Analysis of asphalt deformations on highways after major severe earthquakes and automatic classification of asphalt cracks with deep learning-based approaches

The detection of land surface cracks caused by earthquakes, called seismic ruptures, is of great importance in terms of finding hidden faults, monitoring their movements and predicting possible earthquakes. On February 6, 2023, there were two destructive earthquakes with epicenters in Pazarcık (Kahramanmaraş - Mw = 7.7) and Elbistan (Kahramanmaraş - Mw = 7.6). The earthquakes occurred at 04:17 (01:17 GMT) and 13:24 (10:24 GMT) local time, respectively. These earthquakes occurred on the left-lateral strike-slip East Anatolian Fault (EAF), one of the two major active fault systems in Turkey. According to AFAD data, these earthquakes are shallow earthquakes and the first earthquake occurred at a depth of 8.6 km, while the second earthquake occurred at a depth of 7 km. The earthquake was felt severely in 10 provinces, especially in the epicenter, and a large amount of building stock was damaged. After the main shocks, approximately 1300 earthquakes were recorded until 09.02.2023 at 16.00. After these earthquakes, search and rescue teams and aid materials for 10 provinces should be delivered to the disaster areas as quickly as possible. However, after the Pazarcık and Elbistan earthquakes, the transportation of search and rescue teams and aid materials was disrupted as a result of large deformations on the highways and airport runways. This has revealed how important the road quality should be in regions with high earthquake risk. Therefore, it is necessary to examine the deformations (densely distributed cracks) of the highway network in earthquake zones. It is of great importance that the deformation data obtained as a result of these examinations are classified by experts in the field. Determining the road deformations, which are not particularly large, will prevent the formation of major deformations that will occur due to the next aftershocks, weather events and traffic on the highways. For this reason, all deformations occurring on the highways in the disaster area will be examined in detail and classified according to the degree of deformation with the research team to be formed. With this data set, a detailed map of the deformation-prone highways in disaster areas will be drawn. According to this map, a maintenance-repair plan will be prepared for the deformations that may occur after the earthquake. Thus, the reliability of maintenance-repair works will be increased. In addition, with the obtained labeled data set, material will be created for software applications (especially artificial intelligence) that perform automatic road deformation detection. With this data set, deep learning-based applications that automatically classify deformation degrees on highways will be created in the thesis study. Keywords: Asphalt Deformations