Online urban-waterlogging monitoring based on a recurrent neural network for classification of microblogging text

Abstract. With the global climate change and rapid urbanization, urban flood disasters spread and become increasingly serious in China. Urban rainstorms and waterlogging have become an urgent challenge that needs to be monitored in real time and further predicted for the improvement of urbanization construction. We trained a recurrent neural network (RNN) model to classify microblogging posts related to urban waterlogging and establish an online monitoring system of urban waterlogging caused by flood disasters. We manually curated more than 4400 waterlogging posts to train the RNN model so that it can precisely identify waterlogging-related posts of Sina Weibo to timely determine urban waterlogging. The RNN model has been thoroughly evaluated, and our experimental results showed that it achieved higher accuracy than traditional machine learning methods, such as the support vector machine (SVM) and gradient boosting decision tree (GBDT). Furthermore, we build a nationwide map of urban waterlogging based on recent 2-year microblogging data.