Sürdürülebilir Kalkınma Amaçları
Yazarlar
Yayınlar
- MakaleYalnız künye2026Scopus SJRQ3Burned area detection using Sentinel-1 and Sentinel-2 features and analysis of ensemble models with explainable AI
Günen, Mehmet Akif; Türk, Salih
Wildfires are serious environmental disasters that threaten ecosystem sustainability, reduce biodiversity, and disrupt the global carbon cycle. This study aimed to improve the accuracy and interpretability of burned area mapping in the Bodrum, Köyceğiz, and Marmaris districts of Muğla province, Türkiye, by integrating multi-sensor satellite data with ensemble machine learning and explainable artificial intelligence (XAI). Sentinel-1 and Sentinel-2 imagery were processed to derive 50 optical and radar-based features, which were classified using four ensemble methods: AdaBoost.M1, Random Forest, GentleBoost, and RUSBoost. The SHapley Additive exPlanations framework was applied to quantify the contribution of each feature and guide feature selection. Results indicated that Sentinel-2 spectral indices, particularly NBR, NBRSWIR, and bands B12 and B8, were the most decisive variables for burned area classification, while Sentinel-1 features contributed less strongly overall but the IVH_ratio variable emerged as the most informative radar-based indicator. Among the classifiers, AdaBoost.M1 achieved the most stable and accurate performance, Random Forest showed strong sensitivity to spectral variability, GentleBoost performed effectively with reduced feature sets, and RUSBoost addressed class imbalance but showed weaker spatial continuity. Importantly, classification accuracy saturated after approximately 15 features, demonstrating that high accuracy can be achieved with fewer inputs and lower computational demand. Moreover, McNemar’s statistical test confirmed that the observed differences among classifiers were significant, highlighting GentleBoost’s clear superiority over other methods. Overall, the integration of optical and radar data with XAI provides a transparent, efficient, and replicable framework for operational burned area monitoring in Mediterranean ecosystems.
AtıfScopus2WoS3OpenAlex2
İncele - MakaleYalnız künye2022Scopus SJRQ1Performance comparison of deep learning and machine learning methods in determining wetland water areas using EuroSAT dataset
Günen, Mehmet Akif
Wetlands are critical to the ecology because they maintain biodiversity and provide home for a variety of species. Researching, mapping, and conservation of wetlands is a challenging and time-consuming process. Because they produce temporal and geographical information, remote sensing and photogrammetric approaches are useful tools for analyzing and managing wetlands. In this study, the water areas of five different wetlands obtained with Sentinel-2 images in Turkey were classified. Although obtaining large amounts of high-dimensional dataset labeled for various land types is costly, it is a significant advantage to use it after model training in a wide range of applications. In this paper, the EuroSAT dataset was used in the validation process. Proposed deep learning–based 1D convolutional neural networks (CNN) and traditional machine learning methods (i.e., support vector machine, linear discriminant analysis, K-nearest neighborhood, canonical correlation forests, and AdaBoost.M1) were compared quantitatively (i.e., accuracy, recall, precision, specificity, F-score, and image quality assessment metrics) and qualitatively. Finally, pairwise comparison was made with chi-square-based McNemar’s test. There is a statistical difference between 1D CNN and machine learning method (except the support vector machine vs linear discriminant analysis in Test 1 area). CNN models outperform machine learning algorithms in terms of non-linear function approximation and the ability to extract and articulate data features. Since 1D CNNs can process data in a highly complex and unique feature space, they are very successful in segmenting strongly related and highly correlated discrete signals. It also has advantages over machine learning methods for water body extraction in that it can be integrated with sophisticated image pre-processing and standardization tools, is less susceptible to low-level random noise, and provides shift in variations and contrast-invariant image local transforms.
AtıfScopus74WoS53OpenAlex72
İncele - BildiriAçık Erişim2021QUALITY ASSESSMENT of PANSHARPENED RASAT and LANDSAT-8 IMAGES USING SYNTHETIC SENTINEL-2 PANCHROMATIC IMAGE
Gunen, M.A.; Karas, I.R.; Ben Ahmed, M.; Boudhir, A.A.; Ane, B.K.
Technical and physical limitations often do not allow images to be acquired with high spatial and spectral resolution. Pansharpened images obtained by fusing high spatial resolution panchromatic images and multi-spectral images are widely used in GIS applications. In this study, it is aimed to increase the spatial resolution of the RASAT and Landsat-8 multispectral satellite images with synthetic Sentinel-2 panchromatic data. Six different pansharpening methods were used to test the success of the synthetic panchromatic data generation method using dataset with two different land use/land cover properties. Seven full reference image quality assessment metrics and two referenceless image quality assessment metrics were used to perform quantitative comparison.
AtıfOpenAlex1İncele - BildiriYalnız künye2019Object-based classification of Izmir Metropolitan City by using sentinel-2 images
Ozlem Yilmaz, Elif; Varol, Beril; Hale Topaloglu, Raziye; Sertel, Elif; Menekay, S.; Cetin, O.; Alparslan, O.
This study aims to create Land Cover Land Use (LCLU)map of a part of the Izmir metropolitan city in Turkey, based on an enhanced Urban Atlas nomenclature and object based classification approach. Multi-temporal Sentinel-2 images from different seasons are used and rule-based object oriented classification techniques are applied on the images. Totally 20 LCLU classes are identified in the study area with different accuracy values. Thematic open source data were also integrated into classification to better identify some land use classes and to increase the total classification accuracy. Our results show that 10-m bands of Sentinel-2 images are capable to produce thematically detailed LCLU map with an overall accuracy of 86% and 0.852 Kappa values.
AtıfScopus6OpenAlex9İncele