Aims: Over the past twenty years, Iran has experienced a rise in extreme temperatures, particularly in hot events like extreme temperatures, as indicated by recent studies. This research seeks to analyze the annual maximum temperatures (AMT) in the dry Province of Kerman, Iran, focusing on both stationary (S) and nonstationary (NS) behavior. Materials & Methods: Trend, homogeneity, and stationarity tests were utilized to identify the critical characteristics of the AMTs from 1979 to 2019. Frequency analysis of the AMTs was conducted using both stationary Generalized Extreme Value (S-GEV) and nonstationary GEV (NS-GEV) models, estimating distribution parameters through a maximum likelihood estimator(MLE). In addition to the time-varying NS-GEV (TNS-GEV) investigations, soil moisture (SM) was incorporated as a covariate. Findings: Results demonstrate that, compared to the S-GEV case, the NS-GEV frequency analyses significantly impact the return values of the AMTs, leading to an increase. The NSGEV estimations for 50-year return levels were significantly higher than those in the S-GEV. The study’s findings revealed that the average Akaike Information Criterion (AIC) for both the S-GEV and TNS-GEV estimations decreased from 110 to 71 across all 12 selected stations in Kerman Province. The AIC value for the NS-GEV with the soil moisture (SM) covariate was approximately 94. Thus, the TNS-GEV frequency analysis of AMTs resulted in improved AIC values compared to the NS-GEV with soil moisture as the covariate. Conclusion: Given the nonstationary (NS) conditions caused by natural and/or human activities, it is recommended to utilize NS frequency analysis for estimating hydrologic variables across different design periods. It has been noted that NS-GEV frequency analyses lead to higher return levels of AMTs than S-GEV analyses
