Unsupervised Detection of Disaster-Affected Areas by Combining the Strengths of Change Detection and Anomaly Detection: Target for On-Orbit Application

Timely and accurate monitoring of abrupt natural disasters, such as floods, landslides, and wildfires, is critical for protecting lives and property. On-orbit satellite image change detection offers near-real-time disaster insights, yet existing methods, designed for ground-based tasks, overlook the resource constraints of on-orbit computing environments. To fill this study gap, we propose a novel change detection method, Single-temporal HIgh-spatial rEsoLution image unsupervised change Detection (Shield), tailored to the constraints of on-orbit computing environments. Shield integrates the capabilities of change detection models that can identify various disaster events, with the efficiency of anomaly detection methods, which demand fewer computational resources and only require a single post-disaster image along with prior knowledge as input. First, Shield generates lightweight prior knowledge from pre-disaster imagery to establish connections between the changes and anomalies. Then, Shield employs a 2-step localization strategy to progressively identify change patches and pixels in post-disaster imagery to provide disaster-affected areas of interest. We validated Shield’s performance in 4 typical disaster scenarios: landslides, floods, wildfires, and deforestation. When evaluated against 8 classical and state-of-the-art bi-temporal change detection methods, as well as 2 single-temporal anomaly detection methods, Shield exhibited superior performance, achieving an average F1 score improvement of 24.37%. Furthermore, Shield’s application in 2 large-scale disaster scenarios in 2023 highlighted its robust performance and efficiency. It achieved a 5- to 239-fold reduction in data storage requirements and up to a 136-fold increase in on-orbit real-time detection speed compared to alternative methods, reinforcing its substantial potential for on-orbit operations. Code available at https://github.com/tangkai-RS/Shield .