Browsing by Author "Ozvan, Hande"

Now showing 1 - 2 of 2

A Comparative Analysis of Land Use Classification Methods Using Landsat and Ancillary Data in Urban Mapping
(Springer Heidelberg, 2025) Ozvan, Hande; Satir, Onur
This study compares the performance of parametric (LDA) and non-parametric (CTA, RF, SVM) classification algorithms in mapping urban and surrounding land cover types in Balikesir, T & uuml;rkiye, using Landsat 8 OLI/TIRS imagery and ancillary data. Seven land cover classes-built-up areas, roads, water bodies, forests, meadows, agriculture, and barren land-were classified based on 2,480 ground truth points. The Random Forest (RF) classifier achieved the highest overall classification accuracy (Kappa = 0.90) and an F1-score of 0.99 for the built-up class, outperforming LDA (Kappa = 0.86), SVM (0.83), and CTA (0.78). The integration of the Digital Elevation Model (DEM) with spectral wavebands improved classification performance, particularly in distinguishing urban areas from spectrally similar classes such as barren land and roads. In contrast, additional indices like NDBI and SAVI provided only marginal improvements. Results suggest that incorporating DEM enhances model robustness and spatial accuracy, while the sole use of ancillary indices may introduce redundancy. The study underscores the importance of selecting appropriate classifier-data combinations and highlights the utility of the F1-score, alongside Kappa, for evaluating class-specific accuracy. This research contributes to urban land cover mapping by offering a comparative framework that integrates ancillary variables, helping to refine classification strategies in heterogeneous landscapes.
Impact of Pandemic Measures on Air Quality and Meteorological Parameters During the COVID-19 Spread in the Euphrates Basin, Türkiye
(Springer, 2025) Ozvan, Hande; Stein, Alfred; Aslantas, Pinar; Osei, Frank
This study investigates the impact of COVID-19 pandemic measures on air quality and their relationship with meteorological parameters in the Euphrates Basin, T & uuml;rkiye. It provides a basin-specific analysis of air quality trends during the pandemic, exploring the interplay between meteorological variables and air quality indicators. The analysis examines the COVID-19 rates across 15 provinces about air quality indicators PM10 and SO2 and includes weekly average temperature (Tw) and weekly total precipitation (Pw). Three periods were defined: before the pandemic (Period 1), during the pandemic (Period 2), and after the pandemic (Period 3), each spanning 77 weeks. The spatial-temporal changes in PM10 and SO2 concerning Pw and Tw were analyzed during Periods 1 and 3, while in Period 2, they were related to the COVID-19 rates. The results of this study show that the COVID-19 outbreak was more intense in large cities, while the opposite was true in small cities. Using the Multivariate Auto-Regressive State-Space (MARSS) model, we found that PM10 and SO2 significantly influenced the COVID-19 rate during the second and third waves of the pandemic, most likely due to the decreased social and urban activities during the quarantine period. Moreover, the study identified noteworthy, though statistically non-significant, associations between population density and COVID-19 transmission patterns. These preliminary findings warrant further validation through future, more granular investigations.