Abstract: With a rapid development of information technology and the advent of the era of big data, some spatio-temporal data sets are not only large-scale, but also contain various information variables. Therefore, appropriate expressions are needed to describe the characteristics of this kind of data. Based on the STSS model proposed by French and other scholars, the effects of covariate functions and periodic functions on response variables are introduced. The application of the STSS model on basis functions and penalty functions is used to smooth large-scale data. At the same time, it is accompanied by the influence of covariates and periodicity on the observed variables. This combination enables the improved model to describe the structure and changes of spatio-temporal data more comprehensively and realistically. Finally, superiority and applicability of the method are verified by using the simulated data and real spatio-temporal data.