Precipitation is a critical input for hydrologic simulation and prediction, and is widely used for agriculture, water resources management, and prediction of flood and drought, among other activities. Traditional precipitation prediction researches often established one or more probability models of historical data based on the statistical prediction methods and machine learning techniques. However, few studies have been attempted deep learning methods such as the state-of-the-art for Recurrent Neural Networks (RNNs) networks in meteorological sequence time series predictions. We deployed Long Short-Term Memory (LSTM) network models for predicting the precipitation based on meteorological data from 2008 to 2018 in Jingdezhen City. After identifying the correlation between meteorological variables and the precipitation, nine significant input variables were selected to construct the LSTM model. Then, the selected meteorological variables were refined by the relative importance of input variables to reconstruct the LSTM model. Finally, the LSTM model with final selected input variables is used to predict the precipitation and the performance is compared with other classical statistical algorithms and the machine learning algorithms. The experimental results show that the LSTM is suitable for precipitation prediction. The RNN models, combined with meteorological variables, could predict the precipitation accurately in Jingdezhen City and provide sufficient time to prepare strategies against potential related disasters.

Timely and secure evacuation of residents during flood disasters or other emergency events is an important issue in urban community flood risk management, especially in vulnerable communities. An agent-based modeling framework was proposed in order to indicate how the community properties (e.g., community density and percentage of vulnerable residents), residents’ psychological attributes (e.g., flood risk tolerance threshold) and mutual aid mechanism affect the flood evacuation process. Results indicated that: (1) The community density negatively affected the flood evacuation efficiency. The greater the density of the community, the longer the evacuation time. (2) There was a negative correlation between the flood risk tolerance threshold of residents and evacuation efficiency. (3) The proportion of vulnerable resident agents had opposite effects on the evacuation efficiency of different types of communities, which was to negatively affect low-density communities and positively affect high-density communities. (4) Mutual aid mechanism can reduce evacuation time in low-density communities, and the effect was more pronounced with a higher proportion of vulnerable resident agents in the community. These findings can help managers to develop better emergency evacuation management for urban communities.

Quickly obtaining accurate waterlogging depth data is vital in urban flood events, especially for emergency response and risk mitigation. In this study, a novel approach to measure urban waterlogging depth was developed using images from social networks and traffic surveillance video systems. The Mask region-based convolutional neural network (Mask R-CNN) model was used to detect tires in waterlogging, which were considered to be reference objects. Then, waterlogging depth was calculated using the height differences method and Pythagorean theorem. The results show that tires detected from images can been used as an effective reference object to calculate waterlogging depth. The Pythagorean theorem method performs better on images from social networks, and the height differences method performs well both on the images from social networks and on traffic surveillance video systems. Overall, the low-cost method proposed in this study can be used to obtain timely waterlogging warning information, and enhance the possibility of using existing social networks and traffic surveillance video systems to perform opportunistic waterlogging sensing.