To improve the economy of structural health monitoring and expand its application scope， a temperature field prediction method of long-span bridges based on big-data information from weather stations was proposed to realize lightweight and sustainable bridge temperature field and temperature deformation calculation. Taking a large-span steel arch truss bridge as the research object， the big-data information （including weather， temperature， and wind speed information） from the weather station was obtained through the meteorological data platform， the radiation intensity of each surface for the main components of the bridge was calculated by Elbadry’s improved Kelbek radiation model， the boundary conditions of structural thermal analysis were calculated based on the heat exchange transfer theory， and the structural transient thermal analysis was carried out in combination with the finite element analysis method， to obtain the time-varying temperature field of the main components of the target bridge. The calculation results of the temperature field are in good agreement with the measured temperature on the bridge in terms of time history and vertical distribution of the structure， and absolute value of the average error is within 3%. The calculated structural temperature was applied to the overall finite element model of the bridge structure， and the temperature deformation of the bridge structure was obtained. Moreover， the calculated value of the longitudinal displacement of the bridge support is in good agreement with the measured value， and the average error is within 13mm. The analysis verifies that the proposed bridge temperature field prediction method based on big data from weather stations is feasible， and the temperature deformation of the bridge structure can be further obtained by using this method as well.