Performance Of Support Vector Regression Research Articles

Evaluating the performances of SVR and XGBoost for short-range forecasting of heatwaves across different temperature zones of India

This research aims to forecast maximum temperatures and the frequency of heatwave days across four different temperature zones (Zone 1, 2, 3 and 4) in India. These four zones are categorized based on the 30-year average maximum temperatures (T30AMT) during the summer months of April, May, and June (AMJ). Two Machine Learning (ML) algorithms eXtreme Gradient Boosting (XGBoost) and Support Vector Regression (SVR) are employed to achieve this goal. The study utilizes nine key atmospheric variables namely air temperature, geopotential height, relative humidity, U-wind, V-wind, soil moisture, solar radiation, sea surface temperature, and mean sea level pressure at a daily scale spanning from 1991 to 2020 for the months of March, April, May, and June as predictors. The India Meteorological Department daily maximum temperature data spanning from 1991 to 2020 for the months of AMJ serves as the predictands. ML models are developed using spatially averaged atmospheric variables and daily maximum temperature across the grids falling within each temperature zone. Results indicate that for a 7-day lead time, SVR outperforms XGBoost in Zone-1 (T30AMT > 38 °C) and Zone-2 (T30AMT: 35.01 °C–38 °C) by more accurately capturing peak temperatures during training and testing. Conversely, for a 15-day lead time in Zone-1, XGBoost better predicts temperature peaks in both phases. In Zone-3 (T30AMT: 30 °C–35 °C) and Zone-4 (T30AMT < 30 °C) for both lead times, the performance of both models decline, indicating models and input variables are more effective in predicting higher temperatures typical of Zone-1 and 2 but less so in Zone-3 and 4. In a nutshell, the study attempts to highlight the capability of advanced ML techniques combined with spatial climate data to enhance the prediction of extreme heatwave events. These insights can aid in heatwave preparedness, climate management, and adaptation strategies for different Indian temperature zones.

Foretelling the compressive strength of bamboo using machine learning techniques

PurposeThe purpose of this research was to develop and evaluate a machine learning (ML) algorithm to accurately predict bamboo compressive strength (BCS). Using a dataset of 150 bamboo samples with features such as cross-sectional area, dry weight, density, outer diameter, culm thickness and load, various ML algorithms including artificial neural network (ANN), extreme learning machine (ELM) and support vector regression (SVR) were tested. The ELM algorithm outperformed others, showing superior accuracy based on metrics like R2, MSE, RMSE, MAE and MAPE. The study highlights the efficacy of ELM in enhancing the precision and reliability of BCS predictions, establishing it as a valuable tool for assessing bamboo strength.Design/methodology/approachThis study experimentally created a dataset of 150 bamboo samples to predict BCS using ML algorithms. Key predictive features included cross-sectional area, dry weight, density, outer diameter, culm thickness and load. The performance of various ML algorithms, including ANN, ELM and SVR, was evaluated. ELM demonstrated superior performance based on metrics such as coefficient of determination (R2), mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE), establishing its robustness in predicting BCS accurately.FindingsThe study found that the ELM algorithm outperformed other ML algorithms, including ANN and SVR, in predicting BCS. ELM achieved the highest accuracy based on key metrics such as R2, MSE, RMSE, MAE and MAPE. These results indicate that ELM is a highly effective and reliable tool for predicting the compressive strength of bamboo, thereby enhancing the precision and dependability of BCS evaluations.Originality/valueThis study is original in its application of the ELM algorithm to predict BCS using experimentally derived data. By comparing ELM with other ML algorithms like ANN and SVR, the research establishes ELM’s superior performance and reliability. The findings demonstrate the significant potential of ELM in material strength prediction, offering a novel and robust approach to evaluating bamboo’s compressive properties. This contributes valuable insights into the field of material science and engineering, particularly in the context of sustainable construction materials.

Exploring attitudes and behavioral patterns in residential energy consumption: Data-driven by a machine learning approach

The present study focuses on two main objectives: firstly, to clarify the mechanisms by which attitudes impact behavioral changes related to household energy consumption, and secondly, to offer valuable insights to enhance the understanding of residential energy usage through a novel technique called Support Vector Regression (SVR). This method employs several feature space transformations to convert nNar relationships into linear ones. The results highlight the crucial role of psychological factors in determining energy consumption behaviors, demonstrating that cognitive factors significantly influence attitudes and behavioral patterns. The findings show that psychological variables have a major role in determining how people consume energy, with cognitive variables having a particularly large impact on attitudes and behavior patterns. Our findings demonstrate the superior performance of Support Vector Regression (SVR) with radial basis function kernels over traditional predictive models, with a prediction accuracy of 93.7 % for changes in behavior patterns (CHP) and 94.4 % for changes in attitudes (CHA). These results highlight the value of applying cutting-edge machine-learning approaches to create precise models for comprehending and directing energy-saving actions. The policy implications suggest that reducing cognitive barriers can significantly encourage energy-saving behaviors and contribute to a comprehensive approach for energy-efficiency initiatives

Improving Support Vector Regression for Predicting Mechanical Properties in Low-Alloy Steel and Comparative Analysis

Low-alloy steel is widely employed in the aviation industry for its exceptional mechanical properties. These materials are frequently used in critical structural components such as aircraft landing gear and engine mounts, where a high strength-to-weight ratio is crucial for optimal performance. However, the mechanical properties of low-alloy steel are influenced by various components and their compositions, making identification and prediction challenging. Accurately predicting these mechanical properties can significantly reduce the development time of new alloy steel, lower production costs, and offer valuable insights for design analysis. support vector regression (SVR) is known for its superior learning and generalization capabilities. However, optimizing SVR performance can be challenging due to the significant impact of the penalty factor and kernel parameters. To address this issue, a hybrid method called SMA-SVR is proposed, which combines the Slime Mould Algorithm (SMA) with SVR. This hybrid approach aims to efficiently and accurately predict two crucial mechanical parameters of low-alloy steel: tensile strength and 0.2% proof stress. Detailed descriptions of the modeling processes and principles that are involved in the hybrid method are provided. Furthermore, three other popular hybrid models for comparison are introduced. To evaluate the performance of these models, four statistical measures are utilized: Mean Absolute Error, Root Mean Square Error, R-Squared, and computational time. Using data from the NIMS database and from material tests conducted on a universal testing machine, experiments were carried out to compare the performance of these models. The results indicate that SMA-SVR outperforms the other methods in terms of accuracy and computational efficiency.

Nondestructive freshness evaluation of mackerel fish using Vis/NIR hyperspectral imaging and multivariate analysis

Nondestructive freshness evaluation models for chub mackerel (Scomber japonicus) fillets were developed using visible/near-infrared (Vis/NIR) hyperspectral imaging and multivariate regression analysis. Total 96 mackerel samples were investigated during 6 days of storage under five different conditions for measurement of pH, total volatile basic nitrogen (TVB-N), and K values along with acquisition of hyperspectral images. With partial least squares regression (PLSR) and support vector regression (SVR) along with wavelength selection method using Variables Importance in Projection (VIP) scores, performances of PLSR, VIP-PLSR, SVR, and VIP-SVR models were evaluated and compared. The VIP-PLSR models showed the best performance for predicting the freshness indicators, with R2 values of 0.86, 0.86, and 0.91 for pH, TVB-N, and K values, respectively. Furthermore, it was shown that the identification and removal of noise pixels from the hyperspectral data based on correlation analysis was effective in improving the regression results.

Evaluation of the performance of SVR and ANN Models in Sea Water Level Prediction for the Izmir Coast of the Aegean Sea

Prediction of sea water level is a very important phenomenon for making future projections for flood control, human living conditions and coastal planning. However, it is not easy to estimate sea water level due to the influence of atmospheric conditions. Thus, Artificial Neural Networks (ANN) and Support Vector Regression (SVR) methods are used for the prediction of seawater level of Izmir Coast based on the time series data. Coefficient of determination (R2 ) and root mean square error (RMSE) are applied as model evaluation criteria in this study. 19 months of seawater level data in the time series were used in this study. The results show that the ANN model can predict the water level with R2 of 0.84 and 0.68 for 1st and 2nd days, respectively, while the SVR model can predict the water level with R2 of 0.83 and 0.69 for 1st and 2nd days, respectively.

SPATIAL PREDICTION OF RECEIVED SIGNAL STRENGTH FOR CELLULAR COMMUNICATION USING SUPPORT VECTOR MACHINE AND K-NEAREST NEIGHBOURS REGRESSION

Abstract. Signal strength maps are of great importance for cellular system providers in network planning and operation. Accurate prediction of signal strength is important for solving problems such as link quality. In this study, Received Signal Strength (RSS) prediction model is proposed for the 900 MHz band in the Van Yüzüncü Yıl University campus environment by using machine learning regression methods such as K- Nearest Neıghbours (KNN) and Support Vector Regression (SVR) together with Geographic Information Systems. For the training of this model, signal strength values taken from the RF Spectrum Analyser at different locations and distances were used. In addition, spatial data sets such as the digital elevation model, location of base stations and measurement stations, building heights and location, and land use/cover were used in the model. The effect of these data sets on RSS power is included in the model. The model aims to predict RSS accurately, visualize the estimated signal strength, and analyze the signal field strength coverage. Different kernels from the SVR model such as Polynomial, , and Sigmoid were tested. To increase the success of the model, appropriate parameter values were selected and configured according to SVR and KNN methods. For 900 MHz, the performances of SVR and KNN models were compared and the results of the models were verified using root mean squares (RMSE). Among the measured data, the lowest prediction is found in KNN Manhattan. According to the results of the simulation was observed that the SVR model created with spatial data performs better for Signal Strength. Finally, the lowest RMSE value (1.71 dB) was obtained from the Sigmoid kernel in the best signal strength estimation SVR model. The SVR model is recommended for Campus Area signal strength estimation.

Quantitative analysis of pyrolysis characteristics and chemical components of tobacco materials based on machine learning.

To investigate the quantitative relationship between the pyrolysis characteristics and chemical components of tobacco materials, various machine learning methods were used to establish a quantitative analysis model of tobacco. The model relates the thermal weight loss rate to 19 chemical components, and identifies the characteristic temperature intervals of the pyrolysis process that significantly relate to the chemical components. The results showed that: 1) Among various machine learning methods, partial least squares (PLS), support vector regression (SVR) and Gaussian process regression (GPR) demonstrated superior regression performance on thermogravimetric data and chemical components. 2) The PLS model showed the best performance on fitting and prediction effects, and has good generalization ability to predict the 19 chemical components. For most components, the determination coefficients R 2 are above 0.85. While the performance of SVR and GPR models was comparable, the R 2 for most chemical components were below 0.75. 3) The significant temperature intervals for various chemical components were different, and most of the affected temperature intervals were within 130°C-400°C. The results can provide a reference for the materials selection of cigarette and reveal the possible interactions of various chemical components of tobacco materials in the pyrolysis process.

Estimation of the Bio-Parameters of Winter Wheat by Combining Feature Selection with Machine Learning Using Multi-Temporal Unmanned Aerial Vehicle Multispectral Images

Accurate and timely monitoring of biochemical and biophysical traits associated with crop growth is essential for indicating crop growth status and yield prediction for precise field management. This study evaluated the application of three combinations of feature selection and machine learning regression techniques based on unmanned aerial vehicle (UAV) multispectral images for estimating the bio-parameters, including leaf area index (LAI), leaf chlorophyll content (LCC), and canopy chlorophyll content (CCC), at key growth stages of winter wheat. The performance of Support Vector Regression (SVR) in combination with Sequential Forward Selection (SFS) for the bio-parameters estimation was compared with that of Least Absolute Shrinkage and Selection Operator (LASSO) regression and Random Forest (RF) regression with internal feature selectors. A consumer-grade multispectral UAV was used to conduct four flight campaigns over a split-plot experimental field with various nitrogen fertilizer treatments during a growing season of winter wheat. Eighteen spectral variables were used as the input candidates for analyses against the three bio-parameters at four growth stages. Compared to LASSO and RF internal feature selectors, the SFS algorithm selects the least input variables for each crop bio-parameter model, which can reduce data redundancy while improving model efficiency. The results of the SFS-SVR method show better accuracy and robustness in predicting winter wheat bio-parameter traits during the four growth stages. The regression model developed based on SFS-SVR for LAI, LCC, and CCC, had the best predictive accuracy in terms of coefficients of determination (R2), root mean square error (RMSE) and relative predictive deviation (RPD) of 0.967, 0.225 and 4.905 at the early filling stage, 0.912, 2.711 μg/cm2 and 2.872 at the heading stage, and 0.968, 0.147 g/m2 and 5.279 at the booting stage, respectively. Furthermore, the spatial distributions in the retrieved winter wheat bio-parameter maps accurately depicted the application of the fertilization treatments across the experimental field, and further statistical analysis revealed the variations in the bio-parameters and yield under different nitrogen fertilization treatments. This study provides a reference for monitoring and estimating winter wheat bio-parameters based on UAV multispectral imagery during specific crop phenology periods.

Application of light-weighted CNN for diagnosis of internal concrete defects using hammering sound

ABSTRACT In the past, diagnoses of the internal defects of ageing concrete members by sound tests have relied on the ability and experience of the inspector. However, with the development of deep neural networks, building diagnosis tools without the subjective judgements of humans is feasible. In this study, sound samples are collected from a tapping sound test on concrete slab specimens with internally embedded artificial defects. Spectrograms are generated from the sound samples and used to train a light-weighted convolutional neural network (CNN). Thereafter, the performance of the proposed CNN models at diagnosing the defects of the concrete slabs are examined and compared with convolutional autoencoder (CAE) and support vector regression (SVR). All the models performed well at distinguishing between healthy and defective concrete. Whereas noise can impair the performance of CAE and SVR, CNN is less affected, particularly when classifying sound samples with distinctive features. CNN also has other advantages: the physical area of the artificial defect can be output directly from CNN, and CNN performance is also less affected by the depth of the artificial defect and the rebar embedded in the concrete. At increased depths, the CNN is still able to identify the defect area.

Predicting the quality attributes related to geographical growing regions in red-fleshed kiwifruit by data fusion of electronic nose and computer vision systems

The ability of a data fusion system composed of a computer vision system (CVS) and an electronic nose (e-nose) was evaluated to predict key physiochemical attributes and distinguish red-fleshed kiwifruit produced in three distinct regions in northern Iran. Color and morphological features from whole and middle-cut kiwifruits, along with the maximum responses of the 13 metal oxide semiconductor (MOS) sensors of an e-nose system, were used as inputs to the data fusion system. Principal component analysis (PCA) revealed that the first two principal components (PCs) extracted from the e-nose features could effectively differentiate kiwifruit samples from different regions. The PCA-SVM algorithm achieved a 93.33% classification rate for kiwifruits from three regions based on data from individual e-nose and CVS. Data fusion increased the classification rate of the SVM model to 100% and improved the performance of Support Vector Regression (SVR) for predicting physiochemical indices of kiwifruits compared to individual systems. The data fusion-based PCA-SVR models achieved validation R2 values ranging from 90.17% for the Brix-Acid Ratio (BAR) to 98.57% for pH prediction. These results demonstrate the high potential of fusing artificial visual and olfactory systems for quality monitoring and identifying the geographical growing regions of kiwifruits.

Support Vector Regression-Based Operational Effectiveness Evaluation Approach to Reconnaissance Satellite System

As one of the most important part of weapon system of systems (WSoS), quantitative evaluation of reconnaissance satellite system (RSS) is indispensable during its construction and application. Aiming at the problem of nonlinear effectiveness evaluation under small sample conditions, we propose an evaluation method based on support vector regression (SVR) to effectively address the defects of traditional methods. Considering the performance of SVR is influenced by the penalty factor, kernel type, and other parameters deeply, the improved grey wolf optimizer (IGWO) is employed for parameter optimization. In the proposed IGWO algorithm, the opposition-based learning strategy is adopted to increase the probability of avoiding the local optima, the mutation operator is used to escape from premature convergence and differential convergence factors are applied to increase the rate of convergence. Numerical experiments of 14 test functions validate the applicability of IGWO algorithm dealing with global optimization. The index system and evaluation method are constructed based on the characteristics of RSS. To validate the proposed IGWO-SVR evaluation method, eight benchmark data sets and combat simulation are employed to estimate the evaluation accuracy, convergence performance and computational complexity. According to the experimental results, the proposed method outperforms several prediction based evaluation methods, verifies the superiority and effectiveness in RSS operational effectiveness evaluation.

Total and component forest aboveground biomass inversion via LiDAR-derived features and machine learning algorithms

Forest aboveground biomass (AGB) and its biomass components are key indicators for assessing forest ecosystem health, productivity, and carbon stocks. Light Detection and Ranging (LiDAR) technology has great advantages in acquiring the vertical structure of forests and the spatial distribution characteristics of vegetation. In this study, the 56 features extracted from airborne LiDAR point cloud data were used to estimate forest total and component AGB. Variable importance–in–projection values calculated through a partial least squares regression algorithm were utilized for LiDAR-derived feature ranking and optimization. Both leave-one-out cross-validation (LOOCV) and cross-validation methods were applied for validation of the estimated results. The results showed that four cumulative height percentiles (AIH30,AIH40, AIH20, and AIH25), two height percentiles (H8 and H6), and four height-related variables (Hmean, Hsqrt, Hmad, and Hcurt) are ranked more frequently in the top 10 sensitive features for total and component forest AGB retrievals. Best performance was acquired by random forest (RF) algorithm, with R2 = 0.75, root mean square error (RMSE) = 22.93 Mg/ha, relative RMSE (rRMSE) = 25.30%, and mean absolute error (MAE) = 19.26 Mg/ha validated by the LOOCV method. For cross-validation results, R2 is 0.67, RMSE is 24.56 Mg/ha, and rRMSE is 25.67%. The performance of support vector regression (SVR) for total AGB estimation is R2 = 0.66, RMSE = 26.75 Mg/ha, rRMSE = 28.62%, and MAE = 22.00 Mg/ha using LOOCV validation and R2 = 0.56, RMSE = 30.88 Mg/ha, and rRMSE = 31.41% by cross-validation. For the component AGB estimation, the accuracy from both RF and SVR algorithms was arranged as stem &amp;gt; bark &amp;gt; branch &amp;gt; leaf. The results confirmed the sensitivity of LiDAR-derived features to forest total and component AGBs. They also demonstrated the worse performance of these features for retrieval of leaf component AGB. RF outperformed SVR for both total and component AGB estimation, the validation difference from LOOCV and cross-validation is less than 5% for both total and component AGB estimated results.

Data-Driven Approaches for Bead Geometry Prediction Via Melt Pool Monitoring

Abstract In the realm of additive manufacturing, the selection of process parameters to avoid over and under deposition entails a time-consuming and resource-intensive trial-and-error approach. Given the distinct characteristics of each part geometry, there is a pressing need for advancing real-time process monitoring and control to ensure consistent and reliable part dimensional accuracy. This research shows that support vector regression (SVR) and convolutional neural network (CNN) models offer a promising solution for real-time process control due to the models’ abilities to recognize complex, non-linear patterns with high accuracy. A novel experiment was designed to compare the performance of SVR and CNN models to indirectly detect bead height from a coaxial image of a melt pool from a single-layer, single bead build. The study showed that both SVR and CNN models trained on melt pool data collected from a coaxial optical camera can accurately predict the bead height with a mean absolute percentage error of 3.67% and 3.68%, respectively.

Prediction model of the outflow temperature from stratified reservoir regulated by stratified water intake facility based on machine learning algorithm

Temperature rhythm changes in outflows after reservoir construction cause thermal pollution in downstream rivers, which is unfavorable to the ecological health of downstream rivers. Stratified water intake facilities can effectively mitigate the impact of thermal pollution. However, there is a lack of scientific guidance to ensure that stratified water intake facilities are optimized and meet downstream water temperature requirements; therefore, an efficient and accurate method of predicting outflow temperatures is urgently needed. Based on the influence mechanism of the outflow temperature and the maximal information coefficient, a new machine learning model for predicting the outflow temperature of thermally stratified reservoirs is constructed. The vertical water temperature in front of the dam, outflow quantity, stoplog gate height and submergence depth are used as inputs. Based on prototype observation data, the prediction performance of support vector regression (SVR), K-nearest neighbors (KNN) and the multilayer perceptron neural network (MLPNN) methods is compared. The results show that the three machine learning models can predict the outflow temperature very well. Among them, the SVR model using the radial basis function (RBF) as the kernel function displays the best performance; its mean absolute error for the test set is 0.112 °C, the root mean square error is 0.143 °C, and the Nash-Sutcliffe efficiency coefficient is 0.989. A test of RBF-SVR verifies that it can effectively identify the rules and relationships between the input and output in small-sample training cases and is suitable for solving the nonlinear problem of predicting reservoir outflow temperatures. In addition, RBF-SVR display universal application value. It can not only provide a 1–10 day early warning regarding outflow temperatures but also achieve a good modeling effect for Wudongde Reservoir, which is outside the study area. Overall, the outflow temperatures of thermally stratified reservoirs are efficiently and accurately predicted, and the proposed method provides an effective reference and scientific guidance for adaptive reservoir management.

Prediction of compressive strength of rice husk ash concrete: A comparison of different metaheuristic algorithms for optimizing support vector regression

Concrete made from rice husk ash (RHA) is stronger and more durable than normal concrete. It can also help reduce greenhouse gas emissions. A feasible prediction model to rapidly determine the compressive strength of RHA concrete can save resources and time, and the properties and characteristics of RHA concrete can be more accurately determined. In this study, the compressive strength of RHA concrete is predicted by using support vector regression (SVR) in conjunction with three optimization algorithms, namely firefly algorithm (FA), particle swarm optimization (PSO), and grey wolf optimization (GWO). The coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), a10-index and adjusted R2 are used to assess the predictive accuracy of models. The results show that all the three optimization algorithms can significantly improve the prediction performance of support vector regression. The prediction accuracy is also substantially higher than that of the classical machine learning models like the random forest (RF) model and the back propagation neural network (BPNN) model. The FA-SVR model with R2 values of 0.9544 and 0.9614, adjusted R2 values of 0.9530 and 0.9560, RMSE values of 3.7506 and 3.6571, MAE values of 2.2880 and 3.0732, and a10-index values of 0.8584 and 0.8793 corresponding to the training and test sets, respectively. The FA-SVR model outperforms the other two hybrid models in terms of prediction performance. The sensitivity analysis reveals that the fine aggregate content is the key factor in predicting the compressive strength of RHA concrete.

Monitoring black tea fermentation quality by intelligent sensors: Comparison of image, e-nose and data fusion

To scientifically and objectively monitor the fermentation quality of black tea, a computer vision system (CVS) and electronic nose (e-nose) were employed to analyze the black tea image and odor eigenvalues of Yinghong No. 9 black tea. First, the variation trends of tea polyphenols, volatile substances, image eigenvalues and odor eigenvalues with the extension of fermentation time were analyzed, and the fermentation process was categorized into three stages for classification. Second, principal component analysis (PCA) was employed on the image and odor eigenvalues obtained by CVS and e-nose. Partial least squares discriminant analysis (PLS-DA) was performed on 117 volatile components, and 51 differential volatiles were screened out based on variable importance in projection (VIP ≥1) and one-way analysis of variance (P < 0.05), including geraniol, linalool, nerolidol, and α-ionone. Then, image features and odor features are fused by using a data fusion strategy. Finally, the image, smell and fusion information were combined with random forest (RF), K-nearest neighbor (KNN) and support vector machine (SVM) to establish the classification models of different fermentation stages and to compare them. The results show that the feature-level fusion strategy integrating the SVM was the most efficient approach, with classification accuracy rates of 100% for the training sets and 95.6% for the testing sets. The performance of Support Vector Regression (SVR) prediction models for tea polyphenol content based on feature-level fusion data outperformed data-level models (Rc, RMSEC, Rp and RMSEP of 0.96, 0.48 mg/g, 0.94, 0.6 mg/g).

Assessing a data-driven approach for monthly runoff prediction in a mountain basin of the Central Andes of Argentina

In the semi-arid Central Andes of Argentina, the water from snowmelt runoff plays a fundamental role as a provider of ecosystem services. Nowadays, the global climate change has an observable negative impact on this area, due, principally, to the decrease in both liquid and solid rainfall, with the consequent decrease in water availability. In this context, runoff prediction acquires vital importance for the integrated water resources management. The aim of this study is to investigate the performance of the Support Vector Regression (SVR) technique in predicting monthly discharges with 1-month lead-time in the Tupungato River basin in the Central Andes of Argentina. This methodology has never been applied before in this mountainous region. Different inputs, like meteorological data and satellite-based snow cover area estimates from MODIS, were analyzed in order to identify the suitable inputs predictors to forecast monthly streamflow. The results were compared against the results derived from a Classification and Regression Tree (CART) model and, also, against an Auto-regressive Integrated Moving-average (ARIMA) model. Different metrics were used to evaluate the performance of the SVR tests in reproducing streamflow observations at the basin outlet. The coefficient of determination for each of the analyzed tests lays between 0.75 and 0.89 in the validation set. The comparison with the other models showed a significant improvement in performance of SVR in respect of CART and ARIMA model. SVR models proved a promising approach to support water management and decision making for productive activities, potentially also in other basins in the region.

Comparative Study of Coupling Models of Feature Selection Methods and Machine Learning Techniques for Predicting Monthly Reservoir Inflow

Effective reservoir operation under the effects of climate change is immensely challenging. The accuracy of reservoir inflow forecasting is one of the essential factors supporting reservoir operations. This study aimed to investigate coupling models of feature selection (FS) and machine learning (ML) algorithms to predict the monthly reservoir inflow. The study was carried out using data from the Huai Nam Sai reservoir in southern Thailand. Eighteen years of monthly recorded data (i.e., reservoir inflow, reservoir storage, rainfall, and regional climate indices) with up to a 12-month time lag were utilized. Three ML techniques, i.e., multiple linear regression (MLR), support vector regression (SVR), and artificial neural network (ANN)were compared in their capabilities. In addition, two FS techniques, i.e., genetic algorithm (GA) and backward elimination (BE) methods, were studied with four predictable time intervals, consisting of 3, 6, 9, and 12 months in advance. Ten-fold cross-validation was used for model evaluation. Study results revealed that FS methods (i.e., GA and BE) Could improve the performance of SVR and ANN for predicting monthly reservoir inflow forecasting, but they have no effects on MLR. Different developed forecasting models were suitable for different reservoir inflow forecasting time-step-ahead. BE-ANN provided the best performance for three-time-ahead (T + 3) and nine-time-ahead (T + 9) by giving an OI of 0.9885 and 0.8818, NSE of 0.9546 and 0.9815, RMSE of 1.3155 and 1.2172 MCM/month, MAE of 0.9568 and 0.9644 MCM/month, and r of 0.9796 and 0.9804, respectively. The GA-ANN model showed the highest prediction accuracy for six-time-ahead (T + 6), with an OI of 0.8997, NSE of 0.9407, RMSE of 2.1699 MCM/month, MAE of 1.7549 MCM/month, and r of 0.9759. The ANN model showed the best prediction accuracy for twelve-time-ahead (T + 12), with an OI of 0.9515, NSE of 0.9835, RMSE of 1.1613 MCM/month, MAE of 0.9273 MCM/month, and r of 0.9835.

Multistage wheat yield prediction using hybrid machine learning techniques

Wheat being highly affected by the weather, adverse weather drastically reduces the wheat yield. Model was developed for multi stage wheat yield prediction by stepwise multi linear regression (SMLR), support vector regression (SVR), least absolute shrinkage and selection operator (LASSO) and hybrid machine learning LASSO-SVR and SMLR-SVR techniques. Wheat yield data and weather parameter for generating thermal and weather indices during different growth stage for more than 30 years were collected for study area. Analysis was carried out by fixing 70 % of the data for calibration and remaining 30 % dataset for validation in R software. Results showed that LASSO performed best having nRMSE value between 1.22 % at grain filling stage for IARI, New Delhi to 8.36 % for Hisar at flowering stage. The model performance of SVR is increased if a hybrid model in combination with LASSO and SMLR is applied. The hybrid model LASSO-SVR has shown more improvement than SVR model compared with SMLR-SVR.