In December 2019, corona virus disease 2019 (COVID-19) has broken out in China. Understanding the distribution of disease at the national level contributes to the formulation of public health policies. There are several studies that investigating the influencing factors on distribution of COVID-19 in China. However, more influencing factors need to be considered to improve our understanding about the current epidemic. Moreover, in the absence of effective medicine or vaccine, the Chinese government introduced a series of non-pharmaceutical interventions (NPIs). However, assessing and predicting the effectiveness of these interventions requires further study. In this paper, we used statistical techniques, correlation analysis and GIS mapping expression method to analyze the spatial and temporal distribution characteristics and the influencing factors of the COVID-19 in mainland China. The results showed that the spread of outbreaks in China’s non-Hubei provinces can be divided into five stages. Stage I is the initial phase of the COVID-19 outbreak; in stage II the new peak of the epidemic was observed; in stage III the outbreak was contained and new cases decreased; there was a rebound in stage IV, and stage V led to level off. Moreover, the cumulative confirmed cases were mainly concentrated in the southeastern part of China, and the epidemic in the cities with large population flows from Wuhan was more serious. In addition, statistically significant correlations were found between the prevalence of the epidemic and the temperature, rainfall and relative humidity. To evaluate the NPIs, we simulated the prevalence of the COVID-19 based on an improved SIR model and under different prevention intensity. It was found that our simulation results were compatible with the observed values and the parameter of the time function in the improved SIR model for China is a = − 0.0058. The findings and methods of this study can be effective for predicting and managing the epidemics and can be used as an aid for decision makers to control the current and future epidemics.

Dam deformation monitoring and prediction are crucial for evaluating the safety of reservoirs. There are several elements that influence dam deformation. However, the mixed effects of these elements are not always linear. Oppose to a single-kernel extreme learning machine, which suffers from poor generalization performance and instability, in this study, we proposed an improved bat algorithm for dam deformation prediction based on a hybrid-kernel extreme learning machine. To improve the learning ability of the global kernel and the generalization ability of the local kernel, we combined the global kernel function (polynomial kernel function) and local kernel function (Gaussian kernel function). Moreover, a Lévy flight bat optimization algorithm (LBA) was proposed to overcome the shortages of bat algorithms. The results showed that our model outperformed other models. This proves that our proposed algorithm and methods can be used in dam deformation monitoring and prediction in different projects and regions.