Data fusion is a method to improve the calculation efficiency and reduce redundant data. The air temperature data of Xinlinhe basin is carefully researched. Aiming at the drawback of traditional Kalman filter approach:a slight fluctuation, a novel method is proposed based on the traditional Kalman filter and distribution map to fuse the air temperature data. The task is to make the data collected every five seconds fuse into the air temperature value of an hour. For the demonstration the proposed method, disturbance data and mutation data are set on the basis of the original data. Via the experimental simulation, the improved algorithm has a good fusion effect, with strong anti-interference and stability, which can raise the accuracy of the meteorological data.