Journal of Engineering Geology

---

The study area is located in Jiroft district, Iran, and is a part of Sahand-Bazman volcanic zone. There are various landslide factors and the importance of each factor are identified qualitatively, based on previous studies and regional specifications. Three landslides were recognized in the study area using direct method (field work) and aerial photographs interpretation. One of these landslides is located in the vicinity of Mohammad Abad of Maskoon Village. The aim of this study is landslide hazard mapping using two integration methods that includes Fuzzy Logic and Hybrid Fuzzy-Weight of Evidence (Hybrid F-W of E). The obtained results of maps from both methods, show a good agreement especially in introducing  high hazard regions. The hybrid method is based on the occurred landslide points and is more rigorous, so hazard regions delineated by this method occupy smaller areas than the areas introduced by fuzzy model. Therefore, hazard maps resulted from Hybrid and Fuzzy methods, can be considered as minimum and maximum limits of landslide hazard in the area, respectively. 

---

In this research, one of the new methods for seismic landslides hazard zonation (CAMEL) to predict the behavior of these types of landslides have been discussed.  It is also tried to eveluate this method with the proposed Mahdavifar method.  For achieving this result, the influence of  Sarein earthquake (1997), have been selected as a case study. In order to apply seismic hazard zonation, the methodology of Computing with Words (CW), an approach using fuzzy logic systems in which words are used in place of numbers for computing and reasoning is employed. First, the required information which includes disturbance distance, ground strength class, moisture content, shake intensity, slope angle, slope height, soil depth, terrain roughness, and vegetation have been collected using air photos, Landsat Satellite images, geological and topographic maps, and site investigation of the studied region. The data is digitized and weighted using Geological Information System (GIS). At the next step, the hazard rate and areal concentrations with respect to landslide types are calculated using CAMEL program and then, landslides hazard map produced by the above mentioned method is compared with landslides occurred as a result of Sarein earthquake. Finally, for evaluating on prediction of the earthquake-induced landslides, empirical comparison have been done between CAMEL and Mahdavifar methods.

---

In the present study, landslides occurred during 1997 Sarein, Iran earthquake are discussed and evaluated. In order to meet the objectives, the Computing with Words (CW), an approach using fuzzy logic systems in which words are used in place of numbers for computing and reasoning is applied. Firstly, the necessary information which include disturbance distance, ground class, moisture, shaking intensity, slope angle, slope height, soil depth, terrain roughness, and land-use have been collected using air photos, LANDSAT satellite images, geological and topographic maps, and site investigation of the studied region. The data is digitized and weighted using ARCGIS software. At the next step, the hazard rate and predicted areal concentrations of landslides with respect to their types are calculated using CAMEL software (Miles & Keefer, 2007). CAMEL provides an integrated framework for modeling all types of earthquake-induced landslides using geographical information system(GIS). Finally, landslides hazard map is compared to landslides triggered by Sarein earthquake.

---

The in situ measurement of discontinuity geometry of rock mass exposures is a time consuming and sometimes hazardous process. Moreover, a large proportion of the exposure is often inaccessible. Thus, a fast and safe tool is required in order to acquire the information which characterizes the geological/structural regime. Digital image processing techniques provide the necessary tools for realizing this goal. This paper presents a methodology for automated discontinuity trace detection in digital images of rock mass exposures. In this study at first based on difference in gray level discontinuities with the face, fracture traces detected in images of rock face. Then some parameters of discontinuities geometry such as spacing, linear joint density, persistence, trace angle of joints and value of RQD are obtained. The Automated discontinuity geometry analysis system including: 1- Providing a digital image from rock face 2- The pre-processing on the images 3- Detection of edge or joint traces by the canny detector 4- Description of the edges using line detector by the Hough transform 5- The joint sets estimation using fuzzy methods and 6- Description the rock mass geometry properties.

---

Landslide is one of the mass movement processes that occur in Iran and parts of the world every year. It causes huge human loss and economical damages. In order to check the stability of slopes in Kakasheraf basin, in the first step sliding areas were identified using the aerial photography and field surveys and then distribution map of landslide is provided. The impact of each of these factors which included dip, aspect, altitude, lithology, landuse and distance from the road and drainage are assessed through Arc GIS software merging the effective factors on landslide with the landslide distribution map. Then these factors were prioritized using AHP model. In this study, the fuzzy logic and density area method has been used in the Kakasheraf basin in order to identify landslide hazard zonation. The empirical probability index (EPI) has been used to assess and classify the models outputs in the landslide risk estimation.Results show that the fuzzy logic is more applicable method than density area model for mapping the landslide risk in Kakasheraf basin

---

Maximum surface settlement (MSS) is an important parameter for the design and operation of earth pressure balance (EPB) shields that should determine before operate tunneling. Artificial intelligence (AI) methods are accepted as a technology that offers an alternative way to tackle highly complex problems that can’t be modeled in mathematics. They can learn from examples and they are able to handle incomplete data and noisy. The adaptive network–based fuzzy inference system (ANFIS) and hybrid artificial neural network (ANN) with biogeography-based optimization algorithm (ANN-BBO) are kinds of AI systems that were used in this study to build a prediction model for the MSS caused by EPB shield tunneling. Two ANFIS models were implemented, ANFIS-subtractive clustering method (ANFIS-SCM) and ANFIS-fuzzy c–means clustering method (ANFIS-FCM). The estimation abilities offered using three models were presented by using field data of achieved from Bangkok Subway Project in Thailand. In these models, depth, distance from shaft, ground water level from tunnel invert, average face pressure, average penetrate rate, pitching angle, tail void grouting pressure and percent tail void grout filling were utilized as the input parameters, while the MSS was the output parameter. To compare the performance of models for MSS prediction, the coefficient of correlation (R²) and mean square error (MSE) of the models were calculated, indicating the good performance of the ANFIS-SCM model.

---

Introduction
Landslide is known as one of major natural hazards. Landslide susceptibility mapping is known as efficient approach to mitigate the future hazard and reduce the impact of landslide hazards. The main objective of this research is to apply GIS spatial decision making systems for landslide hazard mapping in the 5^th segment of Ardebil-Mianeh railroad. Evaluation of the landslide criteria mapping and their relevancy for landslide hazard can be also considered. To achieve the research objectives, an integrated approach of Fuzzy-Analytic Hierarchy Process (AHP), Fooler Hierarchical Triangle and Fuzzy logic methods were employed in GIS Environment.
Material and methods
Within this research, we also aimed to apply GIS spatial decision making systems and in particular GIS multi criteria decision analysis which are available in Arc GIS and Idrisi softwares. We have identified 8 casual factors (including: density of vegetation, land use, faults desistance, distance from rivers, distance from roads, slope, aspect, geology) based on literature review. Accordingly, these layers were prepared in GIS dataset by means of applying all GIS ready, editing and topology steps. The criterion weighting was established based F-AHP approach. The criteria weights was derived and rank of each criterion was obtained. Accordingly, the landslide susceptible zones were identified using GIS-MCDA approaches.
Results and discussion
Finally the functionality of each method was validated against known landslide locations. This step was applied to identify most efficient method for landslide mapping. According to the results and based on the values derived from Qs, P, and AUC, the accuracy of fuzzy method was accordingly about 0.33, 0.74 and 0.76, respectively. In context of Fuzz-AHP the accuracy of 1.08, 0.88 and 0.94 were obtained. While, the accuracy of Fooler Hierarchical Triangle were obtained 0.78, 0.84 and 0.91, accordingly.
Conclusion
As results indicated integration of Fuzzy-AHP represented more accurate results. Results of this research are great of important for future research in context of methodological issues for GIScience by means of identifying most efficient methods and techniques for variety of applications such landslide mapping, suitability assessment, site selection and in all for any GIS-MCDA application.

---

Introduction
Drill-bit selection is one of the most important aspects of well planning due to the bearing it can have on the overall cost of the well. Bit selection in conventional and slightly inclined wells is a very delicate and complex process. In high angle and horizontal wells it is even more difficult. Historically, drilling engineers have selected bits on the basis of what has been worked well in the area and what has been determined to have the lowest cost run from offset bit records. Often the best bit records were not available for evaluation, because the best bit may not yet have been run, may have been run by a competitor or the engineer was new to the area. As a result the bit program was generally developed by trial and error and at significant additional costs for a large number of wells. In most cases the optimum program was never reached because there was nothing to predict that a bit selection change could further reduce the cost of the well. In this study, an alternative solution approaches using the concept of the power of data mining algorithms to solve the optimum bit program for a given field is proposed.
Material and methods
It has been considered an offset well to be drilled outside the known boundaries of a known field. For this purpose, the seventh well (X-7) of the same field was used as a verification point. The data was trained using the well log and rock bit data of six wells located in the field and the real well log data of well 7 was input as unknown data. These depths are selected based on reported rock bit program. When compared to the real data, it could be observed that the models (adaptive neuro fuzzy inference system, K-nearest neighbors, decision tree, Bayesian classification theory and association rules) estimates the formation hardness accurately. This minor discrepancy was also present with the company’s suggested rock bit program, which was based on the previous wells’ rock bit data.
Results and discussion
In this paper, data mining algorithms for optimum rock bit program estimation is proposed. The accuracy and efficiency of the developed data mining algorithms (adaptive neuro fuzzy inference system, K-nearest neighbors, decision tree, Bayesian classification theory and association rules) that requires sonic and neutron log data input was tested for several real and synthetic cases. In the case of a development? well to be drilled outside the known boundaries of a field the model estimated rock bits with properties that consider the formation hardness correctly but slightly underestimated further rock bit details. The models also produced reasonable rock bit programs for an advance well to be drilled within the known boundaries of a field and a wildcat well drilled in a nearby field with similar rock properties to the training field. Thus it was concluded that the developed adaptive neuro fuzzy inference system is suitable as a front-end system for rock bit selection that could help engineers in decision-making analysis.
Conclusion
Optimum bit selection is one of the important issues in drilling engineering. Usually, optimum bit selection is determined by the lowest cost per foot and is a function of bit cost and performance as well as penetration rate. Conventional optimum rock bit selection program involves development of computer programs created from mathematical models along with information from previously drilled wells in the same area. Based on the data gathered on a daily basis for each well drilled, the optimum drilling program may be modified and revised as unexpected problems arose. The approaches in this study uses the power of data mining algorithms to solve the optimum bit selection problem. In order to achieve this goal, adaptive neuro fuzzy inference system, K-nearest neighbors, decision tree, Bayesian classification theory and association rules were developed by training the models using real rock bit data for several wells in a carbonated field. The training of the basic models involved use of both gamma ray and sonic log data. After that the models were tested using various drilling scenarios in different lithologic units. It was observed that the adaptive neuro fuzzy inference system model has provided satisfactory results.
 
 

---