Using MODIS land surface temperature data, air temperature data and elevation data from 2000 to 2015 in the Yellow River Basin. The GWR analysis method with high accuracy was chosen to establish the regression model of plateau air temperature, land surface temperature and altitude. In the 12-month GWR regression model, the determination coefficient (Adjusted R2) was above 0.95 or more (0.959-0.980) and the root-mean-square error (RMSE)was between 0.740 and 1.029°C. Depending on the model, the air temperature of the Yellow River Basin is estimated and the accuracy is verified. On this basis, the average monthly air temperature in the basin is converted to altitudes of 4500m and 5000m, and the heating-up effects of various shapes in the basin are compared and discussed. The results show that: (1) Using the GWR method, combined with the observation data of the ground station, the accuracy of the air temperature estimation in the Yellow River Basin can be increased to 0.740°C; (2) According to the estimated annual variation of the spatial distribution of the 12-month average temperature, in the upper of the Tibet Plateau, the Huangshui Valley and the Gannan Plateau have lower annual air temperatures and less spatial distribution. While the air temperature in the northeast of the upstream Inner Mongolia plateau was higher, which was related to the rapid drying temperature rise near the desert. The change of mean monthly temperature in the middle and lower reaches is relatively high and the change is small, which is closely linked to the fact that it is located in the low-elevation area of the basin plain and has perennial light and heat.(3) The heating-up effect in the Yellow River Basin is outstanding. It is preliminaries estimated that at the same altitude, the Tibet Plateau is about 1.5~8°C higher than the Loess Plateau, and about 6~13°C higher than the North China Plain.