Group Method Of Data Handling Model Research Articles

A novel correlation for modeling interfacial tension in binary mixtures of CH₄, CO₂, and N₂ + normal alkanes systems: Application to gas injection EOR process

The Enhanced Oil Recovery (EOR) has received significant attention in recent years by the cessation of primary production of several reservoirs and also the increasing global demand for energy. Miscible gas flooding is one of the most popular EOR techniques. Interfacial Tension (IFT) data plays an important role in determining Minimum Miscibility Pressure (MMP) as well as estimating the recovery performance of the EOR schemes, and the production potential of fractured reservoirs. CH₄, CO₂, and N₂ are the gases widely used for gas injection EOR practices. Normal alkanes can represent the real crude oil samples as they are their most abundant constituents. Acquiring knowledge about the IFT between vapor phase and n-alkanes can shed light on the governing mechanisms between the injected gas phase and the real crude oil in EOR projects. Experimental determination of IFT is often associated with the high cost and arduous and timely procedures. The theoretical works need expensive numerical and computational effort. Data-based methods can offer a promising alternative to compensate for the disadvantages of the mentioned methods. An extensive database including 606, 1131, and 469 data samples of IFT between normal n-alkanes and CH₄, CO₂, and N₂ was utilized in this study to develop predictive models. Proper input variables were analyzed and selected for modeling. The Group Method of Data Handling (GMDH) was used in this study. Separate models were developed for the three vapor phases. The Root Mean Square Errors (RMSE) of 1.24, 1.29, and 1.15 mN/m for respective CH₄, CO₂, and N₂ systems indicate the acceptable accuracy of the developed model. The models were compared with the models available in the literature. It was revealed that the proposed GMDH models provide superior predictions for a wide range of pressure and temperature. External validation was performed using a very recently published dataset to check for the generality of the proposed models. Finally, a systematic method was proposed to select the best predictive model based on the n-alkane type and operational parameters of pressure and temperature. The findings of this study can be utilized in designing and planning efficient EOR schemes.

Modeling of wave run-up by applying integrated models of group method of data handling

Wave-induced inundation in coastal zones is a serious problem for residents. Accurate prediction of wave run-up height is a complex phenomenon in coastal engineering. In this study, several machine learning (ML) models are developed to simulate wave run-up height. The developed methods are based on optimization techniques employing the group method of data handling (GMDH). The invasive weed optimization (IWO), firefly algorithm (FA), teaching–learning-based optimization (TLBO), harmony search (HS), and differential evolution (DE) meta-heuristic optimization algorithms are embedded with the GMDH to yield better feasible optimization. Preliminary results indicate that the developed ML models are robust tools for modeling the wave run-up height. All ML models’ accuracies are higher than empirical relations. The obtained results show that employing heuristic methods enhances the accuracy of the standard GMDH model. As such, the FA, IWO, DE, TLBO, and HS improve the RMSE criterion of the standard GMDH by the rate of 47.5%, 44.7%, 24.1%, 41.1%, and 34.3%, respectively. The GMDH-FA and GMDH-IWO are recommended for applications in coastal engineering.

An Accurate Reservoir's Bubble Point Pressure Correlation.

Bubble point pressure (Pb) is essential for determining petroleum production, simulation, and reservoir characterization calculations. The Pb can be measured from the pressure–volume–temperature (PVT) experiments. Nonetheless, the PVT measurements have limitations, such as being costly and time-consuming. Therefore, some studies used alternative methods, namely, empirical correlations and machine learning techniques, to obtain the Pb. However, the previously published methods have restrictions like accuracy, and some use specific data to build their models. In addition, most of the previously published models have not shown the proper relationships between the features and targets to indicate the correct physical behavior. Therefore, this study develops an accurate and robust correlation to obtain the Pb applying the Group Method of Data Handling (GMDH). The GMDH combines neural networks and statistical methods that generate relationships among the feature and target parameters. A total of 760 global datasets were used to develop the GMDH model. The GMDH model is verified using trend analysis and indicates that the GMDH model follows all input parameters’ exact physical behavior. In addition, different statistical analyses were conducted to investigate the GMDH and the published models’ robustness. The GMDH model follows the correct trend for four input parameters (gas solubility, gas specific gravity, oil specific gravity, and reservoir temperature). The GMDH correlation has the lowest average percent relative error, root mean square error, and standard deviation of 8.51%, 12.70, and 0.09, respectively, and the highest correlation coefficient of 0.9883 compared to published models. The different statistical analyses indicated that the GMDH is the first rank model to accurately and robustly predict the Pb.

Evaluation of Contributing Factors Affecting Number of Vehicles Involved in Crashes Using Machine Learning Techniques in Rural Roads of Cosenza, Italy

The evaluation of road safety is a critical issue having to be conducted for successful safety management in road transport systems, whereas safety management is considered in road transportation systems as a challenging task according to the dynamic of this issue and the presence of a large number of effective parameters on road safety. Therefore, the evaluation and analysis of important contributing factors affecting the number of vehicles involved in crashes play a key role in increasing the efficiency of road safety. For this purpose, in this research work, two machine learning algorithms, including the group method of data handling (GMDH)-type neural network and a combination of support vector machine (SVM) and the grasshopper optimization algorithm (GOA), are employed. Hence, the number of vehicles involved in an accident is considered to be the output, and the seven factors affecting transport safety, including Daylight (DL), Weekday (W), Type of accident (TA), Location (L), Speed limit (SL), Average speed (AS), and Annual average daily traffic (AADT) of rural roads in Cosenza, southern Italy, are selected as the inputs. In this study, 564 data sets from rural areas were investigated, and the relevant, effective parameters were measured. In the next stage, several models were developed to investigate the parameters affecting the safety management of road transportation in rural areas. The results obtained demonstrated that the “Type of accident” has the highest level and “Location” has the lowest importance in the investigated rural area. Finally, although the results of both algorithms were the same, the GOA-SVM model showed a better degree of accuracy and robustness than the GMDH model.

Application of machine and deep learning techniques to estimate NMR-derived permeability from conventional well logs and artificial 2D feature maps

Nuclear magnetic resonance (NMR) logs can provide information on some critical reservoir characteristics, such as permeability, which are rarely obtainable from conventional well logs. Nevertheless, high cost and operational constraints limit the wide application of NMR logging tools. In this study, a machine learning (ML)-based procedure is developed for fast and accurate estimation of NMR-derived permeability from conventional logs. Following a comprehensive preprocessing on the collected data, the procedure is trained and tested on a well log dataset, with selected conventional logs as inputs, and NMR-derived permeability as target, shallow and deep learning (DL) methods are applied to estimate permeability from selected conventional logs through artificial production of NMR-derived information from the input data. Three supervised ML algorithms are utilized and evaluated, including random forest (RF), group method of data handling (GMDH), and one-dimensional convolutional neural network (1D-CNN). Additionally, a modified two-dimensional CNN (named as Residual 2D-CNN) is developed which is fed by artificial 2D feature maps, generated from available conventional logs. The hyper-parameters of the ML and DL models are optimized using genetic algorithm (GA) to improve their performances. By comparing the output of each model with the permeability derived from NMR log, it is illustrated that nonlinear machine and deep learning techniques are helpful in estimation of NMR permeability. The obtained accuracy of RF, GMDH, 1D-CNN and Res 2D-CNN models, respectively, is 0.90, 0.90, 0.91 and 0.97 which indicate that Res 2D-CNN model is the most efficient method among the other applied techniques. This research also highlights the importance of using generated feature maps for training Res 2D-CNN model, and the essential effect of the applied modifications (i.e., implementing residual and deeper bottleneck architectures) on improving the accuracy of the predicted output and reducing the training time.

The combined effects of the minimum miscibility pressure and injection rate variations on recovery of co2 flooding in sandstone reservoir

One of the most effective enhanced oil recovery techniques is carbon dioxide (CO2) flooding. It is because of its high oil recovery rate and associated advantage on the environment. CO2 flooding has been broadly used and commercially proven. Depending on the reservoir and operational conditions, it can be implemented either in immiscible or miscible modes. Determining the injection mode depends on the minimum miscibility pressure (MMP). The conventional ways of determining the MMP (slim-tube experiments, supercritical extractor, etc.) are costly and time-consuming. A simulation approach has been deployed to determine the MMP of a synthetic reservoir model using a one-dimension compositional slim-tube model in ECLIPSE300. The MMP was also determined using the group method of data handling (GMDH) and other existing correlations. The MMP determined by slim-tube simulation was ~ 4176 psia. Comparing the MMPs of the correlations to the slim-tube simulation, the correlation by Maklavani et al. (Braz J Pet, 2010) was the most accurate with a mean absolute percentage error (MAPE) of 0.79%. The GDMH and the correlation of Firoozabadi and Khalid had MAPEs of 4.96% and 6.06%, respectively. The GMDH model introduced in this study was not as accurate as the correlation by Maklavani et al. (Braz J Pet, 2010) . The model could be improved, or other machine learning models with improved training and prediction could be deployed to estimate MMP more accurately. A synthetic reservoir model based on literature data was used to investigate the effect of the MMP and injection rate on oil recovery by CO2 flooding. The impact of MMP was investigated by the miscible and immiscible flooding scenarios. The injection rate was varied in each scenario to determine the optimum injection rate. However, the scenarios with optimum injection rates for both miscible and immiscible CO2 injection were compared to a waterflood scenario. The optimum injection rates for miscible and immiscible flooding were 2800 and 2200 Mscf/day, respectively. The oil recovery efficiencies for the optimum miscible and immiscible injection were 48% and 46%, respectively. In this study, miscible flooding proved to be the more effective method in oil recovery. However, considering the difference in oil recovery and the difficulty in achieving miscibility, the immiscible CO2 flooding proves to be the feasible option for improving oil recovery.

Developing a GMDH-type neural network model for spatial prediction of NOx : A case study of Çerkezköy, Tekirdağ

Air pollution-induced issues involve public health, environmental, agricultural and socio-economic aspects. Therefore, decision-makers need low-cost, efficient tools with high spatiotemporal representation for monitoring air pollutants around urban areas and sensitive regions. Air pollution forecasting models with different time steps and forecast lengths are used as an alternative and support to traditional air quality monitoring stations (AQMS). In recent decades, given their eligibility to reconcile the relationship between parameters of complex systems, artificial neural networks have acquired the utmost importance in the field of air pollution forecasting. In this study, different machine learning regression methods are used to establish a mathematical relationship between air pollutants and meteorological factors from four AQMS (A-D) located between Çerkezköy and Süleymanpaşa, Tekirdağ. The model input variables included air pollutants and meteorological parameters. All developed models were used with the intent to provide instantaneous prediction of the air pollutant parameter NOx within the AQMS and across different stations. In the GMDH (group method of data handling)-type neural network method (namely the self-organizing deep learning approach), a five hidden layer structure consisting of a maximum of five neurons was preferred and, choice of layers and neurons were made in a way to minimize the error. In all models developed, the data were divided into a training (%80) and a testing set (%20). Based on R2, RMSE, and MAE values of all developed models, GMDH provided superior results regarding the NOx prediction within AQMS (reaching 0.94, 10.95, and 6.65, respectively for station A) and between different AQMS. The GMDH model yielded NOx prediction of station B by using station A input variables (without using NOx data as model input) with R2, RMSE and MAE values 0.80, 10.88, 7.31 respectively. The GMDH model is found suitable for being employed to fill in the gaps of air pollution records within and across-AQMS.

Permeability prediction of heterogeneous carbonate gas condensate reservoirs applying group method of data handling

Carbonate petroleum reservoirs typically have lower permeabilities and recovery factors than sandstone reservoirs, so the natural fractures they often incorporate have positive impacts on resource recovery and fluid production rates. Quantifying effective permeability, incorporating contributions from pores and fractures, is therefore essential in the reservoir characterization and flow-regime modelling of carbonate reservoirs. This research applies a robust machine-learning forecasting model to predict permeability (K) for heterogeneous carbonate gas condensate reservoirs. A 212-point dataset from six gas-condensate carbonate reservoirs (Russia and Iran) is compiled. The input variables considered are porosity (Φ, %), specific surface area (Sp, 1/cm) and irreducible water saturation (Swir, %). These variables are assessed using four machine learning models: group method of data handling (GMDH), polynomial regression (PR), support vector machine (SVR), and decision tree (DT) to predict permeability. The GMDH algorithm, a polynomial neural network with a customized architecture is developed, such that it displays increased prediction accuracy and improved learning capabilities. All four models developed in this study substantially improve upon K predictions derived from established empirical correlations. The GMDH model also outperforms the other models in respect of K prediction accuracy using Φ, Swir, and Sp as input variables. It achieves permeability prediction accuracy for the multi-field dataset evaluated with a root mean squared error (RMSE) and coefficient of determination (R2) for the training and testing of the best model (GMDH) of RMSE = 9.2 mD and R2 = 0.9988; RMSE = 0.4 mD and R2 = 0.9972, respectively. The model can be readily adapted for application to other field datasets to estimate K from limited well-log and/or core data.

Discharge modeling in compound channels with non-prismatic floodplains using GMDH and MARS models

Abstract In this study, modeling of discharge was performed in compound open channels with non-prismatic floodplains (CCNPF) using soft computation models including multivariate adaptive regression splines (MARS) and group method of data handling (GMDH), and then their results were compared with the multilayer perceptron neural networks (MLPNN). In addition to the total discharge, the discharge separation between the floodplain and main channel was modeled and predicted. The parameters of relative roughness coefficient, the relative area of flow cross-section, relative hydraulic radius, bed slope, the relative width of water surface, relative depth, convergence or divergence angle, relative longitudinal distance as inputs, and discharge were considered as models output. The results demonstrated that the statistical indices of MARS, GMDH, and MLPNN models in the testing stage are R2 = 0.962(RMSE = 0.003), 0.930(RMSE = 0.004), and 0.933(RMSE = 0.004) respectively. Examination of statistical error indices shows that all the developed models have the appropriate accuracy to estimate the flow discharge in CCNPF. Examination of the structure of developed GMDH and MARS models demonstrated that the relative parameters: roughness, area, hydraulic radius, flow aspect ratio, depth, and angle of convergence or divergence of floodplain have the greatest impact on modeling and estimation of discharge.

Presentation of regression analysis, GP and GMDH models to predict the pedestrian density in various urban facilities

In this study, the relationship between space mean speed (SMS), flow rate and density of pedestrians was investigated in different pedestrian facilities, including 1 walkway, 2 sidewalks, 2 signalized crosswalks and 2 mid-block crosswalks. First, statistical analysis was performed to investigate the normality of data and correlation of variables. Regression analysis was then applied to determine the relationship between SMS, flow rate, and density of pedestrians. Finally, two prediction models of density were obtained using genetic programming (GP) and group method of data handling (GMDH) models, and k-fold and holdout cross-validation methods were used to evaluate the models. By the use of regression analysis, the mathematical relationships between variables in all facilities were calculated and plotted, and the best relationships were observed in flow rate-density diagrams. Results also indicated that GP had a higher R2 than GMDH in the prediction of pedestrian density in terms of flow rate and SMS, suggesting that GP was better able to model SMS and pedestrian density. Moreover, the application of k-fold cross-validation method in the models led to better performances compared to the holdout cross-validation method, which shows that the prediction models using k-fold were more reliable. Finally, density relationships in all facilities were obtained in terms of SMS and flow rate.

A new pressure and temperature dependent relative viscosity model for water-Al2O3 nanofluids using GMDH neural network

The introduction of nanoparticles into fluids have been used in various sciences such as; heat transfer, drilling mud, hydraulic fracturing, EOR, and widely in biotechnology science. The dispersion of nanoparticles in the fluid can affect significantly the viscosity of the system. In this study, a self-organizing polynomial neural network based on a group method of data handling (GMDH) is developed to investigate the viscosity of water-based nanofluids regarding temperature and especially pressure changes. The influence of high pressure has not been previously considered in any correlation. The results were estimated using the GMDH model and have higher accuracy than various theoretical models and empirical equations and show the coefficient of determination of 0.999.

Modeling thermal conductivity of nanofluids using advanced correlative approaches: Group method of data handling and gene expression programming

Accurate estimation of thermal conductivity (TC) of nanofluids is essential in thermophysical studies of nanofluids. In this study, more than 3200 data of thermal conductivity of nanofluids were collected from literature to develop simple-to-use and accurate correlations for predicting relative thermal conductivity of nanofluids. The dataset includes 13 different nanofluids with temperature from −30.00 to 149.15 °C, particle size from 5.00 to 150.00 nm, particle thermal conductivity from 1.20 to 1000.00 W/mk, particle volume fractions from 0.01 to11.22%, and base fluid thermal conductivity from 0.11 to 0.69 W/mk. Group method of data handling (GMDH) and gene expression programming (GEP) as two white-box powerful models were used for modeling. The results of proposed models were compared to 23 well-known theoretical and empirical models. The statistical and graphical results showed that the proposed models are more precise and reliable than the existing ones in literature. The GMDH model showed a better performance compared to GEP, and could predict all data with an average absolute relative error of 2.27% in training and 2.44% in testing data set. In addition, it was found that the proposed models could capture the physically expected trends with variation of temperature, size of nanoparticles, and volume fraction. The sensitivity analysis illustrated that temperature has the highest effect on the relative TC followed by base fluid TC and particle volume fraction

Estimating Daily Rice Crop Evapotranspiration in Limited Climatic Data and Utilizing the Soft Computing Algorithms MLP, RBF, GRNN, and GMDH

Evapotranspiration represents the water requirement of plants during their growing season, and its accurate measurement at the farm is essential for agricultural water planners and managers. Field measurements of evapotranspiration have always been associated with many difficulties that have led researchers to seek a way to remotely measure this component in horticultural and agricultural areas. This study aims to investigate an indirect approach for daily rice crop evapotranspiration (ETc) measurement by machine learning (ML) techniques and the least available climatic variables. For this purpose, daily meteorological variables were obtained from three ground meteorological stations in rice cultivation regions of northern Iran during 2003–2016. The ETc rates were calculated by seven meteorological variables, the FAO‐56 Penman‐Monteith equation, and the regional calibrated rice crop coefficient and considered as the reference data. The MLs, including Multilayer Perceptron (MLP), Radial Basis Function (RBF), Generalized Regression Neural Network (GRNN), and Group Method of Data Handling (GMDH), were utilized for ETc modeling. Different input combinations were applied, based on the use of minimum effective variables as input. Results showed that the models showed the most accurate performances in the input combination of four climatic variables: sunshine duration, maximum temperature, relative humidity, and wind speed. Investigating the accuracy of models in rice growth phases showed that the least estimation error belonged to the initial growing stage, which increased during the mid‐season and late‐season growing stages. A comparison of the models showed that the GMDH model performed better against the other competitors. For this model, both the Nash‐Sutcliffe (NS) coefficient and R2 were greater than 0.98, and the Root Mean Square Error (RMSE) ranged between 0.214 and 0.234 mm per day in all stations. The current approach showed promising results in rice evapotranspiration modeling by only four common meteorological variables and can be reliably applied for indirect measurement of this variable over the rice farms. The studied approach will have research value for rice and other crops in similar/different climatic conditions.

Swarm intelligence optimization of the group method of data handling using the cuckoo search and whale optimization algorithms to model and predict landslides

The robustness of landslide prediction models has become a major focus of researchers worldwide. We developed two novel hybrid predictive models that combine the self-organizing, deep-learning group method of data handling (GMDH) with two swarm intelligence optimization algorithms, i.e., cuckoo search algorithm (CSA) and whale optimization algorithm (WOA) for spatially explicit prediction of landslide susceptibility. Eleven landslide-causing factors and 334 historic landslides in a 31,340 km2 landslide-prone area in Iran were used to produce geospatial training and validation datasets. The GMDH model was employed to develop a basic predictive model that was then restructured and its parameters were optimized using the CSA and WOA algorithms, yielding the novel hybrid GMDH-CSA and GMDH-WOA models. The hybrid models were validated and compared to the standalone GMDH model by calculating the area under the receiver operating characteristic (AUC) curve and root mean square error (RMSE). The results demonstrated that the hybrid models overcame the computational shortcomings of the basic GMDH model and significantly improved landslide susceptibility prediction (GMDH-CSA, AUC = 0.909 and RMSE = 0.089; GMDH-WOA, AUC = 0.902 and RMSE = 0.129; standalone GMDH, AUC = 0.791 and RMSE = 0.226). Further, the hybrid models were more robust than the standalone GMDH model, showing consistently excellent performance when the training and validation datasets were changed. Overall, the swarm intelligence-optimized models, but not the standalone model, identified the best trade-offs among objectives, accuracy, and robustness.

Early detection model for the urban stream syndrome using specific stream power and regime theory

Unmitigated urbanization frequently alters the flow frequency distribution and changes the source and transport rates of sediments in previously “in regime” channels. These changes may result in increased stream erosion, changes in alluvial materials and degradation of water quality and habitat, conditions called “urban stream syndrome”. Early identification of streams with the potential to develop urban stream syndrome may allow for additional implementation of watershed controls such as Low Impact Development or within stream mitigation (e.g. erosion controls). Regime theory applied to dynamically-stable alluvial channels has identified empirical equations linking width (W), depth (H), slope (S), mean sediment particle size (D50), and the 2-yr return bankfull discharge (Q2). This study examines the application of regime-theory equations to urban streams as a means of identifying channels with urban stream syndrome. To begin the assessment of the applicability of regime equations an extensive database of channel morphology variables for 733 in-regime channels, from North America, Britain and South Asia, was compiled from existing publications. Using this database a Group Method of Data Handling (GMDH) model was developed to predict specific stream power for comparison with observed values to determine whether a channel is in or out of regime. The application of the GMDH model was showcased using regional flow and sediment data to predict channel conditions of several watercourses in Southern Ontario, Canada. The GMDH model reliably identified channels both in and out of regime conditions compared with published in-situ assessments based on Rapid Geomorphic Assessments (RGAs). This study has identified changes in specific stream power (ω) as a reliable early detection metric for occurrence of the urban stream syndrome. The model can inform the strategies to mitigate the urban stream syndrome, including within-channel mitigation and watershed initiatives, including Low Impact Developments (LIDs).

Modified Group Method of Data Handling for Flood Quantile Prediction at Ungauged Site

Handling flood quantile with little data is essential in managing water resources. In this paper, we propose a potential model called Modified Group Method of Data Handling (MGMDH) to predict the flood quantile at ungauged sites in Malaysia. In this proposed MGMDH model, the principal component analysis (PCA) method is matched to the group method of data handling (GMDH) with various transfer functions. The MGMDH model consists of four transfer functions: polynomial, sigmoid, radial basis function, and hyperbolic tangent sigmoid transfer functions. The prediction performance of MGMDH models is compared to the conventional GMDH model. The appropriateness and effectiveness of the proposed models are demonstrated with a simulation study. Cauchy distribution is used in the simulation study as a disturbance error. The implementation of Cauchy Distribution as an error disturbance in artificial data illustrates the performance of the proposed models if the extreme value or extreme event occurs in the data set. The simulation study may say that the MGMDH model is superior to other comparison models, namely LR, NLR, GMDH and ANN models. Another beauty of this proposed model is that it shows a strong prediction performance when multicollinearity is absent in the data set.

Comparison of different statistical downscaling models and future projection of areal mean precipitation of a river basin under climate change effect

Abstract Investigation of the hydrological impacts of climate change at the local scale requires the use of a statistical downscaling technique. In order to use the output of a Global Circulation Model (GCM), a downscaling technique is used. In this study, statistical downscaling of monthly areal mean precipitation in the Göksun River basin in Turkey was carried out using the Group Method of Data Handling (GMDH), Support Vector Machine (SVM) and Gene Expression Programming (GEP) techniques. Large-scale weather factors were used for the basin with a monthly areal mean precipitation (PM) record from 1971 to 2000 used for training and testing periods. The R2-value for precipitation in the SVM, GEP and GMDH models are 0.62, 0.59, and 0.6 respectively, for the testing periods. The results show that SVM has the best model performance of the three proposed downscaling models, however, the GEP model has the lowest AIC value. The simulated results for the Canadian GCM3 (CGCM3) A1B and A2 scenarios show a similarity in their average precipitation prediction. Generally, both these scenarios anticipate a decrease in the average monthly precipitation during the simulated periods. Therefore, the results of the future projections show that mean precipitation might decrease during the period of 2021–2100.

Application of the group method of data handling (GMDH) approach for landslide susceptibility zonation using readily available spatial covariates

Landslide susceptibility (LS) mapping is an essential tool for landslide risk assessment. This study aimed to provide a new approach with better performance for landslide mapping and adopting readily available variables. In addition, it investigates the capability of a state-of-the-art model developed using the group method of data handling (GMDH) to spatially model LS. Furthermore, hybridized models of GMDH were developed using different metaheuristic algorithms. The study area was the Bonghwa region of South Korea, for which an accurate landslide inventory dataset is available. We considered a total of 13 spatial covariates (altitude, slope, aspect, topographic wetness index, valley depth, plan curvature, profile curvature, distance from fault, distance from river, distance from road, land use, density of forest, and lithology were chosen as independent variables). Two benchmark models—random forest and boosted regression trees—were used to compare their results with the standalone GMDH and hybridized models. We compared model accuracy using the two most robust evaluation metrics, root mean square error (RMSE) and area under the receiver operating characteristic curve (AUROC). The validation results showed that hybridized models outperformed the standalone GMDH model. Moreover, the hybridized GMDH-PSO (AUC = 0.83, RMSE = 0.108), GMDH-IWO (AUC = 0.81, RMSE = 0.111), GMDH-BBO (AUC = 0.8; RMSE = 0.12), and GMDH-ICA (AUC = 0.8; RMSE = 0.117) had a better predictive performance than both RF and BRT. Therefore, the proposed approach could successfully produce landslide susceptibility maps using relatively few readily available variables and can be repeated in data-scarce regions.

Model development for energy dissipation over gabion stepped weirs using GEP and GMDH techniques

A gabion stepped weir is a permeable weir that consists of a gabion box filled with stone aggregates. It is cost-effective structure used for the dissipation of water flow energy from upstream to downstream. Gabion weir also allows the movement of aquatic life and transportation of physical and chemical substances present in water. In this study, energy dissipation in terms of inverse relative energy dissipation (IRED) over gabion stepped weir has been studied. It was observed that the existing predictor does not give a reasonable estimate for IRED. Therefore, the data have been reanalysed to develop a generalized regression equation for IRED. Generalized models using Gene Expression Programming (GEP) and Group Method of Data Handling (GMDH) were also developed. The predictions based on GMDH model (R = 0.979, E = 0.96 and RMSE = 0.314) were found more satisfactory than those given by traditional regression equations (R = 0.929, E = 0.91 and RMSE = 0.557) as well as those given by the GEP model (R = 0.959, E = 0.94 and RMSE = 0.476). Sensitivity analysis shows that the Froude number before the jump is the most important parameter for the prediction of IRED.

Streamflow Estimation at Ungauged Basin using Modified Group Method of Data Handling

Among the foremost frequent and vital tasks for hydrologist is to deliver a high accuracy estimation on the hydrological variable, which is reliable. It is essential for flood risk evaluation project, hydropower development and for developing efficient water resource management. Presently, the approach of the Group Method of Data Handling (GMDH) has been widely applied in the hydrological modelling sector. Yet, comparatively, the same tool is not vastly used for the hydrological estimation at ungauged basins. In this study, a modified GMDH (MGMDH) model was developed to ameliorate the GMDH model performance on estimating hydrological variable at ungauged sites. The MGMDH model consists of four transfer functions that include polynomial, hyperbolic tangent, sigmoid and radial basis for hydrological estimation at ungauged basins; as well as; it incorporates the Principal Component Analysis (PCA) in the GMDH model. The purpose of PCA is to lessen the complexity of the GMDH model; meanwhile, the implementation of four transfer functions is to enhance the estimation performance of the GMDH model. In evaluating the effectiveness of the proposed model, 70 selected basins were adopted from the locations throughout Peninsular Malaysia. A comparative study on the performance was done between the MGMDH and GMDH model as well as with other extensively used models in the area of flood quantile estimation at ungauged basins known as Linear Regression (LR), Nonlinear Regression (NLR) and Artificial Neural Network (ANN). The results acquired demonstrated that the MGMDH model possessed the best estimation with the highest accuracy comparatively among all models tested. Thus, it can be deduced that MGMDH model is a robust and efficient instrument for flood quantiles estimation at ungauged basins.