Ensemble Of Regression Trees Research Articles

Comparing emulation methods for a high‐resolution storm surge model

AbstractRealistic simulations of complex systems are fundamental for climate and environmental studies. Large computer systems are often not sufficient to run sophisticated computational models for large numbers of different input settings. Statistical surrogate models, or emulators, are key tools enabling fast exploration of the simulator input space. Gaussian processes have become standard for computer simulator emulation. However, they require careful implementation to scale appropriately, motivating alternative methods more recently introduced. We present a comparison study of surrogates of the Sea, Lake, and Overland Surges from Hurricanes (SLOSH) simulator—the simulator of choice for government agencies—using four emulation approaches: BASS; BART; SEPIA; and RobustGaSP. SEPIA and RobustGaSP use Gaussian processes, BASS implements adaptive splines, and BART is based on ensembles of regression trees. We describe the four models and compare them in terms of computation time and predictive metrics. These surrogates use proven and distinct methodologies, are available through accessible software, and quantify prediction uncertainty. Our data cover millions of response values. We find that SEPIA and RobustGaSP provide exceptional predictive power, but cannot scale to emulate experiments as large as the one considered in this paper as effectively as BASS and BART.

Interpretable Machine Learning for Prediction of Post-Fire Self-Healing of Concrete.

Developing accurate and interpretable models to forecast concrete's self-healing behavior is of interest to material engineers, scientists, and civil engineering contractors. Machine learning (ML) and artificial intelligence are powerful tools that allow constructing high-precision predictions, yet often considered "black box" methods due to their complexity. Those approaches are commonly used for the modeling of mechanical properties of concrete with exceptional accuracy; however, there are few studies dealing with the application of ML for the self-healing of cementitious materials. This paper proposes a pioneering study on the utilization of ML for predicting post-fire self-healing of concrete. A large database is constructed based on the literature studies. Twelve input variables are analyzed: w/c, age of concrete, amount of cement, fine aggregate, coarse aggregate, peak loading temperature, duration of peak loading temperature, cooling regime, duration of cooling, curing regime, duration of curing, and specimen volume. The output of the model is the compressive strength recovery, being one of the self-healing efficiency indicators. Four ML methods are optimized and compared based on their performance error: Support Vector Machines (SVM), Regression Trees (RT), Artificial Neural Networks (ANN), and Ensemble of Regression Trees (ET). Monte Carlo analysis is conducted to verify the stability of the selected model. All ML approaches demonstrate satisfying precision, twice as good as linear regression. The ET model is found to be the most optimal with the highest prediction accuracy and sufficient robustness. Model interpretation is performed using Partial Dependence Plots and Individual Conditional Expectation Plots. Temperature, curing regime, and amounts of aggregates are identified as the most significant predictors.

A Closer Look at the Kernels Generated by the Decision and Regression Tree Ensembles

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 from several 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.

A comparative assessment of machine learning methods for predicting housing prices using Bayesian optimization

The valuation of house prices is drawing noteworthy attention due to worldwide financial and real estate crises in the last decade. Therefore, there is an immediate need to design more effective predictive systems of house prices. Indeed, investors, creditors, and governments are all interested in such predictive systems to improve their buying and lending decisions and activities. This study explores the application of artificial intelligence, machine learning, and nonlinear statistical models to house price prediction problems. In that order, we use boosting ensemble regression trees, support vector regression, and Gaussian process regression. Bayesian optimization is implemented in a ten-fold cross-validation framework to determine their respective optimal kernels and parameter values. Four performance metrics are used to evaluate the prediction ability of each predictive system. The experimental results showed that boosting ensemble regression trees performed the best, followed by Gaussian process regression and support vector regression. In addition, all three aforementioned predictive systems outperformed artificial neural networks and multi-variate regression employed in recent work on the same data set. Under this perspective, it is concluded that boosting ensemble regression trees are clear candidates to be considered for operational house price prediction in Taiwan.

Machine learning-based beta transus temperature prediction for titanium alloys

Beta transus temperature (βtr) is one of the most crucial features of titanium alloys. It is typically used as the index while designing the heat treatment process for titanium alloys. The βtr is also a significant parameter to optimize the processing technology of titanium alloys. Four machine learning algorithms and one empirical formula is developed in this study to estimate the βtr of titanium alloys: Artificial Neural Networks (ANN), Gauss Processing Regression (GPR), Super Vector Machine (SVM), and Ensemble Regression Trees (ERT). According to the correlation coefficient (R), Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) to verify the accuracy of models, and the experimentally measured phase transition temperature of Ti600 alloy was also used to verify the generalization ability of the model. Choosing the best model to analyze the sensitivity of the elements and determine how each component affects the βtr. The result demonstrated that the ANN model has the highest prediction accuracy among the five models, and different model structures have different effects on predicting new data. The ANN model with 10 neurons has the highest prediction accuracy, while the ANN model with 8 neurons has the strongest generalization ability. The results of the sensitivity analysis proved that all the alloy compositions used as input parameters were valid parameters.

Investigation of the Effect of ECAP Parameters on Hardness, Tensile Properties, Impact Toughness, and Electrical Conductivity of Pure Cu through Machine Learning Predictive Models.

Copper and its related alloys are frequently adopted in contemporary industry due to their outstanding properties, which include mechanical, electrical, and electronic applications. Equal channel angular pressing (ECAP) is a novel method for producing ultrafine-grained or nanomaterials. Modeling material design processes provides exceptionally efficient techniques for minimizing the efforts and time spent on experimental work to manufacture Cu or its associated alloys through the ECAP process. Although there have been various physical-based models, they are frequently coupled with several restrictions and still require significant time and effort to calibrate and enhance their accuracies. Machine learning (ML) techniques that rely primarily on data-driven models are a viable alternative modeling approach that has recently achieved breakthrough achievements. Several ML algorithms were used in the modeling training and testing phases of this work to imitate the influence of ECAP processing parameters on the mechanical and electrical characteristics of pure Cu, including the number of passes (N), ECAP die angle (φ), processing temperature, and route type. Several experiments were conducted on pure commercial Cu while altering the ECAP processing parameters settings. Linear regression, regression trees, ensembles of regression trees, the Gaussian process, support vector regression, and artificial neural networks are the ML algorithms used in this study. Model predictive performance was assessed using metrics such as root-mean-squared errors and R2 scores. The methodologies presented here demonstrated that they could be effectively used to reduce experimental effort and time by reducing the number of experiments runs required to optimize the material attributes aimed at modeling the ECAP conditions for the following performance characteristics: impact toughness (IT), electrical conductivity (EC), hardness, and tensile characteristics of yield strength (σy), ultimate tensile strength (σu), and ductility (Du).

Artificial Intelligence to Assess the Systemic Impact of Malignant Plasma Cell Clone in Patients with Plasma Cell Dyscrasia

Multiple Myeloma (MM) presents as a multi-system disease with significant derangements in the immune system, hematopoiesis, renal function, bone metabolism and electrolyte homeostasis. End-organ damage is the key factor that differentiates plasma cell (PC) dyscrasia requiring therapy, i.e., active MM, from disease precursor stages (Monoclonal Gammopathy of Undetermined Significance, MGUS and Smoldering MM, SMM) that do not require therapy. The prevailing assumption is that MGUS and SMM patients do not harbor significant or measureable systemic impact of clonal PCs. Therefore, a watch-and-wait approach is employed in MGUS and SMM patients until end-organ damage is evident. Here, we hypothesized that the systemic impact of clonal PCs is a continuum throughout disease progression, rather than a binary process, and that the impact on organ systems correlates directly with the volume of the malignant clone as measured by monoclonal protein levels. Therefore, to capture the systemic impact of PC clones, we utilized a Machine Learning (ML) approach that incorporates all available clinical and lab variables. Methods: A total of 171 patients with PC dyscrasias including 1,472 observations were analyzed. Forty-three clinical and lab variables were identified as predictors of M-spike protein levels and then fed into the ML model. Two lagged variables as the last two preceding M-spike values by the same subject were included. When needed, imputation for missing values was applied through interpolation from subject-level linear trend analysis. The random forest model was used, where regression forests are an ensemble of different regression trees and are used for nonlinear multiple regression. The default number of trees was set at n = 500, and the number of variables considered at each split after random selection was 13. The goal of using a large number of trees was to train enough that each feature had a chance to appear in several models. The data was randomly split into a training set, N=136 (80%) and a test set, N=35 (20%), and a regression tree was built with the training set and then validated using the test set. Bootstrapping was used to generate a collection of data sets (n=500), leading to a random forest of regression trees. Results and estimates were combined across trees. Importance was measured by leaving a covariate out of models, and comparing performance with its inclusion. All analyses were performed using R v3.6.2 and its libraries. Results: Median age of patients included in the study cohort was 73 years (range: 42-96), and 44% were male. Median M-spike value was (0.7 gr/dL, range: 0.1-3.5). Fig. 1 shows the number of observations and magnitude distribution for M-spike levels among the patients included in our study. As shown in Fig. 2, M-spike levels predicted by the ML algorithm, calculated M-spike in the test set, correlated highly with the observed M-spike levels in the test set (R-square: 94% and RMSE of 0.21). The Pearson and Spearman coefficients were 0.97 and 0.95, respectively. Fig. 3b. Indicates the residual distribution for the RF model with most of values are close to and on both side zero value. Conclusions: Here, we assessed the multi-system impact of plasma cell clone using a ML algorithm. Our results show that the degree of systemic involvement induced by the clone correlates directly with magnitude of the ML-calculated M-spike value. Applying this algorithm in longitudinal studies of patients with MGUS and SMM is warranted to detect the optimal point of multi-systemic impact of clonal PCs to start therapy. Figure 1View largeDownload PPTFigure 1View largeDownload PPT Close modal

Machine Learning‐Based Solution for Thermomechanical Analysis of MMIC Packaging

AbstractThermomechanical analysis of monolithic microwave integrated circuit (MMIC) packaging is essential to guarantee the reliability of radio frequency/microwave applications. However, a method for fast and accurate analysis of MMIC packaging structures has not been developed. Here, a machine learning (ML)‐based solution for thermomechanical analysis of MMIC packaging is demonstrated. This ML‐based solution analyzes temperature and thermal stresses considering key design parameters, including material properties, geometric characteristics, and thermal boundary conditions. Finite element simulation with the Monte Carlo method is utilized to prepare a large dataset for supervised learning and validation of the ML solution, and a laser‐assisted thermal experiment is conducted to verify the accuracy of the simulation. After data preparation, regression tree ensemble and artificial neural network (ANN) learning models are investigated. The results show that the ANN model accurately predicts the outcomes with extremely low computing time by analyzing the high‐dimensional dataset. Finally, the developed ML solution is deployed as a web application format for facile approaches. It is believed that this study will provide a guideline for developing ML‐based solutions in chip packaging design technology.

Sparse prediction informed by genetic annotations using the logit normal prior for Bayesian regression tree ensembles.

Using high-dimensional genetic variants such as single nucleotide polymorphisms (SNP) to predict complex diseases and traits has important applications in basic research and other clinical settings. For example, predicting gene expression is a necessary first step to identify (putative) causal genes in transcriptome-wide association studies. Due to weak signals, high-dimensionality, and linkage disequilibrium (correlation) among SNPs, building such a prediction model is challenging. However, functional annotations at the SNP level (e.g., as epigenomic data across multiple cell- or tissue-types) are available and could be used to inform predictor importance and aid in outcome prediction. Existing approaches to incorporate annotations have been based mainly on (generalized) linear models. Bayesian additive regression trees (BART), in contrast, is a reliable method to obtain high-quality nonlinear out of sample predictions without overfitting. Unfortunately, the default prior from BART may be too inflexible to handle sparse situations where the number of predictors approaches or surpasses the number of observations. Motivated by our real data application, this article proposes an alternative prior based on the logit normal distribution because it provides a framework that is adaptive to sparsity and can model informative functional annotations. It also provides a framework to incorporate prior information about the between SNP correlations. Computational details for carrying out inference are presented along with the results from a simulation study and a genome-wide prediction analysis of the Alzheimer's Disease Neuroimaging Initiative data.

Forecasting Day-Ahead Carbon Price by Modelling Its Determinants Using the PCA-Based Approach

Accurate price forecasts on the EU ETS market are of interest to many production and investment entities. This paper describes the day-ahead carbon price prediction based on a wide range of fuel and energy indicators traded on the Intercontinental Exchange market. The indicators are analyzed in seven groups for individual products (power, natural gas, coal, crude, heating oil, unleaded gasoline, gasoil). In the proposed approach, by combining the Principal Component Analysis (PCA) method and various methods of supervised machine learning, the possibilities of prediction in the period of rapid price increases are shown. The PCA method made it possible to reduce the number of variables from 37 to 4, which were inputs for predictive models. In the paper, these models are compared: regression trees, ensembles of regression trees, Gaussian Process Regression (GPR) models, Support Vector Machines (SVM) models and Neural Network Regression (NNR) models. The research showed that the Gaussian Process Regression model turned out to be the most advantageous and its price prediction can be considered very accurate.

Learning Cephalometric Landmarks for Diagnostic Features Using Regression Trees.

Lateral cephalograms provide important information regarding dental, skeletal, and soft-tissue parameters that are critical for orthodontic diagnosis and treatment planning. Several machine learning methods have previously been used for the automated localization of diagnostically relevant landmarks on lateral cephalograms. In this study, we applied an ensemble of regression trees to solve this problem. We found that despite the limited size of manually labeled images, we can improve the performance of landmark detection by augmenting the training set using a battery of simple image transforms. We further demonstrated the calculation of second-order features encoding the relative locations of landmarks, which are diagnostically more important than individual landmarks.

Prediction of Mechanical Properties of Highly Functional Lightweight Fiber-Reinforced Concrete Based on Deep Neural Network and Ensemble Regression Trees Methods.

Currently, one of the topical areas of application of artificial intelligence methods in industrial production is neural networks, which allow for predicting the performance properties of products and structures that depend on the characteristics of the initial components and process parameters. The purpose of the study was to develop and train a neural network and an ensemble model to predict the mechanical properties of lightweight fiber-reinforced concrete using the accumulated empirical database and data from construction industry enterprises, and to improve production processes in the construction industry. The study applied deep learning and an ensemble of regression trees. The empirical base is the result of testing a series of experimental compositions of fiber-reinforced concrete. The predicted properties are cubic compressive strength, prismatic compressive strength, flexural tensile strength, and axial tensile strength. The quantitative picture of the accuracy of the applied methods for strength characteristics varies for the deep neural network method from 0.15 to 0.73 (MAE), from 0.17 to 0.89 (RMSE), and from 0.98% to 6.62% (MAPE), and for the ensemble of regression trees, from 0.11 to 0.62 (MAE), from 0.15 to 0.80 (RMSE), and from 1.30% to 3.4% (MAPE). Both methods have shown high efficiency in relation to such a hard-to-predict material as concrete, which is so heterogeneous in structure and depends on many factors. The value of the developed models lies in the possibility of obtaining additional useful information in the process of preparing highly functional lightweight fiber-reinforced concrete without additional experiments.

Hyperparameter Optimization on Ensemble Regression Tree for Lip Coloring Simulation

Technology helps us in many activities and keeps growing, so it makes activities more efficient, time-saving, using fewer resources and also information and entertainment are accessible. Machine Learning technology is the fastest-growing field in computer science that is used in many areas such as marketing, healthcare, manufacturing, information security, and transportation. One of the machine learning methods is the Ensemble of Regression Tree (ERT) which has succeeded in detecting facial features on the eyebrows, eyes, nose, and lips. However, utilization ERT method has not been found to detect specific areas such as lips only for gaining optimization. Then this research will be conducted to extract the facial feature annotation dataset from the iBUG 300W dataset with 68 facial features to 20 lip area points. The results of the extraction are reduced error rate, resources saving, lip features still detected and lip coloring simulation was successfully carried out using the configuration of hyperparameter values, tree = 4, regularization = 0.25, cascade = 8, feature pool = 500, oversampling = 40 and translation jitter = 0. From observations also discovered optimization that hard disk resource savings are 69.36%, RAM 30.8%, and CPU 3.8%; reduce the error rate by 0.058%; and increase inference speed by 39%.

Regional medical inter-institutional cooperation in medical provider network constructed using patient claims data from Japan.

The aging world population requires a sustainable and high-quality healthcare system. To examine the efficiency of medical cooperation, medical provider and physician networks were constructed using patient claims data. Previous studies have shown that these networks contain information on medical cooperation. However, the usage patterns of multiple medical providers in a series of medical services have not been considered. In addition, these studies used only general network features to represent medical cooperation, but their expressive ability was low. To overcome these limitations, we analyzed the medical provider network to examine its overall contribution to the quality of healthcare provided by cooperation between medical providers in a series of medical services. This study focused on: i) the method of feature extraction from the network, ii) incorporation of the usage pattern of medical providers, and iii) expressive ability of the statistical model. Femoral neck fractures were selected as the target disease. To build the medical provider networks, we analyzed the patient claims data from a single prefecture in Japan between January 1, 2014 and December 31, 2019. We considered four types of models. Models 1 and 2 use node strength and linear regression, with Model 2 also incorporating patient age as an input. Models 3 and 4 use feature representation by node2vec with linear regression and regression tree ensemble, a machine learning method. The results showed that medical providers with higher levels of cooperation reduce the duration of hospital stay. The overall contribution of the medical cooperation to the duration of hospital stay extracted from the medical provider network using node2vec is approximately 20%, which is approximately 20 times higher than the model using strength.

Detection of Student Drowsiness Using Ensemble Regression Trees in Online Learning During a COVID-19 Pandemic

Online lectures are mandatory to deal with the implementation of education during the COVID-19 pandemic. This significant change certainly creates a different experience for students. Regarding online learning, several public health experts and ophthalmologists say that residual radiation from electronic screens is causing an epidemic of eye fatigue. Research on smart classrooms actually appeared several years ago, but in reality it has not been implemented according to the planned concept. The current smart classroom research environment only uses outdated methods, which make the computer system incongruent (such as decision trees in video feeds) or only to the level of empirical studies or blueprints, which are not much help for other academic footing or reference materials. to students. This study aims to build an intelligent system that can evaluate students' attention during online classes, use teaching videos as learning feeds and input for predictions and also use advanced algorithms in several computational domains, namely face segmentation, landmarking, PERCLOS observations, Yawning and decision analysis using Ensemble Regression Trees to detect students' sleepiness, which is expected to patch up the shortcomings of the PERCLOS algorithm and the problems found in the single regression tree-based implementation. Based on the results of the tests that have been carried out, the system developed has been able to observe sleepy objects in learning videos with an accuracy of 80% so that later it can be a lesson for teachers why there are students who are sleepy during online classes either because of uninteresting material or other reasons.

Face Detection by Measuring Thermal Value to Avoid Covid-19

In this study, custom Single Shot Detection (SSD) was used to detect infected people faces because of Covid-19. It has been suggested to determine around the eyes area where the body temperature of the person most accurate by determining the facial landmarks with Ensemble of Regression Trees (ERT) model on these detected faces. Finally, the thermal value was measured from around the eyes area in a non-contact way using sensor fusion. As a result of the analyzes made, it was observed that the proposed system gave results close to the different measurement methods

Application of Soft Computing in Predicting Groundwater Quality Parameters

Evaluating the quality of groundwater in a specific aquifer could be a costly and time-consuming procedure. An attempt was made in this research to predict various parameters of water quality called Fe, Cl, SO4, pH and total hardness (as CaCO3) by measuring properties of total dissolved solids (TDSs) and electrical conductivity (EC). This was reached by establishing relations between groundwater quality parameters, TDS and EC, using various machine learning (ML) models, such as linear regression (LR), tree regression (TR), Gaussian process regression (GPR), support vector machine (SVM), and ensembles of regression trees (ER). Data for these variables were gathered from five unrelated groundwater quality studies. The findings showed that the TR, GPR, and ER models have satisfactory performance compared to that of LR and SVM with respect to different assessment criteria. The ER model attained higher accuracy in terms of R2 in TDS 0.92, Fe 0.89, Cl 0.86, CaCO3 0.87, SO4 0.87, and pH 0.86, while the GPR model attained an EC 0.98 compared to all developed models. Moreover, comparisons among the different developed models were performed using accuracy improvement (AI), improvement in RMSE (PRMSE), and improvement in PMAE to determine a higher accuracy model for predicting target properties. Generally, the comparison of several data-driven regression methods indicated that the boosted ensemble of the regression tree model offered better accuracy in predicting water quality parameters. Sensitivity analysis of each parameter illustrates that CaCO3 is most influential in determining TDS and EC. These results could have a significant impact on the future of groundwater quality assessments.

A Decision Support Tool for Buying Farm Tractors, Based on Predictive Analytics

Data science can help farmers when making a decision about tractor purchase. Buying a tractor represents a big investment for farmers, and price is one of their main concerns. This study presents the development of a web-based decision support tool (DST) that calculate the price of new and second-hand tractors, for the purpose of providing the decision-maker some information that will lead him to the final decision. The tool makes use of different algorithms based on predictive analytics methodologies. The dataset has information about 227 different observations of new tractors and 1003 of second-hand tractors, from different European countries. During the study, the prices of new and used tractor were modeled, testing parametric and non-parametric regression models with different segmentations and predictor variables. Non parametric models includes regression trees, support vector machines, ensembles of regression trees, Gaussian process, and neural networks. In both cases, for predicting the prices of new and second-hand tractors, adjusted R2 higher than 0.99 were achieved. The models developed were implemented in the DST which is fully operative, available in Internet, and free to use.

A machine learning model based on readers’ characteristics to predict their performances in reading screening mammograms

ObjectivesProposing a machine learning model to predict readers’ performances, as measured by the area under the receiver operating characteristics curve (AUC) and lesion sensitivity, using the readers’ characteristics.MethodsData were collected from 905 radiologists and breast physicians who completed at least one case-set of 60 mammographic images containing 40 normal and 20 biopsy-proven cancer cases. Nine different case-sets were available. Using a questionnaire, we collected radiologists’ demographic details, such as reading volume and years of experience. These characteristics along with a case set difficulty measure were fed into two ensemble of regression trees to predict the readers’ AUCs and lesion sensitivities. We calculated the Pearson correlation coefficient between the predicted values by the model and the actual AUC and lesion sensitivity. The usefulness of the model to categorize readers as low and high performers based on different criteria was also evaluated. The performances of the models were evaluated using leave-one-out cross-validation.ResultsThe Pearson correlation coefficient between the predicted AUC and actual one was 0.60 (p < 0.001). The model’s performance for differentiating the reader in the first and fourth quartile based on the AUC values was 0.86 (95% CI 0.83–0.89). The model reached an AUC of 0.91 (95% CI 0.88–0.93) for distinguishing the readers in the first quartile from the fourth one based on the lesion sensitivity.ConclusionA machine learning model can be used to categorize readers as high- or low-performing. Such model could be useful for screening programs for designing a targeted quality assurance and optimizing the double reading practice.

Regression Tree Ensemble Rainfall–Runoff Forecasting Model and Its Application to Xiangxi River, China

The development of an efficient and accurate hydrological forecasting model is essential for water management and flood control. In this study, the ensemble model was applied to predict the daily discharge; it not only could enhance the algorithm and improve the learning accuracy, but it was also the most effective representative model among various combinations of learning parameters. Using the survey data of Xingshan station in Xiangxi River, China, the suitability of the model was proven. The performance of the ensemble model was compared with the multiple linear regression model and the artificial neural network models. Furthermore, the length of the training samples and the peak value predictions were analyzed. The results showed that, firstly, the best effect of the discharge simulation model appeared in the ensemble model, while the simulation accuracy of the multiple linear regression model was lower than that of the artificial neural network model in some cases. Secondly, the prediction effect of the ensemble model for discharge was better than that of the single model to some extent, whereby the maximum absolute value of relative error was 8.11% using the ensemble model. A comprehensive analysis showed that the ensemble model was optimal. Furthermore, the ensemble model performed outstandingly in terms of hydrological forecasting. The ensemble model also provided theoretical support for hydrological forecasting and could be considered as an alternative to multiple linear regression models and artificial neural networks.