Speaker
Description
Urban regeneration projects as transformative operations that strengthen and restructure the built environment under the risk of natural disasters have become one of the prior urban policies. These disaster-responsive projects not only aim to support resilience but also contribute to sustainability and increase the quality of life by optimizing the green infrastructure. One of the main components of the urban ecosystem, green infrastructure is a supportive unit for absorbing carbon emissions, sustaining cooling effects, and enhancing public health. Thus, green-driven urban regeneration projects have developed into effective tools for resilience-oriented climate change adaptation policy.
In Turkey, urban regeneration implementations are based on state law 6306 on the Transformation of Areas at Disaster Risk. The main objective of the law is to constitute healthy and safe urban settlements. Istanbul, as a metropolitan city that has vulnerable building stocks, faces great seismic risk. Therefore, within the aim of the law, urban regeneration projects are operated as comprehensive planning tools in the city. Despite the expectancy of contributing to life quality by escalating the green space in the city, preliminary findings indicate that implemented urban regeneration projects in declared risky regions create diminishing impacts on green spaces (Korkmaz & Balaban, 2020; Yazar et al., 2020). Mostly, those projects result in higher density, and green spaces per cap remain inadequate. Limited empirical research focuses on how urban regeneration projects influence the green infrastructure in Istanbul.
Addressing this issue, this study aims to investigate how urban regeneration projects under law numbered 6306 impact the changes in urban green space. The study sample was selected from regions declared risky by the Ministry of Environment, Urbanization, and Climate Change, whose urban regeneration was completed. The vegetation cover index (NDVI) obtained from Landsat-8 images for 2013 and 2024 will be used to detect changes in green spaces. The supervised machine learning technique Random Forest will be employed to execute the spatiotemporal analysis.
The study expects to reveal how urban regeneration initiatives affect the urban environment and reduce green space over time. Future findings in the study will provide tangible data for policymakers to review and improve urban regeneration projects within a sustainability context. Unlike traditional planning methods, employing machine learning techniques in this study allows for more optimized spatiotemporal analysis to address the complexity of urban space. Ultimately, this study will serve as an adaptable methodology to future empirical research to develop regeneration projects that minimize environmental effects by integrating remote sensing data and machine learning techniques.
References
Korkmaz, C., & Balaban, O. (2020). Sustainability of urban regeneration in Turkey: Assessing the performance of the North Ankara Urban Regeneration Project. Habitat International, 95. https://doi.org/10.1016/j.habitatint.2019.102081
Yazar, M., Hestad, D., Mangalagiu, D., Saysel, A. K., Ma, Y., & Thornton, T. F. (2020). From urban sustainability transformations to green gentrification: urban renewal in Gaziosmanpaşa, Istanbul. Climatic Change, 160(4), 637–653. https://doi.org/10.1007/s10584-019-02509-3
| Keywords | urban regeneration; green infrastructure; vegetation index; random forest; change detection |
|---|---|
| Best Congress Paper Award | No |
