İlgi alanları

Sürdürülebilir Kalkınma Amaçları

• 2
• 2
• 1
• 1
• 1

• 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
• MakaleAçık Erişim2026/r/gumushane/13615
  Integrated MCDM-based evaluation of urban intersection congestion

  Tona, Aziz Ugur; Maraş, Erdem Emin

  This study aimed to systematically evaluate the factors affecting traffic congestion at urban intersections and rank them based on congestion levels. Three multi-criteria decision-making (MCDM) techniques—Content validity method (CVM), best-worst method (BWM), and technique for order preference by similarity to ideal solutions (TOPSIS)—were used in an integrated framework. First, 15 potential congestion-related criteria were identified through literature and expert input. Using CVM, 8 key criteria were selected based on field-measured traffic data, official accident records obtained from relevant authorities, and structured on-site observational measurements. Their optimal weights were then calculated via a linear optimization model within the BWM. These weights were fed into TOPSIS for estimation and ranking of junction congestion. The examination also showed the Karayolları intersection to be the most congested (score: 0.711) and Toplu Konut Boulevard Intersection to be the least congested (score: 0.140). The findings provide essential information for decision-makers, aiding initiatives to enhance urban traffic flow by pinpointing crucial crossings and suggesting alternative geometric configurations. In addition, a sensitivity analysis across different weight conditions has confirmed the reliability and practical usefulness of the model. This proposed approach serves also as a tactical tool to prioritize interventions and improve the efficacy of transportation networks in urban environments.

  • 
  • 
  İncele
• MakaleAçık Erişim2026/r/gumushane/12301
  Assessment of Atmospheric Acidifying Pollutant Trends and Their Potential Impact on Aquatic Carbon Stability in a Semi-Arid Basin: The Case of Konya

  Tona, Aziz Uğur; Demir, Vahdettin

  The behavior of the carbon cycle within the Land-Ocean Aquatic Continuum (LOAC) is shaped not only by aquatic processes but also by chemical interactions occurring at the atmosphere–water interface. In particular, the transport of acid rain precursors such as SO2 and NOx to surface waters via deposition can alter the water’s pH balance, thereby affecting Dissolved Inorganic Carbon (DIC) fractions and CO2 emission potential. In this study, air quality measurements from three monitoring stations (Bosna, Karatay, and Meram) in Konya province of Türkiye, along with precipitation and temperature data from a representative meteorological station for the period 2021–2023, were analyzed using the Mann–Kendall Trend Test. Additionally, seasonal pH values of groundwater were examined, and their trends were compared with those of the other variables. The findings reveal striking differences on a station basis. At the Bosna station, while NO (Z = 10.80), NO2 (Z = 9.47), and NOx (Z = 10.04) showed strong increasing trends, O3 decreased significantly (Z = −15.14). At the Karatay station, significant increasing trends were detected for CO (Z = 10.01), PM10 (Z = 8.59), SO2 (Z = 5.55), and NOx (Z = 2.44), whereas O3 exhibited a negative trend (Z = −6.54). At the Meram station, a significant decrease was observed in CO (Z = −11.63), while NO2 showed an increasing trend (Z = 3.03). Analysis of meteorological series indicated no significant trend in precipitation (Z = −0.04), but a distinct increase in temperature (Z = 2.90, p < 0.01). These findings suggest that the increasing NOx load in the Konya atmosphere accelerates O3 consumption and, combined with rising temperatures, creates a potential for change in the carbon chemistry of aquatic systems. The results demonstrate that atmospheric pollutant trends constitute an indirect but significant pressure factor on the aquatic carbon cycle in semi-arid regions and highlight the necessity of integrating atmospheric processes into carbon budget analyses within the scope of LOAC.

  • 
  • 
  İncele
• MakaleAçık Erişim2025/r/gumushane/19699
  Uydu Görüntüleri Yardımıyla Burdur Gölü'nün Su Seviyesi Değişiminin Farklı Su İndeksleriyle Analizi ve Gelecek Yıllardaki Değişiminin Tahmini

  Demir, Vahdettin; Tona, Aziz Ugur; Öztaş, Ayşe; Eren, Mehmet

  Çalışmanın amacı, Burdur Gölü'nün su yüzey alanı üzerindeki mekânsal değişimleri analiz etmek ve Burdur Gölü Havzası'ndaki uzun yıllık iklim kayıtlarındaki eğilimleri inceleyerek göl yüzey alanının gelecekteki durumu hakkında tahminler yapmaktır. Bu doğrultuda, çalışma alanı için Landsat 4-5 ve Landsat 8 uydu görüntüleri kullanılarak analizler gerçekleştirilmiştir. Bu görüntülerin sınıflandırılması, Modifiye Normalleştirilmiş Fark Su İndeksi (mNDWI), Normalleştirilmiş Fark Su İndeksi (NDWI) ve Su İndeksi 2015 (WI2015) su indisleri kullanılarak yapılmıştır ve 1985-2021 yılları arasında her yıl için göl yüzey alanı verileri toplanmıştır. Çalışmanın sonuçlarına göre, Burdur Gölü'nün su alanı 1985 yılı ile 2021 yılı arasında büyük oranda (81.7-92.3 km²) azalmıştır. Yapılan doğrusal regresyon analizlerine dayanarak, gölün 2070-2080 arasında kuruyacağı tahmin edilmektedir. WI2015 yöntemi, OMH (7.0554) ve GOMH (4.1711) gibi düşük hata değerleri ile 0.9923'lük yüksek korelasyon katsayısı ile en başarılı yöntem olarak değerlendirilebilir.

  • 
  • 
  • 
  İncele