Abstract: Under the framework of the national carbon emission reduction goals, the research on the spatio-temporal evolution of energy consumption carbon emissions and its influencing factors at the county level is of great significance to guide urban agglomerations to achieve carbon peak and carbon neutral goals. Exploratory spatial data analysis can reveal the spatial differences of carbon emissions in the region, while geographic detectors can not only identify the independent influence of influencing factors on carbon emissions, but also identify the influence of interaction effects of influencing factors on the spatial differentiation of carbon emissions. Therefore, the paper spatially simulates the carbon emissions of energy consumption in Lan-Xi urban agglomeration from 1995 to 2019 by correcting and fusing the long time series DMSP/OLS and NPP/VIIRS night light images. From the perspective of county scale, the paper uses exploratory spatial data analysis and geographical detectors to study the spatio-temporal distribution characteristics, spatial correlation characteristics and influencing factors of carbon emissions. The results show that: (1) The total carbon emissions increased from 36.23×10⁶ t in 1995 to 116.61×10⁶ t in 2019, and the growth rate first increased and then decreased, with an average annual growth rate of 4.79%. The range of carbon emissions (10⁴ t) increased from 13.4, 425.4 in 1995 to 103.2, 1051.4 in 2019. The range of carbon emissions (t/10 000 yuan) decreased from 4.2, 9.7 in 2005 to that of 2019 1.6, 5.0. (2) Regional carbon emissions have always shown a spatial distribution pattern of high in the east and low in the west, high in the middle and low in the north and south. High-carbon counties and districts are mainly concentrated in Lanzhou and Xining and the surrounding densely populated and economically developed areas. The spatial difference is shrinking, and the spatial positive autocorrelation is gradually expanding. The local autocorrelation is relatively stable, dominated by high-high and low-low aggregation. The high-high aggregation is mainly concentrated in the main urban area of Lanzhou, and the low-low aggregation is distributed in Huangnan prefecture and Hainan prefecture. (3) The spatial differentiation of carbon emissions is affected by a variety of factors, and the influence of economic development level on the spatial differentiation of carbon emissions is always the strongest. The interaction between GDP and energy intensity, the enterprises number, industrial structure and urbanization level is the main driving force for the sustained growth of carbon emissions.