Monitoring Post-Disaster Urban Recovery Using High-Resolution SAR Time Series and Unsupervised Learning: Evidence from the 2023 Türkiye-Syria Earthquake

2026-07-27

AI Summary

This study addresses the challenge of dynamically monitoring post-disaster urban recovery, which is hindered by the scarcity of ground truth data and the protracted nature of reconstruction processes. It presents the first integration of high-resolution COSMO-SkyMed SAR time series with unsupervised deep anomaly detection to identify persistent temporal anomalies associated with rebuilding activities—without requiring labeled training data—and generates spatially explicit recovery maps. Validation against SDGSAT-1 nighttime light imagery demonstrates SAR’s unique capability in capturing structural changes and highlights its complementarity with luminosity-based indicators. Applied to the severely affected regions of the 2023 Turkey–Syria earthquake, the method successfully delineated debris clearance zones, temporary settlements, and newly constructed residential areas, confirming its effectiveness and scalability for large-scale disaster recovery assessment.

Abstract

Monitoring post-disaster recovery is essential for understanding how urban systems rebuild and progressively return to functionality. However, tracking reconstruction remains difficult because reliable ground-truth information is often scarce and recovery processes evolve over time. This paper proposes an unsupervised framework for recovery monitoring based on multi-temporal synthetic aperture radar (SAR) observations and deep-learning anomaly detection. COSMO-SkyMed time series are used to identify persistent temporal anomalies associated with reconstruction activities and to generate spatially explicit recovery maps. The framework is applied to four cities severely affected by the 2023 Turkiye-Syria earthquakes, revealing heterogeneous reconstruction dynamics across different urban contexts. The results show spatially structured patterns of persistent anomalies related to reconstruction over damaged and cleared areas, temporary container settlements, and new residential districts. Comparison with nighttime-light recovery indicators derived from SDGSAT-1 data highlights the complementary nature of the two modalities: nighttime lights reflect the restoration of electricity supply and nighttime socioeconomic activity, whereas SAR anomalies capture structural changes in the built environment and may reveal reconstruction at earlier stages. The results demonstrate that multi-temporal SAR data combined with unsupervised learning provide an effective and scalable approach for monitoring post-disaster reconstruction when labeled recovery datasets are unavailable.

Problem

• post-disaster recovery
• urban reconstruction
• SAR time series
• unsupervised learning
• disaster monitoring

Innovation

• unsupervised learning
• SAR time series
• post-disaster recovery monitoring
• anomaly detection
• urban reconstruction