Sürdürülebilir Kalkınma Amaçları

• 1
• 1
• 1

• MakaleYalnız künye2026/r/gumushane/13834
  Machine learning-based multi-class classification of rock mass permeability using integrated geotechnical and geophysical parameters

  Sari, Mahmut; Alemdag, Selcuk; Melek, Mesut; Seren, Aysel

  In engineering applications, machine learning (ML) provides a promising approach when direct characterization of subsurface properties is challenging, time-consuming, and costly. This study developed a multi-class ML framework for classifying rock mass permeability based on Lugeon values using 86 observations from drilling and geophysical investigations at the Kırklartepe dam site in Bayburt, Türkiye. Seven predictors were considered: depth, Rock Quality Designation (RQD), joint frequency, Schmidt hammer hardness, P-wave velocity, S-wave velocity, and electrical resistivity. The observations were assigned to four permeability classes: very low, low, moderate, and high. Six classifiers were evaluated: Polynomial Kernel Support Vector Machine (P-SVM), Linear Discriminant Analysis, k-Nearest Neighbors (k-NN), AdaBoostM2, Bagged Trees, and Radial Basis Function SVM. Sequential Forward Feature Selection and Leave-One-Out Cross-Validation were used for feature selection and model evaluation, respectively. Robustness was further assessed using bootstrap confidence intervals, class-imbalance treatments, feature-selection stability, and learning curves. Among the baseline models, P-SVM using all seven predictors achieved the highest accuracy (79.07%), with a macro-F1 of 0.774 and the lowest Golden Distance (GD = 0.4372). When balanced class-wise performance was prioritized, k-NN with in-fold SMOTE achieved the lowest overall GD (0.4126) and a macro-F1 of 0.777. S-wave velocity and electrical resistivity were the most influential predictors. Overall, the findings demonstrate that the proposed framework effectively integrates geotechnical and geophysical data for rock mass permeability classification, providing a robust, data-driven decision-support approach that supports subsurface characterization and complements conventional permeability assessment in engineering applications.

  İncele
• MakaleYalnız künye2026/r/gumushane/13804
  Very fast Kolmogorov-Arnold network for landslide susceptibility prediction

  Günen, Mehmet Akif; Tona, Aziz Uğur

  Landslides represent critical geological events causing loss of life and property. Prediction of landslide susceptibility is essential for risk reduction and decision-making. XGBoost, LightGBM, NGBoost, CatBoost, MLP, and FastKAN were used to predict landslide susceptibility in Gümüşhane, Türkiye, a region with complex topographic and geological structures. 20 factors were used: 9 topographical, 3 hydrological, 4 climatic, 2 geological, and 2 environmental and infrastructure-related factors. Model performance was assessed using Accuracy, Precision, Recall, and F-Score, with SHAP analysis showing feature contributions. A multicollinearity analysis was used to determine the final feature set. Topographical variables (Aspect, Slope) showed lower impacts, while geological and environmental factors (Lithology, Distance to Fault) demonstrated moderate influence across models. For FastKAN, DEM, precipitation, and distance to fault were key factors, while for boosting methods, GHI, Tmax, and DEM were most significant. FastKAN achieved the highest performance under the internal pixel-wise evaluation scheme, with an accuracy of 96.54%, followed by XGBoost at 95.56%. McNemar’s statistical test showed no significant difference between NGBoost and MLP. Post-inventory landslide events observed in 2025 and 2026 were spatially consistent with high and very high susceptibility zones, providing a qualitative consistency check rather than rigorous independent quantitative validation.

  İncele
• MakaleYalnız künye2025/r/gumushane/14283
  Discontinuities identification from rock outcrop using auto-encoder and point clouds

  Günen, Mehmet Akif; Aliyazıcıoğlu, Şener

  Rock slopes and geotechnical structures often exhibit discontinuity planes, which significantly influence their mechanical behavior and stability. The precise identification of these discontinuities is critical for ensuring the safety and cost-effectiveness of construction projects. However, previous methods are often limited by subjectivity, low automation, and challenges in inaccessible or hazardous environments. This study introduces a novel seven-step approach utilizing auto-encoders for estimating the orientation parameters of individual discontinuity sets from point cloud data. The steps include: data collection, filtering point clouds to eliminate outliers, determining neighborhood size, feature extraction, training a stacked auto-encoder for feature learning, estimating discontinuity sets using density-based clustering, and calculating individual discontinuities through the least squares method for orientation parameter estimation. In addition, the methodology incorporates a planarity-based approach for estimating neighborhood size. The statistical performance has been validated through evaluations in two real case studies and one synthetic case study. The classification achieves an accuracy exceeding 95%, highlighting the high efficacy of the approach. Results for orientation parameter estimation show consistency with existing methods and in situ measurements, with average orientation values for discontinuities within 5 degrees for individual sets. This framework represents a considerable advancement in rock discontinuity analysis, offering a robust and automated solution that is particularly effective in hazardous and hard-to-reach areas.

  İncele
• MakaleYalnız künye2022/r/gumushane/14884
  GIS-based determination of potential instabilities and source rock areas on the Torul-Kürtün (Gümüşhane) motorway, rockfall, and protection structure analyses

  Alemdag, Selcuk; Bostanci, Hasan Tahsin; Gacener, Elif

  The Torul-Kürtün-Tirebolu motorway, one of the alternative routes for access between the Eastern Anatolia Region and the Black Sea Region, has an important traffic potential in this respect. However, rockfall events that occur frequently in almost every season especially in the part of the route between Torul and Kürtün may occasionally cause loss of life and property and lead to disruption in transportation in a much more common way. Departing from this point, the parts of the motorway that pose a greater threat in terms of slope instability and rockfall potential were selected as the study area. Instability maps produced by the kinematic analysis results showed that the probability of toppling type failure in the study area was quite higher, while the general results were as follows: the probability of toppling type failure was found in 204 different locations and approximately 97,900 m2 of area. Taking account of geographic information system (GIS)–based final instability maps, profile lines were determined for potential rockfalls in the instability-intense source rock areas. The profile lines which were determined were analyzed two-dimensionally in the RocFall 7.0 computer program. The rockfall analyses revealed that the rolling rock blocks in the section SP7 shall remain on the surface of the slope, while the rock blocks in other sections shall reach the road route. The application of barrier types determined by barrier sensitivity analysis on profile lines will minimize or completely prevent potential hazards.

  • 
  • 
  İncele
• MakaleAçık Erişim2022/r/gumushane/14466
  Determination of rock quality designation (RQD) in metamorphic rocks: a case study (Bayburt-Kırklartepe Dam)

  Alemdag, Selcuk; Sari, Mahmut; Seren, Aysel

  The role and importance of rock mass classification systems from past to present in engineering designs are indisputable. Therefore, the correct estimation of the parameters that make up these systems is essential in terms of reliability, time, and economy. One of the crucial parameters commonly used in rock mass classification is the rock quality designation (RQD). This study aimed to indirectly estimate the RQD value determined from the core samples obtained from the exploration drillings. In this context, P wave velocity (Vp) was obtained by seismic refraction tomography (SRT) from the geophysical measurements applied in the metamorphic rock mass, and the discontinuity frequency parameter was obtained from the line survey studies carried out on the rock mass. What determined RQD values with the help of simple regression analyzes and empirical equations with high estimation capacity using Vp and discontinuity frequency parameters were obtained without drilling in the rock mass. Accordingly, the performance indexes of the equations produced by different researchers and the equations produced in this study were evaluated in determining the RQD parameter. In the generated equations, the highest coefficient of determination value depending on joint frequency and Vp wave velocity with RQD was calculated as R2 = 0.89 and R2 = 0.82, respectively. When the produced equations are evaluated according to the performance indexes, it is seen that the empirical equations obtained by previous studies have the highest root mean square error (RMSE) and values account for (VAF) values compared to the other equations and have very high estimation capacities. Thanks to the equations with high estimation capacity, the RQD value was determined depending on the joint density and Vp speeds.

  İncele
• MakaleAçık Erişim2016/r/gumushane/12931
  Stability assessment of high-steep cut slope debris on a landslide (Gumushane, NE Turkey)

  Kaya, Ayberk; Alemdağ, Selçuk; Dağ, Serhat; Gürocak, Zülfü

  The objective of this study was to examine the effects on the stability of slope debris of planned slope excavations around the vicinity of Gumushane Imam-Hatip High School in NE Turkey. To assess the geotechnical properties of slope debris along the determined cross-sections, four exploration boreholes with a total length of 100 m were drilled and undisturbed soil samples were collected. Slope debris is composed of two soil zones and its depth varies between 15 m and 21 m. It was determined from the experimental results that the soil class of the upper zone is CL (low plasticity clay) and CH (high plasticity clay) whereas the soil class of the lower zone is SC (clayey sand) and GC (clayey gravel). Peak cohesions of the upper and lower zones were 26.3 kPa and 10.2 kPa, and their peak internal friction angles were 16° and 24°, respectively. Limit equilibrium (LE) analyses for the slopes were evaluated using Slide v5.0 software for the pre-excavation, post-excavation, and supported cases. The results of LE analyses showed the existence of a landslide along the SW direction; the landslide would extend to cover the whole region if the excavation were to be performed without applying engineering measures. Finally, the precautions to be taken were determined and stability analyses for the supported case were evaluated. These analyses showed that the active lateral forces applied by the proposed retaining walls to the cut slope should be 8325 and 3103 kN, respectively.

  İncele
• MakaleAçık Erişim2012/r/gumushane/15640
  Assessment of permeability and injection depth at the Atasu dam site (Turkey) based on experimental and numerical analyses

  Gurocak, Zulfu; Alemdag, Selcuk

  This study was performed in order to evaluate the permeability of the basalts and pyroclastics and the maximum depth of grout injection at the Atasu dam site, Turkey, using the equations of Kiraly and Hoek and Bray based on values obtained from Lugeon tests. In order to evaluate maximum discharge values and depth of injection, seepage analyses were performed using the finite element technique for each 10 m up to 100 m. The results indicate that to establish an impermeable zone at the dam site, the depth of injection should be taken as 50 m for the left and right slopes and 40 m for the river bed.

  • 
  İncele
• MakaleYalnız künye2011/r/gumushane/15434
  The Sumela Monastery slope in Maçka, Trabzon, Northeast Turkey: Rock mass properties and stability assessment

  Gelişli, Kenan; Şeren, Aysel; Babacan, Ali Erden; Çataklı, Aycan; Ersoy, Hakan; Kandemir, Raif

  In 2001, rock falls occurred on the southern slope of the Sumela Monastery, which was built on a cliff in Trabzon, north east Turkey, and is visited by many tourists. Considering the steepness of the slope and difficulty of access, rock classifications were made based on seismic wave velocity, rock mass quality (Q), rock quality designation (RQD) and rock mass rating (RMR). The results indicated extremely poor to very poor rock in the cracked, fractured and weathered parts and poor to fair rock in the intact parts of the monastery slope. As a consequence, rock fall, slide and rolling may occur from time to time. These constitute a hazard to the facilities of the monastery and access paths. It is recommended that cracked areas are strengthened with cement-based materials, that accumulated rocks are removed, and that retaining walls are constructed on solid rock around the unstable rock blocks.

  İncele
• MakaleYalnız künye2008/r/gumushane/15043
  An application of the interaction matrices method for slope failure susceptibility zoning: Dogankent settlement area (Giresun, NE Turkey)

  Ceryan, Nurcihan; Ceryan, Sener

  Large-scale instability phenomena frequently occur in slopes in such geologically complex areas as Dogankent in NE Turkey. This study presents an application of the interaction matrices (IM) methodology, as a semi-qualitative method sensitive to large-scale slope instability. For both rock and soil slopes, the main interactive factors were distance from faults, degree of weathering and slope angle. Using IM, a slope failure susceptibility map was created for the Dogankent area and checked again field evidence. The results indicated that IM could be a useful method for slope stability assessment.

  İncele
• MakaleYalnız künye2008/r/gumushane/14067
  Influence of weathering on the engineering properties of Harsit granitic rocks (NE Turkey)

  Ceryan, Sener; Tudes, Sule; Ceryan, Nurcihan

  Weathering and hydrothermal alteration of the granitic rocks in the Eastern Black Sea Region (NE Turkey) are important phenomena affecting the engineering projects in the region. The study investigated the probable paths of rock-forming mineral transformations due to weathering in the Harsit granitoid rocks, the changes of the major oxides as a consequence of weathering and the effects of weathering on the engineering properties. To identify the changes in the major oxides, the volume concentrations were considered in relation to the dry density. Chemical leaching during weathering was shown to be significant in changing the minerals. It was concluded that the engineering properties of the weathered granitic rocks can be most reliably predicted by P-wave velocity.

  İncele