Coğrafi bilgi sistemleri (CBS) ve yapay zeka (Aİ) algoritmalarina dayali sürdürülebilir güç kaynaği yönetimi

Türkiye has been experiencing rapid economic development in recent decades, which has significantly increased its energy needs, and the need for sustainable energy sources such as wind energy has emerged. This thesis aims to provide an integrated framework for selecting optimal locations for wind farms in Türkiye by integrating geographic information systems (GIS) techniques with artificial intelligence (AI) algorithms, specifically supervised and unsupervised machine learning. The study involved the spatial analysis of natural data (wind speed, slope, and elevation), socio-economic factors (proximity to roads and urban areas), and environmental factors (protected areas and water bodies). The results of the unsupervised classification algorithms (K-Means and K-Medoids) demonstrated the ability to identify clear clusters of sites with varying degrees of relevance. In contrast, the supervised algorithms demonstrated high classification accuracy, with SVM outperforming with 95.1% accuracy, followed by K-NN and Random Forest, while Naïve Bayes was the least accurate owing to its assumption of feature independence. The thesis adopted Ensemble Learning to enhance the accuracy and diminish the variance between the algorithms' results, culminating in a final identification of the optimal locations where the findings of the four algorithms converge, which were depicted cartographically using GIS. The study affirms that integrating AI techniques with spatial analysis provides a potent tool for decision-makers, expediting the transition towards renewable energy and mitigating environmental impacts. The thesis recommends further development of the models through the use of real-time data and improved multi-criteria decision-making (MCDA) methods and suggests extending the application to other sustainable energy sources.