 In this paper, the authors propose a novel approach to detecting changes in remote sensing images using a long short-term memory, LSTM, network. This network is trained to recognize patterns in the data which indicate when a change has occurred. Once trained, the network can then be used to detect changes in new target images without any additional learning process. Additionally, the authors show that their method can detect both binary and multi-class changes. This article was authored by Haobu Liu, Huilu, and Li Chaomao.