C. Gokceoglu

The aim of the present study is to prepare a landslide susceptibility map of a region of about 120 km2, between Gökcesu and Pazarköy (around Mengen, NW Turkey) at approximately 10 km north of the North Anatolian Fault Zone, where frequent landslides occur. For this purpose, mechanisms of the landslides were studied by two-dimensional stability analyses together with field observations,

Several scientific processes benefit from Citizen Science (CitSci) and VGI (Volunteered Geographical Information) with the help of mobile and geospatial technologies. Studies on landslides can also take advantage of these approaches to a great extent. However, the quality of the collected data by both approaches is often questionable, and automated procedures to check the quality are needed for this purpose. In the present study, a convolutional neural network (CNN) architecture is proposed to validate landslide photos collected by citizens or nonexperts and integrated into a mobile- and web-based GIS environment designed specifically for a landslide CitSci project. The VGG16 has been used as the base model since it allows finetuning, and high performance could be achieved by selecting the best hyper-parameters. Although the training dataset was small, the proposed CNN architecture was found to be effective as it could identify the landslide photos with 94% precision. The accuracy o...

The effective mitigation of risk sourced from mass movements requires systematic approaches. In large mapping scale or single mass movement case risk assessment can be performed based on conventional geotechnical risk assessment methods, either quantitatively or qualitatively However, in medium to large scale mass movement risk assessment, risk zoning is required which is still very difficult. The main reasons are; lack of systematic methods for mapping of hazard, which involves spatial and temporal evaluation of mass movement probability and lack of mapping methods for potential consequences or worth of losses. In this study, a risk assessment method for qualitative zoning of risk is proposed for the debris flow risk in a selected area from the Western Taurid region of Turkey, because the study area is under debris flow threat. The hazard map is prepared by subjective probability assignments of potential debris flow zones in the study region. The potential debris flow zones are obtained by processing aerial photos and field survey data in geographic information system (GIS) framework. Then a thematic hazard map is prepared in GIS with hazard levels of low, medium and high. The second component of risk, which is consequence or worth of loss mapping, is performed by initially identifying the elements at risk in the study region. The region covers two medium scale towns (Uluborlu and Senirkent) and three villages (Yassioren, Ortayazi and Garip), a forested area under protection, which contains endangered trees of Southwestern Turkey, a main road connecting town and villages to the main city of Isparta and an irrigation channel constructed by The State Hydrolic Works (DSI). The boundaries of residential area are obtained by using Google Earth Technology, and RGB true color composite of Landsat ETM

The success rate in landslide susceptibility mapping efforts increased with the advancements in machine learning algorithms and the availability of geospatial data with high spatial and temporal resolutions. Existing data-driven susceptibility mapping models are not globally applicable due to the high variability of landslide conditioning parameters and the limitations in the availability of up-to-date and accurate data. Among numerous applications, landslide susceptibility maps are essential for site selection and health monitoring of engineering structures, such as dams, for increasing their lifetime and to prevent from disastrous events caused by the damages. In this study, landslide susceptibility mapping performance of XGBoost algorithm was evaluated in a landslide-prone area in the upper basin of Ataturk Dam, which is a prime investment located in the southeast of Turkey. The study area has a size of 2718.7 km2 with an elevation difference of ca. 2000 m and contains 27 litholo...

In railway and highway projects, the expansive soils in arid and semi-arid regions are frequently encountered. Expansive clays result in serious damages on light structures. However, direct determination of swelling pressure requires time consuming test procedure and sophisticated laboratory equipment. For this reason, some prediction models for swelling properties of expansive soils have always been attractive, but these models are generally statistical based. Therefore, in this study, a simple and feasible method based on linguistic "if-then" rules is developed and proposed for the rapid determination of swelling pressure depending on Atterberg limits and clay content of soils.

Nowadays several scientific disciplines utilize Citizen Science (CitSci) as a research approach. Natural hazard research and disaster management also benefit from CitSci since people can provide geodata and the relevant attributes using their mobile devices easily and rapidly during or after an event. An earthquake, depending on its intensity, is among the highly destructive natural hazards. Coordination efforts after a severe earthquake event are vital to minimize its harmful effects and timely in-situ data are crucial for this purpose. The aim of this study is to perform a CitSci pilot study to demonstrate the usability of data obtained by volunteers (citizens) for creating earthquake iso-intensity maps in a short time. The data were collected after a 5.8 Mw Istanbul earthquake which occurred on 26 September 2019. Through the mobile app “I felt the quake”, citizen observations regarding the earthquake intensity were collected from various locations. The intensity values in the app...

Urban areas may be affected by multiple hazards, and integrated hazard susceptibility maps are needed for suitable site selection and planning. Furthermore, geological–geotechnical parameters, construction costs, and the spatial distribution of existing infrastructure should be taken into account for this purpose. Up-to-date land-use and land-cover (LULC) maps, as well as natural hazard susceptibility maps, can be frequently obtained from high-resolution satellite sensors. In this study, an integrated hazard susceptibility assessment was performed for a developing urban settlement (Mamak District of Ankara City, Turkey) considering landslide and flood potential. The flood susceptibility map of Ankara City was produced in a previous study using modified analytical hierarchical process (M-AHP) approach. The landslide susceptibility map was produced using the logistic regression technique in this study. Sentinel-2 images were employed for generating LULC data with the random forest cla...

Abstract Particularly in the last decade, landslide susceptibility and hazard maps have been used for urban planning and site selection of infrastructures. However, the use of seismic activity in susceptibility analysis is still open to discussion. For the reason, the purpose of ...

V. Palade, RJ Howlett, and LC Jain (Eds.): KES 2003, LNAI 2773, pp. 1052-1057, 2003.  Springer-Verlag Berlin Heidelberg 2003 ... A Mamdani Model to Predict the Weighted Joint Density ... Hakan A. Nefeslioglu1, Candan Gokceoglu2, Harun Sonmez2

The possibility for more confidential predictions, leaning on scientific methods and accomplishments of information technology leaves more time for the realization of logistic needs. Longstanding ambitions to acquire desired levels of efficiency within the system with minimal costs of resources, materials, energy and money are the features of executive structures of logistic systems. A successful logistic process is based on validation of technological development, indicating the need for a faster and more confidential integration of logistic systems and "instilling confidence" with military units that provide critical support (supply, transport and maintenance) will be reliably realized according to relevance and priority. Conclusions like these impose the necessity that the decision-making process of logistic organs is accessed carefully and systematically, since any wrong decision leads to a reduced state of readiness for military units. To facilitate the day-to-day operation of the Army of Serbia and the completion of both scheduled and unscheduled tasks it is necessary to satisfy the wide range of transport requirements. In this paper, the Adaptive Neuro Fuzzy Inference System (ANFIS) is described, thus making possible a strategy of coordination of transport assets to formulate an automatic control strategy. This model successfully imitates the decision-making process of the chiefs of logistic support. As a result of the research, it is shown that the suggested ANFIS, which has the ability to learn, has a possibility to imitate the decision-making process of the transport support officers and show the level of competence that is comparable with the level of their competence.

This paper presents an attenuation relationship of peak ground acceleration (PGA) derived from Turkish strong motion data for rock, soil and soft soil sites and an iso-acceleration map of Turkey based on this relationship. For the purpose, among all the three-component accessible ...

... Expert Systems with Applications Volume 37, Issue 3, 15 March 2010, Pages 2265-2272. ... is one of the most crucial rock features for underground excavation and design considerations in rock ... The purpose of the present study is to construct both a fuzzy inference system and ...

With the existing expansive clay in Ankara (Turkey) metropolitan area, some light buildings, road pavements and buried lifelines have suffered some damages due to the heave of the clay. There has been very little work concerning the stabilization of smectite rich Ankara ...

On July 13, 1995, a catastrophic debris flow event occured in Senirkent (Isparta, SW Turkey). This debris flow resulted in death of 74 people, destruction of 180 houses completely and 212 houses heavily, and the lifelines and roads of Senirkent com-pletely. The purpose of this study is to describe the mechanism and environmental impacts of the debris flow. Senirkent locates at a debris fan having an average altitude of 1000 m. This fan exists at the northern lower parts of the Beþparmak mountain. The peak altitude of this mountain is about 2400 m. The precipitation begun on July 10, 1995, however the amount and duration of precipitation of July 13, 1995 reached about 28 mm/m2 and 30 min respectively, according to the records of Senirkent Meteorology Station. According to the local eyewitnesses, most of this precipitation falled during the thirty minutes period before the catastrophe and amounted to more than 28 mm/m2 of the precipitation falled with thunder and flash of lightning on...

ABSTRACT Determination of spatial distribution of coal quality parameters can ease management of the operations in coal mines. In the present study, in order to provide guidance for the excavations, Can coal mine production map showing regions having suitable coal parameters as feed coals for a power plant and also for public sale, was prepared using adaptive neuro-fuzzy inference system (ANFIS) tool. Statistical relationships among calorific value, ash content and sulphur content were evaluated using the data obtained from boreholes opened in the mine between 2006 and 2009. According to the obtained production map, coals of Can mine are not suitable for public sale because of their high sulphur content and hence they should be blended with low sulphur coals to meet the requirements, before sale.

Soil degradation and desertification processes in the Mediterranean basin reflect the interplay between environmental and socioeconomic drivers. An approach to evaluate comparatively the multiple relationships between biophysical variables and socioeconomic factors is illustrated in the present study using the data collected from 586 field sites located in five Mediterranean areas (Spain, Greece, Turkey, Tunisia and Morocco). A total of 47 variables were chosen to illustrate land-use, farm characteristics, population pressure, tourism development, rainfall regime, water availability, soil properties and vegetation cover, among others. A data mining approach incorporating non-parametric inference, principal component analysis and hierarchical clustering was developed to identify candidate syndromes of soil degradation and desertification risk. While field sites in the same study area showed a substantial similarity, the multivariate relationship among variables diverged among study areas. Data mining techniques proved to be a practical tool to identify spatial determinants of soil degradation and desertification risk. Our findings identify the contrasting spatial patterns for biophysical and socioeconomic variables, in turn associated with different responses to land degradation.

Determination of collapse potential of collapsible grounds is an important problem for civil engineers. However, this requires extensive field and laboratory works. For this reason, prediction tools for this purpose are highly attractive for engineers. Considering this ...

On May 21, 1998, a catastrophic mass movement stroke the disseminated Dağköy settlement in the West Black Sea Region and caused demolishment of several tens of houses and death of many domestic animals. The mass movement occurred on a gentle slope with relatively dense vegetation cover after the 3-day lasted heavy rainfall. The ground material, c.a. 0,6 km 3 of volume that composed of marl and quartzite bedrock and overlying several metres thick soil profile, was removed 600 m downslope, blocked the nearby rivercourse and produced an artificial lake. The analysis of the rainfall data for long and short periods (daily and hourly) clearly indicate that the heavy rainfall was the triggering factor for the landslide. The topography, dip of marl bedding, dense high trees and thick soil horizon developed on top of the marly ground contributed to the event in various degrees. The eyewithness of the villagers and subsequent field observations show that the Dağköy landslide is complex in nature in terms of material transport and deposition. Near the crown, dismembering of the ground into slope-parallel slices and their domino-style sliding and rotation are the dominant processes. Within the central part of the accumulation zone, several enormous (with respect to landslide scale) ground blocks without any internal deformation are embedded in the muddy debris material. The highly plastic debris material is mostly clay and silt grade with lesser amount of disseminated gravels. Restoration of the landslide depicts that these large terrains were transported several hundred metres downslope within the mudflow in a rotational manner. The fringes of the accumulation zone were marked by gravel to boulder-sized angular quartzite blocks without binding fine-grained material, which is a fact sugesting another particular process, the grain flow. As the main causes of this, the mechanic fragmentation in the basal part of the landslide under the thick moving material and a pressure relief towards the fringes were suggested. Lastly, the accumulation zone was slightly gullied by subsequent low viscosity mudflows and fluid flows that deposited mud-sized fans in the very distal reach. As a complex failure and mass movement case, the Dağköy landslide was restored by means of the morphology produced, the nature and distribution of the accumulated facies, and eyewithnes of the villagers. It is concluded that the varying transportation processes from debris flow to massive sliding were determined by the initial conditions such as water content and strength of the material. The dynamic conditions such as shape, velocity and stress distribution of the failure, grinding and mixing of the material also should have played significant roles in the formation and distribution of the processes. Ref: T7-1

The term landslide includes a wide range of ground movement, such as slides, falls, flows etc. mainly based on gravity with the aid of many conditioning and triggering factors. Particularly in the last two decades, there is an increasing international interest on the landslide susceptibil-ity, hazard or risk assessments (Aleotti and Chowdhury, 1999). However, several methods and techniques have been proposed and tested to evaluate landslide assessments, but no general agreement has yet been reached about the methods used to produce such maps (Guzzetti et al., 2000). One of the important stages for the landslide susceptibility mapping is the preparation of the landslide inventory maps. In addition, analyzing the factors conditioning the landslides is also vital. In the present study, it is aimed to evaluate the landslide suscepti-bility using the most relevant conditioning parameters on the landslide occurrence in a se-lected landslide prone area in the West Black Sea region of Turkey. For this purpose, a de-tailed landslide inventory map is prepared and the fuzzy relations are considered to select the most relevant parameters. Results are compared with the factor analysis. Finally, landslide susceptibility maps of the study area are produced using two techniques and performances of the produced maps are discussed.