M5 Model Tree Research Articles

A comparative study of black-box and white-box data-driven methods to predict landfill leachate permeability.

Due to the dynamic and complexity of leachate percolation within municipal solid waste (MSW), planning and operation of solid waste management systems are challenging for decision-makers. In this regard, data-driven methods can be considered robust approaches to modeling this problem. In this paper, three black-box data-driven models, including artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), and support vector regression (SVR), and also three white-box data-driven models, including the M5 model tree (M5MT), classification and regression trees (CART), and group method of data handling (GMDH), were developed for modeling and predicting landfill leachate permeability ([Formula: see text]). Based on a previous study conducted by Ghasemi et al. (2021), [Formula: see text] can be formulated as a function of impermeable sheets ([Formula: see text]) and copper pipes ([Formula: see text]). Hence, in the present study, [Formula: see text] and [Formula: see text] were adopted as input variables for the prediction of [Formula: see text] and evaluated for the performance of the suggested black-box and white-box data-driven models. Scatter plots and statistical indices such as coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) were used for qualitative and quantitative evaluations of the effectiveness of the suggested methods. The outcomes indicated all of the provided models successfully predicted [Formula: see text]. However, ANN and GMDH had higher accuracy between the proposed black-box and white-box data-driven models. ANN with R2 = 0.939, RMSE = 0.056, and MAE = 0.017 was marginally better than GMDH with R2 = 0.857, RMSE = 0.064, and MAE = 0.026 in the testing stage. Nevertheless, an explicit mathematical expression provided by GMDH to predict k was easier and more understandable than ANN.

Statistical quality control based on control charts and process efficiency index by the application of fuzzy approach (case study: Ha'il, Saudi Arabia).

Fuzzy methods using linguistic expressions and fuzzy numbers can provide a more accurate examination of manufacturing systems where data is not clear. Researchers expanded fuzzy control charts (CCs) using fuzzy linguistic statements and investigated the current process efficiency index to evaluate the performance, precision, and accuracy of the production process in a fuzzy state. Compared to nonfuzzy data mode, fuzzy linguistic statements provided decision makers with more options and a more accurate assessment of the quality of products. The fuzzy index of the actual process efficiency analyzed the process by considering mean, target value, and variance of the process simultaneously. Inspection of household water meters in Ha'il, Saudi Arabia showed the actual process index values were less than 1, indicating unfavorable production conditions. Fuzzy methods enhance the accuracy and effectiveness of statistical quality control in real-world systems where precise information may not be readily available. In addition, to provide a new perspective on the comparison of urban water and sewage systems, the results obtained from fuzzy-CC were compared with various machine learning methods such as artificial neural network and M5 model tree, in order to identify and understand their respective advantages and limitations.

Estimation of the Ultimate Strength of FRP Strips-to-Masonry Substrates Bond

Fiber-Reinforced Polymers (FRP) were developed as a new method over the past decades due to their many beneficial mechanical properties, and they are commonly applied to strengthen masonry structures. In this paper, the Artificial Neural Network (ANN), K-fold Cross-Validation (KFCV) technique, Multivariate Adaptive Regression Spline (MARS) method, and M5 Model Tree (M5MT) method were utilized to predict the ultimate strength of FRP strips applied on masonry substrates. The results obtained via ANN, KFCV, MARS, and M5MT were compared with the existing models. The results clearly indicate that the considered approaches have better efficiency and higher precision compared to the models available in the literature. The correlation coefficient values for the considered models (i.e., ANN, KFCV, MARS, and M5MT) are promising results, with up to 99% reliability.

Machine learning techniques in estimation of eggplant crop evapotranspiration

This study predicted the daily evapotranspiration of eggplant (Solanum melongena L.) under full and deficit irrigation in the Bafra district of Samsun province, Turkey, using machine learning methods. Artificial neural networks (ANNs), deep neural networks (DNN), M5 model tree (M5Tree), random forest (RF), support vector machine (SVM), k-nearest neighbor (kNN), and adaptive boosting were investigated as machine learning approaches. Determination of evapotranspiration in this study consists of three methods: (i) The reference evapotranspiration (ETo) was obtained from the Food and Agriculture Organization-56 Penman–Monteith equation, (ii) the values of evapotranspiration (ETc) calculated by multiplying the reference evapotranspiration by the crop coefficient (Kc), and (iii) the values of evapotranspiration (ETa) measured using soil water balance between successive soil water measurements as the outputs. The model’s performance in ETo estimation was higher when minimum and maximum temperature (Tmax and Tmin), wind speed (u2), average relative humidity (RHavg), solar radiation (Rs), and days of the year were used as inputs. The best performance was obtained in the ANN model with a coefficient of determination (R2) value of 0.984, a mean absolute error (MAE) of 0.098 mm d−1, a root-mean-square error (RMSE) of 0.153 mm d−1, and Nash–Sutcliffe efficiency of 0.983. The model’s performance in ETc estimation was significantly improved with the addition of leaf area index (LAI) and crop height (hc) to the climate parameters (MAE and RMSE values decreased by 22.6 and 23.2%, respectively). The accuracy of ETc estimation for some plant traits (hc and LAI) and average temperature (Tavg) was sufficient. The best statistical performance in estimating ETa was obtained by the RF model (Tavg, u2, RHavg, and Rs) using climate parameters. DNN proved to be the least successful model compared to the other six models in predicting ETo, ETc, and ETa.

Evaluation of River Water Quality Index Using Remote Sensing and Artificial Intelligence Models

To restrict the entry of polluting components into water bodies, particularly rivers, it is critical to undertake timely monitoring and make rapid choices. Traditional techniques of assessing water quality are typically costly and time-consuming. With the advent of remote sensing technologies and the availability of high-resolution satellite images in recent years, a significant opportunity for water quality monitoring has arisen. In this study, the water quality index (WQI) for the Hudson River has been estimated using Landsat 8 OLI-TIRS images and four Artificial Intelligence (AI) models, such as M5 Model Tree (MT), Multivariate Adaptive Regression Spline (MARS), Gene Expression Programming (GEP), and Evolutionary Polynomial Regression (EPR). In this way, 13 water quality parameters (WQPs) (i.e., Turbidity, Sulfate, Sodium, Potassium, Hardness, Fluoride, Dissolved Oxygen, Chloride, Arsenic, Alkalinity, pH, Nitrate, and Magnesium) were measured between 14 March 2021 and 16 June 2021 at a site near Poughkeepsie, New York. First, Multiple Linear Regression (MLR) models were created between these WQPs parameters and the spectral indices of Landsat 8 OLI-TIRS images, and then, the most correlated spectral indices were selected as input variables of AI models. With reference to the measured values of WQPs, the WQI was determined according to the Canadian Council of Ministers of the Environment (CCME) guidelines. After that, AI models were developed through the training and testing stages, and then estimated values of WQI were compared to the actual values. The results of the AI models’ performance showed that the MARS model had the best performance among the other AI models for monitoring WQI. The results demonstrated the high effectiveness and power of estimating WQI utilizing a combination of satellite images and artificial intelligence models.

Modelling energy performance of residential dwellings by using the MARS technique, SVM-based approach, MLP neural network and M5 model tree

Several previous studies indicate that the energy consumption of buildings has increased steadily during the last decades all over the world. Residential dwellings in European countries are lawfully required to meet the suitable minimum needs concerning energy efficiency according to the European Directives. Specifically heating, ventilation and air conditioning (HVAC) devices represent most of the energy use in dwellings as they have a principal purpose in controlling the inner climate. Hence, one manner to relieve the constantly growing request for supplementary energy supply is to carry more efficient dwelling designs from the energy point of view, which is to say, with superior energy conservation properties. In this sense, an accurate estimation of the heating load (HL) and cooling load (CL) is needed to calculate the detailed descriptions of the heating and cooling device needed to support comfortable indoor air conditions. The goal of this investigation was to acquire some foretold models to achieve a tangible calculation of the HL and CL (output variables) as a function of 8 specific input variables (concretely, relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area and glazing area distribution) at residential dwellings. These eight input factors have been often employed in the literature about the energy performance of dwellings (EPB) to analyse energy-related themes in dwellings. Moreover, a support vector machines (SVM) approach with distinct kernels, an artificial neural network (ANN) of multilayer perceptron network (MLP) kind and M5 model tree were adjusted to the observed data for evaluation of differences. The outcomes of the current investigation are two-fold. First, the importance (or strength) of each input variable on the HL and CL (output variables) is presented through the MARS model. Secondly, the MARS-relied approximation was the most excellent predictor of the EPB. Indeed, a MARS regression was conducted and coefficients of determination equal to 0.9961 for the HL estimation and 0.9651 for the CL estimation were gotten when this approach was employed to 768 diverse residential buildings, respectively. The concordance between the observed data and those predicted with the MARS approximation verified the satisfactory performance of the latter. Finally, the conclusions of this original investigation are summarised.

Evaluation of Hybrid Soft Computing Model’s Performance in Estimating Wave Height

In coastal and port engineering, wind-generated waves have always been a crucial, fundamental, and important topic. As a result, various methods for estimating wave parameters, including field measurement and numerical methods, have been proposed over time. This study evaluates the wave height at Sri-Lanka Hambantota Port using soft computing models such as Artificial Neural Networks (ANNs) and the M5 model tree (M5MT). In order to overcome its nonstationarity, the primary wave height time series were divided into subtime series using the wavelet transform. The collected subtime series were then utilized as input data for ANN and M5MT in order to determine the wave height. For the sake of the model performance, the daily wind and wave data from the Acoustic Wave and Current (AWAC) sensor for Hambantota Port in 2020 and Sanmen Bay in 2017 were used in this study. The training state utilizes 80% of the available data, while the test state uses 20%. The Root Mean Square Error (RMSE) of the ANN, M5, WANN, and Wavelet-M5 models in the Hambantota Port for the test stage are 0.12, 0.11, 0.04, and 0.06, respectively. While in Sanmen Bay, the RMSE of the ANN, M5, WANN, and Wavelet-M5 models for the test stage are 0.14, 0.16, 0.06, and 0.08, respectively. According to the findings of this study, the accuracy of WANN and Wavelet-M5 hybrid models in evaluating wave height is superior to that of classic ANN and M5MT, and it is recommended that WANN and Wavelet-M5 hybrid models be used to estimate wave height.

Prediction of Sediment Yields Using a Data-Driven Radial M5 Tree Model

Reliable estimations of sediment yields are very important for investigations of river morphology and water resources management. Nowadays, soft computing methods are very helpful and famous regarding the accurate estimation of sediment loads. The present study checked the applicability of the radial M5 tree (RM5Tree) model to accurately estimate sediment yields using daily inputs of the snow cover fraction, air temperature, evapotranspiration and effective rainfall, in addition to the flow, in the Gilgit River, Upper Indus Basin (UIB) tributary, Pakistan. The results of the RM5Tree model were compared with support vector regression (SVR), artificial neural network (ANN), multivariate adaptive regression spline (MARS), M5Tree, sediment rating curve (SRC) and response surface method (RSM) models. The resulting accuracy of the models was assessed using Pearson’s correlation coefficient (R2), the root-mean-square error (RMSE) and the mean absolute percentage error (MAPE). The prediction accuracy of the RM5Tree model during the testing period was superior to the ANN, MARS, SVR, M5Tree, RSM and SRC models with the R2, RMSE and MAPE being 0.72, 0.51 tons/day and 11.99%, respectively. The RM5Tree model predicted suspended sediment peaks better, with 84.10% relative accuracy, in comparison to the MARS, ANN, SVR, M5Tree, RSM and SRC models, with 80.62, 77.86, 81.90, 80.20, 74.58 and 62.49% relative accuracies, respectively.

Comparative study of machine learning methods and GR2M model for monthly runoff prediction

Monthly runoff time-series estimation is imperative information for water resources planning and development projects. This article aims to comparatively investigate the applicability of machine learning (ML) methods (i.e., Random Forest (RF), M5 model tree (M5), Support Vector Regression with polynomial kernel function (SVR-poly), and Support Vector Regression with the radial kernel function (SVR-rbf)) and the GR2M model for simulating the monthly runoff hydrograph. The models experimented at six runoff stations in Thailand’s Southern basin. Four performance criteria, including Nash-Sutcliffe Efficiency (NSE), Correlation Coefficient (r), Overall Index (OI), and Combined Index (CI), were utilized for model performance comparison. The finding results revealed that in stations with a low correlation coefficient (r) between input and output data sets, ML algorithms showed superior performance to GR2M. In particular, SVR-rbf showed outstanding performance over other methods. It expressed that SVR-rbf could manage the problem of low-quality data and simulate monthly runoff under limited available data.

The improvement of wavelet-based multilinear regression for suspended sediment load modeling by considering the physiographic characteristics of the watershed.

The aim of this study is to model a relationship between the amount of the suspended sediment load by considering the physiographic characteristics of the Lake Urmia watershed. For this purpose, the information from different stations was used to develop the sediment estimation models. Ten physiographic characteristics were used as input parameters in the simulation process. The M5 model tree was used to select the most important features. The results showed that the four factors of annual discharge, average annual rainfall, form factor and the average elevation of the watershed were the most important parameters, and the multilinear regression models were created based on these factors. Furthermore, it was concluded that the annual discharge was the most influential parameter. Then, the stations were divided into two homogeneous classes based on the selected features. To improve the efficiency of the M5 model, the non-stationary rainfall and runoff signals were decomposed into sub-signals by the wavelet transform (WT). By this technique, the available trends of the main raw signals were eliminated. Finally, the models were developed by multilinear regressions. The model using all four factors had the best performance (DC = 0.93, RMSE = 0.03, ME = 0.05 and RE = 0.15).

Sensitive analysis of meteorological data and selecting appropriate machine learning model for estimation of reference evapotranspiration

This study applies three methods, Gene Expression Programming (GEP), M5 tree (M5T) model and optimized Artificial Neural Network by Genetic Algorithm (ANN-GA) for estimation of reference evapotranspiration in Ahvaz and Dezful in the southwest of Iran. Comparison between results of the FAO Penman-Monteith (FPM) method and the mentioned three methods shows that ANN-GA with the Levenberg-Marquardt training method is the best method and the M5T model is the second appropriate method for estimation of reference evapotranspiration. In Ahvaz, R2 and RMSE of ANN-GA method are 0.996, 0.184 mm/day. For M5T method, these values are 0.997 and 0259 mm/day, and for GEP method, they are 0.979 and 0.521 mm/day. In Dezful, R2 and RMSE of ANN-GA method are 0.994, 0.235 mm/day. For M5T method, these values are 0.992 and 0265 mm/day, and for GEP method, they are 0.963 and 0.544 mm/day. In addition, sensitivity analysis shows that the maximum temperature is the most effective parameter, and the wind speed is second effective parameter. In Dezful, the effect of the maximum temperature is more than those of Ahvaz but the effect of wind speed is less than those of Ahvaz. Because Ahvaz is more flatter than Dezful (the movement of wind in Ahvaz is freer than those of Dezful). The third effective meteorological parameter is the average relative humidity in Ahvaz and the sunny hours in Dezful. The reason for this subject is the less distant of Ahvaz from the Persian Gulf (it is source of moisture).

Machine learning models development for shear strength prediction of reinforced concrete beam: a comparative study

Fiber reinforced polymer (FPR) bars have been widely used as a substitutional material of steel reinforcement in reinforced concrete elements in corrosion areas. Shear resistance of FRP reinforced concrete element can be affected by concrete properties and transverse FRP stirrups. Hence, studying the shear strength (Vs) mechanism is one of the highly essential for pre-design procedure for reinforced concrete elements. This research examines the ability of three machine learning (ML) models called M5-Tree (M5), extreme learning machine (ELM), and random forest (RF) in predicting Vs of 112 shear tests of FRP reinforced concrete beam with transverse reinforcement. For generating the prediction matrix of the developed ML models, statistical correlation analysis was conducted to generate the suitable inputs models for Vs prediction. Statistical evaluation and graphical approaches were used to evaluate the efficiency of the proposed models. The results revealed that all the proposed models performed in general well for all the input combinations. However, ELM-M1 and M5-Tree-M5 models exhibited less accuracy performance in comparison with the other developed models. The study showed that the best prediction performance was revealed by M5 tree model using nine input parameters, with coefficient of determination (R2) and root mean square error (RMSE) equal to 0.9313 and 35.5083 KN, respectively. The comparison results also indicated that ELM and RF were performed significant results with a less slight performance than M5 model. The study outcome contributes to basic knowledge of investigating the impact of stirrups on Vs of FRP reinforced concrete beam with the potential of applying different computer aid models.

Early Prediction in Classification of Cardiovascular Diseases with Machine Learning, Neuro-Fuzzy and Statistical Methods.

Timely and accurate detection of cardiovascular diseases (CVDs) is critically important to minimize the risk of a myocardial infarction. Relations between factors of CVDs are complex, ill-defined and nonlinear, justifying the use of artificial intelligence tools. These tools aid in predicting and classifying CVDs. In this article, we propose a methodology using machine learning (ML) approaches to predict, classify and improve the diagnostic accuracy of CVDs, including support vector regression (SVR), multivariate adaptive regression splines, the M5Tree model and neural networks for the training process. Moreover, adaptive neuro-fuzzy and statistical approaches, nearest neighbor/naive Bayes classifiers and adaptive neuro-fuzzy inference system (ANFIS) are used to predict seventeen CVD risk factors. Mixed-data transformation and classification methods are employed for categorical and continuous variables predicting CVD risk. We compare our hybrid models and existing ML techniques on a CVD real dataset collected from a hospital. A sensitivity analysis is performed to determine the influence and exhibit the essential variables with regard to CVDs, such as the patient's age, cholesterol level and glucose level. Our results report that the proposed methodology outperformed well known statistical and ML approaches, showing their versatility and utility in CVD classification. Our investigation indicates that the prediction accuracy of ANFIS for the training process is 96.56%, followed by SVR with 91.95% prediction accuracy. Our study includes a comprehensive comparison of results obtained for the mentioned methods.

Investigating the Accuracy of Hybrid Models with Wavelet Transform in the Forecast of Watershed Runoff

In the hydrological cycle, runoff precipitation is one of the most significant and complex phenomena. In order to develop and improve predictive models, different perspectives have been presented in its modeling. Hydrological processes can be confidently modeled with the help of artificial intelligence techniques. In this study, the runoff of the Leilanchai watershed was simulated using artificial neural networks (ANNs) and M5 model tree methods and their hybrid with wavelet transform. Seventy percent of the data used in the train state and thirty percent in the test state were collected in this watershed from 2000 to 2021. In addition to daily and monthly scales, simulated and observed results were compared within each scale. Initially, the rainfall and runoff time series were divided into multiple sub-series using the wavelet transform to combat instability. The resultant subheadings were then utilized as input for an ANN and M5 model tree. The results demonstrated that hybrid models with wavelet improved the ANN model's daily accuracy by 4% and its monthly accuracy by 26%. It also improved the M5 model tree's daily and monthly accuracy by 4% and 41%. The wavelet-M5 model's accuracy does not diminish to the same degree as the wavelet-ANN (WANN) model as the forecast horizon lengthens. Consequently, the Leilanchai watershed has a relatively stable behavior pattern. Finally, hybrid models, in conjunction with the wavelet transform, improve forecast accuracy.

Predictive explicit expressions from data-driven models for estimation of scour depth below ski-jump bucket spillways

Abstract Scour depth estimation is an essential factor in water-related engineering problems. Scouring below spillways may endanger a dam's stability and even lead to dam destruction. As a result, it has undesirable environmental effects due to dam failure. Hence, reliable and accurate scour depth estimation below spillways is an exciting topic for researchers. For this purpose, the published and reliable prototype data related to scour depth below ski jump bucket spillways (Ds) was used to develop data-driven models. This study employed two widely used decision tree (DT) methods, including the M5 model tree (M5MT) and the classification and regression tree (CART), and also multivariate adaptive regression splines (MARS) for the estimation of (Ds). The proposed methods provided explicit and clear equations with straightforward applications for estimating scour depth. For the quantitative assessments of the developed formulas, three common statistical metrics, namely root mean square error (RMSE), mean absolute error (MAE), and correlation coefficient (CC), were used. Moreover, comparison results with previous approaches existing in the literature indicated the efficacy of the suggested methods. The obtained results revealed that the MARS technique was the best approach for the estimation of scour depth.

Optimal zinc level and uncertainty quantification in agricultural soils via visible near-infrared reflectance and soil chemical properties

Zinc (Zn) is a vital element required by all living creatures for optimal health and ecosystem functioning. Therefore, several researchers have modeled and mapped its occurrence and distribution in soils. Nonetheless, leveraging model predictive performances while coupling information derived from visible near-infrared (Vis-NIR) and soils (i.e. chemical properties) to estimate potential toxic elements (PTEs) like Zn in agricultural soils is largely untapped. This study applies two methods to rapidly monitor Zn concentration in agricultural soil. Firstly, employing Vis-NIR and machine learning algorithms (MLAs) (Context 1) and secondly, applying Vis-NIR, soil chemical properties (SCP), and MLAs (Context 2). For the Vis-NIR information, single and combined pretreatment methods were applied. The following MLAs were used: conditional inference forest (CIF), partial least squares regression (PLSR), M5 tree model (M5), extreme gradient boosting (EGB), and support vector machine regression (SVMR) respectively. For context 1, the results indicated that M5-MSC (M5 tree model-multiplicative scatter correction) with coefficient of determination (R2) = 0.72, root mean square error (RMSE) = 21.08 (mg/kg), median absolute error (MdAE) = 13.69 and ratio of performance to interquartile range (RPIQ) = 1.63 was promising. Regarding context 2, CIF with spectral pretreatment and soil properties [CIF-DWTLOGMSC + SCP (conditional inference forest-discrete wavelet transformation-logarithmic transformation-multiplicative scatter correction-soil chemical properties)] yielded the best performance of R2 = 0.86, RMSE = 14.52 (mg/kg), MdAE = 6.25 and RPIQ = 1.78. Altogether, for contexts 1 and 2, the CIF-DWTLOGMSC + SCP approach (context 2) was the best Zn model outcome for the agricultural soil. The uncertainty map revealed a low to high error distribution in context 1, and a low to moderate distribution in context 2 for all models except CIF, which had some patches with high uncertainty. We conclude that a multiple optimization approach for modeling Zn levels in agricultural soils is invaluable and may provide fast and reliable information needed for area-specific decision-making.

Reference evapotranspiration estimation in hyper-arid regions via D-vine copula based-quantile regression and comparison with empirical approaches and machine learning models

Study regionTwo hyper-arid regions (Atbara and Kassala stations) in Sudan. Study focusThe study aims to evaluate the potential of the D-vine Copula-based quantile regression (DVQR) model for estimating daily ETo during 2000–2015 based on various input structures. Further, the DVQR model was compared with Multivariate Linear quantile regression (MLQR), Bayesians Model Averaging quantile regression (BMAQR), Empirical Models (EMMs), and Classical Machine Learning (CML). Besides, the CML models including Random Forest (RF), Support Vector Machine (SVM), Extreme Learning Machine (ELM), Extreme Gradient Boosting (XGBoost), and M5 Model Tree (M5Tree) were employed. New hydrological insights for the regionThe original EMMs showed poor performance, which improved after calibration techniques. The DVQR, MLQR, and BMAQR models showed better performance than the calibrated EMMs. However, the DVQR model exhibited the highest accuracy than the MLQR and BMAQR models over two study sites. The M5Tree, SVM, and XGBoost models perfumed better than ELM and RF models at both study sites. The DVQR and XGBoost models showed equivalent performance (R2, NSE, and WIA > 0.99, MAE, and RMSE < 0.2) to the M5Tree and SVM models, but they had significantly more accuracy than the calibrated EMMs, MLQR, BMAQR, ELM, and RF models in two hyper-arid regions. Overall, the high dimensional DVQR model is recommended as a promising alternative technique for estimating daily ETo in hyper-arid climate conditions around the world.

Modeling monthly reference evapotranspiration process in Turkey: application of machine learning methods.

In this study, the predictive power of three different machine learning (ML)-based approaches, namely, multi-gene genetic programming (MGGP), M5 model trees (M5Tree), and K-nearest neighbor algorithm (KNN), for long-term monthly reference evapotranspiration (ET0) prediction were investigated. The input data consist of monthly solar radiation (Rs), maximum air temperature (Tmax), and wind speed (Ws) derived from 163 meteorological stations in Turkey. Different input combinations were created and analyzed. The model's performance was evaluated using criteria such as Nash-Sutcliffe efficiency, Kling-Gupta efficiency, relative root mean squared error, mean absolute percentage error, and determination coefficient. Moreover, Taylor, radar, and boxplot diagrams were created. It was determined that the MGGP model outperformed both the M5Tree and the KNN models. The equation obtained from the MGGP model, for the best-performed combination of Rs-Tmax-Ws, was presented. The best weather conditions were obtained as 0.029 to 31.814MJ/m2, - 5.8 to 45.7°C, and 0.140 to 5.086m/s for Rs, Tmax, and Ws, respectively. It was also found that the Rs was the most potent input variable for ET0 estimation while Ws was the weakest.

HOW MACHINE LEARNING ALGORITHMS ARE USED IN METEOROLOGICAL DATA CLASSIFICATION: A COMPARATIVE APPROACH BETWEEN DT, LMT, M5-MT, GRADIENT BOOSTING AND GWLM-NARX MODELS

Rainfall prediction is one of the most challenging task faced by researchers over the years. Many machine learning and AI based algorithms have been implemented on different datasets for better prediction purposes, but there is not a single solution which perfectly predicts the rainfall. Accurate prediction still remains a question to researchers. We offer a machine learning-based comparison evaluation of rainfall models for Kashmir province. Both local geographic features and the time horizon has influence on weather forecasting. Decision trees, Logistic Model Trees (LMT), and M5 model trees are examples of predictive models based on algorithms. GWLM-NARX, Gradient Boosting, and other techniques were investigated. Weather predictors measured from three major meteorological stations in the Kashmir area of the UT of J&amp;K, India, were utilized in the models. We compared the proposed models based on their accuracy, kappa, interpretability, and other statistics, as well as the significance of the predictors utilized. On the original dataset, the DT model delivers an accuracy of 80.12 percent, followed by the LMT and Gradient boosting models, which produce accuracy of 87.23 percent and 87.51 percent, respectively. Furthermore, when continuous data was used in the M5-MT and GWLM-NARX models, the NARX model performed better, with mean squared error (MSE) and regression value (R) predictions of 3.12 percent and 0.9899 percent in training, 0.144 percent and 0.9936 percent in validation, and 0.311 percent and 0.9988 percent in testing.

Imputation of missing monthly rainfall data using machine learning and spatial interpolation approaches in Thale Sap Songkhla River Basin, Thailand.

Missing rainfall data has been a prevalent issue and primarily interested in hydrology and meteorology. This research aimed to examine the capability of machine learning (ML) and spatial interpolation (SI) methods to estimate missing monthly rainfall data. Six ML algorithms (i.e. multiple linear regression (MLR), M5 model tree (M5), random forest (RF), support vector regression (SVR), multilayer perceptron (MLP), genetic programming (GP)) and four SI methods (i.e. arithmetic average (AA), inverse distance weighting (IDW), correlation coefficient weighted (CCW), normal ratio (NR)) were investigated and compared in their performance. The twelve rainfall stations, located in the Thale Sap Songkhla river basin and nearby basins, were considered as a study case. Tuning hyper-parameters for each ML method was conducted to get the most suitable model for the data sets considered. Three performance criteria matrices (i.e. NSE, OI, and r) were chosen, and the sum of those three performance criteria matrices was introduced for methods' performance comparison. The experimental results pointed out that selecting neighbouring stations were essential when applying SI methods, but not for the ML method. The overall performance showed ML better imputed missing monthly rainfall than SI due to overcoming spatial constraints. GP provided the highest performance by giving NSE = 0.825, OI = 0.877, and r = 0.909 for the training stage. Those values for the testing stage were 0.796, 0.852, and 0.902, respectively. It was followed by SVR-rbf, SVR-poly, and RF. NR provided the best performance among four SI methods, followed by CCW, AA, and IDW. When applying SI methods, it should contemplate a correlation between the target and neighbouring stations greater than 0.80.