Geoacoustic inversion using adaptive neuro-fuzzy inference system

The geoacoustic parameters form significant input for underwater acoustic propagation studies and geoacoustic modeling. Conventional inversion techniques commonly used as indirect approach for extraction of geoacoustic parameters from acoustic or seismic data are computationally intensive and time-consuming. In the present study, we have tried to exploit the advantage of soft computing techniques like, reasoning ability of fuzzy logic and learning abilities of neural networks, in inversion studies. The network model based on the combined approach called adaptive neuro-fuzzy inference system (ANFIS), is found to be very promising in inversion of the acoustic data. The network model once built is capable of invert a few thousand data sets instantaneously, to a reasonably good accuracy. In the case of conventional approaches, repetition of the entire inversion process with each new data set is required. A limited number of sensor’s data are sufficient for simulation of the network model and provides an advantage to use short hydrophone array data. Inversion results of a few hundred test data sets, representing different geoacoustic environments, show the prediction error is much less than 0.01 g/cc, 10 m/s, 10 m and 0.1 against first layer’s density, compressional sound speed, thickness and attenuation respectively for a three-layer geoacoustic model. However, the error is relatively large for the second- and third-layer parameters, which need to be improved. The model is efficient, robust and inexpensive.     

Application of the adaptive neuro-fuzzy inference system for prediction of soil liquefaction

The determination of liquefaction potential of soils induced by earthquake is a major concern and an essential criterion in the design process of the civil engineering structures. A purely empirical interpretation of the filed case histories relating to liquefaction potential is often not well constrained due to the complication associated with this problem. In this study, an integrated fuzzy neural network model, called Adaptive Neuro-Fuzzy Inference System (ANFIS), is developed for the assessment of liquefaction potential. The model is trained with large databases of liquefaction case histories. Nine parameters such as earthquake magnitude, the water table, the total vertical stress, the effective vertical stress, the depth, the peak acceleration at the ground surface, the cyclic stress ratio, the mean grain size, and the measured cone penetration test tip resistance were used as input parameters. The results revealed that the ANFIS model is a fairly promising approach for the prediction of the soil liquefaction potential and capable of representing the complex relationship between seismic properties of soils and their liquefaction potential.     

Application of the adaptive neuro-fuzzy inference system for prediction of a rock engineering classification system

The rock engineering classification system is based on six parameters defined by Bieniawski [5], who employed parallel sets of linguistic and numerical criteria that were acknowledged to influence the behaviour of rock masses and the stability of rock structures. Consequently, experts frequently relate rock joints and discontinuities as well as ground water conditions in linguistic terms, with rough calculations. Recently, intelligence system approaches such as artificial neural network (ANN) and neuro-fuzzy methods have been used successfully for time series modelling. Using neuro-fuzzy approaches, which enable the information that is stored in trained networks to be expressed in the form of a fuzzy rule base, would help to overcome this issue. This paper presents the results of a study of the application of neuro-fuzzy methods to predict rock mass rating. We note that the proposed weights technique was applied in this process. We show that neuro-fuzzy methods give better predictions than conventional modelling approaches.     

Evaluating the support vector machine for suspended sediment load forecasting based on gamma test

Due to the various influencing factors on river suspended sediment transportation, determining an appropriate input combination for developing the suspended sediment load forecasting model is very important for water resources management. The influence of pre-processing of input variables by Gamma Test (GT) was investigated on performance of Support Vector Machine (SVM) with two kernels; Radial Basis Function (RBF) and polynomial in order to forecast daily suspended sediment amount in the period between 1983 and 2014 at Korkorsar basin, northern Iran. The best input combination was identified using GT and correlation coefficient analysis. Then, the SVM model was developed and the suspended sediment amount was forecasted with RBF and polynomial kernels. The obtained results in testing phase showed that GT-SVM (RBF kernel) model can estimate suspended sediment more accurately with the lowest RMSE (14.045 ton/day), highest correlation coefficient (0.88) and highest NSEC coefficient (0.88) than SVM (RBF kernel) model (RMSE?=?18.36ton/day, \( {R}^2=0.79, \) \( NSEC=0.73 \)) and had a better performance than the other models. The results indicated that in forecasting the first nine maximum values of suspended sediment load, GT-SVM (RBF) had a higher capability than the other models and could provide a more accurate estimation from the maximum rate of suspended sediment. The results of this study showed the capability of identifying the priority of the input parameters can change GT to a useful and technical test for input variables pre-processing to forecast the amount of suspended sediments.     

基于ANFIS的单桩竖向极限承载力预测模型

人工神经网络已应用在岩土工程的各个方面。针对常用的BP网络的不足之处,建立了基于自适应神经模糊推理系统（ANFIS）的单桩竖向极限承载力预测模型。利用文献中桩的载荷试验数据来训练ANFIS网络,确定了网络参数。研究结果表明,同常用的BP网络相比,ANFIS预测模型具有学习速度快,拟合能力较好,训练结果唯一等优点,该方法是一种有效地预测单桩极限承载力的方法。     

Comparison between neuro-fuzzy and fractal models for permeability prediction

We have used different techniques for permeability prediction using porosity core data from one well at the Maracaibo Lake, Venezuela. One of these techniques is statistical and uses neuro-fuzzy concepts. Another has been developed by Pape et al. (Geophysics 64(5):1447–1460, 1999), based on fractal theory and the Kozeny–Carman equations. We have also calculated permeability values using the empirical model obtained in 1949 by Tixier and a simple linear regression between the logarithms of permeability and porosity. We have used 100% of the permeability–porosity data to obtain the predictor equations in each case. The best fit, in terms of the root mean-square error, was obtained with the statistical approach. The results obtained from the fractal model, the Tixier equation or the linear approach do not improve the neuro-fuzzy results. We have also randomly taken 25% of the porosity data to obtain the predictor equations. The increase of the input data density for the neuro-fuzzy approach improves the results, as is expected for a statistical analysis. On the contrary, for the physical model based on the fractal theory, the decrease in the data density could allow reaching the ideal theoretical Kozeny–Carman model, on which are based the fractal equations, and hence, the permeability prediction using these expressions is improved.     

Earthquake magnitude prediction by adaptive neuro-fuzzy inference system (ANFIS) based on fuzzy C-means algorithm

This paper investigates the prediction of future earthquakes that would occur with magnitude 5.5 or greater using adaptive neuro-fuzzy inference system (ANFIS). For this purpose, the earthquake data between 1950 and 2013 that had been recorded in the region with 2°E longitude and 4°N latitude in Iran has been used. Thereupon, three algorithms including grid partition (GP), subtractive clustering (SC) and fuzzy C-means (FCM) were used to develop models with the structure of ANFIS. Since the earthquake data for the specified region had been reported on different magnitude scales, suitable relationships were determined to convert the magnitude scales into moment magnitude and all records uniformed based on the relationships. The uniform data were used to calculate seismicity indicators, and ANFIS was developed based on considered algorithms. The results showed that ANFIS-FCM with a high accuracy was able to predict earthquake magnitude.     

Regional rating curve models of suspended sediment transport for Turkey

Estimations of annual suspended sediment loads are required for various types of water resources studies. Often estimation of the sediment load is needed for ungauged watersheds. Regionalization methods provide a practical solution to solve such problems. The purpose of this study is to classify suspended sediment yields in watersheds into homogeneous regions in order to identify their regional sediment rating curves. This study has been carried out for suspended sediment stations on 26 main basins of Turkey. Long term-scale suspended sediment rating curves of 115 gauging stations in Turkey were classified using cluster analysis on the basis of hydrological homogeneity. An agglomerative hierarchical clustering algorithm is used so that stations from different geographical locations are considered in the same cluster independently of their geographical location. 115 gauging stations were clustered into 4 different homogenous regions and the regional suspended sediment rating curve was developed for each region. The performance efficiencies of the developed regional rating curves were evaluated for 8 test stations and compared to the performances of rating curves in test sites. A regionalization model is developed for estimating suspended sediment rating curves for ungauged sites in Turkey. The developed regional rating curve models result in very close performances to those of their corresponding site rating curves.     

Prediction of ground vibrations resulting from the blasting operations in an open-pit mine by adaptive neuro-fuzzy inference system

The aim of this study is to predict the peak particle velocity (PPV) values from both presently constructed simple regression model and fuzzy-based model. For this purpose, vibrations induced by bench blasting operations were measured in an open-pit mine operated by the most important magnesite producing company (MAS) in Turkey. After gathering the ordered pairs of distance and PPV values, the site-specific parameters were determined using traditional regression method. Also, an attempt has been made to investigate the applicability of a relatively new soft computing method called as the adaptive neuro-fuzzy inference system (ANFIS) to predict PPV. To achieve this objective, data obtained from the blasting measurements were evaluated by constructing an ANFIS-based prediction model. The distance from the blasting site to the monitoring stations and the charge weight per delay were selected as the input parameters of the constructed model, the output parameter being the PPV. Valid for the site, the PPV prediction capability of the constructed ANFIS-based model has proved to be successful in terms of statistical performance indices such as variance account for (VAF), root mean square error (RMSE), standard error of estimation, and correlation between predicted and measured PPV values. Also, using these statistical performance indices, a prediction performance comparison has been made between the presently constructed ANFIS-based model and the classical regression-based prediction method, which has been widely used in the literature. Although the prediction performance of the regression-based model was high, the comparison has indicated that the proposed ANFIS-based model exhibited better prediction performance than the classical regression-based model.     

A comparative study of artificial neural networks,Bayesian neural networks and adaptive neuro-fuzzy inference system in groundwater level prediction

Predictive modeling of hydrological time series is essential for groundwater resource development and management. Here, we examined the comparative merits and demerits of three modern soft computing techniques, namely, artificial neural networks (ANN) optimized by scaled conjugate gradient (SCG) (ANN.SCG), Bayesian neural networks (BNN) optimized by SCG (BNN.SCG) with evidence approximation and adaptive neuro-fuzzy inference system (ANFIS) in the predictive modeling of groundwater level fluctuations. As a first step of our analysis, a sensitivity analysis was carried out using automatic relevance determination scheme to examine the relative influence of each of the hydro-meteorological attributes on groundwater level fluctuations. Secondly, the result of stability analysis was studied by perturbing the underlying data sets with different levels of correlated red noise. Finally, guided by the ensuing theoretical experiments, the above techniques were applied to model the groundwater level fluctuation time series of six wells from a hard rock area of Dindigul in Southern India. We used four standard quantitative statistical measures to compare the robustness of the different models. These measures are (1) root mean square error, (2) reduction of error, (3) index of agreement (IA), and (4) Pearson’s correlation coefficient (R). Based on the above analyses, it is found that the ANFIS model performed better in modeling noise-free data than the BNN.SCG and ANN.SCG models. However, modeling of hydrological time series correlated with significant amount of red noise, the BNN.SCG models performed better than both the ANFIS and ANN.SCG models. Hence, appropriate care should be taken for selecting suitable methodology for modeling the complex and noisy hydrological time series. These results may be used to constrain the model of groundwater level fluctuations, which would in turn, facilitate the development and implementation of more effective sustainable groundwater management and planning strategies in semi-arid hard rock area of Dindigul, Southern India and alike.     

Evaluation of blast-induced ground vibrations in open-pit mines by using adaptive neuro-fuzzy inference systems

This study addresses the effects of rock characteristics and blasting design parameters on blast-induced vibrations in the Kangal open-pit coal mine, the Tülü open-pit boron mine, the K?rka open-pit boron mine, and the TKI Çan coal mine fields. Distance (m, R) and maximum charge per delay (kg, W), stemming (m, SB), burden (m, B), and S-wave velocities (m/s, Vs) obtained from in situ field measurements have been chosen as input parameters for the adaptive neuro-fuzzy inference system (ANFIS)-based model in order to predict the peak particle velocity values. In the ANFIS model, 521 blasting data sets obtained from four fields have been used (r ² = 0.57–0.81). The coefficient of ANFIS model is higher than those of the empirical equation (r ² = 1). These results show that the ANFIS model to predict PPV values has a considerable advantage when compared with the other prediction models.     

Prediction of daily suspended sediment load using wavelet and neurofuzzy combined model

This study investigated the prediction of suspended sediment load in a gauging station in the USA by neuro-fuzzy, conjunction of wavelet analysis and neuro-fuzzy as well as conventional sediment rating curve models. In the proposed wavelet analysis and neuro-fuzzy model, observed time series of river discharge and suspended sediment load were decomposed at different scales by wavelet analysis. Then, total effective time series of discharge and suspended sediment load were imposed as inputs to the neuro-fuzzy model for prediction of suspended sediment load in one day ahead. Results showed that the wavelet analysis and neuro-fuzzy model performance was better in prediction rather than the neuro-fuzzy and sediment rating curve models. The wavelet analysis and neuro-fuzzy model produced reasonable predictions for the extreme values. Furthermore, the cumulative suspended sediment load estimated by this technique was closer to the actual data than the others one. Also, the model could be employed to simulate hysteresis phenomenon, while sediment rating curve method is incapable in this event.     

Characteristics of recursive and non-recursive adaptive network-based fuzzy inference system models for the forecast of typhoon inundation levels

The accurate forecasting of typhoon inundation levels is vital for damage mitigation actions during such an event. The objective of this paper is to investigate the characteristics of adaptive network-based fuzzy inference system models for the forecasting of typhoon inundation levels. A novel approach of recursively using the model to achieve higher prediction lead times is proposed. The approach is advantageous in conducting water level forecasts for various prediction lead times using a single model, whereas common non-recursive models are only applicable for the designed prediction leads. In this study, a total of 6 models, with various configurations and types of recursions, are constructed based on the cross-correlations between rainfall and water level records. The performance of each model is evaluated and compared using three indices: coefficient of efficiency, relative time shift, and threshold statistics. The best recursive and non-recursive models are selected and compared with traditional approaches based on autoregressive models with exogenous input. The results show that although the recursive models display somewhat lesser but comparable forecasting capacities compared to the non-recursive models, the former models have achieved forecasts single handedly for all the prediction leads using single models only. On the other hand, although the non-recursive models exhibit better forecasting capacities, this is at the cost of using multiple models, with each designed for a specific prediction lead time. In comparison with other traditional approaches, both the recursive and non-recursive types of models demonstrate superior performance on all the aspects inspected.     

A new GIS-based data mining technique using an adaptive neuro-fuzzy inference system (ANFIS) and k-fold cross-validation approach for land subsidence susceptibility mapping

In this paper, we evaluate the predictive performance of an adaptive neuro-fuzzy inference system (ANFIS) using six different membership functions (MF). In combination with a geographic information system (GIS), ANFIS was used for land subsidence susceptibility mapping (LSSM) in the Marand plain, northwest Iran. This area is prone to droughts and low groundwater levels and subsequent land subsidence damages. Therefore, a land subsidence inventory database was created from an extensive field survey. Areas of land subsidence or areas showing initial signs of subsidence were used for training, while one-third of inventory database were reserved for testing and validation. The inventory database randomly divided into three different folds of the same size. One of the folds was chosen for testing and validation. Other two folds was used for training. This process repeated for every fold in the inventory dataset. Thereafter, land subsidence related factors, such as hydrological and topographical factors, were prepared as GIS layers. Areas susceptible to land subsidence were then analyzed using the ANFIS approach, and land subsidence susceptibility maps were created, whereby six different MFs were applied. Lastly, the results derived from each MF were validated with those areas of the land subsidence database that were not used for training. Receiver operating characteristics (ROC) curves were drawn for all LSSMs, and the areas under the curves were calculated. The ROC analyses for the six LSSMs yielded very high prediction values for two out of the six methods, namely the difference of DsigMF (0.958) and GaussMF (0.951). The integration of ANFIS and GIS generally led to high LSSM prediction accuracies. This study demonstrated that the choice of training dataset and the MF significantly affects the results.     

Modeling diagnosis of suspended sediment transport in tidal estuarine system

A three-dimensional, time-dependent hydrodynamic and suspended sediment transport model was performed and applied to the Danshuei River estuarine system and adjacent coastal sea in northern Taiwan. The model was validated with observed time-series salinity in 2001, and with salinity and suspended sediment distributions in 2002. The predicted results quantitatively agreed with the measured data. A local turbidity maximum was found in the bottom water of the Kuan-Du station. The validated model then was conducted with no salinity gradient, no sediment supply from the sediment bed, wind stress, and different freshwater discharges from upstream boundaries to comprehend the influences on suspended sediment dynamics in the Danshuei River estuarine system. The results reveal that concentrations of the turbidity maximum simulated without salinity gradient are higher than those of the turbidity maximum simulated with salinity gradient at the Kuan-Du station. Without bottom resuspension process, the estuarine turbidity maximum zone at the Kuan-Du station vanishes. This suggests that bottom sediment resuspension is a very important sediment source to the formation of estuarine turbidity maximum. The wind stress with northeast and southwest directions may contribute to decrease the suspended sediment concentration. When the freshwater discharges increase at the upstream boundaries, the limits of salt intrusion pushes downriver toward river mouth. Suspended sediment concentrations increase at the upriver reaches in the Danshuei River to Tahan Stream, while decrease at Kuan-Du station.     

Impact of suspended sediment load on the silting of SMBA reservoir (Algeria)

The phenomenon of suspended sediment load is very complex in Mina River basin because of its important soil heterogeneity, vegetation deficiency and rainfall variability in time and space. The methodological approach adopted in this paper consists of finding a regressive power model, which may explain better the suspended sediment discharge as a function of the flow discharge collected at Wadi El-Abtal and Sidi AEK Djilali hydrometric stations by studying this relation at various temporal scales: daily, annual, monthly and seasonal. The obtained monthly power relations, explaining the greatest part of the variance, lead to interpolate, extrapolate and analyse suspended and bed loads deposited on Sidi M’hamed Ben Aouda (SMBA) reservoir since being in service in 1977/1978. These allow authors to find relations between specific erosion and effective rainfall and propose some solutions for river basin managers and policy makers to reduce the silting of SMBA reservoir.     

The partitioning of the total sediment load of a river into suspended load and bedload: a review of empirical data

The partitioning of the total sediment load of a river into suspended load and bedload is an important problem in fluvial geomorphology, sedimentation engineering and sedimentology. Bedload transport rates are notoriously hard to measure and, at many sites, only suspended load data are available. Often the bedload fraction is estimated with ‘rule of thumb’ methods such as Maddock’s Table, which are inadequately field‐tested. Here, the partitioning of sediment load for the Pitzbach is discussed, an Austrian mountain stream for which high temporal resolution data on both bedload and suspended load are available. The available data show large scatter on all scales. The fraction of the total load transported in suspension may vary between zero and one at the Pitzbach, while its average decreases with rising discharge (i.e. bedload transport is more important during floods). Existing data on short‐term and long‐term partitioning is reviewed and an empirical equation to estimate bedload transport rates from measured suspended load transport rates is suggested. The partitioning averaged over a flood can vary strongly from event to event. Similar variations may occur in the year‐to‐year averages. Using published simultaneous short‐term field measurements of bedload and suspended load transport rates, Maddock’s Table is reviewed and updated. Long‐term average partitioning could be a function of the catchment geology, the fraction of the catchment covered by glaciers and the extent of forest, but the available data are insufficient to draw final conclusions. At a given drainage area, scatter is large, but the data show a minimal fraction of sediment transported in suspended load, which increases with increasing drainage area and with decreasing rock strength for gravel‐bed rivers, whereby in large catchments the bedload fraction is insignificant at ca 1%. For sand‐bed rivers, the bedload fraction may be substantial (30% to 50%) even for large catchments. However, available data are scarce and of varying quality. Long‐term partitioning varies widely among catchments and the available data are currently not sufficient to discriminate control parameters effectively.     

Impact of human activity and climate change on suspended sediment load: the upper Yellow River, China

Fluvial suspended sediment has multi-fold environmental implications and the study of the variation in suspended sediment load (SSL) of rivers is important both in environmental earth sciences and in river environmental management. Based on data collected for the upper Yellow River of China in the past 50–60 years, the purpose of this study is to elucidate the impact of human activity and climate change on SSL, thereby to provide some knowledge for the improvement of the drainage basin management. The results show that the SSL of the upper Yellow River exhibited a remarkable decreasing trend. A number of reservoirs trapped a considerable amount of sediment, resulting in a reduction in SSL at Toudaoguai station, the most downstream station of the upper Yellow River. The analyses based on Mann–Kendall’U and double-mass plot indicate some turning points, which were caused by the Liujiaxia and Longyangxia Reservoirs, two major reservoirs on the upper Yellow River. The implementation of soil and water conservation measures reduced the runoff coefficient, and therefore, the intensity of soil erosion. The climate change also played a role in reducing sediment yield. The increase in air temperature enhanced the evapo-transpiration and reduced the runoff, by which the SSL decreased. The decreased frequency of sand-dust storms reduced the amount of wind-blown, sand and dust to the river reaches located in desert, also reducing the SSL. Seven influencing variables are selected to describe the changing human activity and climate. As some of the influencing variables are strongly inter-correlated, the principle component regression was used to establish the relationship between SSL and the influencing variables. The squared multiple correlation coefficient is R ² = 0.823. Some further research is suggested with the minerals and pollutants related with the SSL.