Seismic Risk Regularization for Urban Changes Due to Earthquakes: A Case of Study of the 2023 Turkey Earthquake Sequence

Abstract

Damage identification soon after a large-magnitude earthquake is a major problem for early disaster response activities. The faster the damaged areas are identified, the higher the survival chances of inhabitants. Current methods for damage identification are based on the application of artificial intelligence techniques using remote sensing data. Such methods require a large amount of high-quality labeled data for calibration and/or fine-tuning processes, which are expensive in the aftermath of large-scale disasters. In this paper, we propose a novel semi-supervised classification approach for identifying urban changes induced by an earthquake between images recorded at different times. We integrate information from a small set of labeled data with information from ground motion and fragility functions computed on large unlabeled data. A relevant consideration is that ground motion and fragility functions can be computed in real time. The urban changes induced by the 2023 Turkey earthquake sequence are reported as an evaluation of the proposed method. The method was applied to the interferometric coherence computed from C-band synthetic aperture radar images from Sentinel-1. We use only 39 samples labeled as changed and 9000 unlabeled samples. The results show that our method is able to identify changes between images associated with the effects of an earthquake with an accuracy of about 81%. We conclude that the proposed method can rapidly identify affected areas in the aftermath of a large-magnitude earthquake.

A New Method for the Identification of Earthquake-Damaged Buildings Using Sentinel-1 Multitemporal Coherence Optimized by Homogeneous SAR Pixels and Histogram Matching

“…Liu and Yamazaki [16] achieved an accuracy of only 60.3% using the method of coseismic and preseismic coherence ratios. Portillo and Moya [6] present a novel semi-supervised classification method to identify urban changes due to the 2023 Turkey earthquake based on Sentinel-1 interferometric coherence, showing 80% agreement with a third-party damage catalogue. Apart from these studies, the validation of most studies is qualitative [27,57,58].…”

“…comprehensive identification of damaged buildings is essential for post-earthquake relief efforts to reduce casualties and economic losses [3][4][5][6].…”

Deprem Sonrasi Ri̇skleri̇ Anlamak: Olasi Marmara Depremi̇ne Yöneli̇k Bi̇r Anali̇z

“…Çalışmada depremlerin sismik kapasitesi karşılaştırılarak değerlendirme gerçekleştirilmiştir. Sismik kapasite ya da dalgalar üzerinde inceleme gerçekleştiren literatürde birden fazla çalışma olduğu da gözlemlenenler arasındadır (Adushkin vd., 2023;Alkan vd., 2023;An vd., 2023;Atanasova-Zlatareva vd., 2023;Bagiya vd., 2023;Cetin vd., 2023;Feng vd., 2023;Gastineau vd., 2023;Gülkan vd., 2023;Hussain vd., 2023;Karabacak vd., 2023;Kırkan vd., 2023;Li vd., 2023;Maletckii vd., 2023;Müller vd., 2023;Okuwaki vd., 2023;Ozkula vd., 2023;Papazafeiropoulos & Plevris, 2023;Portillo & Moya, 2023;Sandıkkaya vd., 2023 vd., 2023;Turunçtur vd., 2023;Utkucu vd., 2023;Wang vd., 2023;Wu vd., 2023;Xu vd., 2023;Yılmaz vd., 2023;Zhao vd., 2023). Depremin vatandaşlara bildirilmesi noktasında inceleme gerçekleştiren ve deprem erken uyarı sisteminin Türkiye'nin birden fazla bölgesinde uygulanmasını amaçlayan Tunç vd., (2023) 'nin çalışması da literatürde yer almaktadır.…”

Placing engineering in the earthquake response and the survival chain

“…Researchers can use high-resolution satellite or UAV imagery to predict building damage and landslides through AI, e.g., convolutional neural networks (CNNs) and semantic segmentation 72 – 76 . Researchers can also use lower-resolution satellite imagery, resulting in coarser predictions but with sizeable geographical coverage 75 , 76 . However, training AI models for damage detection requires substantial data.…”