Accidents induced by natural disasters at sports sites may cause catastrophic loss of great concern. However, previous studies on risk assessments of sports sites have only focused on operational risk and equipment failure. With the frequent occurrence of extreme disasters, the risk of domino chains caused by natural disasters at large-scale events, such as large-scale winter sports sites, cannot be ignored. In this study, a natural disaster-induced accident-chain evolution analysis model (NAEA model) is proposed. Based on the results of the NAEA model, a fuzzy Bayesian network for domino accidents triggered by an earthquake at large-scale winter sports sites was established. Through sensitivity analysis and scenario analysis, it was found that fire and explosion accidents and crowded stampede accidents are the main causes of serious loss in domino disaster chains in large-scale sports sites. Simultaneously, improving the early warning capability, reliability of electrical equipment, and automatic sprinkler systems are the most effective ways to prevent and control major accidents. In addition, an optimal safety strategy improvement analysis was performed to facilitate the decision-making of safety managers to prevent serious accidents and reduce accident loss.@en

Crime issues have been attracting widespread attention from citizens and managers of cities due to their unexpected and massive consequences. As an effective technique to prevent and control urban crimes, the data-driven spatial–temporal crime prediction can provide reasonable estimations associated with the crime hotspot. It thus contributes to the decision making of relevant departments under limited resources, as well as promotes civilized urban development. However, the deficient performance in the aspect of the daily spatial–temporal crime prediction at the urban-district-scale needs to be further resolved, which serves as a critical role in police resource allocation. In order to establish a practical and effective daily crime prediction framework at an urban police-district-scale, an “online” integrated graph model is proposed. A residual neural network (ResNet), graph convolutional network (GCN), and long short-term memory (LSTM) are integrated with an attention mechanism in the proposed model to extract and fuse the spatial–temporal features, topological graphs, and external features. Then, the “online” integrated graph model is validated by daily theft and assault data within 22 police districts in the city of Chicago, US from 1 January 2015 to 7 January 2020. Additionally, several widely used baseline models, including autoregressive integrated moving average (ARIMA), ridge regression, support vector regression (SVR), random forest, extreme gradient boosting (XGBoost), LSTM, convolutional neural network (CNN), and Conv-LSTM models, are compared with the proposed model from a quantitative point of view by using the same dataset. The results show that the predicted spatial–temporal patterns by the proposed model are close to the observations. Moreover, the integrated graph model performs more accurately since it has lower average values of the mean absolute error (MAE) and root mean square error (RMSE) than the other eight models. Therefore, the proposed model has great potential in supporting the decision making for the police in the fields of patrolling and investigation, as well as resource allocation.@en