Generalized Regression Neural Network Model Research Articles

Using Artificial Neural Network to Model Water Discharge and Chemistry in a River Impacted by Acid Mine Drainage

In southeast Ohio, Raccoon Creek Watershed (RC) has an extensive mining history resulting in acid mine drainage (AMD) and subsequent environmental problems. Modeling of the discharge and chemistry of AMD impacted Hewett Fork, a tributary of Raccoon Creek, is the focus of this paper. Discharge measurements are collected by the United States Geological Survey (USGS) gage station at the Bolin Mills (BM) station on the main stem of RC. This data for the period 2011-2019 has been analyzed to develop a prediction model for BM discharge and subsequently use the model to predict flow and water chemistry in Hewett Fork (HF). The Neural Network Model using group method of data handling (GMDH) and generalized regression neural network (GRNN) shows a variation of prediction models for BM due to parameters such as decay factor in API and ATI, as well as in the evapotranspiration input variables of the model. However, the study reveals that the GRNN model for BM is the most suitable for BM prediction based on its performance, with an r-value greater than 0.90, and its ease in predicting discharge by specifying a data set to be added to the data set for training and calibrating the network. The result of the water chemistry model using GMDH, with r values greater than 0.80 for each model, shows the input variables have a good capacity to predict chemical concentration/load in the HF stream. This study shows that Artificial Neural Network (ANN) modeling can help to model successfully and predict flow and chemical evolution of rivers in Ohio and other parts of the world.

On the evaluation of crude oil oxidation during thermogravimetry by generalised regression neural network and gene expression programming: application to thermal enhanced oil recovery

Enhancing oil recovery using in-situ combustion (ISC) is an attractive alternative, especially for heavy crudes. During ISC, part of the hydrocarbon is pyrolysed/oxidised, which generates heat and deposits fuel in the combustion front. In this study, crude reactions during ISC are modelled after their thermogravimetry thermo-oxidative profiles using advanced machine learning systems. The model inputs include the weight per cent of asphaltenes, resins, and °API gravity of the oil as well as the heating rate and the temperature. Four types of artificial neural networks (ANNs); namely multilayer perceptron (MLP), generalised regression neural network (GRNN), cascade-forward neural network (CFNN), and radial basis function (RBF) neural network, were employed to develop models for accurate prediction of the weight per cent of residual crude oil based on 2289 experimental data points. Moreover, three optimisation algorithms; including Bayesian Regularisation (BR), Levenberg–Marquardt (LM), and Scaled Conjugate Gradient (SCG) were applied in the training step of MLP and CFNN to improve the prediction ability. GRNN provided the most accurate prediction with ∼2.3% overall average absolute per cent relative error and coefficient of determination of 0.9983. GRNN model is reliable for crude oils with °API gravity of 5–35 and up to 820°C. Lastly, a mathematical correlation was developed to estimate the residual crude oil from thermogravimetry analysis using gene expression programming (GEP). GEP also predicted the thermo-oxidative profile with high accuracy. On the basis of sensitivity analysis, residue formation during crude oil oxidation was impacted the most by the temperature, oil °API gravity, and asphaltenes content, respectively. The Leverage approach identified 2.9% of the data points as doubtful.

Predicting of mutton sheep stress coupled with multi-environment sensing and supervised learning network in the transportation process

Stress response caused by transportation is an important reason that affects the health and welfare of livestock, and the intelligent and precise monitoring of the stress state during transportation is a blank in research. On-site tracking experiments, literature review, and expert consultation indicate that environmental temperature, relative humidity and vibration intensity of vehicle are important stressors in the transportation process, and cortisol (COR) and adrenocorticotropic hormone (ACTH) are the key biomarkers to characterize the stress level. In this paper, stressors causing stress response were collected through environmental sensor network, and key biomarkers representing stress response were identified through biochemical analysis, and their change rules were analyzed and compared. Furthermore, the predictive models coupled with environmental parameters and stress markers were constructed through supervised learning networks. The results showed that: (1) After testing, the data collection performance of the multi-sensor network is reliable (P < 0.05); transportation will cause significant changes in the concentration of COR and ACTH (P < 0.05); the simulation results of stress markers data have no significant difference compared with the sample data (PSpline > PPchip > 0.90). (2) The validation results of models showed that: for COR, the absolute error and relative error based on general regression neural network (GRNN) are 2.59 ± 0.16 ng/mL and 1.30 ± 0.07%, respectively, which is better than the accuracy based on back propagation neural network (BPNN) and Elman neural network (Elman); for ACTH, the absolute error and relative error based on GRNN models were 1.75 ± 0.13 pg/mL and 2.14 ± 0.17%, respectively, which were better than the accuracy based on BPNN and Elman models. (3) For the prediction performance, the prediction accuracy of GRNN model for COR concentration is basically equal to that of Elman model, which is 0.17% higher than that of BPNN model for COR concentration, but the maximum relative error of BPNN model for COR concentration is the smallest. The prediction accuracy of Elman model for ACTH concentration is 0.09% higher than that of GRNN model, and 0.29% higher than that of BPNN model. But the maximum relative error of Elman model for ACTH concentration is the largest, and the running time is significantly longer. Although the performance of the three modeling methods is different, their overall accuracy has reached more than 97%. Therefore, this study can effectively identify the stress state of mutton sheep in the actual transportation process, and provide technical support for the health traceability and control of mutton sheep.

Analysis and forecasting of crude oil price based on the variable selection-LSTM integrated model

In recent years, the crude oil market has entered a new period of development and the core influence factors of crude oil have also been a change. Thus, we develop a new research framework for core influence factors selection and forecasting. Firstly, this paper assesses and selects core influence factors with the elastic-net regularized generalized linear Model (GLMNET), spike-slab lasso method, and Bayesian model average (BMA). Secondly, the new machine learning method long short-term Memory Network (LSTM) is developed for crude oil price forecasting. Then six different forecasting techniques, random walk (RW), autoregressive integrated moving average models (ARMA), elman neural Networks (ENN), ELM Neural Networks (EL), walvet neural networks (WNN) and generalized regression neural network Models (GRNN) were used to forecast the price. Finally, we compare and analyze the different results with root mean squared error (RMSE), mean absolute percentage error (MAPE), directional symmetry (DS). Our empirical results show that the variable selection-LSTM method outperforms the benchmark methods in both level and directional forecasting accuracy.

Quantitative risk assessment of explosion rescue by integrating CFD modeling with GRNN

Gas explosions remain a significant industrial hazard, characterized by sudden outbreak, rapid development, and huge destruction. Quantitative risk assessment (QRA) has played an effective role in safety management and emergency preparedness for such incidents. Although a lot of attempts have been done to analyze the explosion risks, few works have been conducted on the risk for responding rescuers during these missions. This paper presents an explosion rescue risk assessment methodology for emergency decision support by integrating with a general regression neural network (GRNN) with computational fluid dynamics (CFD) modeling. Underground coal mine gas explosions are taken as an example. The likelihood exposure consequence (LEC) method is combined with a fault tree to establish a rescue risk assessment model that consists of 5 levels. The CFD modeling for possible explosion scenarios is continuously performed by automatically varying the predefined parameters. The generated data is used for the development and improvement of the GRNN model. Provided with real-time data, the GRNN model can predict the effects of a blast within few seconds, which are then used to calculate the occurrence probability of secondary explosions. As a result, the rescuers’ level exposure to explosion risk can be estimated. This will allow a better-informed rescue decision making. The proposed integrated method is applied to the Laoyingyan coal mine to demonstrate its applicability and effectiveness.

Machine Learning‐Aided Process Design: Modeling and Prediction of Transformation Temperature for Pearlitic Steel

In this article, different machine learning (ML) algorithms are provided to predict the transformation temperature of pearlite using relevant material descriptors, austenitizing temperature, and cooling rate. To search for an appropriate model, the predictive performance of ML model including artificial neural network (ANN), generalized regression neural network (GRNN), radial basis function neural network (RBFNN), and extreme learning machine (ELM) is evaluated and compared on testing dataset. To quickly find the appropriate parameters, artificial fish swarm algorithm (AFSA) is applied to further improve the prediction accuracy of ANN model. In view of the distinguished prediction performance, the regression analysis shows that the GRNN model performs favorably against the other learning models. To verify the superiority of proposed model, a type of pearlitic steel with hypereutectoid composition is prepared. The phase transition temperature and transformation products are determined using diametral dilatometric and microscopy technique through continuous cooling transformation with cooling rates of 1 and . As a result, the experimental results agree well with the predictive results. The work proposes a reliable model to predict the phase transition temperature which can facilitate the optimization of process parameters to achieve the best possible microstructure.

Spatiotemporal distributions of pan evaporation and the influencing factors in China from 1961 to 2017

Pan evaporation (EVP) is an important element of the hydrological cycle and exhibits a close relationship with climate change. In this study, the generalized regression neural network (GRNN) model and extreme gradient boosting (Xgboost) model were applied to estimate the monthly EVP. The spatiotemporal distributions of EVP and influencing factors in China and eight subregions from 1961 to 2017 were analyzed. The root mean square error (RMSE) of all GRNN models was approximately 10%, and the Nash-Sutcliffe efficiency (NSE) coefficient was larger than 0.94 in different subregions. The annual mean EVP in all subregions and throughout China showed decreasing trends before 1993, while EVP increasing trends occurred in East China (EC), South China (SC), Southwest China (SWC), west of Northwest China (WNC), and throughout China after 1994. Subsequently, the variable importance in projection (VIP) between EVP and climatic factors obtained by partial least squares (PLS) regression and the relative contribution calculated by Xgboost stepwise regression analysis (SRA) were used to investigate the climatic parameter sensitivity to EVP. The results indicated that the combined effects of the vapor pressure deficit (VPD), sunshine duration (SSD), and wind speed (WIN) were the main reasons for the variations in EVP across China. At the seasonal scale, SSD, WIN, relative humidity (RHU), and VPD were the most sensitive climatic factors to EVP in different seasons. In addition, the Pacific decadal oscillation (PDO) index showed a significant negative correlation with EVP, and the El Niño 3.4 (N3.4) and East Atlantic/Western Russia (EA/WR) indices revealed positive correlations in most regions from 1961 to 1993, while the North Atlantic oscillation (NAO) was negatively correlated with EVP. Moreover, N3.4 and Atlantic multidecadal oscillation (AMO) were positively correlated with EVP from 1994 to 2017. Finally, the yearly number of heatwave events (HWN) was highly correlated with EVP because of the high VPD and SSD levels during the heatwave event periods.

Modeling and optimizing in vitro seed germination of industrial hemp (Cannabis sativa L.)

In vitro seed germination of cannabis as the first physiological stage in the plant life cycle is not only important for studying factors affecting cultivation conditions but also crucial for obtaining juvenile tissue as a potential explant for different in vitro procedures. On the other hand, in vitro seed germination is a multi-variable biological process that can be influenced by genetic (genotype) and physical factors (medium composition and environmental conditions). Therefore, a powerful mathematical methodology such as artificial neural networks (ANNs) is well suited to analyze the data and optimize the conditions this complex system. The current study was aimed to evaluate the effect of different types and concentrations of carbohydrate sources (sucrose and glucose) as well as different strengths of DKW (Driver and Kuniyaki Walnut) and mMS (Murashige and Skoog Medium, Van der Salm modification) media on seed germination indices as well as morphological features of in vitro-grown cannabis seedlings by using three ANNs including multilayer perceptron (MLP), radial basis function (RBF), and generalized regression neural network (GRNN). The GRNN model displayed higher predictive accuracy (r2>0.70) in both training and testing sets for all germination indices and morphological traits in comparison to RBF or MLP. Moreover, non-dominated sorting genetic algorithm-II (NSGA-II) was subjected to the GRNN to find the optimal type and level of media and carbohydrate source for obtaining the best seed germination indices (germination rate and mean germination time). According to the optimization process, 0.43 strength mMS medium supplemented with 2.3 % sucrose would result in the best outcomes. This result showed that a moderate level of salts existing in culture media (0.43 strength of mMS medium) supplemented with a moderate level of sucrose (2.3 %) can improve in vitro seed germination of hemp. The results of a validation experiment revealed that there was a negligible difference between the experimental data and the optimized result. Therefore, GRNN-NSGA-II provided an accurate prediction of seed germination and can likely be employed to optimize different factors involved in in vitro culture of this multi-purpose crop.

AN UNSUPERVISED METHOD BASED ON FIRE INDEX ENHANCEMENT AND GRNN FOR AUTOMATED BURNED AREA MAPPING FROM SINGLE-PERIOD REMOTE SENSING IMAGERY

Abstract. In the current situation of frequent forest fires, the study of forest burned area mapping is important. However, there is still room for improvement in the accuracy of existing forest burning area mapping methods. Therefore, in this paper, an unsupervised method based on fire index enhancement and GRNN (General Regression Neural Network) is proposed for automated forest burned area mapping from single-date post-fire remote sensing imagery. The proposed method first uses adaptive spatial context information to enhance the generated fire index to improve its ability to indicate the burned areas. Then the uncertainty analysis is performed on the enhanced fire index to extract reliable burned samples and non-burned samples for subsequent classifier training. Finally, the improved GRNN model considering the spatial correlation of pixels is used as a classifier to binarize the enhanced fire index to generate the final burned area map. Based on two commonly used fire indexes, NBR (Normalized Burn Ratio) and BAI (Burned Area Index), this paper conducts burned area mapping experiments on a post-fire image of a forest area in Inner Mongolia, China to test the effectiveness of the proposed method, and two commonly used threshold methods (Otsu and Kmeans clustering) are also used to conduct burned area mapping based on threshold segmentation of fire index for comparison experiments. The experimental results prove the effectiveness and superiority of the proposed method. The proposed method is unsupervised and automated, so it has high application value and potential under the current situation of frequent forest fires.

Chatter Stability Prediction and Process Parameters’ Optimization of Milling Considering Uncertain Tool Information

Stability is the prerequisite of a milling operation, and it seriously depends on machining parameters and machine tool dynamics. Considering that the tool information, including the tool clamping length, feeding direction, and spatial position, has significant effects on machine tool dynamics, this paper presents an efficient method to predict the tool information dependent-milling stability. A generalized regression neural network (GRNN) is established to predict the limiting axial cutting depth, where the machining parameters and tool information are taken as input variables. Moreover, an optimization model is proposed based on the machining parameters and tool information to maximize the material removal rate (MRR), where the GRNN model is taken as the stability constraint. A particle swarm optimization (PSO) algorithm is introduced to solve the optimization model and provide an optimal configuration of the machining parameters and tool information. A case study has been developed to train a GRNN model and establish an optimization model of a real machine tool. Then, effects of the tool information on milling stability were discussed, and an origin-symmetric phenomenon was observed as the feeding direction varied. The accuracy of the solved optimal process parameters corresponding to the maximum MRR was validated through a milling test.

Dynamic Modulus Prediction of a High-Modulus Asphalt Mixture

Dynamic modulus is a key evaluation index of the high-modulus asphalt mixture, but it is relatively difficult to test and collect its data. The purpose is to achieve the accurate prediction of the dynamic modulus of the high-modulus asphalt mixture and further optimize the design process of the high-modulus asphalt mixture. Five high-temperature performance indexes of high-modulus asphalt and its mixture were selected. The correlation between the above five indexes and the dynamic modulus of the high-modulus asphalt mixture was analyzed. On this basis, the dynamic modulus prediction models of the high-modulus asphalt mixture based on small sample data were established by multiple regression, general regression neural network (GRNN), and support vector machine (SVM) neural network. According to parameter adjustment and cross-validation, the output stability and accuracy of different prediction models were compared and evaluated. The most effective prediction model was recommended. The results show that the SVM model has more significant prediction accuracy and output stability than the multiple regression model and the GRNN model. Its prediction error was 0.98–9.71%. Compared with the other two models, the prediction error of the SVM model declined by 0.50–11.96% and 3.76–13.44%. The SVM neural network was recommended as the dynamic modulus prediction model of the high-modulus asphalt mixture.

Development of a small-size laser triangulation displacement sensor and temperature drift compensation method

In practical applications, some special working scenarios need to take into account both narrow space and extreme temperature, which puts more strict requirements on the size and temperature adaptability of the laser triangulation displacement sensor (LTDS). In this paper, a small-size LTDS was developed and the measurement error caused by temperature drift of the sensor was corrected. Firstly, based on direct projection laser triangulation imaging with a reflector unit, a mathematical model of the compact geometry optical structure was established; then, an optimization process of the optical parameters was formulated, and the sensor was assembled. Secondly, a temperature drift error database was built by an extreme temperature experiment, and a general regression neural network model was constructed for error compensation. In addition, root mean square error and execution time were used to evaluate and compare different regression methods. Finally, the experimental results showed that the repeatability accuracy of the proposed sensor was ±2.3 µm, and the temperature linearity was 0.001% F.S. °C−1.

Estimation of exchangeable sodium percentage from sodium adsorption ratio of salt-affected soils using traditional and dilution extracts, saturation percentage, electrical conductivity, and generalized regression neural networks

Soil sodicity is best evaluated by the exchangeable sodium percentage (ESP); however, the determination of this index is laborious and time consuming. Alternatively, the sodium adsorption ratio (SAR) is a simpler index that is commonly used to estimate soil sodicity. The objective of this research is to estimate ESP using four approaches: (1) SAR of saturated paste (SARe), and SAR of 1:5 extracts (SAR1:5), (2) a conversion factor (CF) as a function of saturation percentage (θSP), (3) electrical conductivity of 1:5 extracts (EC1:5), and (4) Generalized Regression Neural Networks (GRNN). Approximately 120 surface soil samples were collected from the Jordan Valley region and ESP, SARe, SAR1:5, (θSP), soil texture, and soil hydraulic conductivity (HC) were determined. The GRNN model (i.e., Approach 4) gave the most accurate estimates for the ESP and was able to handle the heteroscedasticity of the data. Meanwhile the traditional dilution extracts (1) showed that soil ESP was highly related to SARe and to SAR1:5; the CF- θSP approach (2) gave better estimates for prediction of ESP. Moreover, EC1:5 (3) gave reasonably accurate estimation of ESP and could be used as a screening test for assessment of sodicity problems. For the case study site investigations, a reduction of 20% in soil HC was observed when SARe increased from 0 to 3.5 or ESP increased from 0 to 6, indicating that this reduction occurred at ECe < 3 dS m−1 for all soils. While the θSP approach reduced the effect of heteroscedasticity of the data on the predictive model ability, the GRNN models can accurately predict the ESP based on easy-to-obtain soil features. Our models represent a rapid and accurate estimator of soil sodicity, and therefore offer a potentially valuable tool in managing soil landscapes that are vulnerable to degradation.

An efficient neural network model for aiding the coagulation process of water treatment plants

In a water treatment plant, the decision to carry out a jar test, for determining the required coagulant dosage, is made based on notable changes in treated water qualities such as treated water turbidity and color, which is essentially a reactive response to changes in water qualities. In addition, until a change that the operator deems as ‘significant’ occurs, the plant tends to use the same dosage determined previously using the jar test for an elongated period of time. In this study, artificial neural network (ANN) models were developed to proactively decide what coagulant dosages to use based on changes in raw water parameters. Use of ANNs also prevents the regular use of costly chemicals used for jar tests and enables responding to sudden changes in water qualities. The general regression neural network (GRNN) and extreme learning machine neural networks require minimal computational effort for model development as they involve minimal model parameters and their training algorithms are not iterative. The current study determines the more convenient and efficient model of the two for aiding the coagulation process. The GRNN and ELM-RBF models predicted test data with R values of 0.9737 and 0.9783, respectively. It was noted that the GRNN was prone to overfitting and the ELM-RBF model demonstrated higher generalization ability than the GRNN. Therefore, it was concluded that the ELM-RBF model was the more suitable model for the prediction of the coagulant dosage.

A C-vine copula framework to predict daily water temperature in the Yangtze River

The thermal regime of rivers plays a crucial role in chemical, biological and ecological processes. Effectively predicting water temperature is a key issue related to environment management. This study develops a probabilistic model based on C-vine copulas for water temperature prediction. The proposed framework is applied to forecast daily water temperature in the Yangtze River, considering long-term effects of preceding air temperature and daily discharge. The prediction performance of this framework is compared with the logistic regression model (LogR) and generalized regression neural network (GRNN). The results of this study indicate that the proposed C-vine copula framework and GRNN model provide better forecasting of stream temperature with weak human-related disturbances than LogR model. The outperformance of C-vine framework is reflected by its ability to accurately capture variations in the water temperature greatly affected by the Three Gorges Reservoir (TGR). This steady and reliable framework is further applied for the conservation of Chinese Sturgeon to estimate the range of suggested discharge, given the daily air temperatures, to adjust the water temperature within 18–20 °C at Yichang station during the spawning season. This application is verified to be more effective, providing indications for reservoir management to lower water temperatures by regulating river flow to ensure the occurrence of spawning activities. The results of this study may provide a scientific reference for the ecological operation of reservoirs in regulated rivers.

A support vector regression model to predict nitrate-nitrogen isotopic composition using hydro-chemical variables

Nitrate is a prominent pollutant in surface and groundwater bodies worldwide. Isotopes in nitrate provide a powerful approach for tracing nitrate sources and transformations in waters. Given that analytical techniques for determining isotopic compositions are generally time-consuming, laborious and expensive, alternative methods are warranted to supplement and enhance existing approaches. Hence, we developed a support vector regression (SVR) model and explored its feasibility to predict nitrogen isotopic composition of nitrate (δ15N–NO3−) in a rural-urban river system in Southeastern China. A total of 16 easily obtained hydro-chemical variables were measured in the wet season (September 2019) and dry season (January 2020) and used to develop the SVR prediction model. The grading method utilized ~75% (35) of the samples for model building while the remaining 11 samples assessed model performance. Principal component analysis (PCA) extracted 7 principal components for SVR model inputs as PCA reduces superfluous variables. We optimized tuning parameters in the SVR model using a grid search technique coupled with V-fold cross-validation. The optimized SVR model provided accurate δ15N–NO3− predictions with a determination coefficient (R2) of 0.88, Nash-Sutcliffe (NS) of 0.87, and mean square error (MSE) of 0.53‰ in the testing step, and performed much better than the corresponding multivariate linear regression model (R2 = 0.60, NS = 0.58 and MSE = 1.76‰) and general regression neural network model (R2 = 0.66, NS = 0.65 and MSE = 1.45‰). Overall, the SVR model provides a potential indirect method to predict environmental isotope values for water quality management that will complement and enhance the interpretation of direct measurements of δ15N–NO3−.

Generalized Regression Neural Network (GRNN) for the Prediction of CRDI Engine Responses Fuelled with Pongamia Biodiesel

The application of General Regression Neural Network (GRNN) for the prediction of performance and emission responses of Common Rail Direct Injection (CRDI) engine using B5, B10 and B20 blend of pongamia biodiesel is presented in this paper. Data required for the prediction is obtained through experimentation on CRDI engine by varying parameters like injection pressure, injection timing and fuel preheating temperature. The experiments were conducted based on L9 Taguchi Orthogonal Array (OA). The experimental values for performance parameters like brake thermal efficiency, specific fuel consumption and emission parameters like CO, Nox and HC were recorded and used for GRNN. GRNN model is trained with 70% of samples and is validated with testing dataset of 30% by selecting optimum spread parameter (σ). The proposed model was found to be reliable and provides a cost effective way for determining performance parameters of engine. The results presented in this study substantially promote the use of GRNN model for the prediction of parameters in CRDI engine.

Application of the fruit fly optimization algorithm to an optimized neural network model in radar target recognition

With the development of computer technology, there are more and more algorithms and models for data processing and analysis, which brings a new direction to radar target recognition. This study mainly analyzed the recognition of high resolution range profile (HRRP) in radar target recognition and applied the generalized regression neural network (GRNN) model for HRRP recognition. In order to improve the performance of HRRP, the fruit fly optimization algorithm (FOA) algorithm was improved to optimize the parameters of the GRNN model. Simulation experiments were carried out on three types of aircraft. The improved FOA-GRNN (IFOA-GRNN) model was compared with the radial basis function (RBF) and GRNN models. The results showed that the IFOA-GRNN model had a better convergence accuracy, the highest average recognition rate (96.4 %), the shortest average calculation time (275 s), and a good recognition rate under noise interference. The experimental results show that the IFOA-GRNN model has a good performance in radar target recognition and can be further promoted and applied in practice.

Prediction of geodetic point velocity using MLPNN, GRNN, and RBFNN models: a comparative study

The prediction of an accurate geodetic point velocity has great importance in geosciences. The purpose of this work is to explore the predictive capacity of three artificial neural network (ANN) models in predicting geodetic point velocities. First, the multi-layer perceptron neural network (MLPNN) model was developed with two hidden layers. The generalized regression neural network (GRNN) model was then applied for the first time. Afterwards, the radial basis function neural network (RBFNN) model was trained and tested with the same data. Latitude ( $$\varphi$$ ) and longitude (λ) were utilized as inputs and the geodetic point velocities ( $${V}_{X}$$ , $${V}_{Y}$$ , $${V}_{Z}$$ ) as outputs to the MLPNN, GRNN, and RBFNN models. The performances of all ANN models were evaluated using root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination ( $${\text{R}}^{2}$$ ). The first investigation demonstrated that it was possible to predict the geodetic point velocities by using all the components as output parameters simultaneously. The other result is that all ANN models were able to predict the geodetic point velocity with satisfactory accuracy; however, the GRNN model provided better accuracy than the MLPNN and RBFNN models. For example, the RMSE and MAE values were 1.77–1.88 mm and 1.44–1.51 mm, respectively, for the GRNN model.

A novel solution for simulating air overpressure resulting from blasting using an efficient cascaded forward neural network

Air overpressure (AOp) is a hazardous effect induced by the blasting method in surface mines. Therefore, it needs to be predicted to reduce the potential risk of damage. The aim of this study is to offer an efficient method to predict AOp using a cascaded forward neural network (CFNN) trained by Levenberg–Marquardt (LM) algorithm, called the CFNN-LM model. Additionally, a generalized regression neural network (GRNN) and extreme learning machine (ELM) were employed to demonstrate the accuracy level of the proposed CFNN-LM model. To conduct the CFNN-LM, GRNN, and ELM models, an extensive database, related to four quarry sites in Malaysia, was used including 62 sets of dependent and independent parameters. Next, the performances of the aforementioned models were checked and discussed through statistical criteria and efficient graphical tools. Finally, the results showed the superiority of CFNN-LM (R2 = 0.9263 and RMSE = 3.0444) over GRNN (R2 = 0.7787 and RMSE = 5.1211) and ELM (R2 = 0.6984 and RMSE = 6.2537) models in terms of prediction accuracy. Furthermore, three different regression analysis metrics were used to perform the sensitivity analysis, and according to the obtained results, the maximum charge per delay ( $$\beta$$ = 0.475, SE = 0.115, t-test = 4.125) was considered as the most influential feature in modeling the AOp.