Standalone Support Vector Regression Research Articles

Mapping high poplar growth areas for bioenergy cultivation: A swarm-optimized approach

Poplar trees are a renewable energy source, and identifying high-growth areas for their cultivation is essential for successful bioenergy production. This study presents a novel approach to identify these areas using support vector regression (SVR) combined with two swarm intelligence optimization algorithms, i.e., particle swarm optimization (PSO) and gray wolf optimizer (GWO). The approach uses a spatial database of thirteen geoenvironmental variables and the location of 136 poplar farms in a rugged and heterogeneous region in western Iran. The PSO and GWO algorithms optimized the hyperparameters of the base SVR model and generated two swarm-optimized models: SVR-PSO and SVR-GWO. The swarm-optimized models were compared to the standalone SVR model using various evaluation metrics. The results showed that the SVR-GWO model achieved the highest performance (accuracy = 82%, sensitivity = 82%, specificity = 74%, and prediction rate = 92%), followed by the SVR-PSO model (accuracy = 81%, sensitivity = 81%, specificity = 72%, and prediction rate = 90%), while the standalone SVR model had accuracy and stability (accuracy = 75%, sensitivity = 77%, specificity = 68%, and prediction rate = 82%). The results also revealed that elevation, slope, topographic wetness index, and proximity to roads and rivers were strongly associated with the distribution of poplar farms in the study area. This study provided a novel and effective approach for identifying high poplar growth areas that can help decision-makers and stakeholders allocate resources and plan interventions to promote poplar cultivation for renewable energy production.

Support vector regression optimized by black widow optimization algorithm combining with feature selection by MARS for mining blast vibration prediction

Ground vibration induced by mine blasting is the most significant adverse effect on nearby residents and surroundings. Accurate prediction of blasting vibration using limited monitor data is a viable option to control ground vibration. This study proposed a novel integration modeling method based on multivariate adaptive regression splines (MARS), support vector regression (SVR) and black widow optimization algorithm (BWOA) for predicting the peak particle velocity (PPV) and frequency. Feature selection was implemented first using the MARS. Subsequently, the variables selected by the MARS were used as the input to build the SVR model. To increase the performance of the SVR model, we introduced the BWOA to tune the hyperparameters of the SVR model. Moreover, two hybrid SVR models also were developed to compare with the hybrid MARS-BWOA-SVR model. The results indicate that the prediction accuracy of the three hybrid models is superior to the standalone SVR model. Among the three hybrid models, the MARS-BWOA-SVR model yields the highest prediction accuracy. The hybrid MARS-BWOA-SVR model not only outperforms other SVR models but also discerns the relative importance of the input variables. There are four main variables with higher relative importance, namely, distance, maximum charge per delay, integrity coefficient and pre-split penetration ratio. The results demonstrate that the hybrid MARS-BWOA-SVR model is a promising tool for blasting vibration prediction.

Estimation of Spring Maize Evapotranspiration in Semi-Arid Regions of Northeast China Using Machine Learning: An Improved SVR Model Based on PSO and RF Algorithms

Accurate estimation of crop evapotranspiration (ETc) is crucial for effective irrigation and water management. To achieve this, support vector regression (SVR) was applied to estimate the daily ETc of spring maize. Random forest (RF) as a data pre-processing technique was utilized to determine the optimal input variables for the SVR model. Particle swarm optimization (PSO) was employed to optimize the SVR model. This study used data obtained from field experiments conducted between 2017 and 2019, including crop coefficient and daily meteorological data. The performance of the innovative hybrid RF–SVR–PSO model was evaluated against a standalone SVR model, a back-propagation neural network (BPNN) model and a RF model, using different input meteorological variables. The ETc values were calculated using the Penman–Monteith equation, which is recommended by the FAO, and used as a reference for the models’ estimated values. The results showed that the hybrid RF–SVR–PSO model performed better than all three standalone models for ETc estimation of spring maize. The Nash–Sutcliffe efficiency coefficient (NSE), root mean square error (RMSE), mean absolute error (MAE) and coefficient of determination (R2) ranges were 0.956–0.958, 0.275–0.282 mm d−1, 0.221–0.231 mm d−1 and 0.957–0.961, respectively. It is proved that the hybrid RF–SVR–PSO model is appropriate for estimation of daily spring maize ETc in semi-arid regions.

Spatial Prediction of Wildfire Susceptibility Using Hybrid Machine Learning Models Based on Support Vector Regression in Sydney, Australia

Australia has suffered devastating wildfires recently, and is predisposed to them due to several factors, including topography, meteorology, vegetation, and ignition sources. This study utilized a geographic information system (GIS) technique to analyze and understand the factors that regulate the spatial distribution of wildfire incidents and machine learning to predict wildfire susceptibility in Sydney. Wildfire inventory data were constructed by combining the fire perimeter through field surveys and fire occurrence data gathered from the visible infrared imaging radiometer suite (VIIRS)-Suomi thermal anomalies product between 2011 and 2020 for the Sydney area. Sixteen wildfire-related factors were acquired to assess the potential of machine learning based on support vector regression (SVR) and various metaheuristic approaches (GWO and PSO) for wildfire susceptibility mapping in Sydney. In addition, the 2019–2020 “Black Summer” fire acted as a validation dataset to assess the predictive capability of the developed model. Furthermore, the information gain ratio (IGR) method showed that driving factors such as land use, forest type, and slope degree have a large impact on wildfire susceptibility in the study area, and the frequency ratio (FR) method represented how the factors influence wildfire occurrence. Model evaluation based on area under the curve (AUC) and root average square error (RMSE) were used, and the outputs showed that the hybrid-based SVR-PSO (AUC = 0.882, RMSE = 0.006) model performed better than the standalone SVR (AUC = 0.837, RMSE = 0.097) and SVR-GWO (AUC = 0.873, RMSE = 0.080) models. Thus, optimizing SVR with metaheuristics improved the accuracy of wildfire susceptibility modeling in the study area. The proposed framework can be an alternative to the modeling approach and can be adapted for any research related to the susceptibility of different disturbances.

Flood susceptibility mapping using multi-temporal SAR imagery and novel integration of nature-inspired algorithms into support vector regression

Flood has long been known as one of the most catastrophic natural hazards worldwide. Mapping flood-prone areas is an important part of flood disaster management. In this study, a flood susceptibility mapping framework was developed based on a novel integration of nature-inspired algorithms into support vector regression (SVR). To this end, various remote sensing (RS) and geographic information system (GIS) datasets were applied to the hybridized SVR models to map flood susceptibility in Ahwaz township, Iran. The proposed framework has two main steps: 1) updating the flood inventory (historical flooded locations) using the proposed RS-based flood detection method developed within the google earth engine (GEE) platform. The mosaicked images of multi-temporal Sentinel-1 synthetic aperture radar (SAR) data have been used in this step; 2) producing flood susceptibility map using the standalone SVR and hybridized model of SVR. The hybridized methods were derived from a novel integration of SVR with meta-heuristic algorithms, hence forming the SVR-bat algorithm (SVR-BA), SVR-invasive weed optimization (SVR-IWO), and SVR-firefly algorithm (SVR-FA). A spatial database of flood locations and 11 conditioning factors (altitude, slope angle, aspect, topographic wetness index, stream power index, normalized difference vegetation index (NDVI), distance to stream, curvature, rainfall, soil type, and land use/cover) were built for the susceptibility modelling. The accuracy of the proposed model was evaluated using the statistical and sensitivity indices, such as root mean square error (RMSE), receiver operating characteristic (ROC) and area under the ROC curve (AUROC) index. The results indicated that all hybridized models outperformed the standalone SVR. According to AUROC values, the predictive power of the SVR-FA was the highest with the value of 0.81, followed by SVR-IWO, SVR-BA, and SVR with values of 0.80, 0.79, and 0.77, respectively.

Prediction of Autogenous Shrinkage of Concrete Incorporating Super Absorbent Polymer and Waste Materials through Individual and Ensemble Machine Learning Approaches.

The use of superabsorbent polymers, sometimes known as SAP, is a tremendously efficacious method for reducing the amount of autogenous shrinkage (AS) that occurs in high-performance concrete. This study utilizes support vector regression (SVR) as a standalone machine-learning algorithm (MLA) which is then ensemble with boosting and bagging approaches to reduce the bias and overfitting issues. In addition, these ensemble methods are optimized with twenty sub-models with varying the nth estimators to achieve a robust R2. Moreover, modified bagging as random forest regression (RFR) is also employed to predict the AS of concrete containing supplementary cementitious materials (SCMs) and SAP. The data for modeling of AS includes water to cement ratio (W/C), water to binder ratio (W/B), cement, silica fume, fly ash, slag, the filer, metakaolin, super absorbent polymer, superplasticizer, super absorbent polymer size, curing time, and super absorbent polymer water intake. Statistical and k-fold validation is used to verify the validation of the data using MAE and RMSE. Furthermore, SHAPLEY analysis is performed on the variables to show the influential parameters. The SVM with AdaBoost and modified bagging (RF) illustrates strong models by delivering R2 of approximately 0.95 and 0.98, respectively, as compared to individual SVR models. An enhancement of 67% and 63% in the RF model, while in the case of SVR with AdaBoost, it was 47% and 36%, in RMSE and MAE of both models, respectively, when compared with the standalone SVR model. Thus, the impact of a strong learner can upsurge the efficiency of the model.

Determination of discharge coefficient of stepped morning glory spillway using a hybrid data-driven method

The accurate assessment of the discharge coefficient (Cd) of spillways is one of the complex problems in the safety of dams and reservoirs. In this research, the capabilities of Support Vector Regression-Invasive Weed Optimization (SVR-IWO), Support Vector Regression (SVR), Gaussian Process Regression (GPR), and Kernel Ridge Regression (KRR) for estimating discharge coefficients of 21 different layouts of morning glory spillways with the different number of vortex breakers are investigated. In addition, the aleatory and epistemic uncertainties are quantified using classical Mutual information theory and four various Bayesian entropies. The Froud number (Fr), number of vortex breakers (N), and three dimensionless parameters consisting of the water height, vortex height, and breaker thickness over the spillway diameter (H/Ds, h/Ds, and t/Ds, respectively), obtained from 120 experiments, were used as input variables. The findings reveal that SVR-IWO is superior to other models based on several performance metrics, including R, RMSE, MSE, and MAE. Besides, the SVR-IWO (R=0.804,RMSE=0.131,MSE=0.017,MAE=0.074) enhanced the performance indices obtained from standalone SVR (R=0.632,RMSE=0.352,MSE=0.124,MAE=0.255) up to 86.13%.

Comparative study of machine learning models for evaluating groundwater vulnerability to nitrate contamination

The accurate evaluation of groundwater contamination vulnerability is essential for the management and prevention of groundwater contamination in the watershed. In this study, advanced multiple machine learning (ML) models of Radial Basis Neural Networks (RBNN), Support Vector Regression (SVR), and ensemble Random Forest Regression (RFR) were applied to determine the most accurate performance for the evaluation of groundwater contamination vulnerability. Eight vulnerability factors of DRASTIC-L were rated based on the modified DRASTIC model (MDM) and were used as input data. The adjusted vulnerability index (AVI) with nitrate values was used as output data for the modeling process. The performance of three models was verified using the statistical performance criteria of MAE, RMSE, r2, and ROC/AUC values. The ensemble RFR model showed the highest performance in comparison with standalone SVR and RBNN models. Specifically, ensemble RFR kept all promising solutions during the model performance due to its flexibility and robustness, and the vulnerability map obtained by the RFR model was more accurate for predicting the most vulnerable areas to contamination. It was concluded that ensemble RFR was a robust tool to enhance the evaluation of groundwater contamination vulnerability, and that it could contribute to environmental safety against groundwater contamination.

Reinforcing bar development length modeling using integrative support vector regression model with response surface method: New approach

Due to the non-uniformity of bond stress distribution, the full bar development length should be tested to validate the development length of the reinforcing bar embedded in concretes. The current study proposed the design of a hybrid artificial intelligence (AI) model using integration of support vector regression (SVR) coupled with response surface method (RSM) for prediction of reinforcement bar development length. Two nonlinear calibrating processes are conducted, RSM is used to connect the input data on the hardening dataset in first stage while SVR is used for determining the nonlinear relation between the hardening dataset and the output development bar stress. 534 pull-out test observations on short unit bar length are used for the modeling. Several physical dimensional properties are incorporated as input attributes for the hybrid predictive model. Stand-alone AI models, empirical formulations, and design codes are used for validation. Parametric analysis is performed to investigate the sensitivity of RSM-SVR model toward as input variables. Results evidenced the capability of the proposed RSM-RVM model to approximate the non-linear relations between physical information and bar development length. The RSM-SVR model proved to be a reliable intelligence model for bar materials design. Additionally, the model was highly consistent in the calibration of the existing design codes for more reliability. In quantitative terms, RSM-SVR model attained minimum root mean square error (RMSE = 25.60 MPa), compared with for example ACI 318-14 modeling design (306.56 MPa) or stand-alone SVR model (90.95 MPa), over the testing phase. The bar development length formulation using RSM-SVR model showed the nonlinear relationship with respect to the influence of the input variables such as transvers bars in development region, reinforcing yield stress, and concrete compressive strength in normal domain.

Prediction of channel sinuosity in perennial rivers using Bayesian Mutual Information theory and support vector regression coupled with meta-heuristic algorithms

Support Vector Regression (SVR) combined with Invasive Weeds Optimization (IWO), standalone SVR, and Radial Basis Function Neural Networks are applied to estimate channel sinuosity in perennial rivers. With this aim, a dataset with 132 sinuosity data and related geomorphologic data, corresponding to 119 perennial streams, is considered. Bayesian Mutual Information theory is used to determine the parameters affecting channel sinuosity to reveal that bankfull depth affects sinuosity the most. Seven input parameter combinations for sinuosity prediction are considered, and in both training and testing stages, the SVR-IWO model $$\left( {R_{Train} = 0.959,RMSE_{Train} = 0.072, MAE_{Train} = 0.037, R_{test} = 0.892, RMSE_{Test} = 0.103, MAE_{Test} = 0.065} \right)$$ R Train = 0.959 , R M S E Train = 0.072 , M A E Train = 0.037 , R test = 0.892 , R M S E Test = 0.103 , M A E Test = 0.065 shows the best prediction performance while the standalone SVR model generated the results with performances of $$\left( {R_{Train} = 0.792,RMSE_{Train} = 0.158, MAE_{Train} = 0.141, R_{test} = 0.704, RMSE_{Test} = 0.163, MAE_{Test} = 0.151} \right)$$ R Train = 0.792 , R M S E Train = 0.158 , M A E Train = 0.141 , R test = 0.704 , R M S E Test = 0.163 , M A E Test = 0.151 . Model prediction uncertainty is quantified in terms of entropy for the three models considered, further confirming that the sinuosity set predicted by the SVR-IWO model is the closest to the observed set.

Global solar radiation prediction: Application of novel hybrid data-driven model

One of the significant prerequisites for harvesting solar energy is precise global solar radiation (GHI) forecasts. However, variability and uncertainty are inherent characteristics of solar radiation. It is challenging to show better generalization using current data analysis approaches. Thus, this research presents a new intelligence framework by hybridizing Support Vector Regression (SVR) with the Grasshopper Optimization Algorithm (GOA) and the Boruta-based feature selection algorithm (BA) for forecasting GHI values at different sites of Saudi Arabia. Interestingly, the most significant distinction that differentiates this proposed prediction model (SVR-GOA-BAK) from other models is that the GOA is automatically employed to search for optimal SVR’s hyperparameters. In contrast, these hyperparameters are chosen randomly and manually in conventional models. Consequently, the contribution helps save time, reduce cost, and avoid the possibility of models’ overfitting or underfitting caused by random and manual selection. A diversity of statistical measures has justified the proposed model’s effectiveness and superiority. In terms of mean absolute percentage error (MAPE), the proposed model outperformed the standalone SVR models by 32.15–39.69% at different study sites. In tuning the SVR’s parameters, GOA outperforms popular optimization algorithms. All the simulation test results demonstrate the superiority of the proposed model. Hence, the proposed approach provides a foundation for precise solar radiation forecasting, which can aid in the growth of renewable-energy-based technologies.

Application of bagging ensemble model for predicting compressive strength of hollow concrete masonry prism

In the current research, a newly developed ensemble intelligent predictive model called Bagging Regression (BGR) is proposed to predict the compressive strength of a hollow concrete masonry prism ( f p ). A matrix of input combinations is constructed based on several predictive variables, including mortar compressive strength ( f m ), concrete block compressive strength ( f b ), and height to thickness ratio ( h/t ). Three modeling scenarios based on the different data divisions (i.e., 80–20%, 75–25%, and 70–30%) for training-testing phases are evaluated. The proposed model is validated against classical support vector regression (SVR) and decision tree regression (DTR) models using statistical indicators and graphical presentations. Results indicate the superiority of the BGR over the other models. In quantitative terms, BGR attains minimum root mean square error (RMSE = 1.51 MPa) using the data division scenario of 80–20% in the testing phase, while DTR and standalone SVR models offer RMSE = 2.55 and 2.33 MPa, respectively.

Coupling a hybrid CNN-LSTM deep learning model with a Boundary Corrected Maximal Overlap Discrete Wavelet Transform for multiscale Lake water level forecasting

Developing accurate lake water level (WL) forecasting models is important for flood control, shoreline maintenance and sustainable water resources planning and management. In this study, improved accuracy of forecasts (up to three months) of Lake Michigan and Lake Ontario WLs was achieved by coupling Boundary Corrected (BC) Maximal Overlap Discrete Wavelet Transform (MODWT) data preprocessing, with a hybrid Convolutional Neural Network (CNN) Long-Short Term Memory (LSTM) deep learning (DL) model. Hybrid DL-based model performance was compared to that of BC-MODWT machine learning (ML) [e.g., Random Forest (RF) and Support Vector Regression (SVR)] models. For each lake, all models were calibrated using 70% of the monthly WL (in meters) data series (January 1918 to February 1988), with the remaining 30% (March 1988 to December 2018) serving for validation. In both standalone and wavelet-machine learning models, a hybrid correlation-based feature selection (CFS)-particle swarm optimization (PSO) search method served to select input variables among candidate WL lags of up to twelve months, whereas for the CNN-LSTM DL models, input variable selection was carried out automatically by the CNN structure. For the MODWT-based ML and DL models, input time series were decomposed using a BC-MODWT approach. Scaling coefficients were developed through several mother wavelet approaches (i.e., Haar, Daubechies, Symlets, Fejer-Korovkin and Coiflets) with different filter lengths (up to twelve) and decomposition levels (up to seven). Model performance was evaluated using several visual and statistical metrics, including the correlation coefficient, r; the root mean standard error, RMSE; and Willmot’s Index, WI. The CNN-LSTM DL model outperformed the standalone SVR and RF models. For all time horizons, coupled MODWT-based CNN-LSTM models outperformed standalone and hybrid models in WL forecasting. Not all wavelet family/filter length/decomposition combinations improved standalone models; however, the proposed BC-MODWT-CNN-LSTM model implementing the Haar mother wavelet (for Lake Michigan — one-month ahead: r = 0.994, RMSE = 0.04 m, WI = 0.996; two-months ahead: r = 0.979, RMSE = 0.07 m, WI = 0.989; three-months ahead: r = 0.957, RMSE = 0.102 m, WI = 0.976; for Lake Ontario — one-month ahead: r = 0.956, RMSE = 0.082 m, WI = 0.978; two-months ahead: r = 0.864, RMSE = 0.141, WI = 0.912; three-months ahead: r = 0.755, RMSE = 0.182 m, WI = 0.841) outperformed standalone ML and BC-MODWT-ML-based models. Accordingly, the BC-MODWT-CNN-LSTM model can be viewed as a potentially useful approach to increase the accuracy of lake WL forecasts.

A differential evolution-based regression framework for forecasting Bitcoin price.

This research proposes a differential evolution-based regression framework for forecasting one day ahead price of Bitcoin. The maximal overlap discrete wavelet transformation first decomposes the original series into granular linear and nonlinear components. We then fit polynomial regression with interaction (PRI) and support vector regression (SVR) on linear and nonlinear components and obtain component-wise projections. The sum of these projections constitutes the final forecast. For accurate predictions, the PRI coefficients and tuning of the hyperparameters of SVR must be precisely estimated. Differential evolution, a metaheuristic optimization technique, helps to achieve these goals. We compare the forecast accuracy of the proposed regression framework with six advanced predictive modeling algorithms- multilayer perceptron neural network, random forest, adaptive neural fuzzy inference system, standalone SVR, multiple adaptive regression spline, and least absolute shrinkage and selection operator. Finally, we perform the numerical experimentation based on—(1) the daily closing prices of Bitcoin for January 10, 2013, to February 23, 2019, and (2) randomly generated surrogate time series through Monte Carlo analysis. The forecast accuracy of the proposed framework is higher than the other predictive modeling algorithms.

Flood spatial prediction modeling using a hybrid of meta-optimization and support vector regression modeling

Flood spatial susceptibility prediction is the first essential step in developing flood mitigation strategies and reducing flood damage. Flood occurrence is a complex process that is not easily predicted through simple methods. This study describes optimization of support vector regression (SVR) using meta-optimization algorithms including the grasshopper optimization algorithm (GOA) and particle swarm optimization (PSO) for flood modeling at Qazvin Plain, Iran. Geospatial data including nine readily available geo-environmental flood conditioning factors (i.e., ground slope, aspect, elevation, planform curvature, profile curvature, proximity to a river, land use, lithology and rainfall) were derived. The information gain ratio (IGR) method was used to determine the relative importance of input variables. A historical flood inventory map for 43 locations was created from existing reports. The geospatial data and historical flood levels were used to construct the training and testing datasets. Then, the training dataset was used to generate flood-susceptibility maps using the optimized SVR model with the GOA and PSO algorithms. Finally, the predictive accuracy of the models was quantified using the statistical measures of root mean square error (RMSE), mean absolute error (MAE), and area under the receiver operating characteristic (ROC) curve (AUC). Although both the GOA and PSO algorithms improved SVR performance, the SVR-GOA model performed best (AUC = 0.959, RMSE = 0.31 and MSE = 0.098), followed by the SVR-PSO model (AUC = 0.959, RMSE = 0.33 and MSE = 0.11) and standalone SVR model (AUC = 0.87, RMSE = 0.35 and MSE = 0.12). Elevation, lithology and aspect had the highest IGR values and were identified as the most effective predictors of flood susceptibility.

Application of an artificial intelligence technique enhanced with intelligent water drops for monthly reference evapotranspiration estimation

Reference evapotranspiration (ET0) is one of the most important parameters, which is required in many fields such as hydrological, agricultural, and climatological studies. Therefore, its estimation via reliable and accurate techniques is a necessity. The present study aims to estimate the monthly ET0 time series of six stations located in Iran. To achieve this objective, gene expression programming (GEP) and support vector regression (SVR) were used as standalone models. A novel hybrid model was then introduced through coupling the classical SVR with an optimization algorithm, namely intelligent water drops (IWD) (i.e., SVR−IWD). Two various types of scenarios were considered, including the climatic data- and antecedent ET0 data-based patterns. In the climatic data-based models, the effective climatic parameters were recognized by using two pre-processing techniques consisting of τ Kendall and entropy. It is worthy to mention that developing the hybrid SVR-IWD model as well as utilizing the τ Kendall and entropy approaches to discern the most influential weather parameters on ET0 are the innovations of current research. The results illustrated that the applied pre-processing methods introduced different climatic inputs to feed the models. The overall results of present study revealed that the proposed hybrid SVR-IWD model outperformed the standalone SVR one under both the considered scenarios when estimating the monthly ET0. In addition to the mentioned models, two types of empirical equations were also used including the Hargreaves−Samani (H−S) and Priestley−Taylor (P−T) in their original and calibrated versions. It was concluded that the calibrated versions showed superior performances compared to their original ones.

Development of novel hybridized models for urban flood susceptibility mapping

Floods in urban environments often result in loss of life and destruction of property, with many negative socio-economic effects. However, the application of most flood prediction models still remains challenging due to data scarcity. This creates a need to develop novel hybridized models based on historical urban flood events, using, e.g., metaheuristic optimization algorithms and wavelet analysis. The hybridized models examined in this study (Wavelet-SVR-Bat and Wavelet-SVR-GWO), designed as intelligent systems, consist of a support vector regression (SVR), integrated with a combination of wavelet transform and metaheuristic optimization algorithms, including the grey wolf optimizer (GWO), and the bat optimizer (Bat). The efficiency of the novel hybridized and standalone SVR models for spatial modeling of urban flood inundation was evaluated using different cutoff-dependent and cutoff-independent evaluation criteria, including area under the receiver operating characteristic curve (AUC), Accuracy (A), Matthews Correlation Coefficient (MCC), Misclassification Rate (MR), and F-score. The results demonstrated that both hybridized models had very high performance (Wavelet-SVR-GWO: AUC = 0.981, A = 0.92, MCC = 0.86, MR = 0.07; Wavelet-SVR-Bat: AUC = 0.972, A = 0.88, MCC = 0.76, MR = 0.11) compared with the standalone SVR (AUC = 0.917, A = 0.85, MCC = 0.7, MR = 0.15). Therefore, these hybridized models are a promising, cost-effective method for spatial modeling of urban flood susceptibility and for providing in-depth insights to guide flood preparedness and emergency response services.

A novel approach for predicting daily pan evaporation in the coastal regions of Iran using support vector regression coupled with krill herd algorithm model

Evaporation is one of the vital components of hydrological cycle. Precise estimation of pan evaporation (Epan) is essential for the sustainable water resources management. The current study proposed a novel approach to estimate daily Epan across the humid region of Iran using support vector regression (SVR) technique coupled with Krill Herd Algorithm (SVR-KHA). Meteorological data were collected from three stations (Bandar Abbas, Rudsar, and Osku) over a period from 2008 to 2018 and used for application. Of the data, 70% were used for training and remaining 30% were used for testing. The study considered seven different combinations of input variables for predicting daily Epan at each station. The influence of KHA hybridization is examined by comparing results of SVR-KHA algorithm with simple SVR through a multitude of statistical performance evaluation criteria such as coefficient of determination (R2), Wilmot’s index (WI), root-mean-square error (RMSE), Mean Absolute Error (MAE), Relative Root Mean Square Error (RRMSE), Mean Absolute Relative Error (MARE), and several graphical tools. Single input SVR1 model hybrid with KHA (SVR-KHA1) showed improved performance (R2 of 0.717 and RMSE of 1.032 mm/day) as compared with multi-input SVR models, e.g., SVR5 (with RMSE and MAE of 1.037 mm/day and 0.773 mm/day), while SVR7 model hybridized with KHA (SVR-KHA7), which considers seven meteorological variables as input, performed best as compared with other models considered in this study. Epan estimates at Bandar Abbas and Rudsar by SVR and SVR-KHA are similar (with R2 statistics values of 0.82 and 0.84 at Bandar Abbas station, and 0.88 and 0.9 at Rudsar station, respectively). However, better improvements in Epan estimates are observed at Osku station (with R2 of 0.91 and 0.86, respectively), which is situated at interior geographical location with a higher altitude than the other two coastal stations. Overall, the results showed consistent performance of SVR-KHA model with stable residuals of lower magnitude as compared with standalone SVR models.

Machine Learning Modeling of Aerobic Biodegradation for Azo Dyes and Hexavalent Chromium

The present study emphasizes the efficacy of a biosurfactant-producing bacterial strain Klebsiella sp. KOD36 in biodegradation of azo dyes and hexavalent chromium individually and in a simultaneous system. The bacterial strain has exhibited a considerable potential for biodegradation of chromium and azo dyes in single and combination systems (maximum 97%, 94% in an individual and combined system, respectively). Simultaneous aerobic biodegradation of azo dyes and hexavalent chromium (SBAHC) was modeled using machine learning programming, which includes gene expression programming, random forest, support vector regression, and support vector regression-fruit fly optimization algorithm. The correlation coefficient includes the dispersion index, and the Willmott agreement index was employed as statistical metrics to assess the performance of each model separately. In addition, the Taylor diagram was used to further investigate the methods used. The findings of the present study were that the support vector regression-fruitfly optimization algorithm (SVR-FOA) with correlation coefficient (CC) of 0.644, (scattered index) SI of 0.374, and (Willmott’s index of agreement) WI of 0.607 performed better than the autonomous support vector regression (SVR), gene expression programming (GEP), and random forest (RF) methods. In addition, the standalone SVR model with CC of 0.146, SI of 0.473, and WI of 0.408 ranked the second best. In summary, the SBAHC can be accurately estimated using the hybrid SVR-FOA method. In other words, FOA has proven to be a powerful optimization algorithm for increasing the accuracy of the SVR method.

Modeling Daily and Monthly Water Quality Indicators in a Canal Using a Hybrid Wavelet-Based Support Vector Regression Structure

Accurate prediction of water quality indicators plays an important role in the effective management of water resources. The models which studied limited water quality indicators in natural rivers may give inadequate guidance for managing a canal being used for water diversion. In this study, a hybrid structure (WA-PSO-SVR) based on wavelet analysis (WA) coupled with support vector regression (SVR) and particle swarm optimization (PSO) algorithms was developed to model three water quality indicators, chemical oxygen demand determined by KMnO4 (CODMn), ammonia nitrogen (NH3-N), and dissolved oxygen (DO), in water from the Grand Canal from Beijing to Hangzhou. Modeling was independently conducted over daily and monthly time scales. The results demonstrated that the hybrid WA-PSO-SVR model was able to effectively predict non-linear stationary and non-stationary time series and outperformed two other models (PSO-SVR and a standalone SVR), especially for extreme values prediction. Daily predictions were more accurate than monthly predictions, indicating that the hybrid model was more suitable for short-term predictions in this case. It also demonstrated that using the autocorrelation and partial autocorrelation of time series enabled the construction of appropriate models for water quality prediction. The results contribute to water quality monitoring and better management for water diversion.