Artificial neural networks approach for zeta potential of Montmorillonite in the presence of different cations     

Yeliz Yukselen  Yusuf Erzin 《Environmental Geology》2008,54(5):1059-1066

In this study, the zeta potential of montmorillonite in the presence of different chemical solutions was modeled by means of artificial neural networks (ANNs). Zeta potential of the montmorillonite was measured in the presence of salt cations, Na⁺, Li⁺ and Ca²⁺ and metals Zn²⁺, Pb²⁺, Cu²⁺, and Al³⁺ at different pH values, and observed values pointed to a different behavior for this mineral in the presence of salt and heavy metal cations. Artificial neural networks were successfully developed for the prediction of the zeta potential of montmorillonite in the presence of salt and heavy metal cations at different pH values and ionic strengths. Resulting zeta potential of montmorillonite shows different behavior in the presence of salt and heavy metal cations, and two ANN models were developed in order to be compared with experimental results. The ANNs results were found to be close to experimentally measured zeta potential values. The performance indices such as coefficient of determination, root mean square error, mean absolute error, and variance account for were used to control the performance of the prediction capacity of the models developed in this study. These indices obtained make it clear that the predictive models constructed are quite powerful. The constructed ANN models exhibited a high performance according to the performance indices. This performance has also shown that the ANNs seem to be a useful tool to minimize the uncertainties encountered during the soil engineering projects. For this reason, the use of ANNs may provide new approaches and methodologies.  相似文献   

Preliminary investigation of underground settlements of Nevşehir Castle region using 2.5-D electrical resistivity tomography: Cappadocia,Turkey     

Nart Coşkun  Özcan Çakır  Murat Erduran  Yusuf Arif Kutlu  Ali Yalçın 《Arabian Journal of Geosciences》2016,9(18):717

The Nev?ehir Castle region located in the middle of Cappadocia with approximately cone shape is investigated for the existence of an underground city using the geophysical method of electrical resistivity tomography. Underground cities are commonly known to exist in Cappadocia. The current study has obtained important clues that there may be another one under the Nev?ehir Castle region. Several 2.5-D resistivity profiles totaling approximately 4 km in length surrounding the Nev?ehir Castle are measured to determine the distribution of electrical resistivities under the study area. Several high resistivity anomalies with a depth range 8–20 m are discovered to associate with a systematic void structure beneath the Nev?ehir Castle. Because of the high-resolution resistivity measurement system currently employed, we were able to isolate the void anomalies from the embedding structure. Using 3-D visualization techniques, we show the extension of the void structure under the measured profiles.  相似文献   

Finger prints of the formation of geothermal springs on the granitoids: Beypazarı–Ankara, Turkey     

Sezen Diker  Mehmet Çelik  Yusuf Kağan Kadıoğlu 《Environmental Geology》2006,51(3):365-375

The Beypazarı granitoid in central Anatolia was emplaced during the Late Cretaceous and it is partly covered with Early Miocene–Quaternary sedimentary and volcanic units. Compression and tension regimes of the Beypazarı granitoid emplacing along the Sakarya River were evaluated considering the kinematical characteristics of discontinuities on granitoids, petrographic/geochemical works, formation of geothermal spring and irregularities in topographic structure. It was determined that the Beypazarı granitoid was witnessed with NE–SW compressional stress and NW–SE extensional stress which resulted in the formation of the Kapullu normal fault with N55–72°E, 78°SE crossing the Kapullu spring site. There are also several other probable normal faults around this fault in the Sakarya River basin. The results of the geochemical studies reveal that SiO₂, Na₂O, Al₂O_3, CaO and K₂O as a major oxide and As, Rb, Sr, Th and U as trace elements are decreased away from the Kapullu bath spring. On the other hand, the ratio of Fe₂O₃ and MgO as major oxide and Y as a trace element with the lost on ignition (LOI) are increased away from the Kapullu fault. Regard as the regional plate tectonism, there is a consistency between the direction of compression in the Beypazarı granitoid and that developed by the southwesterly movement of the Anatolian plate.  相似文献   

Spatial prediction of landslide susceptibility in western Serbia using hybrid support vector regression (SVR) with GWO,BAT and COA algorithms     

Abdul-Lateef Balogun  Fatemeh Rezaie  Quoc Bao Pham  Ljubomir Gigović  Siniša Drobnjak  Yusuf A. Aina  Mahdi Panahi  Shamsudeen Temitope Yekeen  Saro Lee 《地学前缘(英文版)》2021,12(3):101104

In this study, we developed multiple hybrid machine-learning models to address parameter optimization limitations and enhance the spatial prediction of landslide susceptibility models. We created a geographic information system database, and our analysis results were used to prepare a landslide inventory map containing 359 landslide events identified from Google Earth, aerial photographs, and other validated sources. A support vector regression (SVR) machine-learning model was used to divide the landslide inventory into training (70%) and testing (30%) datasets. The landslide susceptibility map was produced using 14 causative factors. We applied the established gray wolf optimization (GWO) algorithm, bat algorithm (BA), and cuckoo optimization algorithm (COA) to fine-tune the parameters of the SVR model to improve its predictive accuracy. The resultant hybrid models, SVR-GWO, SVR-BA, and SVR-COA, were validated in terms of the area under curve (AUC) and root mean square error (RMSE). The AUC values for the SVR-GWO (0.733), SVR-BA (0.724), and SVR-COA (0.738) models indicate their good prediction rates for landslide susceptibility modeling. SVR-COA had the greatest accuracy, with an RMSE of 0.21687, and SVR-BA had the least accuracy, with an RMSE of 0.23046. The three optimized hybrid models outperformed the SVR model (AUC = 0.704, RMSE = 0.26689), confirming the ability of metaheuristic algorithms to improve model performance.  相似文献   

Analysis of largest earthquakes in Turkey and its vicinity by application of the Gumbel III distribution     

Theodoros M. Tsapanos  Yusuf Bayrak  Hakan Cinar  George Ch. Koravos  Erdem Bayrak  Eleni E. Kalogirou  Athina V. Tsapanou  Georgia E. Vougiouka 《Acta Geophysica》2014,62(1):59-82

A study of the spatial distribution of seismicity parameters is undertaken along Turkey and its vicinity, using the Gumbel’s third asymptotic distribution of extreme values (GIII). The data set used spans of 111 years (1900–2010). The seismicity of the whole region is subdivided into equal area mesh of 1° lat. × 1° long. Various seismicity parameters examined, resulted from the application of the GIII method. The results show a quite good correlation between the seismicity parameters and the tectonic regime of the studied area. For instance high values concentrated around North Anatolian Fault. The x ²-test is applied throughout the whole process and in every stage of GIII, in order to check the accuracy of the obtained results. The spatial distribution of upper-bound (ω) formed a W-shape pattern, which shows the difference in the mechanical structure of the materials in the examined area.  相似文献   

Vibration characteristics of a suspension bridge under traffic and no traffic conditions     

Nurdan Memişoglu Apaydın  Yavuz Kaya  Erdal Şafak  Hakan Alçık 《地震工程与结构动力学》2012,41(12):1717-1723

This paper presents the variations of vibration under different traffic conditions on the Fatih Sultan Mehmet suspension bridge in Istanbul, Turkey.The main intention is to determine the vibration amplifications under heavy-traffic as opposed to no-traffic conditions. This is the first study in this particular area that has been performed on this bridge, over which an average of 200,000 cars pass daily. Two full-scale ambient vibration surveys were carried out on two different days to determine the response of the bridge to diverse traffic conditions. Initial measurements were taken as the bridge experienced heavy stress conditions caused by rush-hour traffic. Secondary measurements were recorded after closing the bridge to traffic. The data were analyzed to gauge the vibration effects of heavy-traffic conditions on the bridge and to determine the effects of different traffic conditions on the free vibration characteristics of the bridge. The analyses were performed utilizing different amplification methods. Results show that there are important differences in the amplifications of the vibration amplitudes. Especially heavy-traffic on the bridge causes the vibration response of the bridge to be intensified in comparison to no-traffic conditions. Additionally, predominant frequencies are shifted as a direct result of traffic load acting on the bridge. Even more importantly and is probably analogous for all long-span bridges, is the fact that any movement causing vibration on the bridge is carried and amplified along its length. These significant amplifications indicate the important effect of varying traffic loads and how the bridge responds to the diverse movements it experiences. Copyright © 2011 John Wiley & Sons, Ltd.  相似文献   

Microbial Quality in Coastal Waters of Dardanelles in Relation to the Pollution Sources and Transport Pathways     

Cafer Turkmen  Onder Ayyildiz  Mehmet Akbulut  Hasan Kaya 《洁净——土壤、空气、水》2012,40(12):1320-1325

The coastal water quality of Çanakkale Dardanelles (Turkey) was assessed based on bacteriological data and physical–chemical parameters. Total coliform (TC), fecal coliform (FC), and enterococci (ENT) bacteria along with physicochemical parameters were measured monthly up to a year at 12 different sampling sites located through both coastal lines of the strait. The fecal bacteria were abounded at several sampling sites such as B1, B3, G3, and G4 due to direct wastewater discharges and septic leakages or overloading. Storm water runoff and sediment resuspension were important pathways for the transport of coliform and ENT bacteria to the Dardanelles, as the region receives high precipitation and strong winds for most part of the year. The values of pH, temperature, and salinity were in typical ranges for the studied area. The microbiological and physicochemical data were correlated individually and in combination. The best fit correlations for bacterial data were attained between TC and FC or TC and ENT (R = 0.67 or ?0.68), while those for the combined data were obtained for TC with temperature (R = 0.94) and TC with salinity (R = ? 0.70).  相似文献   

Real-time analysis and interpretation of continuous data from structural health monitoring (SHM) systems   总被引：1，自引：1，他引：0  

Yavuz Kaya  Erdal Safak 《Bulletin of Earthquake Engineering》2015,13(3):917-934

  相似文献   

The Determination of Earthquake Hazard Parameters Deduced from Bayesian Approach for Different Seismic Source Regions of Western Anatolia   总被引：1，自引：0，他引：1  

Yusuf Bayrak  Tuğba Türker 《Pure and Applied Geophysics》2016,173(1):205-220

  相似文献   

Recovery of Cr(VI) by using a novel calix[4]arene polymeric membrane with modified graphene quantum dots     

C. Onaç  A. Kaya  H. K. Alpoğuz  M. L. Yola  S. Eriskin  N. Atar  İ. Şener 《International Journal of Environmental Science and Technology》2017,14(11):2423-2434

  相似文献