reaches the global optimum. In the experiments, we consider a variety of different base learners with increasing complexity: stumps, regression trees, Purely Random Forests, and Breiman's Random Forests. Finally, we consider simulated and benchmark datasets and a real‐world electricity demand dataset to show, by means of numerical experiments, the suitability of our procedure by examining the behavior not only of the final or the aggregated predictor but also of the whole generated sequence. [ABSTRACT FROM AUTHOR]

Rental bike sharing is an urban mobility model that is affordable and ecofriendly. The public bike sharing model is widely used in several cities across the world over the past decade. Because bike use is rising constantly, understanding the system demand in prediction is important to boost the operating system readiness. This article presents a prediction model to meet user demands and efficient operations for rental bikes using Random Forest (RF), which is a homogeneous ensemble method. The approach is carried out in Seoul, South Korea to predict the hourly use of rental bikes. RF is compared with Support Vector Machine with Radial Basis Function Kernel, k‐nearest neighbor and Classification and Regression Trees to verify RF supremacy in rental bike demand prediction. Performance Index measures the efficiency of RF compared to the other predictive models. Also, the variable importance analysis is performed to assess the most important characteristics during different seasons by creating a predictive model using RF for each season. The results show that the influence of variables changes depending on the seasons that suggest different operating conditions. RF models trained with yearly and seasonwise models show that bike sharing demand can be further improved by considering seasonal change. [ABSTRACT FROM AUTHOR]

Pan evaporation modeling and forecasting are needed to provide timely, continuous, and valuable information to support water management. This study aimed to overcome the constraints identified in traditional regression techniques and less explored machine learning models—the CatBoost, to enhance the precision and comprehensiveness of pan evaporation estimation. Additionally, the CatBoost model was compared with other machine-learning approaches, viz., multiple linear regression (MLR), multiple non-linear least-squares regression (MNLSR), multivariate adaptive regression splines (MARS), random forest regression (RF), and M5 model tree (M5Tree). The algorithms were developed using data obtained from the Crop Research Center, Pantnagar- Uttarakhand, India. Stepwise regression was used as an input variable selection algorithm for selecting the best relevant input from several meteorological variables. For the model's development, data were split into two subsets: the first three years were reserved for model calibration, while the fourth-year data was used for model validation. Statistical analyses, namely root mean square error (RMSE), Nash–Sutcliffe efficiency (NSE), Willmott index of agreement (WI), Pearson correlation coefficient (PCC), coefficient of determination (R2), and mean absolute error (MAE) were used to assess the effectiveness of weekly pan evaporation estimation models. Findings indicated that the CatBoost model, based on four predictors, was the most accurate at Pantnagar station, with NSE, WI, MAE, RMSE, PCC and R2 ranging from 0.9838 to 0.9877, 0.9960–0.9968, 0.1991–0.2078, 0.3643–0.3650–0.9955, 0.9925 and 0.9851–0.9911, respectively. RF model was found to be the second-most best-performing model in terms of in accuracy and effectiveness for mapping weekly pan evaporation, followed by MARS, MNLSR, MLR, and M5Tree. In conclusion, CatBoost's approach of considering combinations greedily implies a thoughtful and cautious selection of features during the modeling process. This can enhance the model's robustness and generalization capability, contributing to more accurate predictions in diverse environmental conditions in subtropical and sub-humid regions. [ABSTRACT FROM AUTHOR]

This study aims to understand the dynamic changes in the coral reef habitats of Derawan Island over two decades (2003, 2011, and 2021) using advanced machine learning classification techniques. The motivation stems from the urgent need for accurate, detailed environmental monitoring to inform conservation strategies, particularly in ecologically sensitive areas like coral reefs. We employed non-parametric machine learning algorithms, including Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Tree (CART), to assess spatial and temporal changes in coral habitats. Our analysis utilized high-resolution data from Landsat 9, Landsat 7, Sentinel-2, and Multispectral Aerial Photos. The RF algorithm proved to be the most accurate, achieving an accuracy of 71.43% with Landsat 9, 73.68% with Sentinel-2, and 78.28% with Multispectral Aerial Photos. Our findings indicate that the classification accuracy is significantly influenced by the geographic resolution and the quality of the field and satellite/aerial image data. Over the two decades, there was a notable decrease in the coral reef area from 2003 to 2011, with a reduction to 16 hectares, followed by a slight increase in area but with more heterogeneous densities between 2011 and 2021. The study underscores the dynamic nature of coral reef habitats and the efficacy of machine learning in environmental monitoring. The insights gained highlight the importance of advanced analytical methods in guiding conservation efforts and understanding ecological changes over time. [ABSTRACT FROM AUTHOR]

Tree ensembles can be interpreted as implicit kernel generators, where the ensuing proximity matrix represents the data-driven tree ensemble kernel. Focus of our work is the utility of tree based ensembles as kernel generators that (in conjunction with a regularized linear model) enable kernel learning. We elucidate the performance of the tree based random forest (RF) and gradient boosted tree (GBT) kernels in a comprehensive simulation study comprising of continuous and binary targets. We show that for continuous targets (regression), this kernel learning approach is competitive to the respective tree ensemble in higher dimensional scenarios, particularly in cases with larger number of noisy features. For the binary target (classification), the tree ensemble based kernels and their respective ensembles exhibit comparable performance.We provide the results fromseveral real life datasets for regression and classification relevant for biopharmaceutical and biomedical applications, that are in line with the simulations to show how these insights may be leveraged in practice. We discuss general applicability and extensions of the tree ensemble based kernels for survival targets and interpretable landmarking in classification and regression. Finally, we outline future research for kernel learning due to feature space partitionings. [ABSTRACT FROM AUTHOR]

Nearly 60% of commercial customers are connected to a low-voltage network in Poland with a contractual capacity of more than 40 kW and are assigned a fixed tariff with flat prices for the whole year, no matter the usage volume. With smart meters, more data about how businesses use energy are becoming available to both energy providers and customers. This enables innovation in the structure and type of tariffs on offer in the energy market. Customers can explore their usage patterns to choose the most suitable tariff to benefit from lower prices and thus generate savings. In this paper, we analyzed whether customers' electricity usage matched their optimal tariff and further investigated which of them could benefit or lose from switching the tariff based on the real dataset with the hourly energy readings of 1212 commercial entities in Poland recorded between 2016 and 2019. Three modelling approaches, i.e., the k-nearest neighbors, classification tree and random forest, were tested for optimal tariff classification, while for the benchmark, we used a simple approach, in which the tariff was proposed based on the customers' previous electricity usage. The main findings from the research are threefold: (1) out of all the analyzed entities, on average, 76% of them could have benefited from the tariff switching, which suggests that customers may not be aware of the tariff change benefits, or they had chosen a tariff plan that was not tailored to them; (2) a random forest model offers a viable approach to accurate tariff classification; (3) the policy implication from the research is the need to increase the customers' awareness about the tariffs and propose reliable tools for selecting the optimal tariff. [ABSTRACT FROM AUTHOR]

Missing data and nonnormality are two common factors that can affect analysis results from structural equation modeling (SEM). The current study aims to address a challenging situation in which the two factors coexist (i.e., missing nonnormal data). Using Monte Carlo simulation, we evaluated the performance of four multiple imputation (MI) strategies with respect to parameter and standard error estimation. These strategies include MI with normality-based model (MI-NORM), predictive mean matching (MI-PMM), classification and regression trees (MI-CART), and random forest (MI-RF). We also compared these MI strategies with robust full information maximum likelihood (RFIML), a popular (non-imputation) method to deal with missing nonnormal data in SEM. The results suggest that MI-NORM had similar performance to RFIML. MI-PMM outperformed the other methods when data were not missing on the heavy tail of a skewed distribution. Although MI-CART and MI-RF do not require any distribution assumption, they did not perform well compared with the others. Based on the results, practical guidance is provided. [ABSTRACT FROM AUTHOR]

Atrial fibrillation (AF) is a life threatening disease and can cause stroke, heart failure, and sometimes death. To reduce the rate of mortality and morbidity due to increased prevalence of AF, early detection of the same becomes a prior concern. Traditional machine learning (TML) algorithms and ensemble machine learning (EML) algorithms are proposed to detect AF in this article. The performances of both these methods are compared in this study. Methodology involves computation of RR interval features extracted from electrocardiogram and its classification into: normal, AF, and other rhythms. TML techniques such as Classification and Regression Tree, K Nearest Neighbor, C4.5, Iterative Dichotomiser 3, Support Vector Machine and EML classifier such as Random Forest (RF), and Rotation Forest are used for classification. The proposed method is evaluated using PhysioNet challenge 2017. During the tenfold cross validation, it is observed that RF classifier provided good classification accuracy of 99.10% with area under the curve of 0.998. Apart from contributing a new methodology, the proposed study also experimentally proves higher performance with ensemble learning method, RF. The methodology has many applications in health care management systems including defibrillators, cardiac pacemakers, etc. [ABSTRACT FROM AUTHOR]

Tree ensemble algorithms, such as random forest (RF), are some of the most widely applied methods in machine learning. However, an important hyperparameter, the number of classification or regression trees within the ensemble must be specified in these algorithms. The number of trees within the ensemble can adversely affect bias or computational cost and should ideally be adapted for each task. For this reason, a novel tree ensemble is described, the feature-ranked self-growing forest (FSF), that allows the automatic growth of a tree ensemble based on the structural diversity of the first two levels of trees' nodes. The algorithm's performance was tested with 30 classification and 30 regression datasets and compared with RF. The computational complexity was also theoretically and experimentally analyzed. FSF had a significant higher performance for 57%, and an equivalent performance for 27% of classification datasets compared to RF. FSF had a higher performance for 70% and an equivalent performance for 7% of regression datasets compared to RF. Computational complexity of FSF was competitive compared to that of other tree ensembles, being mainly dependent on the number of observations within the dataset. Therefore, it can be implied that FSF is a suitable out-of-the-box approach with potential as a tool for feature ranking and dataset's complexity analysis using the number of trees computed for a particular task. A MATLAB and Python implementation of the algorithm and a working example for classification and regression are provided for academic use. [ABSTRACT FROM AUTHOR]

Simple Summary: This study aimed to estimate body weight from various biometric measurements and features such as genotype (share of Suffolk and Polish Merino genotypes), birth weight (BiW), sex, birth type and body weight at 12 months of age (LBW) and some body measurements such as withers height (WH), sacrum height (SH), chest depth (CD), chest width (CW), chest circumference (CC), shoulder width (SW) and rump width (RW). Three hundred and forty-four animals were used in the study. Data mining and machine learning algorithms such as Random Forest Regression, Support Vector Regression and classification and regression tree were used to estimate the body weight from various features. Results show that the random forest procedure may help breeders improve characteristics of great importance. In this way, the breeders can get an elite population and determine which features are essential for estimating the body weight of the herd in Poland. The study's main goal was to compare several data mining and machine learning algorithms to estimate body weight based on body measurements at a different share of Polish Merino in the genotype of crossbreds (share of Suffolk and Polish Merino genotypes). The study estimated the capabilities of CART, support vector regression and random forest regression algorithms. To compare the estimation performances of the evaluated algorithms and determine the best model for estimating body weight, various body measurements and sex and birth type characteristics were assessed. Data from 344 sheep were used to estimate the body weights. The root means square error, standard deviation ratio, Pearson's correlation coefficient, mean absolute percentage error, coefficient of determination and Akaike's information criterion were used to assess the algorithms. A random forest regression algorithm may help breeders obtain a unique Polish Merino Suffolk cross population that would increase meat production. [ABSTRACT FROM AUTHOR]

Deep‐water corals are protected in the seas around New Zealand by legislation that prohibits intentional damage and removal, and by marine protected areas where bottom trawling is prohibited. However, these measures do not protect them from the impacts of a changing climate and ocean acidification. To enable adequate future protection from these threats we require knowledge of the present distribution of corals and the environmental conditions that determine their preferred habitat, as well as the likely future changes in these conditions, so that we can identify areas for potential refugia. In this study, we built habitat suitability models for 12 taxa of deep‐water corals using a comprehensive set of sample data and predicted present and future seafloor environmental conditions from an earth system model specifically tailored for the South Pacific. These models predicted that for most taxa there will be substantial shifts in the location of the most suitable habitat and decreases in the area of such habitat by the end of the 21st century, driven primarily by decreases in seafloor oxygen concentrations, shoaling of aragonite and calcite saturation horizons, and increases in nitrogen concentrations. The current network of protected areas in the region appear to provide little protection for most coral taxa, as there is little overlap with areas of highest habitat suitability, either in the present or the future. We recommend an urgent re‐examination of the spatial distribution of protected areas for deep‐water corals in the region, utilising spatial planning software that can balance protection requirements against value from fishing and mineral resources, take into account the current status of the coral habitats after decades of bottom trawling, and consider connectivity pathways for colonisation of corals into potential refugia. [ABSTRACT FROM AUTHOR]

Accurate information on grassland above-ground biomass (AGB) is critical to better understanding the carbon cycle and conserve grassland resources. As a climate-sensitive key ecological function area, it is important to accurately estimate the grassland AGB of the Tibetan Plateau. Sentinel-2 (S2) images have advantages in reducing mixed pixels and the scale effect for remote sensing, while the data volume is correspondingly larger. In order to improve the estimation accuracy while reducing the data volume required for AGB estimation and improving the computational efficiency, this study used the Recursive Feature Elimination (RFE) algorithm to find the optimal feature set and compared the performance of the Cubist, Gradient Boosting Regression Tree (GBRT), random forest (RF) and eXtreme Gradient Boosting (XGBoost) algorithms for estimating AGB. In this study, ten S2 bands, ten S2-derived vegetation indexes, 218 pieces of AGB field survey data, four types of meteorological data and three types of topographic data were used as the alternative input features for the AGB estimation model. The impurity and permutation importance were used as the feature importance calculation method input to the RFE, and the Cubist, GBRT, RF and XGBoost algorithms were used to construct the AGB estimation models. The results showed that the RF algorithm based on the monthly average temperature (T), elevation, Normalized Difference Phenology Index (NDPI), Normalized Difference Infrared Index (NDII) and Palmer Drought Severity Index (PDSI) performed best ( R 2 = 0.8838, RMSE = 35.05 g/m 2 , LCCC = 2.44, RPPD = 0.91). The above findings suggest that the RF model based on the features related to temperature, altitude, humidity and leaf water content is beneficial to estimate the grassland AGB on the Tibetan Plateau. [ABSTRACT FROM AUTHOR]

Forest ecosystem detection and assessment usually requires accurate spatial distribution information of forest tree species. Remote sensing technology has been confirmed as the most important method for tree species acquisition, and space-borne hyperspectral imagery, with the advantages of high spectral resolution, provides a better possibility for tree species classification. However, the present in-orbit hyperspectral imager has proved to be too low in spatial resolution to meet the accuracy needs of tree species classification. In this study, we firstly explored and evaluated the effectiveness of the Gram-Schmidt (GS) Harmonic analysis fusion (HAF) method for image fusion of GaoFen-5 (GF-5) and Sentinel-2A. Then, the Integrated Forest Z-Score (IFZ) was used to extract forest information from the fused image. Next, the spectral and textural features of the fused image, and topographic features extracted from DEM were selected according to random forest importance ranking (Mean Decreasing Gini (MDG) and Mean Decreasing Accuracy (MDA)), and imported into the random forest classifier to complete tree species classification. The results showed that: comparing some evaluation factors such as information entropy, average gradient and standard deviation of the fused images, the GS fusion image was proven to have a higher degree of spatial integration and spectral fidelity. The random forest importance ranking showed that WBI, Aspect, NDNI, ARI2, FRI were more important for tree species classification. Both the classification accuracy and kappa coefficients of the fused images were significantly greatly improved when compared to those of original GF-5 images. The overall classification accuracy ranged from 61.17% to 86.93% for different feature combination scenarios, and accuracy of the selected method based on MDA achieved higher results (OA = 86.93%, Kappa = 0.85). This study demonstrated the feasibility of fusion of GF-5 and Sentinel-2A images for tree species classification, which further provides good reference for application of in-orbit hyperspectral images. [ABSTRACT FROM AUTHOR]

Random forest (RF) is one of the most popular machine learning (ML) models used for both classification and regression problems. As an ensemble model, it demonstrates high predictive accuracy and low variance, while being easy to learn and optimize. In this study, we use RF for short-term load forecasting (STLF), focusing on data representation and training modes. We consider seven methods of defining input patterns and three training modes: local, global and extended global. We also investigate key RF hyperparameters to learn about their optimal settings. The experimental part of the work demonstrates on four STLF problems that our model, in its optimal variant, can outperform both statistical and ML models, providing the most accurate forecasts. [ABSTRACT FROM AUTHOR]

Aim: The aim of the work is to evaluate the accuracy and cross validation in predicting loan approval using Novel Penalty Based Approach Logistic Regression (LR), Random Forest (RF), Decision Tree (DT) and K-Nearest Neighbor (KNN) Classification algorithms. Materials and Methods: The classification algorithm is invoked on a loan approval dataset consisting of 615 records. A framework for forecasting loan approval in the banking sector has been proposed and developed that compares Novel Penalty Based Approach Logistic Regression, decision tree, Random Forest and K-Nearest Neighbor classifiers. Sample size was calculated as 55 in each group using G powers. Sample size was calculated using clinical analysis, with alpha and beta values of 0, 05 and 0. 5, 95% confidence, 80% pre-test g power and enrolment ratio 1. Results: The Novel Penalty Based Approach Logistic Regression classifier produces 77.27% accuracy in predicting the Loan Approval on the data set, whereas the Random Forest, K-Nearest Neighbor, Decision Tree classifiers produce 76.62%, 72.27%, 72.07% respectively. The significant value is 0.016. Hence Novel Penalty Based Approach Logistic Regression is better than KNN, RF, DT classifiers. Conclusion: The results show that the performance of Novel Penalty Based Approach Logistic Regression is better when compared with KNN, RF and DT in terms of both cross validation and accuracy. [ABSTRACT FROM AUTHOR]

Aim: The proposed study aims to perform detection of wrong-lane accidents using Novel Penalty Based Logistic Regression (LR) algorithm and compare accuracy with Decision Tree (DT), Support Vector Machine (SVM) and Random Forest (RF) algorithm. Materials and Methods: Novel Penalty Based Logistic Regression is applied on a road accident dataset that consists of 1834 records. A Machine learning technique for the detection of wrong-lane accidents which compares Novel Penalty Based Logistic Regression with Decision Tree, SVM and Random Forest has been proposed and developed. Sample size was calculated as 21 in each group using G power. Sample size was calculated using clinical analysis, with alpha and beta values of 0, 05 and 0.5, 95% confidence, 80% pre-test power and enrolment ratio is 1. The accuracy of the detection of wronglane accidents was evaluated and recorded. Results: The accuracy was maximum in detection of wrong-lane accidents using Novel Penalty Based Logistic Regression (90.0%) with minimum mean error when compared with Decision Tree (89.88%), SVM (89.90%), Random Forest (89.77%) and attained significance value of p = 0.02. Conclusion: The study proves that the Novel Penalty Based Logistic Regression Algorithm exhibits better accuracy than the Decision Tree, SVM and Random Forest in detection of wrong-lane accidents. [ABSTRACT FROM AUTHOR]

In recent years, environmental problems have become a serious issue worldwide due to the increasing damage caused by climate change. People's environmental awareness has grown, and public opinion is now demanding effective action from governments. Young people around the world are playing an important role in this, with the Fridays For Future movement, calling on policymakers to make environmental protection one of their political priorities. Through a survey of 1,975 high school students, this paper aims to contribute to the study of young people's sustainable behaviors and their awareness to take effective action against environmental degradation, to explore their concerns and opinions about environmental issues, and to find out what ecological practices they are willing to adopt in their daily lives. Data analysis is conducted using tree-based methods to examine the sustainable behaviors and define the key practices that constitute them. The results of classification tree show that sustainable behaviors impact lifestyles, whether through less demanding actions such as turning off the faucet or appliances, or willingness to work as a volunteer, among others. The Random Forest provides us with a ranked list of sustainable behaviors that young people engage in to reduce and stop environmental degradation. The results of this study may be of interest to policy makers who need to plan educational pathways for students from elementary school to university, as environmental culture must be a cornerstone of our society. [ABSTRACT FROM AUTHOR]

Amplifying landslide hazards in the backdrop of warming climate and intensifying human activities calls for an integrated framework for accurately evaluating landslide susceptibility at fine spatiotemporal resolutions, which is critical for the mitigation of increasingly high landslide disaster risks. Yet, dynamic landslide susceptibility mapping is still lacking. Using high-quality data, from 14,435 landslides and non-landslides, we developed an efficient holistic framework for evaluating landslide susceptibility, considering landslide-relevant internal and external factors based on cloud computing platform and algorithmic models, which enables dynamic updating of a landslide susceptibility map at the regional scale, particularly in regions with highly complicated topographical features such as the Hengduan Mountains, as considered in this study. We compared Classification and Regression Trees (CART), Support Vector Machines (SVM), and Random Forest (RF) classifiers to screen out the best portfolio model for landslide susceptibility mapping on the Google Earth Engine (GEE) platform. We found that the Random Forest (RF) classifier integrated with synergy mode had the best modeling performance, with 90.48% and 89.24% accuracy and precision, respectively. We also found that forests and grasslands had the controlling effect on the occurrence of landslides, while human activities had a notable inducing effect on the occurrence of landslides within the Hengduan Mountains. This study highlights the performance of the holistic landslide susceptibility evaluation framework proposed in this study and provides a viable technique for landslide susceptibility evaluation in other regions of the globe. [ABSTRACT FROM AUTHOR]

The levels of total salinity and its ion constituents in estuarine environments are important indicators of the overall suitability of water for environmental, agricultural, and urban use. These constituents include Total Dissolved Solids (TDS), dissolved chloride (Cl−), dissolved sulfate (SO42−), dissolved sodium (Na+), dissolved calcium (Ca2+), dissolved magnesium (Mg2+), dissolved nitrate (NO3), dissolved potassium (K), dissolved bromide (Br−), dissolved boron (B), Alkalinity, and hardness, among others. In practice, salinity is typically measured indirectly as electrical conductance (EC) via automatic sensors while the concentration of each constituent is often measured from discrete water samples (i.e., grab samples) and thus is available much less frequently than salinity. Quadratic regression equations are generally developed between salinity (as the predictor, represented by EC) and individual constituents (as the predictand) based on grab sample data. The regression models are then applied to estimate the concentrations of individual constituents given EC during the period when grab samples are not available. The current study develops four types of machine learning models: the Generalized Additive Model, Regression Trees, Random Forest, and Artificial Neural Networks, to emulate conventional regression equations in salinity-constituent conversion. A case study in the South Sacramento-San Joaquin Delta of California is presented to illustrate the development and application of these models and to compare their performance with that of the benchmark regression models. The results indicate that machine learning models can provide comparable or superior simulations to the regression models. Among the four machine models examined, the Random Forest model tends to yield the best results. The study further discusses the scientific and practical implications of the models proposed, their limitations, as well as future work to further improve their performance and applicability. [ABSTRACT FROM AUTHOR]

Ticks have medical and economic importance due to their ability to transmit pathogens to humans and animals. In tropical and sub‐tropical countries, tick‐borne diseases (TBD) are among the most important diseases affecting livestock and humans. The fast spread of ticks and TBD requires a quick development and application of efficient prevention and/or control programs. Therefore, prior investigations on TBD and related vectors epidemiology, for instance, through accurate epidemiological models, are mandatory. This study aims to develop models to forecast suitable habitat for Rhipicephalus microplus distribution in West Africa. Tick occurrences were assembled from 10 different studies carried out in six West African countries in the past decade. Six statistical models (maximum entropy in a single model and generalised linear model, generalised additive model, random forest, boosted regression tree and support vector machine model in an ensemble model) were applied and compared to predict the habitat suitability of R. microplus distribution in West Africa. Each model was evaluated with the area under the receiver operating characteristic curve (AUC), the true skill statistic (TSS) and the Boyce index (BI). The selected models had good performance according to their AUC (above.8), TSS (above.7) and BI (above.8). Temperature played a key role in MaxEnt model, whereas normalised difference vegetation index (NDVI) was the most important variable in the ensemble model. The model predictions showed coastal countries of West Africa as more suitable for R. microplus. However, some Sahelian areas seems also favourable. We stress the importance of vector surveillance and control in countries that have not yet detected R. microplus but are in the areas predicted to host suitable habitat. Indeed, awareness‐raising and training of different stakeholders must be reinforced for better prevention and control of this tick in these different countries according to their status. [ABSTRACT FROM AUTHOR]

Forest canopy cover (FCC) is one of the most important forest inventory parameters and plays a critical role in evaluating forest functions. This study examines the potential of integrating Sentinel-1 (S-1) and Sentinel-2 (S-2) data to map FCC in the heterogeneous Mediterranean oak forests of western Iran in different data densities (one-year datasets vs. three-year datasets). This study used very high-resolution satellite images from Google Earth, gridded points, and field inventory plots to generate a reference dataset. Based on it, four FCC classes were defined, namely non-forest, sparse forest (FCC = 1–30%), medium-density forest (FCC = 31–60%), and dense forest (FCC > 60%). In this study, three machine learning (ML) models, including Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Tree (CART), were used in the Google Earth Engine and their performance was compared for classification. Results showed that the SVM produced the highest accuracy on FCC mapping. The three-year time series increased the ability of all ML models to classify FCC classes, in particular the sparse forest class, which was not distinguished well by the one-year dataset. Class-level accuracy assessment results showed a remarkable increase in F-1 scores for sparse forest classification by integrating S-1 and S-2 (10.4% to 18.2% increased for the CART and SVM ML models, respectively). In conclusion, the synergetic use of S-1 and S-2 spectral temporal metrics improved the classification accuracy compared to that obtained using only S-2. The study relied on open data and freely available tools and can be integrated into national monitoring systems of FCC in Mediterranean oak forests of Iran and neighboring countries with similar forest attributes. [ABSTRACT FROM AUTHOR]

• pHEMA-PVA cryogels embedded with bacterial cellulose were prepared. • Machine learning model was developed for cryogel preparation and property prediction. • Overlay sampling uniform design was employed as the data strategy in the model. • GBRT showed the best predictive performance compared with RF, FNN and XGBoost. Supermacroporous composite cryogels with enhanced adjustable functionality have received extensive interest in bioseparation, tissue engineering, and drug delivery. However, the variations in their components significantly impactfinal properties. This study presents a two-step hybrid machine learning approach for predicting the properties of innovative poly(2-hydroxyethyl methacrylate)-poly(vinyl alcohol) composite cryogels embedded with bacterial cellulose (pHEMA-PVA-BC) based on their compositions. By considering the ratios of HEMA (1.0–22.0 wt%), PVA (0.2–4.0 wt%), poly(ethylene glycol) diacrylate (1.0–4.5 wt%), BC (0.1–1.5 wt%), and water (68.0–96.0 wt%) as investigational variables, overlay sampling uniform design (OSUD) was employed to construct a high-quality dataset for model development. The random forest (RF) model was used to classify the preparation conditions. Then four models of artificial neural network, RF, gradient boosted regression trees (GBRT), and XGBoost were developed to predict the basic properties of the composite cryogels. The results showed that the RF model achieved an accurate three-class classification of preparation conditions. Among the four models, the GBRT model exhibited the best predictive performance of the basic properties, with the mean absolute percentage error of 16.04 %, 0.85 %, and 2.44 % for permeability, effective porosity, and height of theoretical plate (1.0 cm/min), respectively. Characterization results of the representative pHEMA-PVA-BC composite cryogel showed an effective porosity of 81.01 %, a permeability of 1.20 × 10−12 m2, and a range of height of theoretical plate between 0.40–0.49 cm at flow velocities of 0.5–3.0 cm/min. These indicate that the pHEMA-PVA-BC cryogel was an excellent material with supermacropores, low flow resistance and high mass transfer efficiency. Furthermore, the model output demonstrates that the alteration of the proportions of PVA (0.2–3.5 wt%) and BC (0.1–1.5 wt%) components in composite cryogels resulted in significant changes in the material basic properties. This work represents an attempt to efficiently design and prepare target composite cryogels using machine learning and providing valuable insights for the efficient development of polymers. [ABSTRACT FROM AUTHOR]

• Machine learning models (RF, KNN, GBM, RPART) are used to predict occupational accident causes and consequence. • 10-fold cross validation method was used for model validationwhich increased the accuracy of the models. • RF showed best performance on accuracy with respect to GBM, RPART and KNN. Occupational accidents are one of the main problems in production system especially in metal sector. The aim of this study is to develop a predictive framework using machine learning (ML) to identify the causes of fatalities and amputations in the metal sector based on occupational accident data collected by the Turkish Ministry of Labor and Social Security (MLSS) from 2013 to 2018. Researchers have used a variety of strategies to investigate factors and create effective prediction frameworks for lowering occupational accidents. We used random forest (RF), k-nearest neighbour (KNN), gradient boosting method (GBM) and recursive partitioning and regression trees (RPART) to predict accident causes and consequence. Accuracy, precision, recall and f-score is used to measure the performance of ML frameworks. For model validation 10-fold cross validation method was used which increased the accuracy of the frameworks considerably. We extracted important factors which affected the causes of accident at metal sector using feature importance. Analysis proved RF as the best performing framework with highest classification results with 0.9172 accuracy, 0.9618 precision, 0.9518 recall and 0.9568 f-score using all features as compared to other techniques classification of occupational accident severity. To implement preventive controls and interventions in a more targeted way, it is recommended to use the predictive RF algorithm in the analysis of occupational accidents. With these studies, preventive measures can be taken by predicting occupational accidents that may occur in the future. [ABSTRACT FROM AUTHOR]

Background: Identification of suitable factors that influence significantly to the response is crucial for the traits based breeding program to make a better decision about improvement in productivity. Multiple linear regression (MLR) is the benchmark method commonly using to identify suitable factors for crop improvement. It doesn't work always due to stringent assumption (Multicollinearity, Linearity) behind the MLR model. Here we tried to develop an efficient model for the selection of major traits that contribute to seed yield in soybean by comparing different models. Methods: Field experiment was conducted using 98 soybean core population through augmented design. 18 morphometric traits obtain from soybean core population were considered under the study as regressors. Multiple linear regression (MLR), principle component regression (PCR), regression tree and Random Forest models were compared to select traits based on prediction accuracy. Result: All the models identified the number of pods per plant (NPP) has the most influencing variable to the soybean yield. However random forest has a much higher prediction power (RMSE=4.59, MAPE=0.18) compared to other models under study. The results of random forest revealed that the number of pods per plant, number of branches per plant and other associated characters like plant height at harvest as highly influencing traits for seed yield in soybean. Finally, tried to identify genotypesthat possess superiority about most influencing morphological characters on seed yield using cluster analysis. [ABSTRACT FROM AUTHOR]

The increasing availability of field data presents an opportunity to understand the fundamental ecological relationships and functions of large trees in tropical forests at regional and global scales. However, it is not always clear what the relationships or patterns of diversity and structure are among sites in different biogeographic regions. We evaluated the relationship of the biomass and diameter of the largest trees with a diversity of species and compared, between the sites, the attributes of structure, diversity, and the influence of the 50 hyperdominant species in each site, aiming at the potential formation of groups by sites with characteristics and patterns of similar diversity within biogeographic regions. The average wood density together with the diversity of genera and families are the most important attributes to discriminate biogeographic regions when considering all forest information. Large trees play a fundamental role in forest ecology and seem to express regional environmental characteristics. The upper canopy of tropical forests remains one of the least studied environments in all terrestrial biomes, and is often referred to as "the last biotic frontier" or a "black box," and large trees are also part of this mysterious frontier. [ABSTRACT FROM AUTHOR]

Objective: The occurrence of colon cancer starts in the inner wall of the large intestine. The survival of colon cancer patients strongly relies on early detection. Diagnosing colon cancer using clinical approaches often takes longer, especially in most developing countries with limited facilities. The recent use of microarray technology has presented a new approach for the oncologist to diagnose cancer cells using non-clinical machine learning methods. In this paper, the aim is to predict the status of colon cancer tissues using the Bayesian Additive Regression Trees (BART) and 2 other machine learning methods. Material and Methods: The development and comparative analysis of BART alongside 2 other competing methods (Random Forest: RF and Gradient Boosting Machine: GBM) were implemented. The dataset used for the analysis is the microarray colon cancer data which consists of 2,000 gene expression measurements for 62 tissue samples. Results: The methods are compared based on overall metrics (accuracy, balance accuracy, detection rate, F-measure and AUC) and class-specific metrics (sensitivity, specificity, positive predictive value and negative predictive value). The overall metrics results showed that the best method is RF. The class-specific metrics results showed that BART is better than RF. Conclusion: On average, BART is more sensitive in detecting the presence of colon cancer cells, while RF is more accurate and specific in detecting the presence or absence of colon cancer cells. [ABSTRACT FROM AUTHOR]

Soil organic carbon (SOC) is one of the key soil components for cultivated soils. SOC is regularly monitored and mapped to improve the quality, health, and productivity of the soil. However, traditional SOC-level monitoring is expensive for land managers and farmers. Estimating SOC using satellite imagery provides an easy, efficient, and cost-effective way to monitor surface SOC levels. The objective of this study was to estimate the surface SOC distribution in selected soils of Major Land Resource Areas (MLRA), 102A (Rolling Till Plain, Brookings County, SD), and 103 (Central Iowa and Minnesota Till Prairies, Lac qui Parle County, MN), using satellite imagery with different resolutions (Landsat 8 and PlanetScope). The dominant soils in the study area are Haplustolls, Calciustolls, and Endoaquolls, which are formed in silty sediments, local silty alluvium, and till. Landsat 8 and PlanetScope spectral bands were used to develop SOC prediction models. Parametric and data-driven methods were employed to predict the SOC. Multiple linear regression and Linear Spatial Mixed Model (LSMM) were used on the Landsat 8 and PlanetScope data. In addition to the parametric models, Regression Trees and Random Forest were also employed on both satellite data. The results showed that reduced LSMM provided the lowest RMSE, which are 0.401 and 0.367 for Landsat 8 and PlanetScope, respectively. Furthermore, the random forest has the highest RPD and RPIQ for Landsat 8 (RPD of 2.67 and RPIQ of 2.49) and PlanetScope (RPD of 2.85 and RPIQ of 3.7). In all cases, models obtained from PlanetScope are better than those obtained from Landsat 8. [ABSTRACT FROM AUTHOR]

The PM10 prediction has received considerable attention due to its harmful effects on human health. Machine learning approaches have the potential to predict and classify future PM10 concentrations accurately. Therefore, in this study, three machine learning algorithms—namely, decision tree (DT), boosted regression tree (BRT), and random forest (RF)—were applied for the prediction of PM10 in Kota Bharu, Kelantan. The results from these three methods were compared to find the best method to predict PM10 concentration for the next day by using the maximum daily data from January 2002 to December 2017. To this end, 80% of the data were used for training and 20% for validation of the models. The performance measure of the PM10 concentration was based on accuracy, sensitivity, specificity, and precision for RF, BRT, and DT, respectively, which indicates that these three models were developed effectively, and they are applicable in the prediction of other atmospheric environmental data. The best model to use in predicting the next day's PM10 concentration classification was the random forest classifier, with an accuracy of 98.37, sensitivity of 97.19, specificity of 99.55, and precision of 99.54, but the result of the boosted regression tree was substantially different from the RF model, with an accuracy of 98.12, sensitivity of 97.51, specificity of 98.72, and precision of 98.71. The best model can assist local governments in providing early warnings to people who are at risk of acute and chronic health consequences from air pollution. [ABSTRACT FROM AUTHOR]

SUMMARY: Being able to predict future temperatures on the wall lining is key when controlling and scheduling maintenance for large industrial smelting furnaces. In this paper, we propose and test a machine learning approach for predicting lining temperatures in a ferronickel smelting furnace. This approach was deployed and evaluated in a real‐world scenario, i.e., in one of Cerro Matoso S.A.'s (CMSA) industrial plant furnaces. Different techniques were tested, and finally, a multitarget regression (MTR) model showed the best performance. Previous state of the art focused on predicting only one target sensor; in contrast, our model is capable of predicting up to 12 targets. Two MTR models were tested: the incremental structured output prediction tree (iSOUP‐Tree) and the stacked single‐target Hoeffding tree regressor (SST‐HT). The SST‐HT method had the best behavior in terms of the average mean absolute error (AMAE) and average root mean square error (ARMSE). The results indicate that the developed MTR models can accurately predict the measured temperature on multiple point sensors. Results of this work are expected to help the process of structural control and health monitoring of the furnace linings located at CMSA's plant. [ABSTRACT FROM AUTHOR]

Species distribution modeling (SDM) is widely used in ecology and conservation. Currently, the most available data for SDM are species presence‐only records (available through digital databases). There have been many studies comparing the performance of alternative algorithms for modeling presence‐only data. Among these, a 2006 paper from Elith and colleagues has been particularly influential in the field, partly because they used several novel methods (at the time) on a global data set that included independent presence–absence records for model evaluation. Since its publication, some of the algorithms have been further developed and new ones have emerged. In this paper, we explore patterns in predictive performance across methods, by reanalyzing the same data set (225 species from six different regions) using updated modeling knowledge and practices. We apply well‐established methods such as generalized additive models and MaxEnt, alongside others that have received attention more recently, including regularized regressions, point‐process weighted regressions, random forests, XGBoost, support vector machines, and the ensemble modeling framework biomod. All the methods we use include background samples (a sample of environments in the landscape) for model fitting. We explore impacts of using weights on the presence and background points in model fitting. We introduce new ways of evaluating models fitted to these data, using the area under the precision‐recall gain curve, and focusing on the rank of results. We find that the way models are fitted matters. The top method was an ensemble of tuned individual models. In contrast, ensembles built using the biomod framework with default parameters performed no better than single moderate performing models. Similarly, the second top performing method was a random forest parameterized to deal with many background samples (contrasted to relatively few presence records), which substantially outperformed other random forest implementations. We find that, in general, nonparametric techniques with the capability of controlling for model complexity outperformed traditional regression methods, with MaxEnt and boosted regression trees still among the top performing models. All the data and code with working examples are provided to make this study fully reproducible. [ABSTRACT FROM AUTHOR]

• Propose an improved random forest based on the improvement of decision trees. • Improve the evaluation mechanism for the classification effect of decision trees. • Propose a method for quantifying the diversity between decision trees. • Multiple tests verify the superiority of the proposed improved random forest. Random forest is one of the most widely used machine learning algorithms. Decision trees used to construct the random forest may have low classification accuracies or high correlations, which affects the comprehensive performance of the random forest. Aiming at these problems, the authors proposed an improved random forest based on the classification accuracy and correlation measurement of decision trees in this paper. Its main idea includes two parts, one is retaining the classification and regression trees (CARTs) with better classification effects, the other is reducing the correlations between the CARTs. Specifically, in the classification effect evaluation part, each CART was applied to make predictions on three reserved data sets, then the average classification accuracies were achieved, respectively. Thus, all the CARTs were sorted in descending order according to their achieved average classification accuracies. In the correlation measurement part, the improved dot product method was proposed to calculate the cosine similarity, i.e., the correlation, between CARTs in the feature space. By using the achieved average classification accuracy as reference, the grid search method was used to find the inner product threshold. On this basis, the CARTs with low average classification accuracy among CART pairs whose inner product values are higher than the inner product threshold were marked as deletable. The achieved average classification accuracies and correlations of CARTs were comprehensively considered, those with high correlation and weak classification effect were deleted, and those with better quality were retained to construct the random forest. Multiple experiments show that, the proposed improved random forest achieved higher average classification accuracy than the five random forests used for comparison, and the lead was stable. The G-means and out-of-bag data (OBD) score obtained by the proposed improved random forest were also higher than the five random forests, and the lead was more obvious. In addition, the test results of three non-parametric tests show that, there were significant diversities between the proposed improved random forest and the other five random forests. This effectively proves the superiority and practicability of the proposed improved random forest. [ABSTRACT FROM AUTHOR]

• Data driven disruption prediction using random forest algorithm is studied in KSTAR. • The model shows an overall accuracy of 94.7 % in both phases, and the F-1 score is 0.93. • The prediction model will be implemented in the KSTAR plasma control system to trigger a disruption mitigation system to reduce the harmful effects of plasma disruption. Here, we develop a data driven disruption prediction model using the random forest algorithm using a database of KSTAR disruption shots. A total of 719 disruption shots from the past 3 campaigns have been selected to generate a database, which are terminated during the plasma current flattop phase by plasma physics issues and have all the essential diagnostic data. To train and test our machine learning model, the input features known to be associated with plasma disruption were collected from various diagnostic and analysis data. The slice datasets were labeled as 'disruption' less than 40 ms from thermal quench, and the remainder as 'non-disruption'. The random forest-based disruption prediction model was trained and tested against the database. An out-of-bag (OBB) error indicates the optimal value of the 'number of trees' in the random forest model. A confusion matrix with test database shows an overall accuracy of 91 % in both phases, and an F-1 score of 0.915. This model shows the characteristics of disruptions that occur in KSTAR, and it can be helpful for disruption prediction studies of future superconducting tokamaks. [ABSTRACT FROM AUTHOR]

This paper presents a new approach for regression tree-based models, such as simple regression tree, random forest and gradient boosting, in settings involving correlated data. We show the problems that arise when implementing standard regression tree-based models, which ignore the correlation structure. Our new approach explicitly takes the correlation structure into account in the splitting criterion, stopping rules and fitted values in the leaves, which induces some major modifications of standard methodology. The superiority of our new approach over tree-based models that do not account for the correlation, and over previous work that integrated some aspects of our approach, is supported by simulation experiments and real data analyses. [ABSTRACT FROM AUTHOR]

The city of Venice is an extraordinary architectural, artistic and cultural heritage. Unfortunately, its conservation is increasingly threatened by particularly significant high tides. Predicting the tide level in Venice, especially the high waters, is an essential task for the protection of the city and the lagoon. Complex statistical or hydrodynamic models, which require a large amount of input data, are currently used for this purpose. An effective alternative can be provided by models based on Artificial Intelligence algorithms. In this study, several different forecasting models were developed and each model was built in three variants, varying the implemented machine learning algorithm: M5P Regression Tree, Random Forest and Multilayer Perceptron. Until now, regression tree models had never been used to forecast tide levels. All the proposed models proved to be able to forecast the tide level in Venice with good accuracy. The M5P algorithm provided the best performance in most cases. All the models based on M5P were characterized by a coefficient of determination between 0.924 and 0.996, while the Relative Absolute Error was between 5.98 and 26.84%. In addition, good predictions were achieved by neglecting meteorological factors, even in the case of exceptionally high waters. Finally, satisfactory outcomes were also obtained with a forecast horizon of several hours, while a further specific comparison showed that the models based on the considered Machine Learning algorithms are able to outperform the AutoRegressive Integrated Moving Average models with exogenous input variables in forecasting high water. [ABSTRACT FROM AUTHOR]

Summary: A new method for online evaluation of the transient stability of wind farms incorporated system based on random forest regression is proposed in this paper. The data before contingency was employed as the inputs instead of the post fault features. The critical clearing time is employed as the transient stability boundary, which determines how stable the system is after the given contingency. The mapping function between the pre‐contingency conditions and the corresponding critical clearing time is modeled as ensemble regression trees model, which consists of lots of base learner. Through the bootstrap method and the random selection of variables in the training process, the problem of dimensionality disaster can be avoided naturally without the need to specifically select features. The out‐of‐bag error generated during the bootstrap process is used for parameter selection and variable importance measures. Case study on the New England 39‐bus system incorporated wind farms and IEEE 118‐bus system shows that the proposed method has a strong prediction accuracy and generalization ability. [ABSTRACT FROM AUTHOR]

To improve the accuracy of warfarin daily dose prediction, we develop an evolutionary synthetic oversampling technique (ESMOTE) with a cocktail ensemble model (CEM) called ESMOTE-CEM. Different from conventional oversampling methods, ESMOTE finds the near-optimal oversampling parameters by evolving the parameter representation based on the pre-predicted warfarin dose and then synthesizes new samples to balance the data. The CEM, which improves the performance of random forest (RF) and boosted regression tree (BRT) models using a hybrid mechanism in the regression calculation, estimates the daily dose of warfarin. We test the ESMOTE-CEM on a dataset of 733 samples collected from the First Affiliated Hospital of Soochow University and the International Warfarin Pharmacogenetics Consortium (IWPC). The results show that ESMOTE outperformed the other oversampling methods by at least 6.98% for R2 and 5.03% for the mean squared error (MSE). In terms of the percentage of patients whose predicted warfarin dose is within 20% of the actual stable therapeutic dose (20%-p value), the ESMOTE-CEM achieves a 20%-p value of 50%. Moreover, compared to RF, BRT and AdaBoost models, the CEM is the most suitable base predictive model for ESMOTE. [ABSTRACT FROM AUTHOR]

Using remote sensing data to monitor large area drought is one of the important methods of drought monitoring at present. However, the traditional remote sensing drought monitoring methods mainly focus on monitoring single drought response factors such as soil moisture or vegetation status, and the research on comprehensive multi-factor drought monitoring is limited. In order to improve the ability to resist drought events, this paper takes Henan Province of China as an example, takes multi-source remote sensing data as data sources, considers various disaster-causing factors, adopts random forest method to model, and explores the method of regional remote sensing comprehensive drought monitoring using various remote sensing data sources. Compared with neural network, classification regression tree and linear regression, the performance of random forest is more stable and tolerant to noise and outliers. In order to provide a new method for comprehensive assessment of regional drought, a comprehensive drought monitoring model was established based on multi-source remote sensing data, which comprehensively considered the drought factors such as soil water stress, vegetation growth status and meteorological precipitation profit and loss in the process of drought occurrence and development. [ABSTRACT FROM AUTHOR]

Closed production systems, such as plant factories and vertical farms, have emerged to ensure a sustainable supply of fresh food, to cope with the increasing consumption of natural resource for the growing population. In a plant factory, a microclimate model is one of the direct control components of a whole system. In order to better realize the dynamic regulation for the microclimate model, energy-saving and consumption reduction, it is necessary to optimize the environmental parameters in the plant factory, and thereby to determine the influencing factors of atmosphere control systems. Therefore, this study aims to identify accurate microclimate models, and further to predict temperature change based on the experimental data, using the classification and regression trees (CART) algorithm. A random forest theory was used to represent the temperature control system. A mechanism model of the temperature control system was proposed to improve the performance of the plant factories. In terms of energy efficiency, the main influencing factors on temperature change in the plant factories were obtained, including the temperature and air volume flow of the temperature control device, as well as the internal relative humidity. The generalization error of the prediction model can reach 0.0907. The results demonstrated that the proposed model can present the quantitative relationship and prediction function. This study can provide a reference for the design of high-precision environmental control systems in plant factories. [ABSTRACT FROM AUTHOR]

Air pollution has emerged as one of the most urgent problems worldwide over the past few years. Especially, fine particulate matter with a diameter smaller than 2.5 micrometres (PM2.5) has seriously endangered the human life and health worldwide. Thus, monitoring accurate and spatio-temporal continuously PM2.5 concentrations is essential for controlling air pollution. The key to accurately estimating PM2.5 concentrations is to build a reliable aerosol optical depth (AOD)–PM2.5 model, which is mainly determined by the AOD remotely sensed products, meteorological parameters, and estimating methods. However, no systematic evaluation and analysis of the influence of these three variables on AOD–PM2.5 model has yet been reported. Based on Terra and Aqua Moderate Resolution Imaging Spectroradiometer AOD products, reanalysis meteorological data, and ground-based PM2.5 data during 2014–2015 in eastern China, we analyzed the influence of above mentioned variables on the accuracy of the AOD–PM2.5 model. The four modeling methods investigated are stepwise multiple linear regression (SMLR), backpropagation neural network (BPNN), classification and regression tree (CART), and random forest (RF). Adjusted R2, mean absolute error (MAE), product index (PI), spatial resolution index (SRI), and Taylor diagrams are used to assess the accuracy of models. The results show that adding meteorological elements that vary with time and height can improve the accuracy by 4.97% over eastern China. The average PI of Terra AOD products increased by 0.15 compared with that of Aqua AOD products. Most SRIs have positive values, suggesting that AOD products with a spatial resolution of 10 km can lead to a more accurate AOD–PM2.5 model. The Taylor diagram indicates that RF model > BPNN model > CART model > SMLR model in terms of performance. Therefore, Terra AOD products with spatial resolution of 10 km and RF are more suitable for use with the AOD–PM2.5 model in eastern China. [ABSTRACT FROM AUTHOR]

Research background: Even though unintentional accounting errors leading to financial restatements look like less serious distortion of publicly available information, it has been shown that financial restatements impacts on financial markets are similar to intentional fraudulent activities. Unintentional accounting errors leading to financial restatements then affect value of company shares in the short run which negatively impacts all shareholders. Purpose of the article: The aim of this manuscript is to predict unintentional accounting errors leading to financial restatements based on information from financial statements of companies. The manuscript analysis if financial statements include sufficient information which would allow detection of unintentional accounting errors. Methods: Method of classification and regression trees (decision tree) and random forest have been used in this manuscript to fulfill the aim of this manuscript. Data sample has consisted of 400 items from financial statements of 80 selected international companies. The results of developed prediction models have been compared and explained based on their accuracy, sensitivity, specificity, precision and F1 score. Statistical relationship among variables has been tested by correlation analysis. Differences between the group of companies with and without unintentional accounting error have been tested by means of Kruskal-Wallis test. Differences among the models have been tested by Levene and T-tests. Findings & value added: The results of the analysis have provided evidence that it is possible to detect unintentional accounting errors with high levels of accuracy based on financial ratios (rather than the Beneish variables) and by application of random forest method (rather than classification and regression tree method). [ABSTRACT FROM AUTHOR]

The boiling point rise (BPR) is a critical parameter in the operation and optimal design of a multi-stage flash desalination system. Accurate prediction of BPR would increase the efficiency of freshwater production. In this study, original aggregated random intelligent approach (ARIA) models is developed to enhance the prediction of BPR. The ARIA algorithms, similar to a random forest (RF) technique, combine a set of models trained on different subsets of data in an ensemble structure. Five ARIA-type models were developed based on shallow neural network (SNN), deep neural network (DNN), support vector regression (SVR), classification and regression decision tree (CART), and adaptive neuro-fuzzy inference system (ANFIS). Synthesis index (SI) and visual graphs were used to rank models. Results show that the developed ARIA models are far more accurate than their regular counterparts. The ARIAs increase the prediction efficiency of regular modes by up to 25.04 %. The ARIA-ANFIS with the lowest root mean square error (RMSE) of 0.027 °C outperformed other models and regression equations. The developed ARIA-ANFIS decreases the error of corresponding RF prediction by 69.66 % (RMSE = 0.089 °C), which is a significant achievement because RF is a widely recognized model and numerous studies underline the high accuracies of RF applications. • Novel aggregated random intelligent approach (ARIA) is developed. • Several ARIA models were used to enhance the prediction of boiling point rise (BPR) of multi-stage flash desalination system. • The accuracy of ARIAs was compared with their regular counterparts. • The application of ARIAs for the modeling of other complex scientific and engineering problems is recommended. [ABSTRACT FROM AUTHOR]

Forest live fuel load (LFL) models of tree, shrub, and herbaceous layers were established using linear function (LF), power function (PF), K-nearest neighbor (KNN), gradient boosting regression tree (GBRT), and random forest (RF) algorithms to improve the fit and prediction accuracy and reduce the bias of forest LFL models. Multivariate probability proportional to size sampling (MPPS), probability proportional to size sampling (PPS), and probability proportional to frequency sampling (PPF) were used to obtain mean estimates of the forest LFLs, and the sampling accuracies were assessed. We utilized forest stock and biomass survey data (forest fire risk data and forest resource planning and design survey data) from Kunming, Yunnan, China. The results indicated that the RF model had the highest fit and prediction accuracy. The R2 values of the fitted models for the LFLs of Pinus yunnanensis , Quercus spp., Pinus armandi , Eucalyptus spp., other soft broadleaf species, other hard broadleaf species, other conifer species, shrubs, and herbaceous species were 0.79, 0.89, 0.86, 0.88, 0.91, 0.83, 0.88 0.88, and 0.92, respectively. The F-values were 4.652, 2.582, 2.565, 2.551, 2.738, 3.158, 16.156, 3.479, and 8.468, respectively. The sampling results of forest LFLs were much better for MPPS than for PPF and PPS. Moreover, the two-stage MPPS was the most efficient method for estimating tree, shrub, and herbaceous LFLs. The mean estimates of tree fuel loads, shrub fuel loads, and herbaceous fuel loads were 144.7760, 3.8094, and 0.6442 t/hm2, respectively. There were 555 overlapping subunits for the three types of forest LFLs. The proposed method can significantly reduce the cost of LFL surveys and improve estimation accuracy. [Display omitted] • The studies focused on low-cost methods to achieve high estimation accuracy of different types of forest LFLs on the macro scale, especially using existing forest stock and biomass survey data. • Forest LFLs models were established using LF, PF, KNN, GBRT, and RF to improve the fit and prediction accuracy and reduce the bias of forest LFL models. • MPPS, PPS, and PPF were used to obtain mean estimates of the forest LFLs, and the sampling accuracy was assessed. • The results indicated that the RF model had the highest fit and prediction accuracy. • The sampling results of forest LFLs were better for MPPS than for PPF and PPS. The combined efficiency of two-stage sampling was higher than that of simple sampling. [ABSTRACT FROM AUTHOR]

Aiming at the difficulty of data feature selection under different working conditions and the low recognition rate of single classifier in rolling bearing fault diagnosis, this paper proposed a rolling bearing fault diagnosis algorithm based on discrete wavelet transform and random forest. Firstly the proposed method decomposed the vibration signal by discrete wavelet transform to get n-layer approximate coefficients. Then,it used the sigmoid entropy to construct n-dimensional eigenvectors innovatively. The sigmoid entropy could extract the features of non-stationary signals better and improve the diagnostic accuracy. Finally this paper used random forest to diagnose different fault signals of rolling bearing. It used the bearing data provided by the bearing data center website of Case Western Reserve University for experiments. Comparing with the results of traditional classifier(KNN and SVM) and single classification regression tree CART, this method has better diagnostic results. [ABSTRACT FROM AUTHOR]

Mass movements are among the most dangerous natural hazards in mountainous regions. The present study employs machine learning (ML) models for mass movement susceptibility mapping (MMSM) in Iran based on a comprehensive dataset of 864 mass movements which include debris flow, landslide, and rockfall during the last 42 years (1977–2019) as well as 12 conditional factors. The results of validation stage show that RF (random forest) is the most viable model for mass movement susceptibility maps. In addition, MARS (multivariate adaptive regression splines), MDA (mixture discriminant additive), and BRT (boosted regression trees) models also provide relatively accurate results. Results of the AUC for validation of produced maps were 0.968, 0.845, 0.828, and 0.765 for RF, MARS, MDA, and BRT, respectively. Based on MMSM generated by RF model, 32% of study area is identified to be under high and very high susceptibility classes. Most of the endangered areas for mass movement are in the west and central parts of the Chaharmahal and Bakhtiari Province. In addition, our findings indicate that elevation, slope angle, distance from roads, and distance from faults are critical factors for mass movement. Our results provide a perspective view for decision makers to mitigate natural hazards. [ABSTRACT FROM AUTHOR]

This paper explores the use of discrete event simulation (DES) for decision making in real time based on the potential for data streamed from production line sensors. Technological innovations for data collection and an increasingly competitive global market have led to an increase in the application of discrete event simulation by manufacturing companies in recent years. Scenario analysis and optimisation methods are often applied to these simulation models to improve objectives such as cost, profit and throughput. The literature review has identified key research gaps as the lack of example cases where multi-objective optimisation methods have been applied to simulation models and the need for a framework to visualise the relationship between inputs and outputs of simulation models. A framework is presented to enable the optimisation DES simulation models and optimise multiple objectives simultaneously using design of experiments and meta-models to create a Pareto front of solutions. The results show that the resource allocation meta-model provides acceptable prediction accuracy whilst the lead time meta-model was not able to provide accurate prediction. Regression trees have been proposed to assist stakeholders with understanding the relationships between input and output variables. The framework uses regression and classification trees with overlaid values for multiple objectives and random forests to improve prediction accuracy for new points. A real-life test case involving a turbine assembly process is presented to illustrate the use and validity of the framework. The generated regression tree expressed a general trend by demonstrating relationships between input variables and two conflicting objectives. Random forests were implemented for creating higher accuracy predictions and they produced a mean square error of ~ 0.066 on the training data and ~ 0.081 on test data. [ABSTRACT FROM AUTHOR]

Phenotyping of native cultivars is becoming more essential, as they are an important for breeders as a genetic source for breeding. The variability of morphological properties plays critical role in melon breeding. In this paper various machine learning approaches were implemented to identify melon accession classes. A field experiment was conducted in Zahak Agriculture station to differentiate 144 melon accessions based on 14 traits. For this, Partial Least Square Discriminant Analysis (PLS-DA), Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (KNN) and Classification And Regression Trees (CART) were compared. The most commonly used performance values comprise overall accuracy, kappa value, Receiver Operating Characteristics (ROC) and Area Under Curve (AUC) were performed to identify accuracy of the models. The results showed the best performance for CART than others. The AUC and kappa value were 0.85 and 0.80 and fruit weight was the most important trait that affecting diversity in melon accessions. Regarding to these results Classification And Regression Trees (CART) is reliable for identification of melon accessions classes. [ABSTRACT FROM AUTHOR]