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.     

Tunnel stability analysis during construction using a neuro‐fuzzy system

This paper presents an alternative strategy to evaluate the stability of tunnels during the design and construction stages based on a hybrid system, composed by neural, neuro‐fuzzy and analytical solutions. A prototype of this system is designed using a database formed by 261 cases, 45 real and the rest synthetic. This system is capable of reproducing the displacements induced at the periphery of the tunnel before and after support installation. The stability of the excavation process is evaluated using a criterion that considers dimensionless parameters based on the shear strength of the media, the induced deformation level in the ground, the plastic radii and the advance of excavation without support. The efficiency and validity of the prototype is verified with two examples of actual tunnels, one included in the database used to train the system and the other not included. The results of both examples show a better approximation than other commonly used techniques. Copyright © 2005 John Wiley & Sons, Ltd.     

Prediction of flyrock and backbreak in open pit blasting operation: a neuro-genetic approach

An ideally performed blasting operation enormously influences the mining overall cost. This aim can be achieved by proper prediction and attenuation of flyrock and backbreak. Poor performance of the empirical models has urged the application of new approaches. In this paper, an attempt has been made to develop a new neuro-genetic model for predicting flyrock and backbreak in Sungun copper mine, Iran. Recognition of the optimum model with this method as compared with the classic neural networks is faster and convenient. Genetic algorithm was utilized to optimize neural network parameters. Parameters such as number of neurons in hidden layer, learning rate, and momentum were considered in the model construction. The performance of the model was examined by statistical method in which absolutely higher efficiency of neuro-genetic modeling was proved. Sensitivity analysis showed that the most influential parameters on flyrock are stemming and powder factor, whereas for backbreak, stemming and charge per delay are the most effective parameters.     

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.     

Toward real-time three-dimensional mapping of surficial aquifers using a hybrid modeling approach

A hybrid modeling approach is proposed for near real-time three-dimensional (3D) mapping of surficial aquifers. First, airborne frequency-domain electromagnetic (FDEM) measurements are numerically inverted to obtain subsurface resistivities. Second, a machine-learning (ML) algorithm is trained using the FDEM measurements and inverted resistivity profiles, and borehole geophysical and hydrogeologic data. Third, the trained ML algorithm is used together with independent FDEM measurements to map the spatial distribution of the aquifer system. Efficacy of the hybrid approach is demonstrated for mapping a heterogeneous surficial aquifer and confining unit in northwestern Nebraska, USA. For this case, independent performance testing reveals that aquifer mapping is unbiased with a strong correlation (0.94) among numerically inverted and ML-estimated binary (clay-silt or sand-gravel) layer resistivities (5–20 ohm-m or 21–5,000 ohm-m), and an intermediate correlation (0.74) for heterogeneous (clay, silt, sand, gravel) layer resistivities (5–5,000 ohm-m). Reduced correlation for the heterogeneous model is attributed to over-estimating the under-sampled high-resistivity gravels (about 0.5 % of the training data), and when removed the correlation increases (0.87). Independent analysis of the numerically inverted and ML-estimated resistivities finds that the hybrid procedure preserves both univariate and spatial statistics for each layer. Following training, the algorithms can map 3D surficial aquifers as fast as leveled FDEM measurements are presented to the ML network.     

A simulation using a hybrid method for predicting fault zones ahead of a tunnel face

By monitoring and analysing three‐dimensional absolute displacement during tunnel excavation, it is possible to predict discontinuity zones ahead of tunnel face. This paper presents results of the three‐dimensional displacement obtained from three‐dimensional simulations using hybrid method for assessing the effect of discontinuity zones on monitoring data. The influence of fault zones and in situ initial stresses on the three‐dimensional tunnel movement is evaluated. Copyright © 2002 John Wiley & Sons, Ltd.     

Environmental performance evaluation of suppliers: A hybrid fuzzy multi-criteria decision approach

Increasing environmental problems enforce companies to be more environmental responsible. A company’s environmental performance is not only related to the company’s inner environmental efforts, but also it is affected by the suppliers’ environmental performance and image. As a stakeholder of the company, a supplier with bad environmental image affects badly the company’s environmental image. Also, raw materials and semi-finished products supplied from out of the company recourses- suppliers- affects the products environmental features such as life cycle, re-usability, re-manufacturability, hazardous substances, etc. Considering these direct and indirect effects, managers should also consider environmental performances of their suppliers in their supplier evaluation process. In this paper, a methodology for the evaluation of suppliers’ environmental performances is proposed. In this methodology, a hybrid Fuzzy-Analytic Network Process and Fuzzy-Preference Ranking Organization METHod for Enrichment Evaluations approach is utilized. Additionally, a numerical example is given to foster the better understanding of the methodology and the obtained results are analyzed with sensitivity analyses.     

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.     

Weathering: Toward a Fractal Quantifying

Weathering occurs over a wide range of scales. To link features through these scales is a major challenge for interdisciplinary weathering studies. Fractal approach seems to be specially useful for this purpose. We introduce a multistep fractal weathering assessment scheme devoted to extract fractal weathering classifiers from texture analysis of the mineral's image. Our scheme enables to quantitatively estimate the global and local information about the geometry of the weathering pattern. This information is basic to develop geometrical indices of weathering, which can significantly enrich the common qualitative and semiquantitative weathering assessment schemes. To justify the fractal approach, a strong statistical self-similarity has been documented for both the weathering and fresh features of two common silica minerals: quartz and biogenic A-opal (phytolith) over four orders of length scales. The procedure is fast, drastically reduces thresholding bias, promises to be universal, it is valid for genetically different minerals and rock types, scale independent, and specially useful for monitoring the changes in the mineral's roughness during the alteration. Two of the proposed classifiers seem to be potentially useful for direct application in the field and be used by nonspecialist.     

One‐dimensional analysis of a poroelastic medium during freezing

A solution to the problem of freezing of a poroelastic material is derived and analysed in the case of one‐dimensional deformation. The solution is sought within the framework of thermo‐poroelasticity, with specific account of the behaviour of freezing materials. The governing equations of the problem can be combined into a pair of coupled partial differential equations for the temperature and the fluid pressure, with particular forms in the freezing and the unfrozen regions. In the freezing region, the equations are highly non‐linear, partly due to the dependence of thermal and hydraulic properties on water saturation, which varies with temperature. Consequently, the solution is obtained through numerical methods, with special attention to the propagation of the freezing front boundary. The response to one‐dimensional freezing is illustrated for the case of cement paste. Finally, the influence on the solution of varying selected parameters is analysed, such as the temperature boundary conditions, the parameters characterizing the geometry of the porous system, the ratio of fluid and thermal diffusivities, and the rate of cooling applied at the freezing end. Copyright © 2008 John Wiley & Sons, Ltd.     

On the initialization of tropical cyclones with a three dimensional variational analysis

A method of initializing tropical cyclones in high-resolution numerical models is developed by modifying a data assimilation system, the NRL atmospheric variational data assimilation system (NAVDAS), which was designed for general mesoscale weather prediction using a three-dimensional variational (3DVAR) analysis with intermittent updates. The method includes the following three upgrades to overcome difficulties resulting from tropical cyclone initialization with the NAVDAS analysis. First, synthetic observation soundings are generated on 9 vertical levels at 49 points for strong storms (v _max?>?23.1?m?s^?1) and 41 points for weak storms around each cyclone center to supplement the observations used by the analysis. Secondly, a vortex relocation method for nested grids is developed to correct the cyclone position in the background fields of the analysis for each nested mesh. Lastly, the 3DVAR analysis is modified to gradually reduce the horizontal length scale and geostrophic coupling constraint near the center of a tropical cyclone for minimizing the problems introduced by improper covariances and coupling constraint used in the analysis. The synthetic observations significantly improve the intensity and structure of the analysis and the track forecast. The vortex relocation significantly improves the first guess background, avoiding the large analysis corrections that would be needed to correct cyclone position, and reducing the imbalance introduced by such large analysis increments. The modifications to the analysis length scale and geostrophic coupling constraint successfully improve the inner core analysis, providing a tighter circulation, and reducing the underestimate of the mass field gradient. Among the three upgrades, the vortex relocation provides the largest improvement to the tropical cyclone initialization and forecast.     

Processing of earthquake catalog data of Western Turkey with artificial neural networks and adaptive neuro<Emphasis>-</Emphasis>fuzzy inference system

Turkey is one of several countries frequently facing significant earthquakes because of its geological and tectonic position on earth. Especially, graben systems of Western Turkey occur as a result of seismically quite active tensional tectonics. The prediction of earthquakes has been one of the most important subjects concerning scientists for a long time. Although different methods have already been developed for this task, there is currently no reliable technique for finding the exact time and location of an earthquake epicenter. Recently artificial intelligence (AI) methods have been used for earthquake studies in addition to their successful application in a broad spectrum of data intensive applications from stock market prediction to process control. In this study, earthquake data from one part of Western Turkey (37–39.30° N latitude and 26°–29.30° E longitude) were obtained from 1975 to 2009 with a magnitude greater than M ≥ 3. To test the performance of AI in time series, the monthly earthquake frequencies of Western Turkey were calculated using catalog data from the region and then the obtained data set was evaluated with two neural networks namely as the multilayer perceptron neural networks (MLPNNs) and radial basis function neural networks (RBFNNs) and adaptive neuro-fuzzy inference system (ANFIS). The results show that for monthly earthquake frequency data prediction, the proposed RBFNN provides higher correlation coefficients with real data and smaller error values.     

Probabilistic and fuzzy reliability analysis of a sample slope near Aliano

Slope stability assessment is a geotechnical problem characterized by many sources of uncertainty. Some of them, e.g., are connected to the variability of soil parameters involved in the analysis. Beginning from a correct geotechnical characterization of the examined site, only a complete approach to uncertainty matter can lead to a significant result. The purpose of this paper is to demonstrate how to model data uncertainty in order to perform slope stability analysis with a good degree of significance.

Once the input data have been determined, a probabilistic stability assessment (first-order second moment and Monte Carlo analysis) is performed to obtain the variation of failure probability vs. correlation coefficient between soil parameters. A first result is the demonstration of the stability of first-order second moment (FOSM) (both with normal and lognormal distribution assumption) and Monte Carlo (MC) solutions, coming from a correct uncertainty modelling. The paper presents a simple algorithm (Fuzzy First Order Second Moment, FFOSM), which uses a fuzzy-based analysis applied to data processing.     

复合型含油气系统的特征与描述 : 以塔中含油气系统为例

通过对塔中含油气系统的研究，发现它难以用传统的含油气系统方法来描述。它主要有二个油源区三套生油岩，发育有三套储层；不同油源在不同时期生成的油气在储层内共生、甚至相互混合，使油气成因复杂。据此提出了它是一个复合型含油气系统。在此基础上，进一步指出复合型含油气系统的特点是多油源、多期成烃、油气成因复杂，出现在迭合型盆地。并针对这些特点，初步提出了工作思路及描述方法。     

Pollen representation,source area,and basin size: Toward a unified theory of pollen analysis

The concepts of pollen source area and of production and dispersal biases in pollen representation are quantified by means of a simple theoretical model. Source areas and relative pollen representation are shown to depend on basin size according to functions that describe the amount of pollen remaining airborne at increasing distances from single pollen sources. The form of these functions is determined by physical processes. Standard formulas for elevated sources do not apply, but the integrated form of Sutton's equation for particle dispersal from a ground-level source gives useful approximations applicable to pollen transport over a forest canopy. Simulations using this equation yielded source areas that increased realistically with basin size, showed substantial differences between source areas for pollen grains with different deposition velocities, and predicted that lighter pollen grains should become better represented with increasing basin size. All of these predictions are qualitatively consistent with present knowledge of the characteristics of pollen assemblages in different depositional environments. The model further allows parameters that can be estimated by statistical calibration methods to be predicted from underlying physical quantities. This extension suggests procedures for testing the theory with quantitative data on surface pollen and forest composition. Preliminary results showed reasonable agreement between estimated and predicted values of dispersal indices for the most abundant taxa in pollen spectra from the northern midwestern United States.     

Discriminant analysis as a method of predicting mineral occurrence potentials in central Norway

The statistical technique of discriminant analysis is used to define target areas for detailed general exploration given only general geological information and aeromagnetic anomaly blues. In the test area, located in Central Norway, on-going exploration surveys have revealed the presence of mineralization; however, it still has not been determined if any of the sites will beeconomically feasible. The area was divided into 1400 1-km × 1-km cells by superimposing square grid on 1:50,000-scale geological and geophysical maps. Later the area was divided into two subareas based on major differences in each area's geology. A number of geological natures and the aeromagnetic anomaly values were coded systematically in each cell. The cells representing an advanced degree of exploration were chosen as control cells in each of the subareas. The geological and geophysical parameters were transformed, by means of relatively simple transformations, to produce near-normal frequency distributions. A discriminant function was then obtained by discriminant analysis to divide the control data into two groups, cells with presence of mineral occurrence and cells without mineral occurrence. the discriminant function obtained for the control area proved to be relevant both geologically and statistically. Consequently, the discriminant equation was applied to cells outside the control area. The cells were assigned to one of the two groups by entering the geologic factors pleasured from the maps into the discriminant model. The exploration potential of a large number of cells was evaluated by this procedure. To test the results, field work including geochemical sampling was carried out in the cells with highest probability of mineral occurrance The field work results have shown that the application of discriminant analysis to geological information at 1:50,000 scale with 1-km × 1-km cells combined with a careful selection of techniques for transforming the variables is a feasible method for predicting gaeralization, and as such could become a valuable tool for mining exploration.This paper was presented at Symposium 116.3, Quantitative Strategy for Exploration, held as part of the 25th International Geological Congress, Sydney, Australia, August 1976.     

Recovery of chlorinated solvent trichloroethylene contaminated groundwater using a hybrid treatment system

In this laboratory pilot-scale study, a hybrid treatment system has been developed to remove chlorinated solvent trichloroethylene and fine particles from chlorinated solvent trichloroethylene-contaminated groundwater before it is applied for further recovery. The two-stage system contained fiber-ball filtration followed by nanofiltration membrane processes. The measured chlorinated solvent trichloroethylene and suspended solids of the tested groundwater were 850 μg/L and 1,052 mg/L, respectively. Up to 97.3 % of chlorinated solvent trichloroethylene and 99.9 % of SS could be removed by the hybrid system with an operational pressure of 4.1 kg/cm². The chlorinated solvent trichloroethylene removal mechanism in the fiber-ball filtration process could be due to adsorption. Approximately 98.2 and 78.6 % of chlorinated solvent trichloroethylene rejection was observed when nanofiltration membrane was used for chlorinated solvent trichloroethylene removal with the recover rate of 80 % and initial chlorinated solvent trichloroethylene concentration of 1 and 10 mg/L. Higher chlorinated solvent trichloroethylene rejection can be obtained when lower chlorinated solvent trichloroethylene concentration (1 mg/L) was applied. High chlorinated solvent trichloroethylene concentration (10 mg/L) would increase the pore size of nanofiltration, which causes the decrease in chlorinated solvent trichloroethylene rejection rate. Approximately 46.6 % of flux drop was observed when nanofiltration membrane was used along compared to the system using FF as the first treatment stage. This indicates that the application of fiber-ball filtration could maintain a higher flux of groundwater treatment. The developed fiber-ball filtration and nanofiltration hybrid membrane system is able to reduce the chlorinated solvent trichloroethylene and solid concentrations to meet the water reuse and groundwater remediation standards.     

Toward a general procedure for analysis of extreme random events in the earth sciences

Engineering and scientific approaches to design magnitude estimation are briefly revisited. Some defense is offered for use of annual maxima in design as if they were variables from a common distribution. However, to assume any particular form of distribution tail beyond the largest data value is not justifiable, regardless of the degree of data support over the main body of the distribution. An alternative approach to the design problem is suggested through use of parameter-free nonparametric estimation using the kernel method. Some simulation results are presented which suggest that the parameter-free approach is worthy of further development. A particular advantage of nonparametric methods is that competing estimators can be checked against parametric distributions, leading to a progressive improvement in estimator accuracy.This paper was presented (by title) at Engineering Concepts, MGUS-87 Conference, Redwood City, California, 13–15 April 1987.