In this study, temporIn this study, temporal trend analysis was conducted on the annual and quarterly meteorological variables of Lanzhou from 1951 to 2016, and a weighted Markov model for extremely high-temperature prediction was constructed. Several non-parametric methods were used to analyze the time trend. Considering that sequence autocorrelation may affect the accuracy of the trend test, we performed an autocorrelation test and carried out trend analysis for sequences with autocorrelation after removing correlation. The results show that the maximum temperature, minimum temperature, and average temperature in Lanzhou have a significant rising trend and show different performances in each season. In detail, the maximum temperature in summer does not have a significant change trend, while the minimum temperature in winter is the most significant rising trend, which leads to more and more ”warm winter” phenomenon. Finally, we construct a weighted Markov prediction model for extremely high temperatures and obtain the conclusion that the prediction results by the model are consistent with the real situation. and show different performances in each season. In detail, the maximum temperature in summer does not have a significant change trend, while the minimum temperature in winter is the most significant rising trend, which leads to more and more ”warm winter” phenomenon. Finally, we construct a weighted Markov prediction model for extremely high temperatures and obtain the conclusion that the prediction results by the model are consistent with the real situation.