Machine Learning Models for Prediction of Meteorological Variables for Weather Forecasting

Optimized machine learning models for predicting crown convergence of plateau mountain tunnels

This paper presents a data-driven approach to determine the load and flexural capacities of reinforced concrete (RC) beams strengthened with fabric reinforced cementitious matrix (FRCM) composites in flexure. A total of seven machine learning (ML) models such as kernel ridge regression, K-nearest neighbors, support vector regression, classification and regression trees, random forest, gradient boosted trees, and extreme gradient boosting (xgBoost) are evaluated to propose the best predictive model for FRCM-strengthened beams. Beam geometry, internal steel reinforcement area, FRCM reinforcement area, and mechanical characteristics of concrete, steel, and FRCM are the main input parameters included in the database. Among the studied ML models, the xgBoost model is the most accurate model with the highest coefficient of determination (R2=99.3%) and least root mean square (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). A comparative study of the performance of the proposed and existing analytical models revealed the superior predictive capability and robustness of the proposed model. The predicted flexural and load capacities of the beams based on the existing analytical models are highly scattered and either over-conservative or unsafe. A unified SHapley Additive exPlanations approach is employed to explain the output of the best ML model and identify the most significant input features and interactions that influence the capacity of FRCM-strengthened RC beams in flexure. Furthermore, a reliability analysis is performed to calibrate the resistance reduction factor (ϕ) to achieve a specified target reliability index (βT=3.5).

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.

Solar energy produced by photovoltaic panels is a vital energy source that offers numerous benefits to both the environment and society. However, meteorological variables such as solar irradiation, weather patterns, precipitation and climate conditions present significant challenges to seamless energy integration into the power grid. Accurate forecasting is essential to maintain supply-demand balance, optimize energy storage and ensure grid stability. This study leverages machine learning (ML) techniques to predict solar power generation and address renewable energy integration challenges. Nine ML models were employed, including linear regression, autoregressive integrated moving average (ARIMA), artificial neural network (ANN), support vector machines (SVM), random forest (RF), decision tree, gradient boosting machine (GBM), light gradient boosting (LGBM) and extreme gradient boosting (XGBM). Inputs such as irradiance, humidity, minimum temperature, maximum temperature and surface pressure were used to train these models. The model performances were evaluated using metrics like root mean squared error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). The results highlighted ANN as the most effective model, achieving an RMSE of 274.84 kWh, MAE of 245.93 kWh and a MAPE of 5.26 %. This research contributes to the existing literature by addressing the relatively unexplored application of multiple machine learning models for predicting energy output from photovoltaic systems. A key novelty of this study is its ability to achieve accurate solar power forecasts using a limited dataset from a newly installed solar power plant, unlike many existing studies that rely on large volumes of data. Additionally, it explores the solar power production potential of Namakkal district in Tamil Nadu, India-a region with limited prior research.

This article devises the Artificial Intelligence (AI) methods of designing models of short-term forecasting (in 12 h and 24 h horizons) of electricity production in a selected Small Hydropower Plant (SHP). Renewable Energy Sources (RESs) are difficult to predict due to weather variability. Electricity production by a run-of-river SHP is marked by the variability related to the access to instantaneous flow in the river and weather conditions. In order to develop predictive models of an SHP facility (installed capacity 760 kW), which is located in Southern Poland on the Skawa River, hourly data from nearby meteorological stations and a water gauge station were collected as explanatory variables. Data on the water management of the retention reservoir above the SHP were also included. The variable to be explained was the hourly electricity production, which was obtained from the tested SHP over a period of 3 years and 10 months. Obtaining these data to build models required contact with state institutions and private entrepreneurs of the SHP. Four AI methods were chosen to create predictive models: two types of Artificial Neural Networks (ANNs), Multilayer Perceptron (MLP) and Radial Base Functions (RBFs), and two types of decision trees methods, Random Forest (RF) and Gradient-Boosted Decision Trees (GBDTs). Finally, after applying forecast quality measures of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R2), the most effective model was indicated. The decision trees method proved to be more accurate than ANN models. The best GBDT models’ errors were MAPE 3.17% and MAE 9.97 kWh (for 12 h horizon), and MAPE 3.41% and MAE 10.96 kWh (for 24 h horizon). MLPs had worse results: MAPE from 5.41% to 5.55% and MAE from 18.02 kWh to 18.40 kWh (for 12 h horizon), and MAPE from 7.30% to 7.50% and MAE from 24.12 kWh to 24.83 kWh (for 24 h horizon). Forecasts using RBF were not made due to the very low quality of training and testing (the correlation coefficient was approximately 0.3).

Accurate precipitation forecasting is a vital task for many domains, such as agriculture, water management, flood prevention, and crop yield estimation. The use of machine learning (ML) approaches has improved precipitation forecasting accuracy, exhibiting promising results in capturing the intricate connections between various meteorological variables and precipitation patterns. However, given the vast array of available ML models, a comparative analysis is imperative for identifying the most effective models for precipitation prediction. This study aims to examine the capacities of ML algorithms to forecast precipitation based on weather data for the city of Casablanca, Morocco, which faces challenges in water management and climate change adaptation. Eight different ML models’ performances are compared: linear regression, polynomial regression, K-nearest neighbors (KNN), support vector machine (SVM), decision tree (DT), random forest (RF), XGBoost, and an ensemble learning model. These models are evaluated based on their mean absolute error (MAE), mean squared error (MSE), and R-squared (R2 ) value to determine their effectiveness. The study showcases the potential of ML models in predicting precipitation by utilizing meteorological parameters such as temperature, humidity, wind speed, and pressure.

<p>Accurate water level (WL) forecasting is important for water resources management and planning purposes in the Great Lakes. The objectives of this research are two-fold.  The first objective is to apply machine learning (ML) (i.e., random forest (RF) and support vector regression (SVR)) and hybrid convolutional neural network(CNN)-long-short term memory (LSTM) deep learning (DL) models for multi-step (i.e., one-, two- and three-monthly step ahead) WL forecasting in the Great Lakes (Michigan and Ontario). The second objective is to integrate the boundary corrected (BC) maximal overlap discrete wavelet transform (MODWT) with SVR, RF, and CNN-LSTM models to improve the performance of the individual models. By employing a BC-wavelet decomposition method, the ‘future data’ issue (i.e., data from the future that is not available), often overlooked in the literature and a major barrier to achieving realistic forecasting performance is overcome. </p><p>For Lakes Michigan and Ontario, 1212 monthly WL (m) records (spanning Jan 1918–Dec 2018) were used to develop the models. For the non-wavelet-based models (SVR, RF, and CNN-LSTM), candidate model inputs included the WL recorded over the previous 12 months.  For the BC-MODWT-based models (BC-MODWT-SVR, BC-MODWT-RF, and BC-MODWT-CNN-LSTM), the lagged input time series were decomposed into BC-wavelet and scaling coefficients by using different mother wavelets (Haar, Daubechies, Symlets, Fejer-Korovkin and Coiflets), filter lengths (from two up to 12) and decomposition levels (from one up to seven).  For each method (SVR, RF, and CNN-LSTM), mother wavelet, and decomposition level a model was generated.  For both wavelet- and non-wavelet-based models, the particle swarm optimization (PSO) method was used to select the most appropriate inputs to include in the proposed multi-step WL forecasting models.</p><p>The datasets were partitioned into calibration and validation subsets. After calibrating the models, various performance evaluation metrics, e.g., coefficient of determination (R<sup>2</sup>), root mean square error (RMSE), mean absolute error (MAE), root mean square percentage error (RMSPE), mean absolute percentage error (MAPE) and the Nash-Sutcliffe efficiency coefficient (NSC) were used to assess model accuracy.</p><p>Of the ML models, the SVR outperformed RF while the DL models outperformed the ML models for each forecast lead time (one-, two-, and three-step(s) ahead). Results from this case study indicate that not all wavelet families and decomposition levels perform equally and in some cases, the wavelet-based models do not improve performance over the non-wavelet-based models. However, the BC-MODWT-CNN-LSTM using suitable mother wavelets (e.g., Haar) outperforms the individual ML and BC-MODWT-ML-based models. More accurate forecasts were obtained for Lake Michigan although the performance in both Great Lakes was accurate. The outcomes of this research indicate that the BC-MODWT-CNN-LSTM model is a promising tool for generating accurate WL forecasts.</p>

Rating is one of the most frequently used metrics in the television industry to evaluate television programs or channels. This research is an attempt to develop a prediction model of television program ratings using rating data gathered from UseeTV (interned-based television service from Telkom Indonesia). The machine learning methods (Random Forest and Extreme Gradient Boosting) were tried out utilizing a set of rating data from 20 television programs collected from January 2018 to August 2019 (train dataset) and evaluated using September 2019 rating data (test dataset). Research results show that Random Forest gives a better result than Extreme Gradient Boosting based on evaluation metrics: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). On the training dataset, prediction using Random Forest produced lower RMSE and MAE scores than Extreme Gradient Boosting in all programs, while on the testing dataset, Random Forest produced lower RMSE and MAE scores in 16 programs compared with Extreme Gradient Boosting. According to MAPE score, Random Forest produced more good quality prediction (4 programs in the training dataset, 16 programs in the testing dataset) than Extreme Gradient Boosting method (1 program in the training dataset, 12 programs in the testing dataset) both in training and testing dataset.

Machine learning predictions for bending capacity of ECC-concrete composite beams hybrid reinforced with steel and FRP bars

Accurate prediction of agricultural yield is extremely important to ensure food security and cope with the challenges created by climate change and natural disasters. Forecasting agricultural yield is a challenging task due to the complex nature of variables (fertiliser, rainfall, temperature and others) that affect agricultural production. This study employs six supervised machine learning algorithms: Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN) to build a predictive model using 49 years of historical data (1973-2021) on paddy, wheat, and maize. Model performance was evaluated using Mean Squared Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Squared Error (rMSE). Results show that DT and RF models are the most precise with MSE 1% to 5%, MAE 8% to 21%, followed by SVM and CNN. Key predictors of crop yield include area cultivated, capital expenditure, banking expansion, rainfall, temperature, and fertilizers, while irrigation and road network were less significant. The study recommends that farmers prioritize commercial farming, agricultural equipment, and timely availability of fertilizer for application. The Government of Nepal (GoN) should redirect subsidies towards agricultural mechanization, ensure timely supply of fertilizer, and expand banking services in agricultural areas.

This study examines the wear characteristics of A356-Al 2 O 3 -B 4 C composites produced via stir casting, incorporating three reinforcement compositions (5, 10, and 15 wt.% Al 2 O 3 with a constant 5 wt.% B 4 C). We used seven different machine learning algorithms to predict wear rates based on experimental tribological data: Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Gradient Boosting (GB), Light GBM, and AdaBoost. The Random Forest model was better at making predictions, with a R 2 of 0.83, a mean absolute error (MAE) of 0.0012 m 3 /Nm, a mean absolute percentage error (MAPE) of 1.3%, and a root mean squared error (RMSE) of 0.0094 m 3 /Nm, which means it was 83% accurate. Experimental wear rates ranged from 4.3 × 10 −14 to 3.43 × 10 −13 m 3 /Nm across varying sliding distances (1500–6000 m), loads (10–20 N), and velocities (1.45–2.66 m/s). Systematic k-fold cross-validation and grid search hyperparameter Optimisation to make sure the model worked well. The results show that machine learning, especially ensemble tree-based methods, can accurately predict how well composite materials will wear, which speeds up the process of optimizing material design and cuts down on the cost of experiments. This study shows that combining artificial intelligence with traditional tribological characterization can improve the ability to predict how composite materials will behave in the future. It also sheds light on the relative importance of tribological operating parameters.

Forecasting streamflow in stream basin systems plays a crucial role in facilitating effective urban planning to mitigate floods. In addition to employing intricate hydrological modeling systems, machine learning and statistical techniques offer an alternative means for streamflow forecasts. Nonetheless, the precision and dependability of these methods are subjects of paramount importance. This study rigorously investigates the effectiveness of three distinct machine learning techniques and two statistical approaches when applied to streamflow data from the Göksu Stream in the Marmara Region of Turkey, spanning from 1984 to 2022. Through a comparative analysis of these methodologies, this examination aims to contribute innovative advancements to the existing methodologies used in the prediction of streamflow data. The methodologies employed include machine learning methods such as Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Machine (SVM) and statistical methods such as Simple Exponential Smoothing (SES) and Autoregressive Integrated Moving Average (ARIMA) model. In the study, 444 data points between 1984 and 2020 were used as training data, and the remaining data points for the period 2021–2022 were used for streamflow forecasting in the test validation period. The results were evaluated using various metrics, such as the correlation coefficient (r), mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), coefficient of determination (R2), and Nash–Sutcliffe efficiency (NSE). Upon analyzing the results, it was found that the model generated using the XGBoost algorithm outperformed other machine learning and statistical techniques. Consequently, the models implemented in this study demonstrate a high level of accuracy in predicting potential streamflow in the river basin system.

Nighttime high-power aircraft engine run-ups represent a critical operational activity with potential implications for airport management and environmental assessment; yet, their quantitative prediction remains limited in existing literature. The objective of this study is to develop and evaluate a data-driven machine learning framework capable of accurately predicting nighttime high-power engine run-up characteristics using historical operational data. A supervised learning methodology is adopted using an open-access dataset comprising approximately 860 nighttime run-up records. The proposed framework includes data preprocessing, temporal feature engineering (month, season, and quarter), exploratory data analysis, correlation assessment, and comparative model development using Linear Regression, Random Forest, Gradient Boosting, Extreme Gradient Boosting (XGBoost), and an Artificial Neural Network (multilayer perceptron). Model performance is evaluated using coefficient of determination (R²), root mean square error (RMSE), mean absolute error, and mean absolute percentage error, supported by predicted-versus-actual comparisons and learning-curve analysis. The results demonstrate that ensemble-based models outperform linear and neural network approaches, with XGBoost achieving the highest predictive accuracy on the testing dataset (R² ≈ 0.90, RMSE ≈ 2.15). Learning curves further indicate stable validation performance with increasing training data size. The proposed machine learning framework provides a structured and data-driven approach for predicting nighttime high-power aircraft engine run-up activity within the analyzed operational dataset, offering a valuable analytical tool for data-driven assessment of airport ground operations.

Predicting parameters and sensitivity assessment of nano-silica-based fiber-reinforced concrete: a sustainable construction material

Machine learning approach for predicting impedance signatures of construction steel structures in various tensile pull actions