Adaptive Neuro-fuzzy Inference System Model Research Articles

Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) model for Forecasting Groundwater Level in the Pravara River Basin, India

Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) model for Forecasting Groundwater Level in the Pravara River Basin, India

Decolourization of bromocresol green dye solution by acid functionalized rice husk: Artificial intelligence modeling, GA optimization, and adsorption studies

Novel application and comparison of intelligent models such as adaptive neuro-fuzzy inference systems (ANFIS), artificial neural network (ANN), and response surface methodology (RSM) in adsorptive removal of bromocresol green (BCG) dye via acid functionalized rice husk (AFRH) was the crux of this work. Tetraoxophosphate V acid was used in preparing the AFRH. The effects of process parameters such as initial concentration, solution pH, adsorbent dosage, temperature, and contact time were investigated. The synthesized AFRH was characterized via Scanning Electron Microscope (SEM) and Fourier Transform Infrared (FTIR) spectrophotometer. Genetic algorithm (GA) optimization tool was used in optimizing the process parameters. The result showed that temperature was the most influential parameter in the removal of BCG dye. The predictive modeling of the RSM, ANN and ANFIS models demonstrated good correlation with R2 of 0.9325, 0.9797 and 0.9987 respectively. Low values of calculated error functions of RMSE (ANFIS=0.0025; RSM=0.01899 and ANN=0.01028) and HYBRID (ANFIS=0.0006; RSM=0.03216 and ANN=0.00943) indicated good harmony between experimental values and models’ predictions. Validated GA optimization yielded maximum adsorption capacities of 139.23, 136.29, and 137.14 mg/g for ANFIS-GA, RSM-GA, and ANN-GA respectively. The result showed that the order of the models’ effectiveness for BCG removal is: ANFIS > ANN > RSM. Isotherm study revealed that Freundlich isotherm with R2 of 0.999 best described the equilibrium modeling while the kinetic analysis indicated that pseudo second order (R2 = 0.998) and Elovich (R2 = 0.995) models best accounted for the kinetics of the experimental data. Thermodynamics study denoted that the adsorption process was endothermic and spontaneous. A point of zero charge of 4.65 was obtained. The results of this present work highlighted the potential of the synthesized AFRH in effectively treating BCG dye contaminated wastewater using the optimized conditions.

Adaptive neuro-fuzzy inference system based data interpolation for particle image velocimetry in fluid flow applications

This paper presents an adaptive neuro-fuzzy inference system (ANFIS) approach for recovering the missing velocity vectors that commonly occur during fluid flow measurements in fluid mechanics. The capability of ANFIS in refilling the missing data is demonstrated with two case studies. First, the ANFIS is applied to estimate the velocity field data within the masked region of an available particle image velocimetry (PIV) experiment. Then, the ANFIS is trained using the data from outside the masked region and learns the relationship between the velocity vectors. Thus, it predicts the fluid patterns within the gappy area based on its understanding. ANFIS is also applied in another study to capture the small feature in the fluid flow. The vortices within a small area behind an obstacle are removed, and the rest of the data is introduced into the ANFIS model. The efficacy of the proposed ANFIS algorithm in predicting the missing velocity vectors is compared to both artificial neural network (ANN) and 2D cubic interpolation algorithms. It is found that intelligent algorithms (ANFIS and ANN) can predict the presence of vortices in the fluid flow even when there is no information about a circulating flow in the training dataset. The performance of ANFIS (R2= 0.91) in accurately predicting the velocity vectors is superior to the conventional ANN (R2= 0.86).

Optimisation and performance evaluation of response surface methodology (RSM), artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) in the prediction of biogas production from palm oil mill effluent (POME)

In recent years, machine learning (ML) techniques have been developed to predict the performance of anaerobic digestion (AD) processes including methane potential and reactor stability. However, their practical applications to industrial-scale palm oil mill effluent (POME) treatment plant are limited. In this study, ML algorithms such as response surface methodology (RSM), adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) are employed to model the biogas production and methane yield from the AD of POME in a local industry-scale anaerobic covered lagoon. Results demonstrated that these models were well aligned with two years of operational data with high coefficient of determination (R2) of up to 0.98. ANFIS yields the highest prediction accuracy, with R2 of 0.9791 along with the lowest mean absolute error (MAE) of 0.0730 and root mean squared error (RMSE) of 0.1438. Subsequently, ANFIS is used in the multi-objective optimisation to maximise the biogas production and methane yield. Optimal conditions for the temperature of the anaerobic digester, pH and recirculation ratio are 38.9 °C, 7.03 and 1.89 respectively which could enhance the biogas production and methane yield by 19.4% and 12.2% respectively. Confirmatory experiments were carried out in the biogas plant under this set of optimised variables for a period of two months. The predicted biogas production and methane yield are highly correlated to the actual data with small percentage difference of 1.25% and 5.09% respectively, indicating that ANFIS model was accurate and reliable. Sensitivity analysis shows that pH has the most dominant effect on the methane yield.

An adaptive neuro fuzzy inference system model for studying free in plane and out of plane vibration behavior of curved beams

The current study examines the free vibration behavior of curved beams in detail. Basic, lightweight curved beams are used in many different engineering projects. Therefore, it is very important to study their dynamic behavior extensively. Hence, in this study, numerical analysis on free in-plane and out-of-plane vibration of curved beams is carried out using finite element modeling software ANSYS, and experimental analysis was conducted using Fast Fourier Transform (FFT) spectrum analyzer for validation of numerical results. Adaptive neuro-fuzzy inference system (ANFIS) models are developed using 384 numbers of datasets that are procured from numerical investigations. The input parameters considered are cross-sectional area, radius of curvature, curvature angle, support conditions, and mode of vibration. An empirical equation is derived for estimating natural frequencies. Different statistical indices, such as the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE), is used to evaluate the performance of the input parameters. Sensitivity analysis is used to spot the input parameters that have the greatest influence on the natural frequency of curved beams and rank them in importance.

Investigation of factors affecting rural drinking water consumption using intelligent hybrid models

Identifying the factors affecting drinking water consumption is essential to the rational management of water resources and effective environment protection. In this study, the effects of the factors on rural drinking water demand were studied using the adaptive neuro-fuzzy inference system (ANFIS) and hybrid models, such as the ANFIS–genetic algorithm (GA), ANFIS–particle swarm optimization (PSO), and support vector machine (SVM)–simulated annealing (SA). The rural areas of Hamadan Province in Iran were selected for the case study. Five drinking water consumption factors were selected for the assessment according to the literature, data availability, and the characteristics of the study area (such as precipitation, relative humidity, temperature, the number of subscribers, and water price). The results showed that the standard errors of ANFIS, ANFIS–GA, ANFIS–PSO, and SVM–SA were 0.669, 0.619, 0.705, and 0.578, respectively. Therefore, the hybrid model SVM–SA outperformed other models. The sensitivity analysis showed that of the parameters affecting drinking water consumption, the number of subscribers significantly affected the water consumption rate, while the average temperature was the least significant factor. Water price was a factor that could be easily controlled, but it was always one of the least effective parameters due to the low water fee.

Estudio comparativo de la predicción de energía eléctrica de un sistema fotovoltaico utilizando los sistemas inteligentes ANFIS y ANFIS-GA

Electrical energy generation with hydrocarbons accounts for about 38% of global CO2 emissions. Solar photovoltaic technology is a reliable alternative to reduce these emissions. To predict the electrical energy generation behavior in a photovoltaic system, we developed an adaptive neuro-fuzzy inference system (ANFIS) model which integrates an optimization through a genetic algorithm (GA). The evolutionary ANFIS-GA uses a geographical area's solar radiation and ambient temperature. This model uses the capacity for classification and identification of data patterns of neural networks, and through fuzzy modeling, it calculates the optimal membership functions and fuzzy rules. The ANFIS-GA model is developed using MATLAB® software and is trained with the acquired data weather station and the electrical power output of the photovoltaic system located in Hermosillo, Sonora, México. The above was compared under the same parameters with an ANFIS model based on a hybrid algorithm. Reach values of RSME of 259.41, MAE of 132.7, MAPE of 4.56 for the ANFIS-GA model; RSME of 295.26, MAE of 149.58, and MAPE of 6.98 for the ANFIS model, respectively. The results indicate that the ANFIS-GA model emulates the power output with better precision, thus providing a valuable planning tool to predict photovoltaic system behavior.

Integrated sequential fuzzy logic search models for simulating wastewater treatment plants missing influent parameters

AbstractAiming at achieving optimum operations of wastewater treatment plant (WWTP) processes, it is essential to develop accurate predictive models for expected influent pollutant loads. To overcome limited timespan data and model complexity, this study is devoted to propose an integration of inputs' sequential search with the adaptive neuro‐fuzzy inference system (ANFIS) for reducing the modelling complexity. The input data included nine influent parameters measured bi‐weekly for 12 years at a WWTP, South Africa (SA). The sequential search process was used for input optimization to select the most representative inputs in modelling four parameters. The obtained results indicated a strong correlation with R2 and NSE above 0.85 for the four targeted influent parameters. After validating the developed models using different criteria, the missing records were predicted throughout the study period. The integration of sequential search input optimization and ANFIS modelling was able to provide a high performance in modelling WWTP datasets.

Computer State Evaluation Using Adaptive Neuro-Fuzzy Inference Systems

Several crucial system design and deployment decisions, including workload management, sizing, capacity planning, and dynamic rule generation in dynamic systems such as computers, depend on predictive analysis of resource consumption. An analysis of the computer components' utilizations and their workloads is the best way to assess the performance of the computer's state. Especially, analyzing the particular or whole influence of components on another component gives more reliable information about the state of computer systems. There are many evaluation techniques proposed by researchers. The bulk of them have complicated metrics and parameters such as utilization, time, throughput, latency, delay, speed, frequency, and the percentage which are difficult to understand and use in the assessing process. According to these, we proposed a simplified evaluation method using components' utilization in percentage scale and its linguistic values. The use of the adaptive neuro-fuzzy inference system (ANFIS) model and fuzzy set theory offers fantastic prospects to realize use impact analyses. The purpose of the study is to examine the usage impact of memory, cache, storage, and bus on CPU performance using the Sugeno type and Mamdani type ANFIS models to determine the state of the computer system. The suggested method is founded on keeping an eye on how computer parts behave. The developed method can be applied for all kinds of computing system, such as personal computers, mainframes, and supercomputers by considering that the inference engine of the proposed ANFIS model requires only its own behavior data of computers' components and the number of inputs can be enriched according to the type of computer, for instance, in cloud computers' case the added number of clients and network quality can be used as the input parameters. The models present linguistic and quantity results which are convenient to understand performance issues regarding specific bottlenecks and determining the relationship of components.

Density and Refractive Index of Binary Ionic Liquid Mixtures with Common Cations/Anions, along with ANFIS Modelling

Ionic liquids have many interesting properties as they share the properties of molten salts as well as organic liquids, such as low volatility, thermal stability, electrical conductivity, non-flammability, and much more. Ionic liquids are known to be good solvents for many polar and nonpolar solutes. Combined with their special properties, ionic liquids are good replacements for the conventional toxic and volatile organic solvents. Each ionic liquid has different properties than others. In order to alter, tune, and enhance the properties of ionic liquids, sometimes, it is necessary to mix different ionic liquids to achieve the desired properties. However, using mixtures of ionic liquids in chemical processes requires reliable estimations of the mixtures’ physical properties such as refractive index and density. The ionic liquids used in this work are 1-butyl-3-methylimidazolium thiocyanate ([BMIM][SCN]), 1-butyl-3-methylimidazolium tetrafluoroborate ([BMIM][BF4]), 1-hexyl-3-methylimidazolium tetrafluoroborate ([HMIM][BF4]), and 1-hexyl-3-methylimidazolium hexafluorophosphate ([HMIM][PF6]). These ionic liquids were supplied by Io-li-tec and used as received. However, new measurements for the density and refractive index were taken for the pure ionic liquids to be used as reference. In the present work, the densities and refractive indices of four different binary mixtures of ionic liquids with common cations and/or anions have been measured at various compositions and room conditions. The accuracy of different empirical mixing rules for calculation of the mixtures refractive indices was also studied. It was found that the overall absolute average percentage deviation from the ideal solution in the calculation of the molar volume of the examined binary mixtures was 0.78%. Furthermore, all of the examined mixing rules for the calculation of the refractive indices of the mixtures were found to be accurate. However, the most accurate empirical formula was found to be Heller’s relation, with an average percentage error of 0.24%. Furthermore, an artificial intelligence model, an adaptive neuro-fuzzy inference system (ANFIS), was developed to predict the density and refractive index of the different mixtures studied in this work as well as the published literature data. The predictions of the developed model were analyzed by various methods including both statistical and graphical approaches. The obtained results show that the developed model accurately predicts the density and refractive index with overall R2, RMSE, and AARD% values of 0.968, 7.274, 0.368% and 0.948, 7.32 × 10−3 and 0.319%, respectively, for the external validation dataset. Finally, a variance-based global sensitivity analysis was formed using extended the Fourier amplitude sensitivity test (EFAST). Our modelling showed that the ANFIS model outperforms the best available empirical models in the literature for predicting the refractive index of the different mixtures of ionic liquids.

Spatial interpolation of surface point velocity using an adaptive neuro-fuzzy inference system model: a comparative study

Spatial interpolation of surface point velocity using an adaptive neuro-fuzzy inference system model: a comparative study

Predictive comparison and assessment of ANFIS and ANN, as efficient tools in modeling degradation of total petroleum hydrocarbon (TPH)

Composting is an effective organic waste management practice with a sustainable environmental impact on soil. In most cases, composting materials are agricultural residues constituting a huge environmental challenge. This study investigates the composting biostimulation of total petroleum hydrocarbon (TPH) contaminated soil using organic compost prepared from palm oil mill effluent (CPOME). The performance of CPOME in TPH degradation was evaluated using the first-order kinetic model and CO₂ evolution. The artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) modelling approaches were further employed to optimize the experimental response. The experimental designs for ANFIS and ANN modelling were done using the central composite design (CCD). Statistical parameters such as RMSE, MSE, and MAE were used to evaluate model performance and comparisons. The first-order kinetic model and CO₂ released showed that TPH degradation favours contaminated soil with 40 g/L initial TPH concentration. The first-order kinetic model observed a decrease in the constant degradation rate with increasing TPH concentration. The CO₂ evolution, which measures microbial respiration/activity, also showed a decline in released CO₂ with increasing TPH concentration. Lower values of RMSE, MSE, and MAE were obtained for the ANFIS model compared with the ANN. The R² values between the experimental and model-predicted responses showed that the ANFIS (0.9349) model predictions fitted adequately compared to the ANN (0.8862). Finally, comparison and model performances showed that the ANFIS model prediction capability was considerably better than the ANN. • The compost from palm oil mill effluent proved effective in TPH degradation • ANFIS predicted TPH degradation was better than the ANN predicted • Notable organic materials in the compost includes polysaccharides, nitrogen and lignin

Prediction of energy content of biomass based on hybrid machine learning ensemble algorithm

• Machine learning models were developed for biomass higher heating value prediction • Proximate analysis variables formed seven input combinations to the developed models • Improved prediction accuracy was achieved by integrating ensemble algorithms • Single biomass proximate analysis component cannot guarantee accurate prediction • Adaptive neuro-fuzzy inference system is superb in prediction model development In this study, three novel ensemble algorithms, namely, simple averaging, weighted averaging, and meta-learning ensemble algorithms were employed to predict the higher heating value of biomass. These strategies were implemented in two main stages. In the first stage, four heterogeneous standalone models: an artificial neural network, a multivariate regression, a support vector regression, and an adaptive neuro-fuzzy inference system (ANFIS) were developed to predict the higher heating value. In the second stage, the outputs of the standalone models were aggregated for ensemble learning implementation. Seven input combinations of the biomass proximate analysis components formed the proposed models’ inputs. In the pre-ensemble phase, the ANFIS model having ash and volatile matter as an input combination presented the most accurate performance based on the Willmott's index of agreement of 0.9741 and the mean square error of 0.0032. The ensemble algorithms demonstrated improvement in the overall prediction performances with the meta-learning ensemble ranked superior for an average error decrease of up to 15% when ash, volatile matter, and fixed carbon served as the model's input combination. The findings of this work provide a robust foundation for the use of ensemble algorithms in the prediction of the biomass higher heating value.

Adaptive neuro-fuzzy inference system (ANFIS) and multiple linear regression (MLR) modelling of Cu, Cd, and Pb adsorption onto tropical soils

Soils interact in many ways with metal ions thereby modifying their mobility, phase distribution, plant availability, speciation, and so on. The most prominent of such interactions is sorption. In this study, we investigated the sorption of Pb, Cd, and Cu in five natural soils of Nigerian origin. A relatively sparsely used method of modelling soil-metal ion adsorption, i.e. adaptive neuro-fuzzy inference system (ANFIS), was applied comparatively with multiple linear regression (MLR) models. The isotherms were well described by Freundlich and Langmuir equations (R2 ≥ 0.95) and the kinetics by nonlinear two-stage kinetic model, TSKM (R2 ≥ 0.81). Based on the values delivered by the Langmuir equation, the maximum adsorption capacities (Qm*) were found to be in the ranges 10,000–20,000, 12,500–50,000, and 4929–35,037 µmol kg−1 for Cd, Cu, and Pb, respectively. The study revealed significant correlations between Qm* and routinely determined soil parameters such as soil organic carbon (Corg), cation exchange capacity (CEC), amorphous Fe and Mn oxides, and percentage clay content. These soil parameters, combined with operational variables (i.e. solution/soil pH, initial metal concentration (Co), and temperature), were used as input vectors in ANFIS and MLR models to predict the adsorption capacities (Qe) of the soil-metal ion systems. A total of 255 different ANFIS and 255 different MLR architectures/models were developed and compared based on three performance metrics: MAE (mean absolute error), RMSE (root mean square errors), and R2 (coefficient of determination). The best ANFIS returned MAEtest 0.134, RMSEtest 0.164, and R2test 0.76, while the best MLR returned MAEtest 0.158, RMSEtest 0.199, and R2test 0.66, indicating the predictive advantage of ANFIS over MLR. Thus, ANFIS can fairly accurately predict the adsorption capacity and/or distribution coefficient of a soil-metal ion system a priori. Nevertheless, more investigation is required to further confirm the robustness/generalisation of the proposed ANFIS.

Improving prediction performance of significant wave height via hybrid SVD-Fuzzy model

Significant wave height forecasting is an important aspect of many ocean related engineering and scientific phenomena. However, due to the complicated and chaotic nature of ocean waves, in general, data in hand has to be decomposed into its deterministic and stochastic features before feeding into the predictive model. The present study introduces a refined singular value decomposition (SVD) based algorithm for decomposing raw data into its hierarchally energetic pertinent features. SVD-fuzzy model is developed via hybridizing Adaptive Neuro-Fuzzy Inference Systems (ANFIS) model with the proposed algorithm. SVD-fuzzy model is compared with stand-alone fuzzy and combination of a widely used wavelet transformation and fuzzy logic (wavelet-fuzzy) models in predicting SWH in five distinctive Pacific Ocean locations for future lead times 1 h, 2 h, 3 h, 4 h, 5 h, 6 h, 12 h, 18 h and 24 h from two previous hourly SWH data. According to mean square error (MSE), the Nash-Sutcliffe coefficient of efficiency (CE), coefficient of determination (R2), and mean absolute error (MAE) model evaluation metrics, it is found that SVD-fuzzy model outperformed the stand-alone fuzzy model for all lead times and data (Maximum CE of SVD-Fuzzy model is 0.991). Further, SVD-fuzzy model results compare well with those of Wavelet-Fuzzy model. The outcomes of this study indicate that the integrated SVD-fuzzy modeling approach, with no underlying assumptions a priori, is a promising principled tool for its possible future applications not only for coastal and ocean problems but in engineering and scientific disciplines where future state space prediction of a complex and stochastic dynamical system is significant.

Estimation of hydraulic conductivity of porous media using data-driven techniques

Abstract Knowledge of hydraulic conductivity (K) is inevitable for sub-surface flow and aquifer studies. Hydrologists and groundwater researchers are employing data-driven techniques to indirectly evaluate K using porous media characteristics as an alternative to direct measurement. The study examines the ability of the Adaptive Neuro-Fuzzy Inference System (ANFIS) to predict the K of porous media using two membership functions (MFs), i.e., triangular and Gaussian, and support vector machine (SVM) via four kernel functions, i.e., linear, quadratic, cubic, and Gaussian. The techniques used easily measurable parameters namely effective and mean grain size, uniformity coefficient, and porosity as input variables. A 70 and 30% dataset is used for the training and testing of models, respectively. The correlation coefficient (R) and root mean square error (RMSE) were used to evaluate the models. The Gaussian MF-based ANFIS model outperformed the triangular model having R and RMSE values of 0.9661 & 0.0010 and 0.9532 & 0.0015, respectively, whereas the quadratic kernel-based SVM model with R and RMSE values of 0.9520 and 0.0015 performs better than the other SVM models. Based on the evaluation of ANFIS and SVM models, the study establishes the efficacy of the Gaussian MF-based ANFIS model in estimating the K of porous media.

Power System Voltage Stability Margin Estimation Using Adaptive Neuro-Fuzzy Inference System Enhanced with Particle Swarm Optimization

In the current era of e-mobility and for the planning of sustainable grid infrastructures, developing new efficient tools for real-time grid performance monitoring is essential. Thus, this paper presents the prediction of the voltage stability margin (VSM) of power systems by the critical boundary index (CBI) approach using the machine learning technique. Prediction models are based on an adaptive neuro-fuzzy inference system (ANFIS) and its enhanced model with particle swarm optimization (PSO). Standalone ANFIS and PSO-ANFIS models are implemented using the fuzzy ‘c-means’ clustering method (FCM) to predict the expected values of CBI as a veritable tool for measuring the VSM of power systems under different loading conditions. Six vital power system parameters, including the transmission line and bus parameters, the power injection, and the system voltage derived from load flow analysis, are used as the ANFIS model implementation input. The performances of the two ANFIS models on the standard IEEE 30-bus and the Nigerian 28-bus systems are evaluated using error and regression analysis metrics. The performance metrics are the root mean square error (RMSE), mean absolute percentage error (MAPE), and Pearson correlation coefficient (R) analyses. For the IEEE 30-bus system, RMSE is estimated to be 0.5833 for standalone ANFIS and 0.1795 for PSO-ANFIS; MAPE is estimated to be 13.6002% for ANFIS and 5.5876% for PSO-ANFIS; and R is estimated to be 0.9518 and 0.9829 for ANFIS and PSO-ANFIS, respectively. For the NIGERIAN 28-bus system, the RMSE values for ANFIS and PSO-ANFIS are 5.5024 and 2.3247, respectively; MAPE is 19.9504% and 8.1705% for both ANFIS and PSO-ANFIS variants, respectively, and the R is estimated to be 0.9277 for ANFIS and 0.9519 for ANFIS-PSO, respectively. Thus, the PSO-ANFIS model shows a superior performance for both test cases, as indicated by the percentage reduction in prediction error, although at the cost of a higher simulation time.

Estimation of groundwater quality using an integration of water quality index, artificial intelligence methods and GIS: Case study, Central Mediterranean Region of Turkey

Groundwater is one of the most important natural resources in the world and is widely used for irrigation purposes. Groundwater quality is affected by various natural heterogeneities and anthropogenic activities. Consequently, monitoring groundwater quality and assessing its suitability are crucial for sustainable agricultural irrigation. In this study, the suitability of groundwater for irrigation was determined by using sodium adsorption ratio (SAR), residual sodium carbonate (RSC), Kelly index (KI), percentage of sodium (Na%), magnesium ratio (MR), potential salinity (PS) and permeability index (PI). The groundwater samples were collected and analyzed from 37 different sampling stations for this purpose. Along with suitability analysis, artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) models were used to predict irrigation water quality parameters. The models were evaluated by comparing the measured values and the predicted values using the statistical criteria [coefficient of determination (R2), mean absolute error (MAE), root mean square error (RMSE) and Nash–Sutcliffe efficiency (NS)]. In the estimation of all irrigation water quality parameters, the ANN model has performed much higher compared with the ANFIS model. Spatial distribution maps were generated for measured and ANN model-estimated irrigation water quality indices using the IDW interpolation method. Spatial distributions of groundwater quality indices revealed that MR was higher than the allowable limits in most of the study areas and the other quality criteria were within the permissible limits. It has been determined that the interpolation maps obtained as a result of artificial intelligence methods have appropriate sensitivity when compared with the observed maps. Based on the present findings, ANN models could be used as an efficient tool for estimating groundwater quality indices in unsampled sections of the study area and the other regions with similar conditions.

Prediction of lake water-level fluctuations using adaptive neuro-fuzzy inference system hybridized with metaheuristic optimization algorithms

Lakes help increase the sustainability of the natural environment and decrease food chain risk, agriculture, ecosystem services, and leisure recreational activities locally and globally. Reliable simulation of monthly lake water levels is still an ongoing demand for multiple environmental and hydro-informatics engineering applications. The current research aims to utilize newly developed hybrid data-intelligence models based on the ensemble adaptive neuro-fuzzy inference system (ANFIS) coupled with metaheuristics algorithms for lake water-level simulation by considering the effect of seasonality on Titicaca Lake water-level fluctuations. The classical ANFIS model was trained using three metaheuristics nature-inspired optimization algorithms, including the genetic algorithm (ANFIS-GA), particle swarm optimizer (ANFIS-PSO), and whale optimization algorithm (ANFIS-WOA). For determining the best set of the input variables, an evolutionary approach based on several lag months has been utilized prior to the lake water-level simulation process using the hybrid models. The proposed hybrid models were investigated for accurately simulating the monthly water levels at Titicaca Lake. The ANFIS-WOA model exhibited the best prediction performance for lake water-level pattern measurement in this study. For the best scenario (the inputs were {X}_{t-1},; {X}_{t-2}, ;{X}_{t-3}, ;{X}_{t-4}, ; {X}_{t-12}) the ANFIS-WOA model attained root mean square error (RMSE approx 0.08 m), mean absolute error (MAE approx 0.06 m), and coefficient of determination (R2approx 0.96). Also, the results showed that long-term seasonal memory for this lake is suitable input for lake water-level models so that the long-term dynamic memory of 1-year time series for lake water-level data is the best input for estimating the water level of Titicaca Lake.

An optimized neuro-fuzzy system using advance nature-inspired Aquila and Salp swarm algorithms for smart predictive residual and solubility carbon trapping efficiency in underground storage formations

Carbon dioxide (CO2) emission is an emergency issue in terms of environmental pollution. Estimation of carbon capture, utilization, and storage (CCUS) is a necessary task that received wide attention. Due to this fact, numerous studies proposed underground carbon storage to reduce CO2 emissions in the atmosphere. However, there are some drawbacks about estimation accuracy trapping efficiency in deep saline aquifers. Also, the time computation of conventional reservoir simulators requires weeks or months to complete the simulation tasks. Hence, a new approach about accuracy and a fast predictive model needs to propose for promoting the application of carbon capture and storage projects. Therefore, this paper proposes an optimized Adaptive Neuro fuzzy inference system (ANFIS) to predict two indices of the CO2 Trapping in deep saline aquifers, namely, solubility trapping index (STI) residual trapping index (RTI), using 6810 simulation samples, 8 input features of subsurface information from 33 fields of ten previous studies. We utilize the recently developed optimization algorithms, called Aquila optimizer (AO) and Salp Swarm Algorithm (SSA), to train the ANFIS model and to optimize its parameters to boost the prediction performance of the traditional ANFIS. The search mechanism of the SSA is used instead of the original one of the AO algorithm, which enhances the exploration process of the traditional AO. The proposed AOSSA-ANFIS is outperformed to seven optimized ANFIS models.Futhermore, AOSSA-ANFIS schemes achieves overall Mean Relative Absolute Error (MRAE) of 0.69495 and 0.36304, Mean Absolute Error (MAE) of 0.09771 and 0.04594, Root Mean Square Error (RMSE) of 0.15001 and 0.06904, and Mean Square Error (MSE) of 0.02269 and 0.00484 for RTI and STI, respectively. Additionally, the developed AOSSA-ANFIS demonstrated the superiority to existing study that used SVR, ANN, Liner regression and MLP. Due to this latter, the findings of this study provide a better understanding of the role of optimized hybrid ANFIS for CCUS as well as other subsurface disciplines. Finally, this study consider as template is easy to adapt to the similar effort of fast computational modeling.