Kutalmis Gumus

Dr. Kutalmis Gumus

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 June 2025 in Turkish Journal of Remote Sensing
Verified
Journal Article
Open access
PDF file
MGMünevver Gizem Gümüş
Münevver Gizem Gümüş
KGKutalmis Gumus
Kutalmis Gumus
The expansion of impervious surfaces, reduction of vegetation cover, and heat-retaining properties of artificial materials intensify the Urban Heat Island (UHI) effect, leading to higher surface temperatures in urban areas compared to rural surroundings. This phenomenon increases energy demand, interacts with climate change, and negatively impacts public health. This study investigates the spatial and temporal changes in vegetation, impervious surface density, and land surface temperature (LST) in Niğde, Türkiye, between 2013 and 2024. NDVI (Normalized Difference Vegetation Index), NDBI (Normalized Difference Built-up Index), and LST were derived from Landsat 8 OLI/TIRS satellite imagery and analyzed using Google Earth Engine (GEE) and ArcGIS 10.8. Index values were extracted from 500 randomly distributed points. Data normality was assessed using Kolmogorov-Smirnov and Shapiro-Wilk tests. Paired sample t-tests and Wilcoxon signed-rank tests were used to evaluate temporal differences, while Pearson, Spearman's rho, and Kendall's tau-b correlation coefficients were used to determine the level of relationship between variables. Results show no significant change in NDVI (p > 0.05), but statistically significant increases in both NDBI and LST (p < 0.05). A strong negative correlation was observed between NDVI and NDBI (r = -0.91), and a positive correlation between NDBI and LST (r = 0.39). Between 2013 and 2024, impervious surfaces expanded by 59.63% (from 14.02 km² to 22.38 km²), while dense vegetation areas declined by 50%. These findings confirm that urbanization has led to vegetation loss and increased surface temperatures. The study offers valuable insights into the UHI effect using remote sensing and statistical analysis and contributes to sustainable urban planning and climate adaptation strategies.

30 December 2020 in Aksaray University Journal of Science and Engineering
Verified
Journal Article
Open access
ABAslı Bozdağ
Aslı Bozdağ
MGMünevver Gizem Gümüş
Münevver Gizem Gümüş
KGKutalmis Gumus
Kutalmis Gumus
SDSüleyman savaş Durduran
Süleyman savaş Durduran
Spatial legibility is related to the obtainment of spatial information (2D and 3D) that is in the urban area according to the characteristics of the observer who perceives this space. The aim of this research is to examine the spatial legibility of the campus of Selçuk University which is located in Konya province according to the characteristics of the area and the observer. The spatial characteristics of the application area were determined with the analyzes that were conducted with the help of Geographical Information Systems (GIS) and the characteristics of the observer were determined with analyzes that reveal the understanding of the observer to the area (Lynch analysis, questionnaire application and statistical evaluations). When the conducted spatial analyzes and statistical evaluations are examined, it was determined that the spatial legibility of the campus has a statistically significant relationship with the characteristics of the area and the observer.

25 November 2025 in Modeling Earth Systems and Environment
Verified
Journal Article
Closed access
PDF file
ÇIÇiftçi
Çiftçi
HÇHasan Çağatay
Hasan Çağatay
GÜGümüş
Gümüş
MGMünevver Gizem Gümüş
Münevver Gizem Gümüş
KGKutalmis Gumus
Kutalmis Gumus

19 May 2023 in Systems
Verified
Journal Article
Open access
PDF file
Alper SenAlper Sen
Alper Sen
KGKutalmis Gumus
Kutalmis Gumus
Digital Elevation Models (DEMs) are commonly used for environment, engineering, and architecture-related studies. One of the most important factors for the accuracy of DEM generation is the process of spatial interpolation, which is used for estimating the height values of the grid cells. The use of machine learning methods, such as artificial neural networks for spatial interpolation, contributes to spatial interpolation with more accuracy. In this study, the performances of FBNN interpolation based on different parameters such as the number of hidden layers and neurons, epoch number, processing time, and training functions (gradient optimization algorithms) were compared, and the differences were evaluated statistically using an analysis of variance (ANOVA) test. This research offers significant insights into the optimization of neural network gradients, with a particular focus on spatial interpolation. The accuracy of the Levenberg–Marquardt training function was the best, whereas the most significantly different training functions, gradient descent backpropagation and gradient descent with momentum and adaptive learning rule backpropagation, were the worst. Thus, this study contributes to the investigation of parameter selection of ANN for spatial interpolation in DEM height estimation for different terrain types and point distributions.

31 January 2017 in Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi
Verified
Journal Article
Open access
PDF file
KGKutalmis Gumus
Kutalmis Gumus
AŞAlper Şen
Alper Şen
En tr    The accuracy of digital elevation models which are constituted in accordance with different parameters, are quite important in terms of spatial analysis and representation of land topography familiar to reality. The purpose of this study is to research the positional accuracy of different interpolation methods (Inverse Distance Weighted (IDW), Ordinary Kriging (OK), Modified Shepard's (MS), Multiquadric Radial Basis Function (MRBF) and Triangulation with Linear (TWL)) statistically which are used for forming digital elevation models in terms of different point densities (100% and 50%), different point distributions (curvature, grid, uniform and random), and land types with different topography (flat, hilly, mountainous). With this aim, analysis of variance (ANOVA) was implemented. For sub-groups obtained from point densities, point distributions and land types, it was sought statistically with ANOVA whether there was a significant difference amongst the positional accuracies obtained from interpolation methods. The accuracy reaching from decimeters to meters was obtained from especially mountainous and hilly land types. The land topography affects the accuracy of formed digital elevation models. The results obtained from all (100%) data sets were always found better than 50% data sets. Generally speaking, similar properties resulted for curvature and uniform distributions in different point distributions (50%), and better accuracies were obtained considering other distributions. Grid distribution resulted worse than other distributions. OK and MRBF interpolation methods showed similar properties for different land types and point distributions. The accuracy of these methods resulted better considering other methods. The accuracy obtained from IDW method for all three land types was less than other methods. The accuracy obtained from MS and TWL methods was similar. The interpolation methods used in this study were ordered in terms of obtained accuracy from the best to the worst as MRBF, OK, MS, TWL and IDW. Farklı parametrelere göre oluşturulan sayısal yükseklik modellerinin doğruluğu, birçok uygulama alanında mekânsal analiz ve arazi topografyasının gerçeğe yakın şekilde gösterimi açısından oldukça önemlidir. Bu çalışmanın amacı, sayısal yükseklik modeli oluşturmada kullanılan farklı mekânsal enterpolasyon yöntemlerinin (Ters mesafe ağırlıklı (Inverse Distance Weighted-IDW), Normal Kriging (Ordinary Kriging-OK), Değiştirilmiş Shepard (Modified Shepard's-(MS), Çoklu kuadratik Radyal Tabanlı Fonksiyon (Multiquadric Radial Basis Function-MRBF) ve Doğrusal Üçgenleme ile enterpolasyon (Triangulation with Linear-(TWL)), farklı nokta yoğunlukları (tamamı (%100) ve yarısı (%50)), farklı nokta dağılımları (eğrisel (curvature), kareler ağı (grid), düzenli (uniform) ve rastgele (random)) ve farklı topografyaya sahip arazi tipleri (düzlük, engebeli, dağlık) açısından konumsal doğruluğunu istatiksel olarak araştırmaktır. Bu amaçla varyans analizi (ANOVA) uygulanmıştır. ANOVA ile enterpolasyon yöntemlerinden elde edilen konumsal doğruluklar arasında, nokta yoğunlukları, nokta dağılımları ve arazi tiplerine göre oluşturulan alt gruplar için istatiksel olarak anlamlı bir fark olup olmadığı bulunmaya çalışılmıştır. Özelikle dağlık ve engebeli arazilerde desimetrelerden metreye ulaşan doğruluklar elde edilmiştir. Arazinin topografyası, oluşturulan sayısal yükseklik modellerinin doğruluğunu etkilemektedir. Tüm (%100) veri setinden elde edilen sonuçlar, %50’lik veri setlerine göre her zaman daha iyi bulunmuştur. Genel ifadelerle, %50’lik farklı nokta dağılımlarında ise eğriselliğe göre ve düzenli dağılımlar için benzer özellik göstermiş ve diğer dağılımlara göre daha iyi doğruluklar elde edilmiştir. Grid dağılım ise diğer dağılımlara göre daha zayıf sonuç vermiştir. OK ve MRBF enterpolasyon yöntemleri farklı arazi tipi ve nokta dağılımları için benzer özellikler göstermiştir. Bu yöntemlerin doğruluğu diğer yöntemlere göre daha iyi sonuç vermiştir. Her üç arazi tipi için IDW yönteminden elde edilen doğruluk, diğer yöntemlere göre daha azdır. MS ve TWL yöntemlerinden elde edilen doğruluklar birbirine benzerdir. Bu çalışmada kullanılan enterpolasyon yöntemleri elde edilen doğruluk açısından en iyiden en kötüye doğru MRBF, OK, MS, TWL ve IDW şeklinde sıralanmıştır.

20 January 2025 in Earth Science Informatics
Verified
Journal Article
Open access
PDF file
MGMünevver Gizem Gümüş
Münevver Gizem Gümüş
HÇHasan Çağatay Çiftçi
Hasan Çağatay Çiftçi
KGKutalmis Gumus
Kutalmis Gumus
Analysis of long-term meteorological data is critical for monitoring climate trends and understanding the drought situation in a given region. In this study, monthly average precipitation data from the Niğde meteorological station in Turkey covering the period 1950–2020 were used. Within the scope of the study, seven different drought index methods were used for drought analysis, and the number and percentages of drought conditions were calculated according to these indices. For example, according to the Standardized Precipitation Index (SPI) method, the proportion of dry periods was determined as 16.2% and the proportion of humid periods as 83.8%. The Mann-Kendall trend analysis performed to determine the drought trends of the region revealed an increasing trend towards humidity in all indices (e.g., z = 1.299, p = 0.194 for SPI). In the study, 60-month drought forecasts covering the years 2020–2025 were realized using the Nonlinear Autoregressive Neural Network (NARNN) model, and the results were compared with the Autoregressive (AR) model. In the prediction performance analysis, the NARNN model showed superior prediction performance for all indices with lower RMSE values (e.g., NARNN RMSE = 0.977 for SPI; AR RMSE = 1.704). The prediction performances of different training algorithms and activation functions used in the NARNN model were analyzed. The best performance was obtained with the trainbr training algorithm and sigmoid activation function (e.g., RMSE = 0.997 for SPI). Based on these best parameters, more than 70% of the drought conditions during the 2020–2025 period were found to be normal or humid according to NARNN predictions. This study demonstrates the superiority of the NARNN model in nonlinear time series analyses and that it is a reliable tool, especially for future drought forecasts. In addition, comprehensive analyses with different index methods have significantly contributed to understanding the long-term drought trends in the Niğde region.