Evaporation Rate Prediction Using Advanced Machine Learning Models: A Comparative Study

A stock price index measures the change in several share prices, which can describe the market and assist investors in deciding on a specific investment. Thus, foreseeing the stock price index benefits investors in creating a better investment strategy. However, forecasting the stock price index can be challenging due to its non-linearity, non-stationary and high uncertainty. Gaussian process regression (GPR) is an attractive and powerful approach for prediction, especially when the data fluctuates over time with fewer restrictions. Besides, the GPR gains advantages over other forecasting techniques as it can offer predictions with uncertainty to provide margin errors. In this study, we evaluate the use of GPR to predict the stock price of Thailand (SET). The SET data are divided into 2 datasets; the data in the year 2015 - 2020 and the data in the year 2020 due to the massive change during the COVID-19 pandemic. The prediction results from the GPR are then compared to the machine learning approaches, artificial neural network (ANN) and recurrent neural network (RNN) using evaluation scores; the root mean square error (RMSE), the mean absolute error (MAE), the mean absolute percentage error (MAPE) and the Nash-Sutcliffe efficiency (NSE). The results indicate that the GPR is superior to the ANN and RNN for both datasets as it provides a high prediction accuracy. Moreover, the results suggest that the GPR is less sensitive to the number of input lags in the model. Therefore, the GPR is more favorable for the prediction of SET than the ANN and RNN.
 HIGHLIGHTS
 
 The Gaussian process regression (GPR) was applied to predict the stock price index of Thailand (SET)
 The predictive performance of the GPR was compared to artificial neural networks (ANNs) and recurrent neural networks (RNNs)
 The results indicate that GPR outperformed the other methods as it provided a high prediction accuracy along with prediction intervals
 
 GRAPHICAL ABSTRACT

Accurate forecasts of water demand are a crucial factor in the strategic planning and judicious use of finite water resources within a region, underpinning sustainable socio-economic development. This study aims to compare the applicability of various artificial intelligence models for long-term water demand forecasting across different water use sectors. We utilized the Tuojiang River basin in Sichuan Province as our case study, comparing the performance of five artificial intelligence models: Genetic Algorithm optimized Back Propagation Neural Network (GA-BP), Extreme Learning Machine (ELM), Gaussian Process Regression (GPR), Support Vector Regression (SVR), and Random Forest (RF). These models were employed to predict water demand in the agricultural, industrial, domestic, and ecological sectors using actual water demand data and relevant influential factors from 2005 to 2020. Model performance was evaluated based on the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE), with the most effective model used for 2025 water demand projections for each sector within the study area. Our findings reveal that the GPR model demonstrated superior results in predicting water demand for the agricultural, domestic, and ecological sectors, attaining R2 values of 0.9811, 0.9338, and 0.9142 for the respective test sets. Also, the GA-BP model performed optimally in predicting industrial water demand, with an R2 of 0.8580. The identified optimal prediction model provides a useful tool for future long-term water demand forecasting, promoting sustainable water resource management.

Drought is a complex and frequently occurring natural hazard in many parts of the world. Therefore, accurate drought forecasting is essential to mitigate its adverse impacts. This research has inferred the implication and the appropriateness of the extreme learning machine (ELM) algorithm for drought forecasting. For numerical evaluation, time series data of the Standardized Precipitating Temperature Index (SPTI) are used for nine meteorological stations located in various climatological zones of Pakistan. To assess the performance of ELM, this research includes parallel inferences of multilayer perceptron (MLP) and autoregressive integrated moving average (ARIMA) models. The performance of each model is assessed using root mean square error (RMSE), mean absolute error (MAE), mean absolute percent error (MAPE), Kling‐Gupta efficiency (KGE), Willmott index (WI), and Karl Pearson’s correlation coefficient. Generally, graphical results illustrated an excellent performance of the ELM algorithm over MLP and ARIMA models. For training data of SPTI‐1, ELM’s best performance has observed at Chitral station (RMSE = 0.374, KGE = 0.838, WI = 0.960, MAE = 0.272, MAPE = 259.59, R = 0.93). For SPTI‐1 at Astore station, the numerical results are (RMSE = 0.688, KGE = 0.988, WI = 0.997, MAE = 0.798, MAPE = 247.35). The overall results indicate that the ELM outperformed by producing the smallest RMSE, MAE, and MAPE values and maximum values for KGE, WI, and correlation coefficient values at almost all the selected meteorological stations for (1, 3, 6, 9, and 12) month time scales. In summary, this research endorses the use of ELM for accurate drought forecasting.

Development of machine learning-based standalone GUI application for predicting hydraulic conductivity and compaction parameters of lateritic soils

Stock price prediction is a crucial, yet highly challenging task due to the nonlinear, volatile, and complex nature of financial markets. Traditional forecasting methods often struggle to capture intricate patterns in real-world data. This study proposes a machine learning-based approach using Gaussian Process Regression (GPR) to predict short-term stock prices, specifically targeting the Open, High, and Low values of stocks listed under the NIFTY 500 index. The model incorporates a rich set of financial indicators including previous close price, trading volume, 52-week highs/lows, and the percentage increase or decrease in value over the past 30 days and past 1 year. The dataset is cleaned, log-transformed to reduce skewness in highly varying financial attributes, scaled and evaluated using k-fold cross-validation to ensure robust performance estimation. The GPR model is trained with a composite kernel combining Radial Basis Function (RBF), WhiteKernel, and ConstantKernel. The model outputs not only point predictions but also provides uncertainty estimations, making it highly suitable for real-world financial decision-making. Evaluation metrics such as Mean Squared Error (MSE), <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathrm{R}^{2}$</tex> score, Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) are computed, and the predictions are visualized for interpretability. Experimental results demonstrate that the proposed model is both accurate and interpretable, with the ability to support investor decisions through data-driven insights. The system achieves a MAPE of 0.748567% and an <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathrm{R}^{2}$</tex> score of 0.997453, indicating promising performance in forecasting key stock indicators.

Accurate estimation of crop parameters, such as Leaf Area Index (LAI) and biomass over large areas using remote sensing techniques, is crucial for monitoring crop growth and yield prediction. In this study, a Gaussian Process Regression (GPR) method was developed to estimate LAI and biomass values of sugarcane during growth season using optical and synthetic-Aperture Radar (SAR) data fusion. Predicting LAI on an independent test data set using the GPR and the combined optical and SAR indices provided better prediction accuracies of LAI; with the GPR based on radial basis function (Root Mean Square Error [RMSE] = 0.34, Mean Absolute Error [MAE] = 0.28 and Mean Absolute Percentage Error [MAPE] = 10.5%) and polynomial function (RMSE = 0.42, MAE = 0.31 and MAPE = 12.58%), respectively. The test results of sugarcane biomass also showed that the GPR (poly) produced the highest statistical results (RMSE = 2.45 kg/m2, MAE = 1.72 kg/m2, MAPE = 8.1%) using the combined indices. The results suggest that the crop biophysical retrieval based on optical and SAR data fusion and GPR proposed in this study could improve LAI and biomass estimation that could help for effective crop growth monitoring and mapping applications.

Globally, wind energy if properly harnessed, could serve as a source of energy generation in Africa. This study compared the performance of two Machine Learning (ML) algorithms (Linear regression and Random Forest) in predicting wind speed in five major cities in Africa (Yaoundé, Pretoria, Nairobi, Cairo and Abuja). Wind data were collected between January 1, 2000, and December 31, 2022, using the Solar Radiation Data Archive. The data preprocessing was carried out with 80% of the data used for training and 20% for validation. The performance of these ML algorithms was evaluated using Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and coefficient of determination (R2). The result shows that Nairobi (3.814795 m/s) closely followed by Cairo (3.606453 m/s) has the highest mean wind speed while Yaoundé (1.090512 m/s) has the lowest. Based on the performance metrics used, the two Machine Learning algorithms were competitive. Still, the Linear Regression (LR) algorithm outperformed the Random Forest Algorithm in predicting wind speed in all the selected major African cities. In Yaoundé (RMSE = 0.3892, MAE= 0.3001, MAPE =0.5030), Pretoria (RMSE=1.2339, MAE=0.9480, MAPE=0.7450) Nairobi (RMSE= 0.4223, MAE =0.6499, MAPE =0.1872), Nairobi (RMSE=0.6499, MAE=0.5171, MAPE =0.1872), Cairo (RMSE =1.0909, MAE =0.8544, MAPE =0.3541) and Abuja (RMSE = 0.70245, MAE =0.5441, MAPE= 0.4515) the Linear regression algorithms was found to outperformed Random Forest Regression. Therefore, the Linear regression algorithm is more reliable in predicting wind speed compared with the Random Forest regression.

The matter of success in forecasting precipitation is of great significance to flood control and drought relief, and water resources planning and management. For the nonlinear problem in forecasting precipitation time series, a hybrid prediction model based on variational mode decomposition (VMD) coupled with extreme learning machine (ELM) is proposed to reduce the difficulty in modeling monthly precipitation forecasting and improve the prediction accuracy. The monthly precipitation data in the past 60 years from Yan’an City and Huashan Mountain, Shaanxi Province, are used as cases to test this new hybrid model. First, the nonstationary monthly precipitation time series are decomposed into several relatively stable intrinsic mode functions (IMFs) by using VMD. Then, an ELM prediction model is established for each IMF. Next, the predicted values of these components are accumulated to obtain the final prediction results. Finally, three predictive indicators are adopted to measure the prediction accuracy of the proposed hybrid model, back propagation (BP) neural network, Elman neural network (Elman), ELM, and EMD-ELM models: mean absolute error (MAE), root mean squared error (RMSE), and mean absolute percentage error (MAPE). The experimental simulation results show that the proposed hybrid model has higher prediction accuracy and can be used to predict the monthly precipitation time series.

The increasing effects of climate change require the accurate measurement and prediction of carbon emissions from building construction operations. This study aims to assess the performance of Gaussian Process Regression (GPR) and Support Vector Machine (SVM) in predicting emissions and determine which model is best suited for improving sustainable construction practices. The GPR and SVM models were trained and tested using empirical datasets with varying parameter values. Model performance is evaluated using correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE). The analysis reveals that GPR consistently performs better than SVM across diverse datasets, especially in intricate and varied data situations. The superior performance of GPR highlights its robustness and versatility in handling the complexities of construction-related emissions data. The results indicate that GPR has the potential to assist significantly many stakeholders in the construction sector, including planners and environmental managers, in making better-informed decisions that are in line with carbon reduction objectives. Further studies could examine the incorporation of further predictive variables into the GPR model, such as economic indicators and the effects of material innovation.

In the hot strip rolling process, accurate prediction of bending force can improve the control accuracy of the strip flatness and further improve the quality of the strip. In this paper, based on the production data of 1300 pieces of strip collected from a hot rolling factory, a series of bending force prediction models based on an extreme learning machine (ELM) are proposed. To acquire the optimal model, the parameter settings of the models were investigated, including hidden layer nodes, activation function, population size, crossover probability, and hidden layer structure. Four models are established, one hidden layer ELM model, an optimized ELM model (GAELM) by genetic algorithm (GA), an optimized ELM model (SGELM) by hybrid simulated annealing (SA) and GA, and two-hidden layer optimized ELM model (SGITELM) optimized by SA and GA. The prediction performance is evaluated from the mean absolute error (MAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE). The results show that the SGITELM has the highest prediction accuracy in the four models. The RMSE of the proposed SGITELM is 11.2678 kN, and 98.72% of the prediction data have an absolute error of less than 25 kN. This indicates that the proposed SGITELM with strong learning ability and generalization performance can be well applied to hot rolling production.

River stream estimation is a subject matter that needs constant research and development since it is all-important in the management of water resources, meeting the water demand, irrigation and agricultural activities, and providing distant signal in unwanted situations such as floods. Unfortunately, a universal technique has been impossible to talk about yet although many techniques have been used for estimation and modeling. This has made it necessary to develop different techniques and / or to make comparisons between techniques and to determine the most accurate method for the parameters used. In this context, in this study, the distribution graphs of the flow data fourteen stations located in the Euphrates-Tigris Basin for the years 1981-2010 were created and their conformity to the normal distribution was investigated Evaluation has been made with Adaptive Neural Fuzzy Logic System (ANFIS), Support Vector Regression (SVR) techniques and the newly introduced Gaussian Process Regression (GPR), Extreme Learning Machine (ELM) and Emotional Neural Networks (ENN) artificial intelligence techniques. Root Mean Square Error (RMSE), Mean Square Error (MSE), Mean Absolute Error (MAE) and correlation coefficient (r), which are frequently used, were used to determine the model performance. In addition, it is aimed to find out which technique gives better results with rank analysis. Although all models work well, the sequence with regards to the comparison outcomes of the techniques obtained from rank analysis was observed to be ELM, GPR, ENN, SVR, ANFIS respectively. In order to better interpret the results, Taylor diagrams and time series graphics of the model outputs were created.

Accurate streamflow estimation is critical in water resources management and requires precise estimation. In this study, multiple tree-based models (decision tree, random forest, light gradient boosting machine, and gradient boosting machine (GBM)) are employed to estimate streamflow in the Cau River basin at Thac Rieng station, providing an illustrative example. Six indices named correlation coefficient (r), Nash–Sutcliffe efficiency (NSE), Kling–Gupta efficiency (KGE), root mean square error (RMSE), mean absolute error (MAE), and mean error (ME) are implemented to quantitatively assess model performance. First, using the available hydro-meteorological data from 1/1/1960 to 31/12/1981, hyper-parameters in each tree model are determined. The results show that four models reproduced well-observed streamflow, with dimensionless errors (r, NSE, and KGE) ranging from 0.84 to 0.99 and dimensional errors (RMSE, MAE, and ME) are less than 10 m3/s (approximately 3.6% of the observed streamflow magnitude). Second, the GBM model was found as the most suitable for simulating observed streamflow in the studied river basin. Third, four models were applied to estimate streamflow in the period from 1/1/1982 to 31/12/2022, revealing similar magnitudes of different statistical indicators of observed and estimated streamflow. The capability of four models in simulating streamflow is finally discussed.

The wind power industry has experienced a significant increase and popularity in recent times, and the latest statistics indicate that this sector is still thriving. However, one of the essential steps in developing wind energy projects is finding suitable sites for wind farms, which involves understanding the nature of wind speed, wind direction, terrain, and environmental impacts. To predict the wind energy production over the expected lifespan of a wind farm, vertical wind speed extrapolation to the hub height of the wind turbine is necessary. Therefore, this study presents a comprehensive evaluation of seven statistical approaches for vertical wind speed extrapolation, including Generalized Linear Models (GLM), Linear Regression (LR), Support Vector Machines (SVM), Generalized Additive Models (GAM), Gaussian Process Regression (GPR), Regression Tree (RT), and Ensemble Regression (ER). The accuracy of these methods is assessed using performance metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Normalized RMSE (NRMSE), Normalized MSE (NMSE), Mean Bias Error (MBE), Mean Absolute Error (MAE), Mean Percentage Error (MPE), Mean Absolute Percentage Error (MAPE), Symmetric Mean Absolute Percentage Error (SMAPE), and R-squared (R2). The study concludes that, on average, GLM performs the best out of all seven statistical methods.

The modeling and optimization of electrospinning parameters are essential for controlling the fiber diameter and material properties. This study uses machine learning to examine the effects of multiple electrospinning parameters on fiber diameter. Ten regression models were evaluated, with hyperparameter optimization performed using grid search cross-validation and Bayesian optimization with multiple fold configurations. The Random Forest model demonstrated superior performance (root mean square error = 129.308, coefficient of determination = 0.542, mean absolute error = 104.014, mean absolute percentage error = 0.371). Further improvement was achieved through Bayesian optimization (root mean square error = 127.400, coefficient of determination = 0.555, mean absolute percentage error = 0.360). Extreme Gradient Boosting and Gradient Boosting also showed high accuracy, while linear models performed poorly. The Shapley Additive Explanations analysis identified rotational speed as the most influential parameter (value = 0.473), followed by flow rate (0.36), porosity (0.32) and needle diameter (0.27), all positively affecting fiber diameter. In contrast, voltage (-0.24), temperature (-0.19), towing (-0.14), and humidity (-0.13) showed negative impacts. Experimentally, Polycaprolactone (Molecular number = 80,000) nanofibers were manufactured at three rotation speeds (150, 450 and 750 revolutions per minute), resulting in fiber diameters of 100.09, 154.0, and 175.45 nanometers, respectively. These findings reveal complex interactions between the electrospinning parameters and the fiber morphology, demonstrating the potential of machine learning to optimize nanofiber production.

Perfluorooctanoic acid (PFOA) is used in a variety of industries and is highly persistent in the environment, with potential human health risks. Photocatalysis has been extensively used for the decomposition of various organic pollutants, yet its simulation and modeling are challenging. This research aimed to establish different machine learning (ML) algorithms which can simulate and predict the photocatalytic degradation of PFOA. The published results were used to estimate and predict the photocatalytic degradation of PFOA. Statistical criteria including the coefficient of determination (R2 ), mean absolute error (MAE), and mean squared error (MSE) were considered in assessing the best method of modeling. Among the seven ML algorithms pre-screened, Adaptive Boosting (AdaBoost), Gradient Boosting Machine (GBM), and Random Forest (RF) showed the best performance and were chosen for deep modeling and analysis. Grid search was used to optimize the models developed by AdaBoost, GBM, and RF; and permutation variable importance (PVI) was used to analyze the relative importance of different variables. Based on the modeling results, GBM model (R2 = 0.878, MSE = 106.660, MAE = 6.009) and RF model (R2 = 0.867, MSE = 107.500, MAE = 6.796) showed superior performances compared with AdaBoost model (R2 = 0.574, MSE = 388.369, MAE = 16.480). Furthermore, the PVI results suggested that the GBM model provided the best outcome, with the light irradiation time, type of catalyst, dosage of catalyst, solution pH, irradiation intensity, initial PFOA concentration, oxidizing agents (peroxymonosulfate, ammonium persulfate, and sodium persulfate), irradiation wavelength, and solution temperature as the most important process variables in decreasing order.