Işık Yilmaz

Landslide susceptibility mapping using frequency ratio, logistic regression, artificial neural networks and their comparison: A case study from Kat landslides (Tokat-Turkey)

The purpose of this study is to compare the landslide susceptibility mapping methods of frequency ratio (FR), logistic regression and artificial neural networks (ANN) applied in the Kat County (Tokat-Turkey). Digital elevation model (DEM) was first constructed using GIS software. Landslide-related factors such as geology, faults, drainage system, topographical elevation, slope angle, slope aspect, topographic wetness index (TWI) and stream power index (SPI) were used in the landslide susceptibility analyses. Landslide susceptibility maps were produced from the frequency ratio, logistic regression and neural networks models, and they were then compared by means of their validations. The higher accuracies of the susceptibility maps for all three models were obtained from the comparison of the landslide susceptibility maps with the known landslide locations. However, respective area under curve (AUC) values of 0.826, 0.842 and 0.852 for frequency ratio, logistic regression and artificial neural networks showed that the map obtained from ANN model is more accurate than the other models, accuracies of all models can be evaluated relatively similar. The results obtained in this study also showed that the frequency ratio model can be used as a simple tool in assessment of landslide susceptibility when a sufficient number of data were obtained. Input process, calculations and output process are very simple and can be readily understood in the frequency ratio model, however logistic regression and neural networks require the conversion of data to ASCII or other formats. Moreover, it is also very hard to process the large amount of data in the statistical package.

Multiple regression, ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils

Research highlights? The use of multiple regression (MR), artificial neural network (ANN) and artificial neuro-fuzzy inference system (ANFIS) models, for the prediction of swell percent of soils, was described and compared. ? However the accuracies of ANN and ANFIS models may be evaluated relatively similar, it is shown that the constructed ANN models of RBF and MLP exhibit a high performance than ANFIS and multiple regression for predicting swell percent of clays. ? The performance comparison showed that the soft computing system is a good tool for minimizing the uncertainties in the soil engineering projects. ? The use of soft computing will also may provide new approaches and methodologies, and minimize the potential inconsistency of correlations. In the recent years, new techniques such as; artificial neural networks and fuzzy inference systems were employed for developing of the predictive models to estimate the needed parameters. Soft computing techniques are now being used as alternate statistical tool. Determination of swell potential of soil is difficult, expensive, time consuming and involves destructive tests. In this paper, use of MLP and RBF functions of ANN (artificial neural networks), ANFIS (adaptive neuro-fuzzy inference system) for prediction of S% (swell percent) of soil was described, and compared with the traditional statistical model of MR (multiple regression). However the accuracies of ANN and ANFIS models may be evaluated relatively similar. It was found that the constructed RBF exhibited a high performance than MLP, ANFIS and MR for predicting S%. The performance comparison showed that the soft computing system is a good tool for minimizing the uncertainties in the soil engineering projects. The use of soft computing will also may provide new approaches and methodologies, and minimize the potential inconsistency of correlations.

Correlation of Schmidt hardness with unconfined compressive strength and Young's modulus in gypsum from Sivas (Turkey)

Abstract This study aims to express the relationships between Schmidt rebound number ( N ) with unconfined compressive strength (UCS) and Youngs modulus ( E t ) of the gypsum by empirical equations. As known, the Schmidt hammer has been used worldwide as an index test for a quick rock strength and deformability characterisation due to its rapidity and easiness in execution, simplicity, portability, low cost and nondestructiveness. In this study, gypsum samples have been collected from various locations in the Miocene-aged gypsum of Sivas Basin and tested. The tests include the determination of Schmidt hammer rebound number ( N ), tangent Youngs modulus ( E t ) and unconfined compressive strength. Finally, obtained parameters were correlated and regression equations were established among Schmidt hammer rebound hardness, tangent Youngs modulus and unconfined compressive strength, presenting high coefficients of correlation. It appears that there is a possibility of estimating unconfined compressive strength and Youngs modulus of gypsum, from their Schmidt hammer rebound number by using the proposed empirical relationships of UCS=exp(0.818+0.059 N ) and E t =exp(1.146+0.054 N ). However, the equations must be used only for the gypsum with an acceptable accuracy, especially at the preliminary stage of designing a structure. Finally, by using the obtained Schmidt hammer rebound number from this study, unconfined compressive strength was calculated and compared with the calculated value from different empirical equations proposed by different authors. It can be said that it is impossible to obtain only one relation for all types of the rocks.

Landslide hazard and risk assessment: a case study from the Hlohovec–Sered’ landslide area in south-west Slovakia

Landslide hazard or susceptibility assessment is based on the selection of relevant factors which play a role on the slope instability, and it is assumed that landslides will occur at similar conditions to those in the past. The selected statistical method compares parametric maps with the landslide inventory map, and results are then extrapolated to the entire evaluated territory with a final product of landslide hazard or susceptibility map. Elements at risk are defined and analyzed in relation with landslide hazard, and their vulnerability is thus established. The landslide risk map presents risk scenarios and expected financial losses caused by landslides, and it utilizes prognoses and analyses arising from the landslide hazard map. However, especially the risk scenarios for future in a selected area have a significant importance, the literature generally consists of the landslide susceptibility assessment and papers which attempt to assess and construct the map of the landslide risk are not prevail. In the paper presented herein, landslide hazard and risk assessment using bivariate statistical analysis was applied in the landslide area between Hlohovec and Sered’ cities in the south-western Slovakia, and methodology for the risk assessment was explained in detail.

Neural computing models for prediction of permeability coefficient of coarse-grained soils

Correlations are very significant from the earliest days; in some cases, it is essential as it is difficult to measure the amount directly, and in other cases it is desirable to ascertain the results with other tests through correlations. Soft computing techniques are now being used as alternate statistical tool, and new techniques such as artificial neural networks, fuzzy inference systems, genetic algorithms, and their hybrids were employed for developing the predictive models to estimate the needed parameters, in the recent years. Determination of permeability coefficient (k) of soils is very important for the definition of hydraulic conductivity and is difficult, expensive, time-consuming, and involves destructive tests. In this paper, use of some soft computing techniques such as ANNs (MLP, RBF, etc.) and ANFIS (adaptive neuro-fuzzy inference system) for prediction of permeability of coarse-grained soils was described and compared. As a result of this paper, it was obtained that the all constructed soft computing models exhibited high performance for predicting k. In order to predict the permeability coefficient, ANN models having three inputs, one output were applied successfully and exhibited reliable predictions. However, all four different algorithms of ANN have almost the same prediction capability, and accuracy of MLP was relatively higher than RBF models. The ANFIS model for prediction of permeability coefficient revealed the most reliable prediction when compared with the ANN models, and the use of soft computing techniques will provide new approaches and methodologies in prediction of some parameters in soil mechanics.

Deformation of slopes as a cause of underground mining activities: three case studies from Ostrava–Karviná coal field (Czech Republic)

Underground mining activities may potentially play a role on the initiation and reactivation of the slope movements. However, an adequate attention has not yet been paid to these problems; in this study, the possible influence of present and former mining activities on the selected set of model slope deformations in the Ostrava–Karviná Coalfield (Opliji, Repiste and Orlova Lazy District) was analysed and a methodology for their observation for application to similar conditions and influence was described. Isocatabase maps, terrain deformation parameters calculated for the point lying on the slope deformation surface, length measurement by zone extensometer and dilatometer measurement in cracks was also provided for evaluation of the underground mining impact. It was found that inclinations of both boreholes were evidence of underground mining impact, and localization of inclinometer measurement on boreholes in the active part as well as in the near vicinity was very important as an important result of this study. Analysis of underground mining activity influence on model localities in relation to performed mining operations, subsidence and other influences on the ground surface was also determined. Thus, the study will contribute to a more objective knowledge of these problems of interest for the professional public and also for the state administration to solve problems associated with the utilisation and settlement of such affected areas.

GIS-based kinematic slope instability and slope mass rating (SMR) maps: application to a railway route in Sivas (Turkey)

The paper discusses the use of kinematic stability and slope mass rating (SMR) maps in GIS based on field studies recording the relationships between the bedding/joint geometry relative to the orientation of the free face. The results indicated the potential for both planar and wedge type failures in many locations along a railway route. Whilst the results showed the procedure to be a useful first assessment of slope stability, it is recommended that the construction of the maps by kinematic slope stability and SMR analysis within the GIS medium should be used in conjunction with more sophisticated slope stability models taking into account of the material strengths, hydrostatic pressures, seepage forces, active forces, passive forces, etc.RésuméL’article considère l’utilisation de cartes présentant les conditions cinématiques de rupture de pente et un indice SMR de pente, dans un système d’information géographique, cartes établies à partir d’études de terrain comparant les attitudes respectives des pentes et des joints dans une masse rocheuse. Les résultats montrent que des ruptures planes et des ruptures de dièdres sont possibles en plusieurs endroits le long de la voie ferrée étudiée. La procédure est utile pour une première évaluation de la stabilité des pentes, mais il est recommandé que les cartes donnant les conditions cinématiques de rupture de pente et l’indice SMR de pente, dans un SIG, soient utilisées conjointement avec des modèles plus sophistiqués de stabilité des pentes prenant en compte les résistances des matériaux, les pressions hydrostatiques, les forces d’écoulement, les forces motrices, les forces résistantes, etc.

Subsidence map of underground mining influence for urban planning: an example from the Czech Republic

The objective of this study is to produce a subsidence map linked to underground mining influence in a mining region. Ground subsidence represents the most important characteristic of a subsidence basin. However, ground subsidence itself does not carry information on geohazards by means of the impacts on the built-up area. Based on long-term experience and studies carried out, three basic subsidence intervals of varying influence were proposed. The lowest degree of undermining influence is connected with subsidence up to 12 cm; the second category is for subsidence from 12 to 100 cm, where constructions are considered possible under certain conditions but special technological procedures must be adhered to; and the third category of hazard is for subsidence over 100 cm. The study was implemented in the largest mining region (black coal deep mining) of the Czech Republic, in the locality of Orlova, Petrvald and Karvina. The study also involved an overall evaluation of subsidence influence, its variation with time, its relation to the current built-up area and to the future built-up area according to the land use plan, and its relation to engineering-geological zones and landslides.

Geotechnical evaluation of Miocene gypsum from Sivas (Turkey)

Gypsum is widely distributed in Sivas (Turkey), occurring chiefly in the formations of Miocene age. The gypsum is generally of the alabastrine type with a little of the porphiroblast type and contains traces of clay minerals, anhydrite and calcite. It is a moderately strong rock in terms of its unconfined compressive strength which is related to the crystal size. Strength increases as the crystal size decreases. The strength of gypsum was reduced by approximately 55%, when the samples were kept in the water for 20 days. Most samples exhibit plastic–elastic–plastic deformation. The gypsum has a high modulus ratio, and is a moderately deformable rock. High lateral deformations and low vertical deformations are observed under the vertical stress conditions in accordance with the relationship between modulus ratio and strain.

Utilization of ground subsidence caused by underground mining to produce a map of possible land-use areas for urban planning purposes

The presented work deals with a new type of map titled—a map of a possible area use for planned built-up area purposes in areas affected by underground mining-related subsidence. Generally, accepted theory of a subsidence basin must be applied to such areas, and in order to produce the map, ground subsidence isolines, land-use plan, and slope deformation distribution were considered. The map can be used by land-use planners, future developers, investors, engineering geologists, etc. to inform future development of such land. It is clear that land-use planners may not have sufficient knowledge to decide whether the ground subsidence value is acceptable or not for a particular development purpose. At the same time, it shows that the existence of slope deformations also influences the siting of new buildings in undermined areas and therefore these were included in the map compilation process. The outcome is three area categories where mining subsidence impacts surface development, namely—low influence on the planned development, economically acceptable influence on the planned development, and extreme influence with development prohibited. The research was carried out in the Darkov Region in the northeast of the Czech Republic, where black coal is mined and extensive mining impact on the surface identified. The map produced in this study will help the controlled development of the region by means of appropriate land-use planning.