Flooding and waterlogging have become one of the optimal-related disasters and one of the most sensitive issues in the world,while global climate change has led to an increase in extreme events.By taking the city of Shanghai,China as an example,the influencing factors and multiple regression model of urban waterlogging were studied in this paper,based on GIS techniques and modeling methods.The historical data and GIS spatial analysis, precipitation,urban construction lands expansion,population distribution,digital elevation model (DEM), infrastructure drainability and other factors were analyzed in the study to carry out a conclusion of the impacts of these factors on rainstorm waterlogging in downtown Shanghai.Meanwhile a multiple logistic regression model was constructed based on the scikit-learn machine learning module in Python,which was used to judge the occurrence of flood-waterlog according to the above factors,and the accuracy rate was above 90%.The results showed that the DEM,impervious surface distribution and population distribution of downtown in Shanghai significantly affect the incidence of rainstorm waterlogging.