On November 26, 2024, Gökçe Yağmur Budak will present her internship results on ” Leveraging Data-Driven Approaches for Seismic Risk Assessment in Istanbul ” at 12:30 in seminar room 3, John-Skilton-Str. 4a.
From the abstract: This internship aims to create time series data using seismic exposure information for a potential earthquake in Istanbul and forecast future exposure patterns with LSTM-based models. The project utilizes open-source satellite imagery and geospatial datasets to more accurately analyze the seismic vulnerability of buildings across Istanbul. Structural factors such as building type, height, and age are considered to examine seismic exposure data in more detail. Disaggregation methods are used to more precisely separate exposure data based on building types and structural features, enabling a more detailed analysis of risk levels in different areas. This approach also facilitates the accurate segmentation of spatial and temporal data, allowing for more reliable predictions of future seismic threats. The developed model will become an important tool for predicting city-specific seismic threats, formulating disaster management strategies, and contributing to urban planning. Additionally, the internship includes collaboration with various stakeholders, including the Istanbul Metropolitan Municipality, to explore data-driven solutions aimed at enhancing urban resilience. The work aims to develop innovative data-driven solutions to increase Istanbul’s seismic resilience and mitigate the impacts of disasters.
1st supervisor: Dr. Insa Otte Hosting Institution: University of Bonn
From the abstract: This internship aims to create time series data using seismic exposure information for a potential earthquake in Istanbul and forecast future exposure patterns with LSTM-based models. The project utilizes open-source satellite imagery and geospatial datasets to more accurately analyze the seismic vulnerability of buildings across Istanbul. Structural factors such as building type, height, and age are considered to examine seismic exposure data in more detail. Disaggregation methods are used to more precisely separate exposure data based on building types and structural features, enabling a more detailed analysis of risk levels in different areas. This approach also facilitates the accurate segmentation of spatial and temporal data, allowing for more reliable predictions of future seismic threats. The developed model will become an important tool for predicting city-specific seismic threats, formulating disaster management strategies, and contributing to urban planning. Additionally, the internship includes collaboration with various stakeholders, including the Istanbul Metropolitan Municipality, to explore data-driven solutions aimed at enhancing urban resilience. The work aims to develop innovative data-driven solutions to increase Istanbul’s seismic resilience and mitigate the impacts of disasters.
1st supervisor: Dr. Insa Otte Hosting Institution: University of Bonn
