Abstract: Forest biomass is a cumulation of long-term production and metabolic activities of the forest ecosystem, and it is also the energy basis and material source of forest ecosystem operation. Forest management inventory of Malipo county and Maguan county in 2016 (updated data in 2020) were selected as ground data and remote sensing estimation was carried out on the Cunninghamia lanceolata forest AGB in the study area based on Landsat 8 OLI remote sensing images in the same period. Single-band factors (7), texture feature factors (280), vegetation index factors (5), and topographic factors (3) were extracted from the Landsat 8 OLI remote sensing image data. Correlation analysis was conducted between extracted factors and Cunninghamia lanceolata forest AGB in the study area based on SPSS 26.0. Multiple linear regression model was used to eliminate irrelevant variables, extract some remote sensing factors as independent variables, and selected the model to build the AGB estimation model based on multiple linear regression, random forest, and K-nearest neighbor method. The model was evaluated to determine the optimal remote Cunninghamia lanceolata forest AGB estimation model of Cunninghamia lanceolata forest in the study area and invert the AGB of Cunninghamia lanceolata forest in the study area according to the optimal model in order to provide some references for the remote sensing AGB estimation of Chinese fir forest in southeast Yunnan. The main study results are presented as follows. The most relevant remote sensing factors of Cunninghamia lanceolata forest AGB in the study area are the five remote sensing factors under the 7×7 window. The remote sensing AGB estimation model of Cunninghamia lanceolata forest unit area based on the random forest model is the optimal model in this study. The inversion of the unit area AGB of Cunninghamia lanceolata forest by using the optimal model lays a certain foundation for the relevant studies of remote sensing AGB estimation of Cunninghamia lanceolata forest in the study area in the future.