Determining climate change resistant habitat strategies: KTU kanuni campus example

In today's world, where the negative impacts of climate change are strongly felt, many concepts and measures are being developed to mitigate the negative impacts of climate change and to adapt to change. Ecosystem services, one of the most important of these concepts, have a complex structure that depends on many variables. This complex structure makes it difficult to plan and design urban green spaces based on ecosystem services. When the literature is examined, there are few findings on which characteristics of plant communities that will provide ecosystem services can increase the resilience and flexibility value of the community by affecting the gains more. In this thesis, it is aimed to use regulatory ecosystem services as a tool to develop resilient habitats in campus landscapes within public open spaces. Within the scope of this purpose, the existing habitat patches were identified with the plant-based habitat classification system and the regulatory ecosystem services of the features that make up the habitat were calculated. In order to determine the input parameters that most affect the gain output values obtained as a result of these calculations, 32 input parameters and 14 gain outputs were evaluated in 4 different prediction models with machine learning. According to the results of the prediction model with the highest performance, 20 parameters that affect the gains the most, were identified. In line with the identified parameters, recommendations were developed for the formation of resilient habitat patches and the resilience of the habitats forming the KTU Kanuni Campus.