Detection of Non-Designated Evacuation Shelters from Real-Time Population Dynamics Using Autoencoder-Based Anomaly Detection
Keiichi Ochiai, Masayuki Terada, Makoto Hanashima, Hiroaki Sano, and Yuichiro Usuda
ACM Transaction on Spatial Algorithms and Systems, Oct 2024
In a disaster situation, local and municipal governments need to distribute relief supplies and provide administrative support to evacuees.Although people are supposed to evacuate to evacuation shelters designated by local governments, some people take refuge at non-designated facilities, called non-designated evacuation shelters, due to unavoidable circumstances such as damage on the access routes to designated evacuation shelters. Upon occurrence of a disaster, therefore, it is necessary for the local governments to quickly find the locations of non-designated evacuation shelters. In this article, we propose a method to detect non-designated evacuation shelters based on autoencoder (AE)-based anomaly detection using real-time population dynamics generated from operation data of cellular phone networks. We assume that reconstruction errors of an AE model include both the errors due to characteristic differences between locations and the errors due to anomalies in population dynamics. Thus, we propose to use the ratio of the reconstruction error before and after the earthquake to determine the threshold of anomaly detection. We evaluate the performance of the proposed method on data from three actual earthquakes in Japan. The evaluation results show that our reconstruction error based approach can achieve better accuracy for the actual disaster data compared to a baseline method that exploits statistical anomaly detection.